rstudioweb's picture
Upload log.txt with huggingface_hub
4c0e196 verified
Running 1 job
{
"type": "diffusion_trainer",
"training_folder": "/teamspace/studios/this_studio/ai-toolkit/output",
"sqlite_db_path": "/teamspace/studios/this_studio/ai-toolkit/aitk_db.db",
"device": "cuda",
"trigger_word": "srutixzit1",
"performance_log_every": 10,
"network": {
"type": "lora",
"linear": 32,
"linear_alpha": 32,
"conv": 16,
"conv_alpha": 16,
"lokr_full_rank": true,
"lokr_factor": -1,
"network_kwargs": {
"ignore_if_contains": []
}
},
"save": {
"dtype": "bf16",
"save_every": 250,
"max_step_saves_to_keep": 4,
"save_format": "diffusers",
"push_to_hub": false
},
"datasets": [
{
"folder_path": "/teamspace/studios/this_studio/ai-toolkit/datasets/sruti",
"mask_path": null,
"mask_min_value": 0.1,
"default_caption": "",
"caption_ext": "txt",
"caption_dropout_rate": 0.03,
"cache_latents_to_disk": false,
"is_reg": false,
"network_weight": 1,
"resolution": [
1024,
768,
512
],
"controls": [],
"shrink_video_to_frames": true,
"num_frames": 1,
"flip_x": false,
"flip_y": false,
"num_repeats": 1
}
],
"train": {
"batch_size": 1,
"bypass_guidance_embedding": false,
"steps": 3000,
"gradient_accumulation": 1,
"train_unet": true,
"train_text_encoder": false,
"gradient_checkpointing": true,
"noise_scheduler": "flowmatch",
"optimizer": "adamw8bit",
"timestep_type": "weighted",
"content_or_style": "balanced",
"optimizer_params": {
"weight_decay": 0.0001
},
"unload_text_encoder": false,
"cache_text_embeddings": false,
"lr": 0.0001,
"ema_config": {
"use_ema": false,
"ema_decay": 0.99
},
"skip_first_sample": false,
"force_first_sample": false,
"disable_sampling": false,
"dtype": "bf16",
"diff_output_preservation": false,
"diff_output_preservation_multiplier": 1,
"diff_output_preservation_class": "person",
"switch_boundary_every": 1,
"loss_type": "mse"
},
"logging": {
"log_every": 1,
"use_ui_logger": true
},
"model": {
"name_or_path": "Tongyi-MAI/Z-Image-Turbo",
"quantize": true,
"qtype": "qfloat8",
"quantize_te": true,
"qtype_te": "qfloat8",
"arch": "zimage:turbo",
"low_vram": true,
"model_kwargs": {},
"layer_offloading": false,
"layer_offloading_text_encoder_percent": 1,
"layer_offloading_transformer_percent": 1,
"assistant_lora_path": "ostris/zimage_turbo_training_adapter/zimage_turbo_training_adapter_v2.safetensors"
},
"sample": {
"sampler": "flowmatch",
"sample_every": 250,
"width": 1024,
"height": 1024,
"samples": [
{
"prompt": "ultra realistic portrait of a beautiful Indian 20y woman, soft natural skin texture, detailed face, expressive eyes, subtle makeup, cinematic lighting, 85mm lens, shallow depth of field, high detail, photorealistic, natural skin pores"
},
{
"prompt": "full body shot of a young Indian 20y nude woman standing naturally, perfect body proportions, realistic anatomy, long legs, natural pose, detailed hands and fingers, soft lighting, high resolution, photorealistic, balanced composition"
},
{
"prompt": "A young Indian woman, elegant and natural, is on her knees beside a fully naked man beneath a warm bathroom shower. They are completely nude in a private, intimate moment. The scene takes place inside a modern yet warm bathroom at dawn \u2014 soft morning light streams through a large window or diffuses from the shower curtain. She performs a deep throat swallow on his large penis with focused intensity and quiet passion in her eyes. Her hair is wet, glossy, and cascading over her shoulders and back, clinging to her neck and face, catching the water droplets and soft light. The atmosphere is intimate, sensual, and peaceful \u2014 realistic skin texture, steam rising from the shower, visible moisture on her skin, natural lighting, subtle details of hands, expression, and body language. Style: photorealistic, high detail, cinematic soft glow, warm tones, atmospheric humidity."
},
{
"prompt": "a confident Indian 20y nude woman in a relaxed indoor setting, no outfit, natural body posture, soft window light, realistic skin tones, detailed anatomy, elegant and sensual mood, cinematic shadows, ultra realistic"
},
{
"prompt": "A full-body portrait of a stunning Indian 20y woman with long, flowing black hair cascading down her back, standing nude and poised in a serene, softly lit bedroom. Her body is sculpted with perfect, natural curves \u2014 full, round breasts with dark brownish areolas and nipples, a smooth midriff leading to a gently curved waist, and a deeply toned, naturally darkened pubic area that accentuates her feminine form. Her legs are long and slender, ending in a firm, rounded ass that subtly tenses as she stands with her arms relaxed at her sides, fingers slightly curled, exuding quiet confidence and sensual grace. Her gaze is direct and unflinching, meeting the viewer\u2019s eyes with a calm, alluring intensity that draws you in. The environment is minimalist and intimate, set against a soft, neutral beige background that enhances the natural tones of her skin and hair. Behind her, sheer white curtains filter in diffused daylight, casting gentle shadows across the room, while a simple bed with rumpled white linens and a potted green plant in the corner add subtle domestic warmth without distracting from the central focus. The lighting is soft and even, highlighting the smooth texture of her skin, the subtle contours of her anatomy, and the natural sheen of her hair \u2014 all rendered with photorealistic precision to emphasize her flawless, voluptuous form. This is a portrait of raw, unfiltered beauty \u2014 a celebration of the female body in its most natural state. Her posture is relaxed yet commanding, her expression serene and self-assured, embodying both innocence and sensuality. The composition is vertically framed, drawing attention to her full, symmetrical silhouette, while the muted, monochromatic backdrop ensures every curve, every detail of her anatomy \u2014 from the delicate arch of her collarbone to the subtle definition of her hips \u2014 is rendered with exquisite clarity. She stands as a living sculpture, a vision of erotic elegance, inviting the viewer to appreciate the harmony of her form and the quiet power of her presence.\""
}
],
"neg": "",
"seed": 42,
"walk_seed": true,
"guidance_scale": 1,
"sample_steps": 8,
"num_frames": 1,
"fps": 1
}
}
Using SQLite database at /teamspace/studios/this_studio/ai-toolkit/aitk_db.db
Job ID: "d407179c-af27-48d6-b914-1358334da7d9"
#############################################
# Running job: my_first_lora_v1
#############################################
Running 1 process
Loading ZImage model
Loading transformer
Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 33%|###3 | 1/3 [00:00<00:01, 1.20it/s] Loading checkpoint shards: 33%|###3 | 1/3 [00:00<00:01, 1.20it/s] Loading checkpoint shards: 67%|######6 | 2/3 [00:01<00:00, 1.24it/s] Loading checkpoint shards: 67%|######6 | 2/3 [00:01<00:00, 1.24it/s] Loading checkpoint shards: 100%|##########| 3/3 [00:01<00:00, 1.65it/s] Loading checkpoint shards: 100%|##########| 3/3 [00:01<00:00, 1.65it/s] Loading checkpoint shards: 100%|##########| 3/3 [00:01<00:00, 1.50it/s] Loading checkpoint shards: 100%|##########| 3/3 [00:01<00:00, 1.50it/s]
Loading assistant LoRA
create LoRA network. base dim (rank): 64, alpha: 64
neuron dropout: p=None, rank dropout: p=None, module dropout: p=None
create LoRA for Text Encoder: 0 modules.
create LoRA for U-Net: 276 modules.
enable LoRA for U-Net
Merging in assistant LoRA
Missing keys: []
Quantizing Transformer
- quantizing 30 transformer blocks
0%| | 0/30 [00:00<?, ?it/s] 0%| | 0/30 [00:00<?, ?it/s] 3%|3 | 1/30 [00:00<00:04, 6.62it/s] 3%|3 | 1/30 [00:00<00:04, 6.62it/s] 7%|6 | 2/30 [00:00<00:03, 7.70it/s] 7%|6 | 2/30 [00:00<00:03, 7.70it/s] 10%|# | 3/30 [00:00<00:03, 8.20it/s] 10%|# | 3/30 [00:00<00:03, 8.20it/s] 17%|#6 | 5/30 [00:00<00:02, 9.25it/s] 17%|#6 | 5/30 [00:00<00:02, 9.25it/s] 20%|## | 6/30 [00:00<00:02, 9.11it/s] 20%|## | 6/30 [00:00<00:02, 9.11it/s] 23%|##3 | 7/30 [00:00<00:02, 9.02it/s] 23%|##3 | 7/30 [00:00<00:02, 9.02it/s] 30%|### | 9/30 [00:00<00:02, 9.58it/s] 30%|### | 9/30 [00:00<00:02, 9.58it/s] 37%|###6 | 11/30 [00:01<00:01, 9.91it/s] 37%|###6 | 11/30 [00:01<00:01, 9.91it/s] 40%|#### | 12/30 [00:01<00:01, 9.67it/s] 40%|#### | 12/30 [00:01<00:01, 9.67it/s] 43%|####3 | 13/30 [00:01<00:01, 9.48it/s] 43%|####3 | 13/30 [00:01<00:01, 9.48it/s] 47%|####6 | 14/30 [00:01<00:01, 9.29it/s] 47%|####6 | 14/30 [00:01<00:01, 9.29it/s] 50%|##### | 15/30 [00:01<00:01, 9.22it/s] 50%|##### | 15/30 [00:01<00:01, 9.22it/s] 53%|#####3 | 16/30 [00:01<00:01, 9.17it/s] 53%|#####3 | 16/30 [00:01<00:01, 9.17it/s] 57%|#####6 | 17/30 [00:01<00:01, 9.12it/s] 57%|#####6 | 17/30 [00:01<00:01, 9.12it/s] 63%|######3 | 19/30 [00:02<00:01, 9.71it/s] 63%|######3 | 19/30 [00:02<00:01, 9.71it/s] 70%|####### | 21/30 [00:02<00:00, 10.02it/s] 70%|####### | 21/30 [00:02<00:00, 10.02it/s] 77%|#######6 | 23/30 [00:02<00:00, 10.51it/s] 77%|#######6 | 23/30 [00:02<00:00, 10.51it/s] 83%|########3 | 25/30 [00:02<00:00, 10.14it/s] 83%|########3 | 25/30 [00:02<00:00, 10.14it/s] 90%|######### | 27/30 [00:02<00:00, 9.76it/s] 90%|######### | 27/30 [00:02<00:00, 9.76it/s] 93%|#########3| 28/30 [00:02<00:00, 9.63it/s] 93%|#########3| 28/30 [00:02<00:00, 9.63it/s] 97%|#########6| 29/30 [00:03<00:00, 9.50it/s] 97%|#########6| 29/30 [00:03<00:00, 9.50it/s] 100%|##########| 30/30 [00:03<00:00, 9.51it/s] 100%|##########| 30/30 [00:03<00:00, 9.51it/s]
- quantizing extras
Moving transformer to CPU
Text Encoder
`torch_dtype` is deprecated! Use `dtype` instead!
`torch_dtype` is deprecated! Use `dtype` instead!
Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 100%|##########| 3/3 [00:00<00:00, 71.36it/s] Loading checkpoint shards: 100%|##########| 3/3 [00:00<00:00, 71.36it/s]
Quantizing Text Encoder
Loading VAE
Making pipe
Preparing Model
Model Loaded
create LoRA network. base dim (rank): 32, alpha: 32
neuron dropout: p=None, rank dropout: p=None, module dropout: p=None
apply LoRA to Conv2d with kernel size (3,3). dim (rank): 16, alpha: 16
create LoRA for Text Encoder: 0 modules.
create LoRA for U-Net: 240 modules.
enable LoRA for U-Net
#### IMPORTANT RESUMING FROM /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v1/my_first_lora_v1_000000500.safetensors ####
Loading from /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v1/my_first_lora_v1_000000500.safetensors
Missing keys: []
Found step 500 in metadata, starting from there
Loading optimizer state from /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v1/optimizer.pt
Updating optimizer LR from params
Dataset: /teamspace/studios/this_studio/ai-toolkit/datasets/sruti
- Preprocessing image dimensions
0%| | 0/52 [00:00<?, ?it/s] 0%| | 0/52 [00:00<?, ?it/s] 15%|#5 | 8/52 [00:00<00:00, 52.84it/s] 15%|#5 | 8/52 [00:00<00:00, 52.84it/s] 29%|##8 | 15/52 [00:00<00:00, 58.81it/s] 29%|##8 | 15/52 [00:00<00:00, 58.81it/s] 42%|####2 | 22/52 [00:00<00:00, 45.70it/s] 42%|####2 | 22/52 [00:00<00:00, 45.70it/s] 52%|#####1 | 27/52 [00:00<00:00, 44.18it/s] 52%|#####1 | 27/52 [00:00<00:00, 44.18it/s] 75%|#######5 | 39/52 [00:00<00:00, 61.62it/s] 75%|#######5 | 39/52 [00:00<00:00, 61.62it/s] 88%|########8 | 46/52 [00:00<00:00, 62.29it/s] 88%|########8 | 46/52 [00:00<00:00, 62.29it/s] 100%|##########| 52/52 [00:00<00:00, 56.53it/s] 100%|##########| 52/52 [00:00<00:00, 56.53it/s]
- Found 52 images
Bucket sizes for /teamspace/studios/this_studio/ai-toolkit/datasets/sruti:
576x992: 4 files
672x992: 6 files
704x1248: 12 files
480x800: 3 files
576x800: 1 files
832x1152: 6 files
480x832: 3 files
1024x1024: 3 files
640x960: 1 files
608x800: 1 files
672x960: 5 files
672x544: 1 files
416x608: 1 files
448x640: 1 files
576x832: 1 files
768x1344: 1 files
768x1280: 1 files
448x768: 1 files
18 buckets made
Dataset: /teamspace/studios/this_studio/ai-toolkit/datasets/sruti
- Preprocessing image dimensions
0%| | 0/52 [00:00<?, ?it/s] 0%| | 0/52 [00:00<?, ?it/s] 100%|##########| 52/52 [00:00<00:00, 44629.39it/s] 100%|##########| 52/52 [00:00<00:00, 44629.39it/s]
- Found 52 images
Bucket sizes for /teamspace/studios/this_studio/ai-toolkit/datasets/sruti:
576x992: 17 files
608x896: 12 files
480x800: 3 files
576x800: 1 files
672x864: 6 files
480x832: 3 files
768x768: 3 files
608x800: 1 files
672x544: 1 files
416x608: 1 files
448x640: 1 files
576x832: 1 files
576x960: 1 files
448x768: 1 files
14 buckets made
Dataset: /teamspace/studios/this_studio/ai-toolkit/datasets/sruti
- Preprocessing image dimensions
0%| | 0/52 [00:00<?, ?it/s] 0%| | 0/52 [00:00<?, ?it/s] 100%|##########| 52/52 [00:00<00:00, 46257.44it/s] 100%|##########| 52/52 [00:00<00:00, 46257.44it/s]
- Found 52 images
Bucket sizes for /teamspace/studios/this_studio/ai-toolkit/datasets/sruti:
384x672: 18 files
416x608: 13 files
384x640: 8 files
416x576: 9 files
512x512: 3 files
544x448: 1 files
6 buckets made
my_first_lora_v1: 17%|#6 | 500/3000 [00:00<?, ?it/s] my_first_lora_v1: 17%|#6 | 500/3000 [00:00<?, ?it/s] my_first_lora_v1: 17%|#6 | 500/3000 [00:02<?, ?it/s, lr: 1.0e-04 loss: 7.922e-02] my_first_lora_v1: 17%|#6 | 500/3000 [00:02<?, ?it/s, lr: 1.0e-04 loss: 7.922e-02] my_first_lora_v1: 17%|#6 | 500/3000 [00:02<?, ?it/s, lr: 1.0e-04 loss: 7.922e-02] my_first_lora_v1: 17%|#6 | 500/3000 [00:02<?, ?it/s, lr: 1.0e-04 loss: 7.922e-02] my_first_lora_v1: 17%|#6 | 500/3000 [00:03<?, ?it/s, lr: 1.0e-04 loss: 5.713e-01] my_first_lora_v1: 17%|#6 | 500/3000 [00:03<?, ?it/s, lr: 1.0e-04 loss: 5.713e-01] my_first_lora_v1: 17%|#6 | 501/3000 [00:04<3:05:19, 4.45s/it, lr: 1.0e-04 loss: 5.887e-01] my_first_lora_v1: 17%|#6 | 501/3000 [00:04<3:05:19, 4.45s/it, lr: 1.0e-04 loss: 5.887e-01] my_first_lora_v1: 17%|#6 | 502/3000 [00:05<1:48:21, 2.60s/it, lr: 1.0e-04 loss: 6.899e-01] my_first_lora_v1: 17%|#6 | 502/3000 [00:05<1:48:21, 2.60s/it, lr: 1.0e-04 loss: 6.899e-01] my_first_lora_v1: 17%|#6 | 503/3000 [00:06<1:26:34, 2.08s/it, lr: 1.0e-04 loss: 7.851e-01] my_first_lora_v1: 17%|#6 | 503/3000 [00:06<1:26:34, 2.08s/it, lr: 1.0e-04 loss: 7.851e-01] my_first_lora_v1: 17%|#6 | 504/3000 [00:08<1:29:35, 2.15s/it, lr: 1.0e-04 loss: 5.455e-01] my_first_lora_v1: 17%|#6 | 504/3000 [00:08<1:29:35, 2.15s/it, lr: 1.0e-04 loss: 5.455e-01] my_first_lora_v1: 17%|#6 | 505/3000 [00:09<1:18:43, 1.89s/it, lr: 1.0e-04 loss: 7.178e-01] my_first_lora_v1: 17%|#6 | 505/3000 [00:09<1:18:43, 1.89s/it, lr: 1.0e-04 loss: 7.178e-01] my_first_lora_v1: 17%|#6 | 506/3000 [00:10<1:15:47, 1.82s/it, lr: 1.0e-04 loss: 7.179e-01] my_first_lora_v1: 17%|#6 | 506/3000 [00:10<1:15:47, 1.82s/it, lr: 1.0e-04 loss: 7.179e-01] my_first_lora_v1: 17%|#6 | 507/3000 [00:11<1:11:12, 1.71s/it, lr: 1.0e-04 loss: 7.898e-01] my_first_lora_v1: 17%|#6 | 507/3000 [00:11<1:11:12, 1.71s/it, lr: 1.0e-04 loss: 7.898e-01] my_first_lora_v1: 17%|#6 | 508/3000 [00:14<1:14:25, 1.79s/it, lr: 1.0e-04 loss: 1.202e-01] my_first_lora_v1: 17%|#6 | 508/3000 [00:14<1:14:25, 1.79s/it, lr: 1.0e-04 loss: 1.202e-01] my_first_lora_v1: 17%|#6 | 509/3000 [00:16<1:14:02, 1.78s/it, lr: 1.0e-04 loss: 7.792e-01] my_first_lora_v1: 17%|#6 | 509/3000 [00:16<1:14:02, 1.78s/it, lr: 1.0e-04 loss: 7.792e-01] my_first_lora_v1: 17%|#7 | 510/3000 [00:17<1:10:52, 1.71s/it, lr: 1.0e-04 loss: 3.275e-01] my_first_lora_v1: 17%|#7 | 510/3000 [00:17<1:10:52, 1.71s/it, lr: 1.0e-04 loss: 3.275e-01] my_first_lora_v1: 17%|#7 | 511/3000 [00:17<1:07:24, 1.62s/it, lr: 1.0e-04 loss: 5.657e-01] my_first_lora_v1: 17%|#7 | 511/3000 [00:17<1:07:24, 1.62s/it, lr: 1.0e-04 loss: 5.657e-01] my_first_lora_v1: 17%|#7 | 512/3000 [00:20<1:12:10, 1.74s/it, lr: 1.0e-04 loss: 1.310e-01] my_first_lora_v1: 17%|#7 | 512/3000 [00:20<1:12:10, 1.74s/it, lr: 1.0e-04 loss: 1.310e-01] my_first_lora_v1: 17%|#7 | 513/3000 [00:21<1:09:11, 1.67s/it, lr: 1.0e-04 loss: 4.133e-01] my_first_lora_v1: 17%|#7 | 513/3000 [00:21<1:09:11, 1.67s/it, lr: 1.0e-04 loss: 4.133e-01] my_first_lora_v1: 17%|#7 | 514/3000 [00:22<1:08:00, 1.64s/it, lr: 1.0e-04 loss: 5.946e-01] my_first_lora_v1: 17%|#7 | 514/3000 [00:22<1:08:00, 1.64s/it, lr: 1.0e-04 loss: 5.946e-01] my_first_lora_v1: 17%|#7 | 515/3000 [00:23<1:05:42, 1.59s/it, lr: 1.0e-04 loss: 7.198e-02] my_first_lora_v1: 17%|#7 | 515/3000 [00:23<1:05:42, 1.59s/it, lr: 1.0e-04 loss: 7.198e-02] my_first_lora_v1: 17%|#7 | 516/3000 [00:25<1:05:42, 1.59s/it, lr: 1.0e-04 loss: 3.937e-02] my_first_lora_v1: 17%|#7 | 516/3000 [00:25<1:05:42, 1.59s/it, lr: 1.0e-04 loss: 3.937e-02] my_first_lora_v1: 17%|#7 | 517/3000 [00:26<1:03:54, 1.54s/it, lr: 1.0e-04 loss: 2.880e-01] my_first_lora_v1: 17%|#7 | 517/3000 [00:26<1:03:54, 1.54s/it, lr: 1.0e-04 loss: 2.880e-01] my_first_lora_v1: 17%|#7 | 518/3000 [00:27<1:02:06, 1.50s/it, lr: 1.0e-04 loss: 5.471e-01] my_first_lora_v1: 17%|#7 | 518/3000 [00:27<1:02:06, 1.50s/it, lr: 1.0e-04 loss: 5.471e-01] my_first_lora_v1: 17%|#7 | 519/3000 [00:27<1:00:33, 1.46s/it, lr: 1.0e-04 loss: 6.222e-01] my_first_lora_v1: 17%|#7 | 519/3000 [00:27<1:00:33, 1.46s/it, lr: 1.0e-04 loss: 6.222e-01] my_first_lora_v1: 17%|#7 | 520/3000 [00:30<1:02:22, 1.51s/it, lr: 1.0e-04 loss: 5.988e-01] my_first_lora_v1: 17%|#7 | 520/3000 [00:30<1:02:22, 1.51s/it, lr: 1.0e-04 loss: 5.988e-01] my_first_lora_v1: 17%|#7 | 521/3000 [00:31<1:02:06, 1.50s/it, lr: 1.0e-04 loss: 7.513e-01] my_first_lora_v1: 17%|#7 | 521/3000 [00:31<1:02:06, 1.50s/it, lr: 1.0e-04 loss: 7.513e-01] my_first_lora_v1: 17%|#7 | 522/3000 [00:32<1:00:45, 1.47s/it, lr: 1.0e-04 loss: 7.143e-01] my_first_lora_v1: 17%|#7 | 522/3000 [00:32<1:00:45, 1.47s/it, lr: 1.0e-04 loss: 7.143e-01] my_first_lora_v1: 17%|#7 | 523/3000 [00:33<1:00:45, 1.47s/it, lr: 1.0e-04 loss: 1.898e-01] my_first_lora_v1: 17%|#7 | 523/3000 [00:33<1:00:45, 1.47s/it, lr: 1.0e-04 loss: 1.898e-01] my_first_lora_v1: 17%|#7 | 524/3000 [00:34<1:00:02, 1.45s/it, lr: 1.0e-04 loss: 4.728e-01] my_first_lora_v1: 17%|#7 | 524/3000 [00:34<1:00:02, 1.45s/it, lr: 1.0e-04 loss: 4.728e-01] my_first_lora_v1: 18%|#7 | 525/3000 [00:37<1:01:28, 1.49s/it, lr: 1.0e-04 loss: 3.384e-01] my_first_lora_v1: 18%|#7 | 525/3000 [00:37<1:01:28, 1.49s/it, lr: 1.0e-04 loss: 3.384e-01] my_first_lora_v1: 18%|#7 | 526/3000 [00:38<1:00:47, 1.47s/it, lr: 1.0e-04 loss: 2.737e-01] my_first_lora_v1: 18%|#7 | 526/3000 [00:38<1:00:47, 1.47s/it, lr: 1.0e-04 loss: 2.737e-01] my_first_lora_v1: 18%|#7 | 527/3000 [00:40<1:02:27, 1.52s/it, lr: 1.0e-04 loss: 7.807e-01] my_first_lora_v1: 18%|#7 | 527/3000 [00:40<1:02:27, 1.52s/it, lr: 1.0e-04 loss: 7.807e-01] my_first_lora_v1: 18%|#7 | 528/3000 [00:43<1:04:02, 1.55s/it, lr: 1.0e-04 loss: 4.485e-01] my_first_lora_v1: 18%|#7 | 528/3000 [00:43<1:04:02, 1.55s/it, lr: 1.0e-04 loss: 4.485e-01] my_first_lora_v1: 18%|#7 | 529/3000 [00:45<1:04:00, 1.55s/it, lr: 1.0e-04 loss: 1.387e-01] my_first_lora_v1: 18%|#7 | 529/3000 [00:45<1:04:00, 1.55s/it, lr: 1.0e-04 loss: 1.387e-01] my_first_lora_v1: 18%|#7 | 530/3000 [00:45<1:02:56, 1.53s/it, lr: 1.0e-04 loss: 7.452e-01] my_first_lora_v1: 18%|#7 | 530/3000 [00:45<1:02:56, 1.53s/it, lr: 1.0e-04 loss: 7.452e-01] my_first_lora_v1: 18%|#7 | 531/3000 [00:47<1:02:48, 1.53s/it, lr: 1.0e-04 loss: 3.003e-01] my_first_lora_v1: 18%|#7 | 531/3000 [00:47<1:02:48, 1.53s/it, lr: 1.0e-04 loss: 3.003e-01] my_first_lora_v1: 18%|#7 | 532/3000 [00:48<1:01:52, 1.50s/it, lr: 1.0e-04 loss: 5.769e-01] my_first_lora_v1: 18%|#7 | 532/3000 [00:48<1:01:52, 1.50s/it, lr: 1.0e-04 loss: 5.769e-01] my_first_lora_v1: 18%|#7 | 533/3000 [00:49<1:01:48, 1.50s/it, lr: 1.0e-04 loss: 6.600e-01] my_first_lora_v1: 18%|#7 | 533/3000 [00:49<1:01:48, 1.50s/it, lr: 1.0e-04 loss: 6.600e-01] my_first_lora_v1: 18%|#7 | 534/3000 [00:50<1:00:55, 1.48s/it, lr: 1.0e-04 loss: 5.852e-01] my_first_lora_v1: 18%|#7 | 534/3000 [00:50<1:00:55, 1.48s/it, lr: 1.0e-04 loss: 5.852e-01] my_first_lora_v1: 18%|#7 | 535/3000 [00:51<1:00:05, 1.46s/it, lr: 1.0e-04 loss: 9.749e-02] my_first_lora_v1: 18%|#7 | 535/3000 [00:51<1:00:05, 1.46s/it, lr: 1.0e-04 loss: 9.749e-02] my_first_lora_v1: 18%|#7 | 536/3000 [00:51<59:16, 1.44s/it, lr: 1.0e-04 loss: 5.240e-01] my_first_lora_v1: 18%|#7 | 536/3000 [00:51<59:16, 1.44s/it, lr: 1.0e-04 loss: 5.240e-01] my_first_lora_v1: 18%|#7 | 537/3000 [00:53<59:29, 1.45s/it, lr: 1.0e-04 loss: 5.111e-01] my_first_lora_v1: 18%|#7 | 537/3000 [00:53<59:29, 1.45s/it, lr: 1.0e-04 loss: 5.111e-01] my_first_lora_v1: 18%|#7 | 538/3000 [00:54<58:58, 1.44s/it, lr: 1.0e-04 loss: 6.515e-01] my_first_lora_v1: 18%|#7 | 538/3000 [00:54<58:58, 1.44s/it, lr: 1.0e-04 loss: 6.515e-01] my_first_lora_v1: 18%|#7 | 539/3000 [00:57<1:00:11, 1.47s/it, lr: 1.0e-04 loss: 6.104e-01] my_first_lora_v1: 18%|#7 | 539/3000 [00:57<1:00:11, 1.47s/it, lr: 1.0e-04 loss: 6.104e-01] my_first_lora_v1: 18%|#8 | 540/3000 [00:58<1:00:23, 1.47s/it, lr: 1.0e-04 loss: 1.705e-01] my_first_lora_v1: 18%|#8 | 540/3000 [00:58<1:00:23, 1.47s/it, lr: 1.0e-04 loss: 1.705e-01] my_first_lora_v1: 18%|#8 | 541/3000 [01:00<1:00:37, 1.48s/it, lr: 1.0e-04 loss: 2.235e-01] my_first_lora_v1: 18%|#8 | 541/3000 [01:00<1:00:37, 1.48s/it, lr: 1.0e-04 loss: 2.235e-01] my_first_lora_v1: 18%|#8 | 542/3000 [01:01<59:56, 1.46s/it, lr: 1.0e-04 loss: 7.822e-01] my_first_lora_v1: 18%|#8 | 542/3000 [01:01<59:56, 1.46s/it, lr: 1.0e-04 loss: 7.822e-01] my_first_lora_v1: 18%|#8 | 543/3000 [01:02<59:15, 1.45s/it, lr: 1.0e-04 loss: 2.012e-01] my_first_lora_v1: 18%|#8 | 543/3000 [01:02<59:15, 1.45s/it, lr: 1.0e-04 loss: 2.012e-01] my_first_lora_v1: 18%|#8 | 544/3000 [01:03<59:14, 1.45s/it, lr: 1.0e-04 loss: 4.028e-01] my_first_lora_v1: 18%|#8 | 544/3000 [01:03<59:14, 1.45s/it, lr: 1.0e-04 loss: 4.028e-01] my_first_lora_v1: 18%|#8 | 545/3000 [01:04<58:35, 1.43s/it, lr: 1.0e-04 loss: 4.118e-01] my_first_lora_v1: 18%|#8 | 545/3000 [01:04<58:35, 1.43s/it, lr: 1.0e-04 loss: 4.118e-01] my_first_lora_v1: 18%|#8 | 546/3000 [01:05<58:35, 1.43s/it, lr: 1.0e-04 loss: 3.879e-01] my_first_lora_v1: 18%|#8 | 546/3000 [01:05<58:35, 1.43s/it, lr: 1.0e-04 loss: 3.879e-01] my_first_lora_v1: 18%|#8 | 547/3000 [01:06<58:00, 1.42s/it, lr: 1.0e-04 loss: 1.645e-02] my_first_lora_v1: 18%|#8 | 547/3000 [01:06<58:00, 1.42s/it, lr: 1.0e-04 loss: 1.645e-02] my_first_lora_v1: 18%|#8 | 548/3000 [01:08<58:01, 1.42s/it, lr: 1.0e-04 loss: 8.212e-02] my_first_lora_v1: 18%|#8 | 548/3000 [01:08<58:01, 1.42s/it, lr: 1.0e-04 loss: 8.212e-02] my_first_lora_v1: 18%|#8 | 549/3000 [01:09<58:01, 1.42s/it, lr: 1.0e-04 loss: 9.392e-01] my_first_lora_v1: 18%|#8 | 549/3000 [01:09<58:01, 1.42s/it, lr: 1.0e-04 loss: 9.392e-01] my_first_lora_v1: 18%|#8 | 550/3000 [01:12<59:13, 1.45s/it, lr: 1.0e-04 loss: 8.099e-01] my_first_lora_v1: 18%|#8 | 550/3000 [01:12<59:13, 1.45s/it, lr: 1.0e-04 loss: 8.099e-01] my_first_lora_v1: 18%|#8 | 551/3000 [01:13<58:41, 1.44s/it, lr: 1.0e-04 loss: 1.429e-01] my_first_lora_v1: 18%|#8 | 551/3000 [01:13<58:41, 1.44s/it, lr: 1.0e-04 loss: 1.429e-01] my_first_lora_v1: 18%|#8 | 552/3000 [01:14<58:40, 1.44s/it, lr: 1.0e-04 loss: 8.382e-01] my_first_lora_v1: 18%|#8 | 552/3000 [01:14<58:40, 1.44s/it, lr: 1.0e-04 loss: 8.382e-01] my_first_lora_v1: 18%|#8 | 553/3000 [01:15<58:20, 1.43s/it, lr: 1.0e-04 loss: 6.671e-01] my_first_lora_v1: 18%|#8 | 553/3000 [01:15<58:20, 1.43s/it, lr: 1.0e-04 loss: 6.671e-01] my_first_lora_v1: 18%|#8 | 554/3000 [01:16<57:49, 1.42s/it, lr: 1.0e-04 loss: 1.314e-01] my_first_lora_v1: 18%|#8 | 554/3000 [01:16<57:49, 1.42s/it, lr: 1.0e-04 loss: 1.314e-01] my_first_lora_v1: 18%|#8 | 555/3000 [01:17<57:21, 1.41s/it, lr: 1.0e-04 loss: 9.338e-01] my_first_lora_v1: 18%|#8 | 555/3000 [01:17<57:21, 1.41s/it, lr: 1.0e-04 loss: 9.338e-01] my_first_lora_v1: 19%|#8 | 556/3000 [01:18<56:54, 1.40s/it, lr: 1.0e-04 loss: 3.569e-01] my_first_lora_v1: 19%|#8 | 556/3000 [01:18<56:54, 1.40s/it, lr: 1.0e-04 loss: 3.569e-01] my_first_lora_v1: 19%|#8 | 557/3000 [01:19<56:25, 1.39s/it, lr: 1.0e-04 loss: 6.860e-01] my_first_lora_v1: 19%|#8 | 557/3000 [01:19<56:25, 1.39s/it, lr: 1.0e-04 loss: 6.860e-01] my_first_lora_v1: 19%|#8 | 558/3000 [01:20<56:27, 1.39s/it, lr: 1.0e-04 loss: 4.700e-01] my_first_lora_v1: 19%|#8 | 558/3000 [01:20<56:27, 1.39s/it, lr: 1.0e-04 loss: 4.700e-01] my_first_lora_v1: 19%|#8 | 559/3000 [01:21<56:28, 1.39s/it, lr: 1.0e-04 loss: 9.211e-01] my_first_lora_v1: 19%|#8 | 559/3000 [01:21<56:28, 1.39s/it, lr: 1.0e-04 loss: 9.211e-01] my_first_lora_v1: 19%|#8 | 560/3000 [01:23<56:38, 1.39s/it, lr: 1.0e-04 loss: 2.297e-01] my_first_lora_v1: 19%|#8 | 560/3000 [01:23<56:38, 1.39s/it, lr: 1.0e-04 loss: 2.297e-01] my_first_lora_v1: 19%|#8 | 561/3000 [01:25<56:39, 1.39s/it, lr: 1.0e-04 loss: 4.912e-01] my_first_lora_v1: 19%|#8 | 561/3000 [01:25<56:39, 1.39s/it, lr: 1.0e-04 loss: 4.912e-01] my_first_lora_v1: 19%|#8 | 562/3000 [01:27<57:34, 1.42s/it, lr: 1.0e-04 loss: 4.022e-01] my_first_lora_v1: 19%|#8 | 562/3000 [01:27<57:34, 1.42s/it, lr: 1.0e-04 loss: 4.022e-01] my_first_lora_v1: 19%|#8 | 563/3000 [01:30<58:11, 1.43s/it, lr: 1.0e-04 loss: 5.133e-02] my_first_lora_v1: 19%|#8 | 563/3000 [01:30<58:11, 1.43s/it, lr: 1.0e-04 loss: 5.133e-02] my_first_lora_v1: 19%|#8 | 564/3000 [01:31<57:54, 1.43s/it, lr: 1.0e-04 loss: 1.754e-01] my_first_lora_v1: 19%|#8 | 564/3000 [01:31<57:54, 1.43s/it, lr: 1.0e-04 loss: 1.754e-01] my_first_lora_v1: 19%|#8 | 565/3000 [01:32<57:53, 1.43s/it, lr: 1.0e-04 loss: 3.328e-01] my_first_lora_v1: 19%|#8 | 565/3000 [01:32<57:53, 1.43s/it, lr: 1.0e-04 loss: 3.328e-01] my_first_lora_v1: 19%|#8 | 566/3000 [01:33<57:39, 1.42s/it, lr: 1.0e-04 loss: 1.757e-01] my_first_lora_v1: 19%|#8 | 566/3000 [01:33<57:39, 1.42s/it, lr: 1.0e-04 loss: 1.757e-01] my_first_lora_v1: 19%|#8 | 567/3000 [01:34<57:14, 1.41s/it, lr: 1.0e-04 loss: 8.516e-01] my_first_lora_v1: 19%|#8 | 567/3000 [01:34<57:14, 1.41s/it, lr: 1.0e-04 loss: 8.516e-01] my_first_lora_v1: 19%|#8 | 568/3000 [01:35<56:58, 1.41s/it, lr: 1.0e-04 loss: 5.956e-01] my_first_lora_v1: 19%|#8 | 568/3000 [01:35<56:58, 1.41s/it, lr: 1.0e-04 loss: 5.956e-01] my_first_lora_v1: 19%|#8 | 569/3000 [01:37<57:30, 1.42s/it, lr: 1.0e-04 loss: 5.797e-01] my_first_lora_v1: 19%|#8 | 569/3000 [01:37<57:30, 1.42s/it, lr: 1.0e-04 loss: 5.797e-01] my_first_lora_v1: 19%|#9 | 570/3000 [01:40<58:01, 1.43s/it, lr: 1.0e-04 loss: 4.576e-02] my_first_lora_v1: 19%|#9 | 570/3000 [01:40<58:01, 1.43s/it, lr: 1.0e-04 loss: 4.576e-02] my_first_lora_v1: 19%|#9 | 571/3000 [01:41<57:38, 1.42s/it, lr: 1.0e-04 loss: 1.129e-01] my_first_lora_v1: 19%|#9 | 571/3000 [01:41<57:38, 1.42s/it, lr: 1.0e-04 loss: 1.129e-01] my_first_lora_v1: 19%|#9 | 572/3000 [01:41<57:16, 1.42s/it, lr: 1.0e-04 loss: 6.309e-01] my_first_lora_v1: 19%|#9 | 572/3000 [01:41<57:16, 1.42s/it, lr: 1.0e-04 loss: 6.309e-01] my_first_lora_v1: 19%|#9 | 573/3000 [01:43<57:09, 1.41s/it, lr: 1.0e-04 loss: 7.422e-02] my_first_lora_v1: 19%|#9 | 573/3000 [01:43<57:09, 1.41s/it, lr: 1.0e-04 loss: 7.422e-02] my_first_lora_v1: 19%|#9 | 574/3000 [01:44<57:18, 1.42s/it, lr: 1.0e-04 loss: 1.651e-01] my_first_lora_v1: 19%|#9 | 574/3000 [01:44<57:18, 1.42s/it, lr: 1.0e-04 loss: 1.651e-01] my_first_lora_v1: 19%|#9 | 575/3000 [01:47<57:58, 1.43s/it, lr: 1.0e-04 loss: 4.300e-01] my_first_lora_v1: 19%|#9 | 575/3000 [01:47<57:58, 1.43s/it, lr: 1.0e-04 loss: 4.300e-01] my_first_lora_v1: 19%|#9 | 576/3000 [01:48<57:56, 1.43s/it, lr: 1.0e-04 loss: 7.016e-01] my_first_lora_v1: 19%|#9 | 576/3000 [01:48<57:56, 1.43s/it, lr: 1.0e-04 loss: 7.016e-01] my_first_lora_v1: 19%|#9 | 577/3000 [01:50<57:53, 1.43s/it, lr: 1.0e-04 loss: 4.581e-01] my_first_lora_v1: 19%|#9 | 577/3000 [01:50<57:53, 1.43s/it, lr: 1.0e-04 loss: 4.581e-01] my_first_lora_v1: 19%|#9 | 578/3000 [01:51<57:53, 1.43s/it, lr: 1.0e-04 loss: 7.403e-01] my_first_lora_v1: 19%|#9 | 578/3000 [01:51<57:53, 1.43s/it, lr: 1.0e-04 loss: 7.403e-01] my_first_lora_v1: 19%|#9 | 579/3000 [01:53<57:58, 1.44s/it, lr: 1.0e-04 loss: 1.271e-01] my_first_lora_v1: 19%|#9 | 579/3000 [01:53<57:58, 1.44s/it, lr: 1.0e-04 loss: 1.271e-01] my_first_lora_v1: 19%|#9 | 580/3000 [01:55<58:10, 1.44s/it, lr: 1.0e-04 loss: 7.147e-01] my_first_lora_v1: 19%|#9 | 580/3000 [01:55<58:10, 1.44s/it, lr: 1.0e-04 loss: 7.147e-01] my_first_lora_v1: 19%|#9 | 581/3000 [01:56<58:09, 1.44s/it, lr: 1.0e-04 loss: 3.768e-01] my_first_lora_v1: 19%|#9 | 581/3000 [01:56<58:09, 1.44s/it, lr: 1.0e-04 loss: 3.768e-01] my_first_lora_v1: 19%|#9 | 582/3000 [01:58<58:06, 1.44s/it, lr: 1.0e-04 loss: 6.908e-01] my_first_lora_v1: 19%|#9 | 582/3000 [01:58<58:06, 1.44s/it, lr: 1.0e-04 loss: 6.908e-01] my_first_lora_v1: 19%|#9 | 583/3000 [01:59<57:45, 1.43s/it, lr: 1.0e-04 loss: 6.475e-01] my_first_lora_v1: 19%|#9 | 583/3000 [01:59<57:45, 1.43s/it, lr: 1.0e-04 loss: 6.475e-01] my_first_lora_v1: 19%|#9 | 584/3000 [01:59<57:24, 1.43s/it, lr: 1.0e-04 loss: 5.136e-01] my_first_lora_v1: 19%|#9 | 584/3000 [01:59<57:24, 1.43s/it, lr: 1.0e-04 loss: 5.136e-01] my_first_lora_v1: 20%|#9 | 585/3000 [02:00<57:04, 1.42s/it, lr: 1.0e-04 loss: 6.305e-01] my_first_lora_v1: 20%|#9 | 585/3000 [02:00<57:04, 1.42s/it, lr: 1.0e-04 loss: 6.305e-01] my_first_lora_v1: 20%|#9 | 586/3000 [02:01<56:47, 1.41s/it, lr: 1.0e-04 loss: 7.490e-01] my_first_lora_v1: 20%|#9 | 586/3000 [02:01<56:47, 1.41s/it, lr: 1.0e-04 loss: 7.490e-01] my_first_lora_v1: 20%|#9 | 587/3000 [02:02<56:45, 1.41s/it, lr: 1.0e-04 loss: 7.152e-01] my_first_lora_v1: 20%|#9 | 587/3000 [02:02<56:45, 1.41s/it, lr: 1.0e-04 loss: 7.152e-01] my_first_lora_v1: 20%|#9 | 588/3000 [02:03<56:28, 1.40s/it, lr: 1.0e-04 loss: 1.740e-01] my_first_lora_v1: 20%|#9 | 588/3000 [02:03<56:28, 1.40s/it, lr: 1.0e-04 loss: 1.740e-01] my_first_lora_v1: 20%|#9 | 589/3000 [02:04<56:26, 1.40s/it, lr: 1.0e-04 loss: 2.774e-01] my_first_lora_v1: 20%|#9 | 589/3000 [02:04<56:26, 1.40s/it, lr: 1.0e-04 loss: 2.774e-01] my_first_lora_v1: 20%|#9 | 590/3000 [02:06<56:26, 1.41s/it, lr: 1.0e-04 loss: 7.028e-01] my_first_lora_v1: 20%|#9 | 590/3000 [02:06<56:26, 1.41s/it, lr: 1.0e-04 loss: 7.028e-01] my_first_lora_v1: 20%|#9 | 591/3000 [02:07<56:09, 1.40s/it, lr: 1.0e-04 loss: 2.368e-02] my_first_lora_v1: 20%|#9 | 591/3000 [02:07<56:09, 1.40s/it, lr: 1.0e-04 loss: 2.368e-02] my_first_lora_v1: 20%|#9 | 592/3000 [02:09<56:33, 1.41s/it, lr: 1.0e-04 loss: 2.632e-01] my_first_lora_v1: 20%|#9 | 592/3000 [02:09<56:33, 1.41s/it, lr: 1.0e-04 loss: 2.632e-01] my_first_lora_v1: 20%|#9 | 593/3000 [02:10<56:16, 1.40s/it, lr: 1.0e-04 loss: 1.463e-01] my_first_lora_v1: 20%|#9 | 593/3000 [02:10<56:16, 1.40s/it, lr: 1.0e-04 loss: 1.463e-01] my_first_lora_v1: 20%|#9 | 594/3000 [02:12<56:22, 1.41s/it, lr: 1.0e-04 loss: 3.245e-01] my_first_lora_v1: 20%|#9 | 594/3000 [02:12<56:22, 1.41s/it, lr: 1.0e-04 loss: 3.245e-01] my_first_lora_v1: 20%|#9 | 595/3000 [02:12<56:05, 1.40s/it, lr: 1.0e-04 loss: 2.043e-01] my_first_lora_v1: 20%|#9 | 595/3000 [02:12<56:05, 1.40s/it, lr: 1.0e-04 loss: 2.043e-01] my_first_lora_v1: 20%|#9 | 596/3000 [02:14<56:12, 1.40s/it, lr: 1.0e-04 loss: 7.554e-01] my_first_lora_v1: 20%|#9 | 596/3000 [02:14<56:12, 1.40s/it, lr: 1.0e-04 loss: 7.554e-01] my_first_lora_v1: 20%|#9 | 597/3000 [02:16<56:18, 1.41s/it, lr: 1.0e-04 loss: 5.966e-01] my_first_lora_v1: 20%|#9 | 597/3000 [02:16<56:18, 1.41s/it, lr: 1.0e-04 loss: 5.966e-01] my_first_lora_v1: 20%|#9 | 598/3000 [02:17<56:18, 1.41s/it, lr: 1.0e-04 loss: 5.751e-01] my_first_lora_v1: 20%|#9 | 598/3000 [02:17<56:18, 1.41s/it, lr: 1.0e-04 loss: 5.751e-01] my_first_lora_v1: 20%|#9 | 599/3000 [02:18<56:02, 1.40s/it, lr: 1.0e-04 loss: 1.461e-01] my_first_lora_v1: 20%|#9 | 599/3000 [02:18<56:02, 1.40s/it, lr: 1.0e-04 loss: 1.461e-01] my_first_lora_v1: 20%|## | 600/3000 [02:19<55:46, 1.39s/it, lr: 1.0e-04 loss: 3.433e-01] my_first_lora_v1: 20%|## | 600/3000 [02:19<55:46, 1.39s/it, lr: 1.0e-04 loss: 3.433e-01] my_first_lora_v1: 20%|## | 601/3000 [02:20<55:45, 1.39s/it, lr: 1.0e-04 loss: 1.673e-01] my_first_lora_v1: 20%|## | 601/3000 [02:20<55:45, 1.39s/it, lr: 1.0e-04 loss: 1.673e-01] my_first_lora_v1: 20%|## | 602/3000 [02:21<55:29, 1.39s/it, lr: 1.0e-04 loss: 7.576e-01] my_first_lora_v1: 20%|## | 602/3000 [02:21<55:29, 1.39s/it, lr: 1.0e-04 loss: 7.576e-01] my_first_lora_v1: 20%|## | 603/3000 [02:23<55:32, 1.39s/it, lr: 1.0e-04 loss: 6.373e-01] my_first_lora_v1: 20%|## | 603/3000 [02:23<55:32, 1.39s/it, lr: 1.0e-04 loss: 6.373e-01] my_first_lora_v1: 20%|## | 604/3000 [02:25<55:59, 1.40s/it, lr: 1.0e-04 loss: 3.169e-01] my_first_lora_v1: 20%|## | 604/3000 [02:25<55:59, 1.40s/it, lr: 1.0e-04 loss: 3.169e-01] my_first_lora_v1: 20%|## | 605/3000 [02:26<55:49, 1.40s/it, lr: 1.0e-04 loss: 5.859e-01] my_first_lora_v1: 20%|## | 605/3000 [02:26<55:49, 1.40s/it, lr: 1.0e-04 loss: 5.859e-01] my_first_lora_v1: 20%|## | 606/3000 [02:28<55:50, 1.40s/it, lr: 1.0e-04 loss: 4.316e-01] my_first_lora_v1: 20%|## | 606/3000 [02:28<55:50, 1.40s/it, lr: 1.0e-04 loss: 4.316e-01] my_first_lora_v1: 20%|## | 607/3000 [02:29<55:45, 1.40s/it, lr: 1.0e-04 loss: 5.392e-01] my_first_lora_v1: 20%|## | 607/3000 [02:29<55:45, 1.40s/it, lr: 1.0e-04 loss: 5.392e-01] my_first_lora_v1: 20%|## | 608/3000 [02:30<55:31, 1.39s/it, lr: 1.0e-04 loss: 3.521e-01] my_first_lora_v1: 20%|## | 608/3000 [02:30<55:31, 1.39s/it, lr: 1.0e-04 loss: 3.521e-01] my_first_lora_v1: 20%|## | 609/3000 [02:32<55:52, 1.40s/it, lr: 1.0e-04 loss: 1.161e-01] my_first_lora_v1: 20%|## | 609/3000 [02:32<55:52, 1.40s/it, lr: 1.0e-04 loss: 1.161e-01] my_first_lora_v1: 20%|## | 610/3000 [02:33<55:38, 1.40s/it, lr: 1.0e-04 loss: 2.101e-01] my_first_lora_v1: 20%|## | 610/3000 [02:33<55:38, 1.40s/it, lr: 1.0e-04 loss: 2.101e-01] my_first_lora_v1: 20%|## | 611/3000 [02:35<55:39, 1.40s/it, lr: 1.0e-04 loss: 3.029e-01] my_first_lora_v1: 20%|## | 611/3000 [02:35<55:39, 1.40s/it, lr: 1.0e-04 loss: 3.029e-01] my_first_lora_v1: 20%|## | 612/3000 [02:35<55:25, 1.39s/it, lr: 1.0e-04 loss: 2.024e-02] my_first_lora_v1: 20%|## | 612/3000 [02:35<55:25, 1.39s/it, lr: 1.0e-04 loss: 2.024e-02] my_first_lora_v1: 20%|## | 613/3000 [02:36<55:14, 1.39s/it, lr: 1.0e-04 loss: 6.526e-01] my_first_lora_v1: 20%|## | 613/3000 [02:36<55:14, 1.39s/it, lr: 1.0e-04 loss: 6.526e-01] my_first_lora_v1: 20%|## | 614/3000 [02:38<55:21, 1.39s/it, lr: 1.0e-04 loss: 3.895e-01] my_first_lora_v1: 20%|## | 614/3000 [02:38<55:21, 1.39s/it, lr: 1.0e-04 loss: 3.895e-01] my_first_lora_v1: 20%|## | 615/3000 [02:40<55:21, 1.39s/it, lr: 1.0e-04 loss: 6.142e-01] my_first_lora_v1: 20%|## | 615/3000 [02:40<55:21, 1.39s/it, lr: 1.0e-04 loss: 6.142e-01] my_first_lora_v1: 21%|## | 616/3000 [02:40<55:07, 1.39s/it, lr: 1.0e-04 loss: 2.092e-01] my_first_lora_v1: 21%|## | 616/3000 [02:40<55:07, 1.39s/it, lr: 1.0e-04 loss: 2.092e-01] my_first_lora_v1: 21%|## | 617/3000 [02:41<54:53, 1.38s/it, lr: 1.0e-04 loss: 1.415e-01] my_first_lora_v1: 21%|## | 617/3000 [02:41<54:53, 1.38s/it, lr: 1.0e-04 loss: 1.415e-01] my_first_lora_v1: 21%|## | 618/3000 [02:43<54:54, 1.38s/it, lr: 1.0e-04 loss: 1.287e-01] my_first_lora_v1: 21%|## | 618/3000 [02:43<54:54, 1.38s/it, lr: 1.0e-04 loss: 1.287e-01] my_first_lora_v1: 21%|## | 619/3000 [02:44<54:41, 1.38s/it, lr: 1.0e-04 loss: 8.439e-01] my_first_lora_v1: 21%|## | 619/3000 [02:44<54:41, 1.38s/it, lr: 1.0e-04 loss: 8.439e-01] my_first_lora_v1: 21%|## | 620/3000 [02:45<54:34, 1.38s/it, lr: 1.0e-04 loss: 7.732e-01] my_first_lora_v1: 21%|## | 620/3000 [02:45<54:34, 1.38s/it, lr: 1.0e-04 loss: 7.732e-01] my_first_lora_v1: 21%|## | 621/3000 [02:45<54:21, 1.37s/it, lr: 1.0e-04 loss: 8.604e-01] my_first_lora_v1: 21%|## | 621/3000 [02:45<54:21, 1.37s/it, lr: 1.0e-04 loss: 8.604e-01] my_first_lora_v1: 21%|## | 622/3000 [02:47<54:22, 1.37s/it, lr: 1.0e-04 loss: 2.706e-01] my_first_lora_v1: 21%|## | 622/3000 [02:47<54:22, 1.37s/it, lr: 1.0e-04 loss: 2.706e-01] my_first_lora_v1: 21%|## | 623/3000 [02:48<54:10, 1.37s/it, lr: 1.0e-04 loss: 6.800e-01] my_first_lora_v1: 21%|## | 623/3000 [02:48<54:10, 1.37s/it, lr: 1.0e-04 loss: 6.800e-01] my_first_lora_v1: 21%|## | 624/3000 [02:50<54:28, 1.38s/it, lr: 1.0e-04 loss: 7.578e-01] my_first_lora_v1: 21%|## | 624/3000 [02:50<54:28, 1.38s/it, lr: 1.0e-04 loss: 7.578e-01] my_first_lora_v1: 21%|## | 625/3000 [02:51<54:16, 1.37s/it, lr: 1.0e-04 loss: 7.610e-01] my_first_lora_v1: 21%|## | 625/3000 [02:51<54:16, 1.37s/it, lr: 1.0e-04 loss: 7.610e-01] my_first_lora_v1: 21%|## | 626/3000 [02:52<54:16, 1.37s/it, lr: 1.0e-04 loss: 1.142e-01] my_first_lora_v1: 21%|## | 626/3000 [02:52<54:16, 1.37s/it, lr: 1.0e-04 loss: 1.142e-01] my_first_lora_v1: 21%|## | 627/3000 [02:53<54:04, 1.37s/it, lr: 1.0e-04 loss: 7.469e-01] my_first_lora_v1: 21%|## | 627/3000 [02:53<54:04, 1.37s/it, lr: 1.0e-04 loss: 7.469e-01] my_first_lora_v1: 21%|## | 628/3000 [02:54<53:52, 1.36s/it, lr: 1.0e-04 loss: 5.950e-01] my_first_lora_v1: 21%|## | 628/3000 [02:54<53:52, 1.36s/it, lr: 1.0e-04 loss: 5.950e-01] my_first_lora_v1: 21%|## | 629/3000 [02:56<54:09, 1.37s/it, lr: 1.0e-04 loss: 2.114e-01] my_first_lora_v1: 21%|## | 629/3000 [02:56<54:09, 1.37s/it, lr: 1.0e-04 loss: 2.114e-01] my_first_lora_v1: 21%|##1 | 630/3000 [02:58<54:06, 1.37s/it, lr: 1.0e-04 loss: 6.602e-01] my_first_lora_v1: 21%|##1 | 630/3000 [02:58<54:06, 1.37s/it, lr: 1.0e-04 loss: 6.602e-01] my_first_lora_v1: 21%|##1 | 631/3000 [02:59<54:02, 1.37s/it, lr: 1.0e-04 loss: 2.018e-01] my_first_lora_v1: 21%|##1 | 631/3000 [02:59<54:02, 1.37s/it, lr: 1.0e-04 loss: 2.018e-01] my_first_lora_v1: 21%|##1 | 632/3000 [03:00<53:55, 1.37s/it, lr: 1.0e-04 loss: 5.567e-02] my_first_lora_v1: 21%|##1 | 632/3000 [03:00<53:55, 1.37s/it, lr: 1.0e-04 loss: 5.567e-02] my_first_lora_v1: 21%|##1 | 633/3000 [03:01<53:43, 1.36s/it, lr: 1.0e-04 loss: 2.245e-01] my_first_lora_v1: 21%|##1 | 633/3000 [03:01<53:43, 1.36s/it, lr: 1.0e-04 loss: 2.245e-01] my_first_lora_v1: 21%|##1 | 634/3000 [03:02<53:46, 1.36s/it, lr: 1.0e-04 loss: 6.502e-01] my_first_lora_v1: 21%|##1 | 634/3000 [03:02<53:46, 1.36s/it, lr: 1.0e-04 loss: 6.502e-01] my_first_lora_v1: 21%|##1 | 635/3000 [03:04<53:47, 1.36s/it, lr: 1.0e-04 loss: 2.388e-01] my_first_lora_v1: 21%|##1 | 635/3000 [03:04<53:47, 1.36s/it, lr: 1.0e-04 loss: 2.388e-01] my_first_lora_v1: 21%|##1 | 636/3000 [03:05<53:47, 1.37s/it, lr: 1.0e-04 loss: 6.186e-01] my_first_lora_v1: 21%|##1 | 636/3000 [03:05<53:47, 1.37s/it, lr: 1.0e-04 loss: 6.186e-01] my_first_lora_v1: 21%|##1 | 637/3000 [03:06<53:40, 1.36s/it, lr: 1.0e-04 loss: 9.820e-02] my_first_lora_v1: 21%|##1 | 637/3000 [03:06<53:40, 1.36s/it, lr: 1.0e-04 loss: 9.820e-02] my_first_lora_v1: 21%|##1 | 638/3000 [03:07<53:34, 1.36s/it, lr: 1.0e-04 loss: 7.029e-01] my_first_lora_v1: 21%|##1 | 638/3000 [03:07<53:34, 1.36s/it, lr: 1.0e-04 loss: 7.029e-01] my_first_lora_v1: 21%|##1 | 639/3000 [03:10<53:54, 1.37s/it, lr: 1.0e-04 loss: 4.288e-01] my_first_lora_v1: 21%|##1 | 639/3000 [03:10<53:54, 1.37s/it, lr: 1.0e-04 loss: 4.288e-01] my_first_lora_v1: 21%|##1 | 640/3000 [03:12<53:59, 1.37s/it, lr: 1.0e-04 loss: 7.121e-02] my_first_lora_v1: 21%|##1 | 640/3000 [03:12<53:59, 1.37s/it, lr: 1.0e-04 loss: 7.121e-02] my_first_lora_v1: 21%|##1 | 641/3000 [03:12<53:48, 1.37s/it, lr: 1.0e-04 loss: 7.981e-01] my_first_lora_v1: 21%|##1 | 641/3000 [03:12<53:48, 1.37s/it, lr: 1.0e-04 loss: 7.981e-01] my_first_lora_v1: 21%|##1 | 642/3000 [03:13<53:38, 1.36s/it, lr: 1.0e-04 loss: 6.734e-01] my_first_lora_v1: 21%|##1 | 642/3000 [03:13<53:38, 1.36s/it, lr: 1.0e-04 loss: 6.734e-01] my_first_lora_v1: 21%|##1 | 643/3000 [03:15<53:35, 1.36s/it, lr: 1.0e-04 loss: 3.681e-01] my_first_lora_v1: 21%|##1 | 643/3000 [03:15<53:35, 1.36s/it, lr: 1.0e-04 loss: 3.681e-01] my_first_lora_v1: 21%|##1 | 644/3000 [03:16<53:37, 1.37s/it, lr: 1.0e-04 loss: 3.339e-01] my_first_lora_v1: 21%|##1 | 644/3000 [03:16<53:37, 1.37s/it, lr: 1.0e-04 loss: 3.339e-01] my_first_lora_v1: 22%|##1 | 645/3000 [03:19<53:56, 1.37s/it, lr: 1.0e-04 loss: 7.698e-01] my_first_lora_v1: 22%|##1 | 645/3000 [03:19<53:56, 1.37s/it, lr: 1.0e-04 loss: 7.698e-01] my_first_lora_v1: 22%|##1 | 646/3000 [03:20<53:49, 1.37s/it, lr: 1.0e-04 loss: 6.759e-01] my_first_lora_v1: 22%|##1 | 646/3000 [03:20<53:49, 1.37s/it, lr: 1.0e-04 loss: 6.759e-01] my_first_lora_v1: 22%|##1 | 647/3000 [03:21<53:46, 1.37s/it, lr: 1.0e-04 loss: 4.445e-01] my_first_lora_v1: 22%|##1 | 647/3000 [03:21<53:46, 1.37s/it, lr: 1.0e-04 loss: 4.445e-01] my_first_lora_v1: 22%|##1 | 648/3000 [03:23<53:49, 1.37s/it, lr: 1.0e-04 loss: 4.623e-01] my_first_lora_v1: 22%|##1 | 648/3000 [03:23<53:49, 1.37s/it, lr: 1.0e-04 loss: 4.623e-01] my_first_lora_v1: 22%|##1 | 649/3000 [03:24<53:48, 1.37s/it, lr: 1.0e-04 loss: 4.062e-01] my_first_lora_v1: 22%|##1 | 649/3000 [03:24<53:48, 1.37s/it, lr: 1.0e-04 loss: 4.062e-01] my_first_lora_v1: 22%|##1 | 650/3000 [03:26<53:47, 1.37s/it, lr: 1.0e-04 loss: 3.730e-01] my_first_lora_v1: 22%|##1 | 650/3000 [03:26<53:47, 1.37s/it, lr: 1.0e-04 loss: 3.730e-01] my_first_lora_v1: 22%|##1 | 651/3000 [03:26<53:37, 1.37s/it, lr: 1.0e-04 loss: 2.728e-01] my_first_lora_v1: 22%|##1 | 651/3000 [03:26<53:37, 1.37s/it, lr: 1.0e-04 loss: 2.728e-01] my_first_lora_v1: 22%|##1 | 652/3000 [03:29<53:59, 1.38s/it, lr: 1.0e-04 loss: 3.203e-01] my_first_lora_v1: 22%|##1 | 652/3000 [03:29<53:59, 1.38s/it, lr: 1.0e-04 loss: 3.203e-01] my_first_lora_v1: 22%|##1 | 653/3000 [03:32<54:13, 1.39s/it, lr: 1.0e-04 loss: 6.646e-02] my_first_lora_v1: 22%|##1 | 653/3000 [03:32<54:13, 1.39s/it, lr: 1.0e-04 loss: 6.646e-02] my_first_lora_v1: 22%|##1 | 654/3000 [03:33<54:06, 1.38s/it, lr: 1.0e-04 loss: 1.706e-01] my_first_lora_v1: 22%|##1 | 654/3000 [03:33<54:06, 1.38s/it, lr: 1.0e-04 loss: 1.706e-01] my_first_lora_v1: 22%|##1 | 655/3000 [03:34<54:00, 1.38s/it, lr: 1.0e-04 loss: 5.612e-01] my_first_lora_v1: 22%|##1 | 655/3000 [03:34<54:00, 1.38s/it, lr: 1.0e-04 loss: 5.612e-01] my_first_lora_v1: 22%|##1 | 656/3000 [03:36<54:14, 1.39s/it, lr: 1.0e-04 loss: 1.553e-01] my_first_lora_v1: 22%|##1 | 656/3000 [03:36<54:14, 1.39s/it, lr: 1.0e-04 loss: 1.553e-01] my_first_lora_v1: 22%|##1 | 657/3000 [03:37<54:10, 1.39s/it, lr: 1.0e-04 loss: 6.193e-01] my_first_lora_v1: 22%|##1 | 657/3000 [03:37<54:10, 1.39s/it, lr: 1.0e-04 loss: 6.193e-01] my_first_lora_v1: 22%|##1 | 658/3000 [03:38<54:00, 1.38s/it, lr: 1.0e-04 loss: 5.824e-01] my_first_lora_v1: 22%|##1 | 658/3000 [03:38<54:00, 1.38s/it, lr: 1.0e-04 loss: 5.824e-01] my_first_lora_v1: 22%|##1 | 659/3000 [03:39<53:50, 1.38s/it, lr: 1.0e-04 loss: 7.648e-01] my_first_lora_v1: 22%|##1 | 659/3000 [03:39<53:50, 1.38s/it, lr: 1.0e-04 loss: 7.648e-01] my_first_lora_v1: 22%|##2 | 660/3000 [03:41<54:04, 1.39s/it, lr: 1.0e-04 loss: 3.206e-01] my_first_lora_v1: 22%|##2 | 660/3000 [03:41<54:04, 1.39s/it, lr: 1.0e-04 loss: 3.206e-01] my_first_lora_v1: 22%|##2 | 661/3000 [03:44<54:25, 1.40s/it, lr: 1.0e-04 loss: 8.328e-01] my_first_lora_v1: 22%|##2 | 661/3000 [03:44<54:25, 1.40s/it, lr: 1.0e-04 loss: 8.328e-01] my_first_lora_v1: 22%|##2 | 662/3000 [03:45<54:19, 1.39s/it, lr: 1.0e-04 loss: 4.335e-01] my_first_lora_v1: 22%|##2 | 662/3000 [03:45<54:19, 1.39s/it, lr: 1.0e-04 loss: 4.335e-01] my_first_lora_v1: 22%|##2 | 663/3000 [03:46<54:13, 1.39s/it, lr: 1.0e-04 loss: 4.382e-01] my_first_lora_v1: 22%|##2 | 663/3000 [03:46<54:13, 1.39s/it, lr: 1.0e-04 loss: 4.382e-01] my_first_lora_v1: 22%|##2 | 664/3000 [03:47<54:03, 1.39s/it, lr: 1.0e-04 loss: 5.692e-01] my_first_lora_v1: 22%|##2 | 664/3000 [03:47<54:03, 1.39s/it, lr: 1.0e-04 loss: 5.692e-01] my_first_lora_v1: 22%|##2 | 665/3000 [03:48<53:55, 1.39s/it, lr: 1.0e-04 loss: 3.967e-01] my_first_lora_v1: 22%|##2 | 665/3000 [03:48<53:55, 1.39s/it, lr: 1.0e-04 loss: 3.967e-01] my_first_lora_v1: 22%|##2 | 666/3000 [03:49<53:45, 1.38s/it, lr: 1.0e-04 loss: 6.958e-01] my_first_lora_v1: 22%|##2 | 666/3000 [03:49<53:45, 1.38s/it, lr: 1.0e-04 loss: 6.958e-01] my_first_lora_v1: 22%|##2 | 667/3000 [03:50<53:39, 1.38s/it, lr: 1.0e-04 loss: 1.931e-01] my_first_lora_v1: 22%|##2 | 667/3000 [03:50<53:39, 1.38s/it, lr: 1.0e-04 loss: 1.931e-01] my_first_lora_v1: 22%|##2 | 668/3000 [03:51<53:30, 1.38s/it, lr: 1.0e-04 loss: 3.429e-01] my_first_lora_v1: 22%|##2 | 668/3000 [03:51<53:30, 1.38s/it, lr: 1.0e-04 loss: 3.429e-01] my_first_lora_v1: 22%|##2 | 669/3000 [03:52<53:20, 1.37s/it, lr: 1.0e-04 loss: 7.913e-01] my_first_lora_v1: 22%|##2 | 669/3000 [03:52<53:20, 1.37s/it, lr: 1.0e-04 loss: 7.913e-01] my_first_lora_v1: 22%|##2 | 670/3000 [03:53<53:24, 1.38s/it, lr: 1.0e-04 loss: 6.584e-01] my_first_lora_v1: 22%|##2 | 670/3000 [03:53<53:24, 1.38s/it, lr: 1.0e-04 loss: 6.584e-01] my_first_lora_v1: 22%|##2 | 671/3000 [03:55<53:20, 1.37s/it, lr: 1.0e-04 loss: 5.031e-01] my_first_lora_v1: 22%|##2 | 671/3000 [03:55<53:20, 1.37s/it, lr: 1.0e-04 loss: 5.031e-01] my_first_lora_v1: 22%|##2 | 672/3000 [03:55<53:11, 1.37s/it, lr: 1.0e-04 loss: 5.853e-01] my_first_lora_v1: 22%|##2 | 672/3000 [03:55<53:11, 1.37s/it, lr: 1.0e-04 loss: 5.853e-01] my_first_lora_v1: 22%|##2 | 673/3000 [03:57<53:10, 1.37s/it, lr: 1.0e-04 loss: 6.201e-01] my_first_lora_v1: 22%|##2 | 673/3000 [03:57<53:10, 1.37s/it, lr: 1.0e-04 loss: 6.201e-01] my_first_lora_v1: 22%|##2 | 674/3000 [03:58<53:05, 1.37s/it, lr: 1.0e-04 loss: 5.645e-01] my_first_lora_v1: 22%|##2 | 674/3000 [03:58<53:05, 1.37s/it, lr: 1.0e-04 loss: 5.645e-01] my_first_lora_v1: 22%|##2 | 675/3000 [03:59<53:03, 1.37s/it, lr: 1.0e-04 loss: 8.318e-01] my_first_lora_v1: 22%|##2 | 675/3000 [03:59<53:03, 1.37s/it, lr: 1.0e-04 loss: 8.318e-01] my_first_lora_v1: 23%|##2 | 676/3000 [04:01<53:03, 1.37s/it, lr: 1.0e-04 loss: 3.720e-01] my_first_lora_v1: 23%|##2 | 676/3000 [04:01<53:03, 1.37s/it, lr: 1.0e-04 loss: 3.720e-01] my_first_lora_v1: 23%|##2 | 677/3000 [04:02<52:57, 1.37s/it, lr: 1.0e-04 loss: 5.956e-01] my_first_lora_v1: 23%|##2 | 677/3000 [04:02<52:57, 1.37s/it, lr: 1.0e-04 loss: 5.956e-01] my_first_lora_v1: 23%|##2 | 678/3000 [04:03<52:57, 1.37s/it, lr: 1.0e-04 loss: 1.076e-01] my_first_lora_v1: 23%|##2 | 678/3000 [04:03<52:57, 1.37s/it, lr: 1.0e-04 loss: 1.076e-01] my_first_lora_v1: 23%|##2 | 679/3000 [04:05<53:09, 1.37s/it, lr: 1.0e-04 loss: 3.158e-01] my_first_lora_v1: 23%|##2 | 679/3000 [04:05<53:09, 1.37s/it, lr: 1.0e-04 loss: 3.158e-01] my_first_lora_v1: 23%|##2 | 680/3000 [04:06<53:03, 1.37s/it, lr: 1.0e-04 loss: 6.733e-01] my_first_lora_v1: 23%|##2 | 680/3000 [04:06<53:03, 1.37s/it, lr: 1.0e-04 loss: 6.733e-01] my_first_lora_v1: 23%|##2 | 681/3000 [04:08<53:03, 1.37s/it, lr: 1.0e-04 loss: 4.066e-01] my_first_lora_v1: 23%|##2 | 681/3000 [04:08<53:03, 1.37s/it, lr: 1.0e-04 loss: 4.066e-01] my_first_lora_v1: 23%|##2 | 682/3000 [04:09<52:54, 1.37s/it, lr: 1.0e-04 loss: 2.904e-01] my_first_lora_v1: 23%|##2 | 682/3000 [04:09<52:54, 1.37s/it, lr: 1.0e-04 loss: 2.904e-01] my_first_lora_v1: 23%|##2 | 683/3000 [04:11<53:09, 1.38s/it, lr: 1.0e-04 loss: 8.508e-01] my_first_lora_v1: 23%|##2 | 683/3000 [04:11<53:09, 1.38s/it, lr: 1.0e-04 loss: 8.508e-01] my_first_lora_v1: 23%|##2 | 684/3000 [04:13<53:09, 1.38s/it, lr: 1.0e-04 loss: 3.946e-01] my_first_lora_v1: 23%|##2 | 684/3000 [04:13<53:09, 1.38s/it, lr: 1.0e-04 loss: 3.946e-01] my_first_lora_v1: 23%|##2 | 685/3000 [04:15<53:20, 1.38s/it, lr: 1.0e-04 loss: 1.883e-01] my_first_lora_v1: 23%|##2 | 685/3000 [04:15<53:20, 1.38s/it, lr: 1.0e-04 loss: 1.883e-01] my_first_lora_v1: 23%|##2 | 686/3000 [04:16<53:12, 1.38s/it, lr: 1.0e-04 loss: 6.806e-01] my_first_lora_v1: 23%|##2 | 686/3000 [04:16<53:12, 1.38s/it, lr: 1.0e-04 loss: 6.806e-01] my_first_lora_v1: 23%|##2 | 687/3000 [04:18<53:12, 1.38s/it, lr: 1.0e-04 loss: 6.646e-01] my_first_lora_v1: 23%|##2 | 687/3000 [04:18<53:12, 1.38s/it, lr: 1.0e-04 loss: 6.646e-01] my_first_lora_v1: 23%|##2 | 688/3000 [04:20<53:26, 1.39s/it, lr: 1.0e-04 loss: 5.424e-01] my_first_lora_v1: 23%|##2 | 688/3000 [04:20<53:26, 1.39s/it, lr: 1.0e-04 loss: 5.424e-01] my_first_lora_v1: 23%|##2 | 689/3000 [04:21<53:21, 1.39s/it, lr: 1.0e-04 loss: 6.273e-02] my_first_lora_v1: 23%|##2 | 689/3000 [04:21<53:21, 1.39s/it, lr: 1.0e-04 loss: 6.273e-02] my_first_lora_v1: 23%|##3 | 690/3000 [04:23<53:20, 1.39s/it, lr: 1.0e-04 loss: 5.719e-01] my_first_lora_v1: 23%|##3 | 690/3000 [04:23<53:20, 1.39s/it, lr: 1.0e-04 loss: 5.719e-01] my_first_lora_v1: 23%|##3 | 691/3000 [04:25<53:23, 1.39s/it, lr: 1.0e-04 loss: 6.726e-01] my_first_lora_v1: 23%|##3 | 691/3000 [04:25<53:23, 1.39s/it, lr: 1.0e-04 loss: 6.726e-01] my_first_lora_v1: 23%|##3 | 692/3000 [04:25<53:15, 1.38s/it, lr: 1.0e-04 loss: 3.553e-01] my_first_lora_v1: 23%|##3 | 692/3000 [04:25<53:15, 1.38s/it, lr: 1.0e-04 loss: 3.553e-01] my_first_lora_v1: 23%|##3 | 693/3000 [04:27<53:16, 1.39s/it, lr: 1.0e-04 loss: 6.890e-01] my_first_lora_v1: 23%|##3 | 693/3000 [04:27<53:16, 1.39s/it, lr: 1.0e-04 loss: 6.890e-01] my_first_lora_v1: 23%|##3 | 694/3000 [04:28<53:07, 1.38s/it, lr: 1.0e-04 loss: 2.425e-01] my_first_lora_v1: 23%|##3 | 694/3000 [04:28<53:07, 1.38s/it, lr: 1.0e-04 loss: 2.425e-01] my_first_lora_v1: 23%|##3 | 695/3000 [04:28<52:59, 1.38s/it, lr: 1.0e-04 loss: 4.542e-01] my_first_lora_v1: 23%|##3 | 695/3000 [04:28<52:59, 1.38s/it, lr: 1.0e-04 loss: 4.542e-01] my_first_lora_v1: 23%|##3 | 696/3000 [04:29<52:50, 1.38s/it, lr: 1.0e-04 loss: 3.766e-01] my_first_lora_v1: 23%|##3 | 696/3000 [04:29<52:50, 1.38s/it, lr: 1.0e-04 loss: 3.766e-01] my_first_lora_v1: 23%|##3 | 697/3000 [04:31<52:49, 1.38s/it, lr: 1.0e-04 loss: 5.490e-01] my_first_lora_v1: 23%|##3 | 697/3000 [04:31<52:49, 1.38s/it, lr: 1.0e-04 loss: 5.490e-01] my_first_lora_v1: 23%|##3 | 698/3000 [04:31<52:41, 1.37s/it, lr: 1.0e-04 loss: 7.326e-01] my_first_lora_v1: 23%|##3 | 698/3000 [04:31<52:41, 1.37s/it, lr: 1.0e-04 loss: 7.326e-01] my_first_lora_v1: 23%|##3 | 699/3000 [04:32<52:33, 1.37s/it, lr: 1.0e-04 loss: 8.804e-02] my_first_lora_v1: 23%|##3 | 699/3000 [04:32<52:33, 1.37s/it, lr: 1.0e-04 loss: 8.804e-02] my_first_lora_v1: 23%|##3 | 700/3000 [04:33<52:24, 1.37s/it, lr: 1.0e-04 loss: 3.755e-01] my_first_lora_v1: 23%|##3 | 700/3000 [04:33<52:24, 1.37s/it, lr: 1.0e-04 loss: 3.755e-01] my_first_lora_v1: 23%|##3 | 701/3000 [04:34<52:24, 1.37s/it, lr: 1.0e-04 loss: 4.553e-01] my_first_lora_v1: 23%|##3 | 701/3000 [04:34<52:24, 1.37s/it, lr: 1.0e-04 loss: 4.553e-01] my_first_lora_v1: 23%|##3 | 702/3000 [04:36<52:20, 1.37s/it, lr: 1.0e-04 loss: 4.523e-01] my_first_lora_v1: 23%|##3 | 702/3000 [04:36<52:20, 1.37s/it, lr: 1.0e-04 loss: 4.523e-01] my_first_lora_v1: 23%|##3 | 703/3000 [04:36<52:12, 1.36s/it, lr: 1.0e-04 loss: 3.559e-01] my_first_lora_v1: 23%|##3 | 703/3000 [04:36<52:12, 1.36s/it, lr: 1.0e-04 loss: 3.559e-01] my_first_lora_v1: 23%|##3 | 704/3000 [04:39<52:29, 1.37s/it, lr: 1.0e-04 loss: 7.071e-01] my_first_lora_v1: 23%|##3 | 704/3000 [04:39<52:29, 1.37s/it, lr: 1.0e-04 loss: 7.071e-01] my_first_lora_v1: 24%|##3 | 705/3000 [04:40<52:21, 1.37s/it, lr: 1.0e-04 loss: 4.153e-01] my_first_lora_v1: 24%|##3 | 705/3000 [04:40<52:21, 1.37s/it, lr: 1.0e-04 loss: 4.153e-01] my_first_lora_v1: 24%|##3 | 706/3000 [04:41<52:17, 1.37s/it, lr: 1.0e-04 loss: 7.833e-02] my_first_lora_v1: 24%|##3 | 706/3000 [04:41<52:17, 1.37s/it, lr: 1.0e-04 loss: 7.833e-02] my_first_lora_v1: 24%|##3 | 707/3000 [04:43<52:17, 1.37s/it, lr: 1.0e-04 loss: 5.688e-01] my_first_lora_v1: 24%|##3 | 707/3000 [04:43<52:17, 1.37s/it, lr: 1.0e-04 loss: 5.688e-01] my_first_lora_v1: 24%|##3 | 708/3000 [04:44<52:12, 1.37s/it, lr: 1.0e-04 loss: 5.972e-02] my_first_lora_v1: 24%|##3 | 708/3000 [04:44<52:12, 1.37s/it, lr: 1.0e-04 loss: 5.972e-02] my_first_lora_v1: 24%|##3 | 709/3000 [04:45<52:05, 1.36s/it, lr: 1.0e-04 loss: 1.767e-01] my_first_lora_v1: 24%|##3 | 709/3000 [04:45<52:05, 1.36s/it, lr: 1.0e-04 loss: 1.767e-01] my_first_lora_v1: 24%|##3 | 710/3000 [04:46<52:00, 1.36s/it, lr: 1.0e-04 loss: 4.055e-01] my_first_lora_v1: 24%|##3 | 710/3000 [04:46<52:00, 1.36s/it, lr: 1.0e-04 loss: 4.055e-01] my_first_lora_v1: 24%|##3 | 711/3000 [04:47<51:55, 1.36s/it, lr: 1.0e-04 loss: 1.877e-01] my_first_lora_v1: 24%|##3 | 711/3000 [04:47<51:55, 1.36s/it, lr: 1.0e-04 loss: 1.877e-01] my_first_lora_v1: 24%|##3 | 712/3000 [04:48<51:55, 1.36s/it, lr: 1.0e-04 loss: 7.765e-01] my_first_lora_v1: 24%|##3 | 712/3000 [04:48<51:55, 1.36s/it, lr: 1.0e-04 loss: 7.765e-01] my_first_lora_v1: 24%|##3 | 713/3000 [04:51<52:05, 1.37s/it, lr: 1.0e-04 loss: 2.927e-01] my_first_lora_v1: 24%|##3 | 713/3000 [04:51<52:05, 1.37s/it, lr: 1.0e-04 loss: 2.927e-01] my_first_lora_v1: 24%|##3 | 714/3000 [04:52<52:04, 1.37s/it, lr: 1.0e-04 loss: 1.055e-01] my_first_lora_v1: 24%|##3 | 714/3000 [04:52<52:04, 1.37s/it, lr: 1.0e-04 loss: 1.055e-01] my_first_lora_v1: 24%|##3 | 715/3000 [04:53<52:02, 1.37s/it, lr: 1.0e-04 loss: 1.460e-01] my_first_lora_v1: 24%|##3 | 715/3000 [04:53<52:02, 1.37s/it, lr: 1.0e-04 loss: 1.460e-01] my_first_lora_v1: 24%|##3 | 716/3000 [04:55<52:04, 1.37s/it, lr: 1.0e-04 loss: 5.838e-01] my_first_lora_v1: 24%|##3 | 716/3000 [04:55<52:04, 1.37s/it, lr: 1.0e-04 loss: 5.838e-01] my_first_lora_v1: 24%|##3 | 717/3000 [04:56<52:00, 1.37s/it, lr: 1.0e-04 loss: 7.892e-01] my_first_lora_v1: 24%|##3 | 717/3000 [04:56<52:00, 1.37s/it, lr: 1.0e-04 loss: 7.892e-01] my_first_lora_v1: 24%|##3 | 718/3000 [04:59<52:15, 1.37s/it, lr: 1.0e-04 loss: 7.228e-01] my_first_lora_v1: 24%|##3 | 718/3000 [04:59<52:15, 1.37s/it, lr: 1.0e-04 loss: 7.228e-01] my_first_lora_v1: 24%|##3 | 719/3000 [05:00<52:08, 1.37s/it, lr: 1.0e-04 loss: 7.815e-01] my_first_lora_v1: 24%|##3 | 719/3000 [05:00<52:08, 1.37s/it, lr: 1.0e-04 loss: 7.815e-01] my_first_lora_v1: 24%|##4 | 720/3000 [05:01<52:04, 1.37s/it, lr: 1.0e-04 loss: 7.218e-01] my_first_lora_v1: 24%|##4 | 720/3000 [05:01<52:04, 1.37s/it, lr: 1.0e-04 loss: 7.218e-01] my_first_lora_v1: 24%|##4 | 721/3000 [05:02<52:03, 1.37s/it, lr: 1.0e-04 loss: 2.635e-02] my_first_lora_v1: 24%|##4 | 721/3000 [05:02<52:03, 1.37s/it, lr: 1.0e-04 loss: 2.635e-02] my_first_lora_v1: 24%|##4 | 722/3000 [05:04<52:05, 1.37s/it, lr: 1.0e-04 loss: 1.770e-01] my_first_lora_v1: 24%|##4 | 722/3000 [05:04<52:05, 1.37s/it, lr: 1.0e-04 loss: 1.770e-01] my_first_lora_v1: 24%|##4 | 723/3000 [05:05<51:58, 1.37s/it, lr: 1.0e-04 loss: 5.131e-02] my_first_lora_v1: 24%|##4 | 723/3000 [05:05<51:58, 1.37s/it, lr: 1.0e-04 loss: 5.131e-02] my_first_lora_v1: 24%|##4 | 724/3000 [05:06<51:58, 1.37s/it, lr: 1.0e-04 loss: 6.817e-01] my_first_lora_v1: 24%|##4 | 724/3000 [05:06<51:58, 1.37s/it, lr: 1.0e-04 loss: 6.817e-01] my_first_lora_v1: 24%|##4 | 725/3000 [05:07<51:50, 1.37s/it, lr: 1.0e-04 loss: 6.681e-01] my_first_lora_v1: 24%|##4 | 725/3000 [05:07<51:50, 1.37s/it, lr: 1.0e-04 loss: 6.681e-01] my_first_lora_v1: 24%|##4 | 726/3000 [05:09<51:53, 1.37s/it, lr: 1.0e-04 loss: 3.497e-01] my_first_lora_v1: 24%|##4 | 726/3000 [05:09<51:53, 1.37s/it, lr: 1.0e-04 loss: 3.497e-01] my_first_lora_v1: 24%|##4 | 727/3000 [05:10<51:46, 1.37s/it, lr: 1.0e-04 loss: 7.640e-01] my_first_lora_v1: 24%|##4 | 727/3000 [05:10<51:46, 1.37s/it, lr: 1.0e-04 loss: 7.640e-01] my_first_lora_v1: 24%|##4 | 728/3000 [05:11<51:45, 1.37s/it, lr: 1.0e-04 loss: 4.614e-01] my_first_lora_v1: 24%|##4 | 728/3000 [05:11<51:45, 1.37s/it, lr: 1.0e-04 loss: 4.614e-01] my_first_lora_v1: 24%|##4 | 729/3000 [05:13<51:47, 1.37s/it, lr: 1.0e-04 loss: 6.523e-01] my_first_lora_v1: 24%|##4 | 729/3000 [05:13<51:47, 1.37s/it, lr: 1.0e-04 loss: 6.523e-01] my_first_lora_v1: 24%|##4 | 730/3000 [05:14<51:40, 1.37s/it, lr: 1.0e-04 loss: 1.727e-01] my_first_lora_v1: 24%|##4 | 730/3000 [05:14<51:40, 1.37s/it, lr: 1.0e-04 loss: 1.727e-01] my_first_lora_v1: 24%|##4 | 731/3000 [05:16<51:49, 1.37s/it, lr: 1.0e-04 loss: 6.107e-01] my_first_lora_v1: 24%|##4 | 731/3000 [05:16<51:49, 1.37s/it, lr: 1.0e-04 loss: 6.107e-01] my_first_lora_v1: 24%|##4 | 732/3000 [05:18<51:49, 1.37s/it, lr: 1.0e-04 loss: 7.228e-01] my_first_lora_v1: 24%|##4 | 732/3000 [05:18<51:49, 1.37s/it, lr: 1.0e-04 loss: 7.228e-01] my_first_lora_v1: 24%|##4 | 733/3000 [05:19<51:43, 1.37s/it, lr: 1.0e-04 loss: 4.098e-01] my_first_lora_v1: 24%|##4 | 733/3000 [05:19<51:43, 1.37s/it, lr: 1.0e-04 loss: 4.098e-01] my_first_lora_v1: 24%|##4 | 734/3000 [05:19<51:36, 1.37s/it, lr: 1.0e-04 loss: 7.374e-01] my_first_lora_v1: 24%|##4 | 734/3000 [05:19<51:36, 1.37s/it, lr: 1.0e-04 loss: 7.374e-01] my_first_lora_v1: 24%|##4 | 735/3000 [05:20<51:29, 1.36s/it, lr: 1.0e-04 loss: 6.426e-01] my_first_lora_v1: 24%|##4 | 735/3000 [05:20<51:29, 1.36s/it, lr: 1.0e-04 loss: 6.426e-01] my_first_lora_v1: 25%|##4 | 736/3000 [05:22<51:31, 1.37s/it, lr: 1.0e-04 loss: 1.538e-01] my_first_lora_v1: 25%|##4 | 736/3000 [05:22<51:31, 1.37s/it, lr: 1.0e-04 loss: 1.538e-01] my_first_lora_v1: 25%|##4 | 737/3000 [05:23<51:24, 1.36s/it, lr: 1.0e-04 loss: 4.824e-01] my_first_lora_v1: 25%|##4 | 737/3000 [05:23<51:24, 1.36s/it, lr: 1.0e-04 loss: 4.824e-01] my_first_lora_v1: 25%|##4 | 738/3000 [05:24<51:24, 1.36s/it, lr: 1.0e-04 loss: 1.324e-01] my_first_lora_v1: 25%|##4 | 738/3000 [05:24<51:24, 1.36s/it, lr: 1.0e-04 loss: 1.324e-01] my_first_lora_v1: 25%|##4 | 739/3000 [05:25<51:17, 1.36s/it, lr: 1.0e-04 loss: 6.102e-01] my_first_lora_v1: 25%|##4 | 739/3000 [05:25<51:17, 1.36s/it, lr: 1.0e-04 loss: 6.102e-01] my_first_lora_v1: 25%|##4 | 740/3000 [05:26<51:17, 1.36s/it, lr: 1.0e-04 loss: 7.646e-02] my_first_lora_v1: 25%|##4 | 740/3000 [05:26<51:17, 1.36s/it, lr: 1.0e-04 loss: 7.646e-02] my_first_lora_v1: 25%|##4 | 741/3000 [05:28<51:17, 1.36s/it, lr: 1.0e-04 loss: 7.024e-01] my_first_lora_v1: 25%|##4 | 741/3000 [05:28<51:17, 1.36s/it, lr: 1.0e-04 loss: 7.024e-01] my_first_lora_v1: 25%|##4 | 742/3000 [05:30<51:27, 1.37s/it, lr: 1.0e-04 loss: 9.174e-01] my_first_lora_v1: 25%|##4 | 742/3000 [05:30<51:27, 1.37s/it, lr: 1.0e-04 loss: 9.174e-01] my_first_lora_v1: 25%|##4 | 743/3000 [05:32<51:31, 1.37s/it, lr: 1.0e-04 loss: 1.664e-01] my_first_lora_v1: 25%|##4 | 743/3000 [05:32<51:31, 1.37s/it, lr: 1.0e-04 loss: 1.664e-01] my_first_lora_v1: 25%|##4 | 744/3000 [05:33<51:24, 1.37s/it, lr: 1.0e-04 loss: 7.812e-01] my_first_lora_v1: 25%|##4 | 744/3000 [05:33<51:24, 1.37s/it, lr: 1.0e-04 loss: 7.812e-01] my_first_lora_v1: 25%|##4 | 745/3000 [05:36<51:37, 1.37s/it, lr: 1.0e-04 loss: 4.078e-01] my_first_lora_v1: 25%|##4 | 745/3000 [05:36<51:37, 1.37s/it, lr: 1.0e-04 loss: 4.078e-01] my_first_lora_v1: 25%|##4 | 746/3000 [05:38<51:37, 1.37s/it, lr: 1.0e-04 loss: 5.356e-01] my_first_lora_v1: 25%|##4 | 746/3000 [05:38<51:37, 1.37s/it, lr: 1.0e-04 loss: 5.356e-01] my_first_lora_v1: 25%|##4 | 747/3000 [05:40<51:45, 1.38s/it, lr: 1.0e-04 loss: 1.029e-01] my_first_lora_v1: 25%|##4 | 747/3000 [05:40<51:45, 1.38s/it, lr: 1.0e-04 loss: 1.029e-01] my_first_lora_v1: 25%|##4 | 748/3000 [05:41<51:38, 1.38s/it, lr: 1.0e-04 loss: 3.008e-02] my_first_lora_v1: 25%|##4 | 748/3000 [05:41<51:38, 1.38s/it, lr: 1.0e-04 loss: 3.008e-02] my_first_lora_v1: 25%|##4 | 749/3000 [05:42<51:37, 1.38s/it, lr: 1.0e-04 loss: 7.045e-01] my_first_lora_v1: 25%|##4 | 749/3000 [05:42<51:37, 1.38s/it, lr: 1.0e-04 loss: 7.045e-01]
Saving at step 750
Saved checkpoint to /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v1/my_first_lora_v1_000000750.safetensors
Saved optimizer to /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v1/optimizer.pt
Unloading assistant lora
Generating Images: 0%| | 0/5 [00:00<?, ?it/s] Generating Images: 0%| | 0/5 [00:00<?, ?it/s]
Generating Images: 20%|## | 1/5 [00:07<00:30, 7.70s/it] Generating Images: 20%|## | 1/5 [00:07<00:30, 7.70s/it]
Generating Images: 40%|#### | 2/5 [00:15<00:23, 7.70s/it] Generating Images: 40%|#### | 2/5 [00:15<00:23, 7.70s/it]
Generating Images: 60%|###### | 3/5 [00:23<00:15, 7.79s/it] Generating Images: 60%|###### | 3/5 [00:23<00:15, 7.79s/it]
Generating Images: 80%|######## | 4/5 [00:30<00:07, 7.72s/it] Generating Images: 80%|######## | 4/5 [00:30<00:07, 7.72s/it]
Generating Images: 100%|##########| 5/5 [00:39<00:00, 7.94s/it] Generating Images: 100%|##########| 5/5 [00:39<00:00, 7.94s/it]
Loading assistant lora
my_first_lora_v1: 25%|##5 | 750/3000 [05:44<51:40, 1.38s/it, lr: 1.0e-04 loss: 6.526e-01] my_first_lora_v1: 25%|##5 | 750/3000 [05:44<51:40, 1.38s/it, lr: 1.0e-04 loss: 6.526e-01] my_first_lora_v1: 25%|##5 | 751/3000 [05:45<51:34, 1.38s/it, lr: 1.0e-04 loss: 2.037e-01] my_first_lora_v1: 25%|##5 | 751/3000 [05:45<51:34, 1.38s/it, lr: 1.0e-04 loss: 2.037e-01] my_first_lora_v1: 25%|##5 | 752/3000 [05:46<51:27, 1.37s/it, lr: 1.0e-04 loss: 7.476e-01] my_first_lora_v1: 25%|##5 | 752/3000 [05:46<51:27, 1.37s/it, lr: 1.0e-04 loss: 7.476e-01] my_first_lora_v1: 25%|##5 | 753/3000 [05:47<51:27, 1.37s/it, lr: 1.0e-04 loss: 6.817e-01] my_first_lora_v1: 25%|##5 | 753/3000 [05:47<51:27, 1.37s/it, lr: 1.0e-04 loss: 6.817e-01] my_first_lora_v1: 25%|##5 | 754/3000 [05:49<51:29, 1.38s/it, lr: 1.0e-04 loss: 6.500e-01] my_first_lora_v1: 25%|##5 | 754/3000 [05:49<51:29, 1.38s/it, lr: 1.0e-04 loss: 6.500e-01] my_first_lora_v1: 25%|##5 | 755/3000 [05:50<51:26, 1.38s/it, lr: 1.0e-04 loss: 3.339e-01] my_first_lora_v1: 25%|##5 | 755/3000 [05:50<51:26, 1.38s/it, lr: 1.0e-04 loss: 3.339e-01] my_first_lora_v1: 25%|##5 | 756/3000 [05:53<51:36, 1.38s/it, lr: 1.0e-04 loss: 6.398e-01] my_first_lora_v1: 25%|##5 | 756/3000 [05:53<51:36, 1.38s/it, lr: 1.0e-04 loss: 6.398e-01] my_first_lora_v1: 25%|##5 | 757/3000 [05:56<51:48, 1.39s/it, lr: 1.0e-04 loss: 5.967e-01] my_first_lora_v1: 25%|##5 | 757/3000 [05:56<51:48, 1.39s/it, lr: 1.0e-04 loss: 5.967e-01] my_first_lora_v1: 25%|##5 | 758/3000 [05:58<51:55, 1.39s/it, lr: 1.0e-04 loss: 4.454e-01] my_first_lora_v1: 25%|##5 | 758/3000 [05:58<51:55, 1.39s/it, lr: 1.0e-04 loss: 4.454e-01] my_first_lora_v1: 25%|##5 | 759/3000 [05:59<51:53, 1.39s/it, lr: 1.0e-04 loss: 7.287e-02] my_first_lora_v1: 25%|##5 | 759/3000 [05:59<51:53, 1.39s/it, lr: 1.0e-04 loss: 7.287e-02] my_first_lora_v1: 25%|##5 | 760/3000 [06:00<51:46, 1.39s/it, lr: 1.0e-04 loss: 7.430e-01] my_first_lora_v1: 25%|##5 | 760/3000 [06:00<51:46, 1.39s/it, lr: 1.0e-04 loss: 7.430e-01] my_first_lora_v1: 25%|##5 | 761/3000 [06:01<51:40, 1.38s/it, lr: 1.0e-04 loss: 4.118e-01] my_first_lora_v1: 25%|##5 | 761/3000 [06:01<51:40, 1.38s/it, lr: 1.0e-04 loss: 4.118e-01] my_first_lora_v1: 25%|##5 | 762/3000 [06:03<51:41, 1.39s/it, lr: 1.0e-04 loss: 7.204e-01] my_first_lora_v1: 25%|##5 | 762/3000 [06:03<51:41, 1.39s/it, lr: 1.0e-04 loss: 7.204e-01] my_first_lora_v1: 25%|##5 | 763/3000 [06:04<51:42, 1.39s/it, lr: 1.0e-04 loss: 5.918e-01] my_first_lora_v1: 25%|##5 | 763/3000 [06:04<51:42, 1.39s/it, lr: 1.0e-04 loss: 5.918e-01] my_first_lora_v1: 25%|##5 | 764/3000 [06:05<51:36, 1.38s/it, lr: 1.0e-04 loss: 6.729e-01] my_first_lora_v1: 25%|##5 | 764/3000 [06:05<51:36, 1.38s/it, lr: 1.0e-04 loss: 6.729e-01] my_first_lora_v1: 26%|##5 | 765/3000 [06:07<51:43, 1.39s/it, lr: 1.0e-04 loss: 1.701e-01] my_first_lora_v1: 26%|##5 | 765/3000 [06:07<51:43, 1.39s/it, lr: 1.0e-04 loss: 1.701e-01] my_first_lora_v1: 26%|##5 | 766/3000 [06:08<51:37, 1.39s/it, lr: 1.0e-04 loss: 6.894e-01] my_first_lora_v1: 26%|##5 | 766/3000 [06:08<51:37, 1.39s/it, lr: 1.0e-04 loss: 6.894e-01] my_first_lora_v1: 26%|##5 | 767/3000 [06:11<51:44, 1.39s/it, lr: 1.0e-04 loss: 1.778e-01] my_first_lora_v1: 26%|##5 | 767/3000 [06:11<51:44, 1.39s/it, lr: 1.0e-04 loss: 1.778e-01] my_first_lora_v1: 26%|##5 | 768/3000 [06:12<51:38, 1.39s/it, lr: 1.0e-04 loss: 3.125e-01] my_first_lora_v1: 26%|##5 | 768/3000 [06:12<51:38, 1.39s/it, lr: 1.0e-04 loss: 3.125e-01] my_first_lora_v1: 26%|##5 | 769/3000 [06:13<51:36, 1.39s/it, lr: 1.0e-04 loss: 3.389e-01] my_first_lora_v1: 26%|##5 | 769/3000 [06:13<51:36, 1.39s/it, lr: 1.0e-04 loss: 3.389e-01] my_first_lora_v1: 26%|##5 | 770/3000 [06:14<51:30, 1.39s/it, lr: 1.0e-04 loss: 5.321e-01] my_first_lora_v1: 26%|##5 | 770/3000 [06:14<51:30, 1.39s/it, lr: 1.0e-04 loss: 5.321e-01] my_first_lora_v1: 26%|##5 | 771/3000 [06:15<51:29, 1.39s/it, lr: 1.0e-04 loss: 3.383e-01] my_first_lora_v1: 26%|##5 | 771/3000 [06:15<51:29, 1.39s/it, lr: 1.0e-04 loss: 3.383e-01] my_first_lora_v1: 26%|##5 | 772/3000 [06:17<51:29, 1.39s/it, lr: 1.0e-04 loss: 3.312e-01] my_first_lora_v1: 26%|##5 | 772/3000 [06:17<51:29, 1.39s/it, lr: 1.0e-04 loss: 3.312e-01] my_first_lora_v1: 26%|##5 | 773/3000 [06:18<51:28, 1.39s/it, lr: 1.0e-04 loss: 5.609e-01] my_first_lora_v1: 26%|##5 | 773/3000 [06:18<51:28, 1.39s/it, lr: 1.0e-04 loss: 5.609e-01] my_first_lora_v1: 26%|##5 | 774/3000 [06:19<51:21, 1.38s/it, lr: 1.0e-04 loss: 2.697e-01] my_first_lora_v1: 26%|##5 | 774/3000 [06:19<51:21, 1.38s/it, lr: 1.0e-04 loss: 2.697e-01] my_first_lora_v1: 26%|##5 | 775/3000 [06:20<51:20, 1.38s/it, lr: 1.0e-04 loss: 7.181e-01] my_first_lora_v1: 26%|##5 | 775/3000 [06:20<51:20, 1.38s/it, lr: 1.0e-04 loss: 7.181e-01] my_first_lora_v1: 26%|##5 | 776/3000 [06:22<51:23, 1.39s/it, lr: 1.0e-04 loss: 5.015e-01] my_first_lora_v1: 26%|##5 | 776/3000 [06:22<51:23, 1.39s/it, lr: 1.0e-04 loss: 5.015e-01] my_first_lora_v1: 26%|##5 | 777/3000 [06:25<51:32, 1.39s/it, lr: 1.0e-04 loss: 1.992e-01] my_first_lora_v1: 26%|##5 | 777/3000 [06:25<51:32, 1.39s/it, lr: 1.0e-04 loss: 1.992e-01] my_first_lora_v1: 26%|##5 | 778/3000 [06:26<51:26, 1.39s/it, lr: 1.0e-04 loss: 6.022e-01] my_first_lora_v1: 26%|##5 | 778/3000 [06:26<51:26, 1.39s/it, lr: 1.0e-04 loss: 6.022e-01] my_first_lora_v1: 26%|##5 | 779/3000 [06:26<51:20, 1.39s/it, lr: 1.0e-04 loss: 3.029e-01] my_first_lora_v1: 26%|##5 | 779/3000 [06:26<51:20, 1.39s/it, lr: 1.0e-04 loss: 3.029e-01] my_first_lora_v1: 26%|##6 | 780/3000 [06:27<51:14, 1.38s/it, lr: 1.0e-04 loss: 6.832e-01] my_first_lora_v1: 26%|##6 | 780/3000 [06:27<51:14, 1.38s/it, lr: 1.0e-04 loss: 6.832e-01] my_first_lora_v1: 26%|##6 | 781/3000 [06:28<51:08, 1.38s/it, lr: 1.0e-04 loss: 6.858e-01] my_first_lora_v1: 26%|##6 | 781/3000 [06:28<51:08, 1.38s/it, lr: 1.0e-04 loss: 6.858e-01] my_first_lora_v1: 26%|##6 | 782/3000 [06:30<51:07, 1.38s/it, lr: 1.0e-04 loss: 1.360e-01] my_first_lora_v1: 26%|##6 | 782/3000 [06:30<51:07, 1.38s/it, lr: 1.0e-04 loss: 1.360e-01] my_first_lora_v1: 26%|##6 | 783/3000 [06:31<51:06, 1.38s/it, lr: 1.0e-04 loss: 1.488e-01] my_first_lora_v1: 26%|##6 | 783/3000 [06:31<51:06, 1.38s/it, lr: 1.0e-04 loss: 1.488e-01] my_first_lora_v1: 26%|##6 | 784/3000 [06:32<51:05, 1.38s/it, lr: 1.0e-04 loss: 6.671e-01] my_first_lora_v1: 26%|##6 | 784/3000 [06:32<51:05, 1.38s/it, lr: 1.0e-04 loss: 6.671e-01] my_first_lora_v1: 26%|##6 | 785/3000 [06:34<51:04, 1.38s/it, lr: 1.0e-04 loss: 8.424e-01] my_first_lora_v1: 26%|##6 | 785/3000 [06:34<51:04, 1.38s/it, lr: 1.0e-04 loss: 8.424e-01] my_first_lora_v1: 26%|##6 | 786/3000 [06:36<51:10, 1.39s/it, lr: 1.0e-04 loss: 7.344e-01] my_first_lora_v1: 26%|##6 | 786/3000 [06:36<51:10, 1.39s/it, lr: 1.0e-04 loss: 7.344e-01] my_first_lora_v1: 26%|##6 | 787/3000 [06:38<51:09, 1.39s/it, lr: 1.0e-04 loss: 5.514e-01] my_first_lora_v1: 26%|##6 | 787/3000 [06:38<51:09, 1.39s/it, lr: 1.0e-04 loss: 5.514e-01] my_first_lora_v1: 26%|##6 | 788/3000 [06:39<51:08, 1.39s/it, lr: 1.0e-04 loss: 6.770e-01] my_first_lora_v1: 26%|##6 | 788/3000 [06:39<51:08, 1.39s/it, lr: 1.0e-04 loss: 6.770e-01] my_first_lora_v1: 26%|##6 | 789/3000 [06:41<51:14, 1.39s/it, lr: 1.0e-04 loss: 1.699e-01] my_first_lora_v1: 26%|##6 | 789/3000 [06:41<51:14, 1.39s/it, lr: 1.0e-04 loss: 1.699e-01] my_first_lora_v1: 26%|##6 | 790/3000 [06:42<51:11, 1.39s/it, lr: 1.0e-04 loss: 7.336e-01] my_first_lora_v1: 26%|##6 | 790/3000 [06:42<51:11, 1.39s/it, lr: 1.0e-04 loss: 7.336e-01] my_first_lora_v1: 26%|##6 | 791/3000 [06:43<51:05, 1.39s/it, lr: 1.0e-04 loss: 7.493e-01] my_first_lora_v1: 26%|##6 | 791/3000 [06:43<51:05, 1.39s/it, lr: 1.0e-04 loss: 7.493e-01] my_first_lora_v1: 26%|##6 | 792/3000 [06:44<50:58, 1.39s/it, lr: 1.0e-04 loss: 2.528e-01] my_first_lora_v1: 26%|##6 | 792/3000 [06:44<50:58, 1.39s/it, lr: 1.0e-04 loss: 2.528e-01] my_first_lora_v1: 26%|##6 | 793/3000 [06:46<50:58, 1.39s/it, lr: 1.0e-04 loss: 7.004e-01] my_first_lora_v1: 26%|##6 | 793/3000 [06:46<50:58, 1.39s/it, lr: 1.0e-04 loss: 7.004e-01] my_first_lora_v1: 26%|##6 | 794/3000 [06:46<50:52, 1.38s/it, lr: 1.0e-04 loss: 1.717e-01] my_first_lora_v1: 26%|##6 | 794/3000 [06:46<50:52, 1.38s/it, lr: 1.0e-04 loss: 1.717e-01] my_first_lora_v1: 26%|##6 | 795/3000 [06:47<50:47, 1.38s/it, lr: 1.0e-04 loss: 4.323e-01] my_first_lora_v1: 26%|##6 | 795/3000 [06:47<50:47, 1.38s/it, lr: 1.0e-04 loss: 4.323e-01] my_first_lora_v1: 27%|##6 | 796/3000 [06:48<50:41, 1.38s/it, lr: 1.0e-04 loss: 9.050e-01] my_first_lora_v1: 27%|##6 | 796/3000 [06:48<50:41, 1.38s/it, lr: 1.0e-04 loss: 9.050e-01] my_first_lora_v1: 27%|##6 | 797/3000 [06:49<50:37, 1.38s/it, lr: 1.0e-04 loss: 4.140e-01] my_first_lora_v1: 27%|##6 | 797/3000 [06:49<50:37, 1.38s/it, lr: 1.0e-04 loss: 4.140e-01] my_first_lora_v1: 27%|##6 | 798/3000 [06:50<50:31, 1.38s/it, lr: 1.0e-04 loss: 4.138e-01] my_first_lora_v1: 27%|##6 | 798/3000 [06:50<50:31, 1.38s/it, lr: 1.0e-04 loss: 4.138e-01] my_first_lora_v1: 27%|##6 | 799/3000 [06:51<50:30, 1.38s/it, lr: 1.0e-04 loss: 6.096e-01] my_first_lora_v1: 27%|##6 | 799/3000 [06:51<50:30, 1.38s/it, lr: 1.0e-04 loss: 6.096e-01] my_first_lora_v1: 27%|##6 | 800/3000 [06:53<50:30, 1.38s/it, lr: 1.0e-04 loss: 8.442e-02] my_first_lora_v1: 27%|##6 | 800/3000 [06:53<50:30, 1.38s/it, lr: 1.0e-04 loss: 8.442e-02] my_first_lora_v1: 27%|##6 | 801/3000 [06:55<50:32, 1.38s/it, lr: 1.0e-04 loss: 3.775e-01] my_first_lora_v1: 27%|##6 | 801/3000 [06:55<50:32, 1.38s/it, lr: 1.0e-04 loss: 3.775e-01] my_first_lora_v1: 27%|##6 | 802/3000 [06:56<50:28, 1.38s/it, lr: 1.0e-04 loss: 3.308e-01] my_first_lora_v1: 27%|##6 | 802/3000 [06:56<50:28, 1.38s/it, lr: 1.0e-04 loss: 3.308e-01] my_first_lora_v1: 27%|##6 | 803/3000 [06:57<50:27, 1.38s/it, lr: 1.0e-04 loss: 4.689e-02] my_first_lora_v1: 27%|##6 | 803/3000 [06:57<50:27, 1.38s/it, lr: 1.0e-04 loss: 4.689e-02] my_first_lora_v1: 27%|##6 | 804/3000 [06:58<50:22, 1.38s/it, lr: 1.0e-04 loss: 6.403e-01] my_first_lora_v1: 27%|##6 | 804/3000 [06:58<50:22, 1.38s/it, lr: 1.0e-04 loss: 6.403e-01] my_first_lora_v1: 27%|##6 | 805/3000 [06:59<50:18, 1.38s/it, lr: 1.0e-04 loss: 7.946e-01] my_first_lora_v1: 27%|##6 | 805/3000 [06:59<50:18, 1.38s/it, lr: 1.0e-04 loss: 7.946e-01] my_first_lora_v1: 27%|##6 | 806/3000 [07:01<50:19, 1.38s/it, lr: 1.0e-04 loss: 1.219e-01] my_first_lora_v1: 27%|##6 | 806/3000 [07:01<50:19, 1.38s/it, lr: 1.0e-04 loss: 1.219e-01] my_first_lora_v1: 27%|##6 | 807/3000 [07:02<50:18, 1.38s/it, lr: 1.0e-04 loss: 1.390e-01] my_first_lora_v1: 27%|##6 | 807/3000 [07:02<50:18, 1.38s/it, lr: 1.0e-04 loss: 1.390e-01] my_first_lora_v1: 27%|##6 | 808/3000 [07:03<50:12, 1.37s/it, lr: 1.0e-04 loss: 7.468e-01] my_first_lora_v1: 27%|##6 | 808/3000 [07:03<50:12, 1.37s/it, lr: 1.0e-04 loss: 7.468e-01] my_first_lora_v1: 27%|##6 | 809/3000 [07:04<50:12, 1.37s/it, lr: 1.0e-04 loss: 2.060e-01] my_first_lora_v1: 27%|##6 | 809/3000 [07:04<50:12, 1.37s/it, lr: 1.0e-04 loss: 2.060e-01] my_first_lora_v1: 27%|##7 | 810/3000 [07:07<50:20, 1.38s/it, lr: 1.0e-04 loss: 8.632e-01] my_first_lora_v1: 27%|##7 | 810/3000 [07:07<50:20, 1.38s/it, lr: 1.0e-04 loss: 8.632e-01] my_first_lora_v1: 27%|##7 | 811/3000 [07:08<50:16, 1.38s/it, lr: 1.0e-04 loss: 4.458e-01] my_first_lora_v1: 27%|##7 | 811/3000 [07:08<50:16, 1.38s/it, lr: 1.0e-04 loss: 4.458e-01] my_first_lora_v1: 27%|##7 | 812/3000 [07:11<50:25, 1.38s/it, lr: 1.0e-04 loss: 1.378e-01] my_first_lora_v1: 27%|##7 | 812/3000 [07:11<50:25, 1.38s/it, lr: 1.0e-04 loss: 1.378e-01] my_first_lora_v1: 27%|##7 | 813/3000 [07:14<50:35, 1.39s/it, lr: 1.0e-04 loss: 6.734e-01] my_first_lora_v1: 27%|##7 | 813/3000 [07:14<50:35, 1.39s/it, lr: 1.0e-04 loss: 6.734e-01] my_first_lora_v1: 27%|##7 | 814/3000 [07:15<50:30, 1.39s/it, lr: 1.0e-04 loss: 2.606e-01] my_first_lora_v1: 27%|##7 | 814/3000 [07:15<50:30, 1.39s/it, lr: 1.0e-04 loss: 2.606e-01] my_first_lora_v1: 27%|##7 | 815/3000 [07:16<50:29, 1.39s/it, lr: 1.0e-04 loss: 3.408e-01] my_first_lora_v1: 27%|##7 | 815/3000 [07:16<50:29, 1.39s/it, lr: 1.0e-04 loss: 3.408e-01] my_first_lora_v1: 27%|##7 | 816/3000 [07:17<50:26, 1.39s/it, lr: 1.0e-04 loss: 1.088e-01] my_first_lora_v1: 27%|##7 | 816/3000 [07:17<50:26, 1.39s/it, lr: 1.0e-04 loss: 1.088e-01] my_first_lora_v1: 27%|##7 | 817/3000 [07:19<50:25, 1.39s/it, lr: 1.0e-04 loss: 8.321e-01] my_first_lora_v1: 27%|##7 | 817/3000 [07:19<50:25, 1.39s/it, lr: 1.0e-04 loss: 8.321e-01] my_first_lora_v1: 27%|##7 | 818/3000 [07:20<50:21, 1.38s/it, lr: 1.0e-04 loss: 3.418e-01] my_first_lora_v1: 27%|##7 | 818/3000 [07:20<50:21, 1.38s/it, lr: 1.0e-04 loss: 3.418e-01] my_first_lora_v1: 27%|##7 | 819/3000 [07:21<50:16, 1.38s/it, lr: 1.0e-04 loss: 1.499e-01] my_first_lora_v1: 27%|##7 | 819/3000 [07:21<50:16, 1.38s/it, lr: 1.0e-04 loss: 1.499e-01] my_first_lora_v1: 27%|##7 | 820/3000 [07:22<50:12, 1.38s/it, lr: 1.0e-04 loss: 7.172e-01] my_first_lora_v1: 27%|##7 | 820/3000 [07:22<50:12, 1.38s/it, lr: 1.0e-04 loss: 7.172e-01] my_first_lora_v1: 27%|##7 | 821/3000 [07:23<50:11, 1.38s/it, lr: 1.0e-04 loss: 7.029e-01] my_first_lora_v1: 27%|##7 | 821/3000 [07:23<50:11, 1.38s/it, lr: 1.0e-04 loss: 7.029e-01] my_first_lora_v1: 27%|##7 | 822/3000 [07:25<50:12, 1.38s/it, lr: 1.0e-04 loss: 2.651e-01] my_first_lora_v1: 27%|##7 | 822/3000 [07:25<50:12, 1.38s/it, lr: 1.0e-04 loss: 2.651e-01] my_first_lora_v1: 27%|##7 | 823/3000 [07:26<50:08, 1.38s/it, lr: 1.0e-04 loss: 6.121e-01] my_first_lora_v1: 27%|##7 | 823/3000 [07:26<50:08, 1.38s/it, lr: 1.0e-04 loss: 6.121e-01] my_first_lora_v1: 27%|##7 | 824/3000 [07:27<50:07, 1.38s/it, lr: 1.0e-04 loss: 1.904e-02] my_first_lora_v1: 27%|##7 | 824/3000 [07:27<50:07, 1.38s/it, lr: 1.0e-04 loss: 1.904e-02] my_first_lora_v1: 28%|##7 | 825/3000 [07:28<50:02, 1.38s/it, lr: 1.0e-04 loss: 4.469e-01] my_first_lora_v1: 28%|##7 | 825/3000 [07:28<50:02, 1.38s/it, lr: 1.0e-04 loss: 4.469e-01] my_first_lora_v1: 28%|##7 | 826/3000 [07:29<49:57, 1.38s/it, lr: 1.0e-04 loss: 1.569e-01] my_first_lora_v1: 28%|##7 | 826/3000 [07:29<49:57, 1.38s/it, lr: 1.0e-04 loss: 1.569e-01] my_first_lora_v1: 28%|##7 | 827/3000 [07:30<49:51, 1.38s/it, lr: 1.0e-04 loss: 2.485e-01] my_first_lora_v1: 28%|##7 | 827/3000 [07:30<49:51, 1.38s/it, lr: 1.0e-04 loss: 2.485e-01] my_first_lora_v1: 28%|##7 | 828/3000 [07:31<49:51, 1.38s/it, lr: 1.0e-04 loss: 1.072e-01] my_first_lora_v1: 28%|##7 | 828/3000 [07:31<49:51, 1.38s/it, lr: 1.0e-04 loss: 1.072e-01] my_first_lora_v1: 28%|##7 | 829/3000 [07:33<49:50, 1.38s/it, lr: 1.0e-04 loss: 2.871e-01] my_first_lora_v1: 28%|##7 | 829/3000 [07:33<49:50, 1.38s/it, lr: 1.0e-04 loss: 2.871e-01] my_first_lora_v1: 28%|##7 | 830/3000 [07:34<49:50, 1.38s/it, lr: 1.0e-04 loss: 6.522e-01] my_first_lora_v1: 28%|##7 | 830/3000 [07:34<49:50, 1.38s/it, lr: 1.0e-04 loss: 6.522e-01] my_first_lora_v1: 28%|##7 | 831/3000 [07:37<49:58, 1.38s/it, lr: 1.0e-04 loss: 5.016e-01] my_first_lora_v1: 28%|##7 | 831/3000 [07:37<49:58, 1.38s/it, lr: 1.0e-04 loss: 5.016e-01] my_first_lora_v1: 28%|##7 | 832/3000 [07:38<49:52, 1.38s/it, lr: 1.0e-04 loss: 1.451e-01] my_first_lora_v1: 28%|##7 | 832/3000 [07:38<49:52, 1.38s/it, lr: 1.0e-04 loss: 1.451e-01] my_first_lora_v1: 28%|##7 | 833/3000 [07:39<49:51, 1.38s/it, lr: 1.0e-04 loss: 6.321e-01] my_first_lora_v1: 28%|##7 | 833/3000 [07:39<49:51, 1.38s/it, lr: 1.0e-04 loss: 6.321e-01] my_first_lora_v1: 28%|##7 | 834/3000 [07:40<49:46, 1.38s/it, lr: 1.0e-04 loss: 1.040e-02] my_first_lora_v1: 28%|##7 | 834/3000 [07:40<49:46, 1.38s/it, lr: 1.0e-04 loss: 1.040e-02] my_first_lora_v1: 28%|##7 | 835/3000 [07:42<49:51, 1.38s/it, lr: 1.0e-04 loss: 4.703e-01] my_first_lora_v1: 28%|##7 | 835/3000 [07:42<49:51, 1.38s/it, lr: 1.0e-04 loss: 4.703e-01] my_first_lora_v1: 28%|##7 | 836/3000 [07:43<49:46, 1.38s/it, lr: 1.0e-04 loss: 4.024e-01] my_first_lora_v1: 28%|##7 | 836/3000 [07:43<49:46, 1.38s/it, lr: 1.0e-04 loss: 4.024e-01] my_first_lora_v1: 28%|##7 | 837/3000 [07:46<49:51, 1.38s/it, lr: 1.0e-04 loss: 2.958e-01] my_first_lora_v1: 28%|##7 | 837/3000 [07:46<49:51, 1.38s/it, lr: 1.0e-04 loss: 2.958e-01] my_first_lora_v1: 28%|##7 | 838/3000 [07:46<49:46, 1.38s/it, lr: 1.0e-04 loss: 6.176e-01] my_first_lora_v1: 28%|##7 | 838/3000 [07:46<49:46, 1.38s/it, lr: 1.0e-04 loss: 6.176e-01] my_first_lora_v1: 28%|##7 | 839/3000 [07:47<49:41, 1.38s/it, lr: 1.0e-04 loss: 1.052e-01] my_first_lora_v1: 28%|##7 | 839/3000 [07:47<49:41, 1.38s/it, lr: 1.0e-04 loss: 1.052e-01] my_first_lora_v1: 28%|##8 | 840/3000 [07:49<49:42, 1.38s/it, lr: 1.0e-04 loss: 7.100e-01] my_first_lora_v1: 28%|##8 | 840/3000 [07:49<49:42, 1.38s/it, lr: 1.0e-04 loss: 7.100e-01] my_first_lora_v1: 28%|##8 | 841/3000 [07:51<49:47, 1.38s/it, lr: 1.0e-04 loss: 5.912e-01] my_first_lora_v1: 28%|##8 | 841/3000 [07:51<49:47, 1.38s/it, lr: 1.0e-04 loss: 5.912e-01] my_first_lora_v1: 28%|##8 | 842/3000 [07:53<49:46, 1.38s/it, lr: 1.0e-04 loss: 3.169e-01] my_first_lora_v1: 28%|##8 | 842/3000 [07:53<49:46, 1.38s/it, lr: 1.0e-04 loss: 3.169e-01] my_first_lora_v1: 28%|##8 | 843/3000 [07:54<49:43, 1.38s/it, lr: 1.0e-04 loss: 2.450e-01] my_first_lora_v1: 28%|##8 | 843/3000 [07:54<49:43, 1.38s/it, lr: 1.0e-04 loss: 2.450e-01] my_first_lora_v1: 28%|##8 | 844/3000 [07:56<49:43, 1.38s/it, lr: 1.0e-04 loss: 2.245e-01] my_first_lora_v1: 28%|##8 | 844/3000 [07:56<49:43, 1.38s/it, lr: 1.0e-04 loss: 2.245e-01] my_first_lora_v1: 28%|##8 | 845/3000 [07:57<49:39, 1.38s/it, lr: 1.0e-04 loss: 2.646e-01] my_first_lora_v1: 28%|##8 | 845/3000 [07:57<49:39, 1.38s/it, lr: 1.0e-04 loss: 2.646e-01] my_first_lora_v1: 28%|##8 | 846/3000 [07:58<49:38, 1.38s/it, lr: 1.0e-04 loss: 5.516e-01] my_first_lora_v1: 28%|##8 | 846/3000 [07:58<49:38, 1.38s/it, lr: 1.0e-04 loss: 5.516e-01] my_first_lora_v1: 28%|##8 | 847/3000 [07:59<49:33, 1.38s/it, lr: 1.0e-04 loss: 6.876e-01] my_first_lora_v1: 28%|##8 | 847/3000 [07:59<49:33, 1.38s/it, lr: 1.0e-04 loss: 6.876e-01] my_first_lora_v1: 28%|##8 | 848/3000 [08:00<49:28, 1.38s/it, lr: 1.0e-04 loss: 7.313e-01] my_first_lora_v1: 28%|##8 | 848/3000 [08:00<49:28, 1.38s/it, lr: 1.0e-04 loss: 7.313e-01] my_first_lora_v1: 28%|##8 | 849/3000 [08:00<49:23, 1.38s/it, lr: 1.0e-04 loss: 6.939e-01] my_first_lora_v1: 28%|##8 | 849/3000 [08:00<49:23, 1.38s/it, lr: 1.0e-04 loss: 6.939e-01] my_first_lora_v1: 28%|##8 | 850/3000 [08:01<49:19, 1.38s/it, lr: 1.0e-04 loss: 8.308e-01] my_first_lora_v1: 28%|##8 | 850/3000 [08:01<49:19, 1.38s/it, lr: 1.0e-04 loss: 8.308e-01] my_first_lora_v1: 28%|##8 | 851/3000 [08:02<49:14, 1.38s/it, lr: 1.0e-04 loss: 7.479e-01] my_first_lora_v1: 28%|##8 | 851/3000 [08:02<49:14, 1.38s/it, lr: 1.0e-04 loss: 7.479e-01] my_first_lora_v1: 28%|##8 | 852/3000 [08:03<49:09, 1.37s/it, lr: 1.0e-04 loss: 3.372e-01] my_first_lora_v1: 28%|##8 | 852/3000 [08:03<49:09, 1.37s/it, lr: 1.0e-04 loss: 3.372e-01] my_first_lora_v1: 28%|##8 | 853/3000 [08:04<49:09, 1.37s/it, lr: 1.0e-04 loss: 7.451e-01] my_first_lora_v1: 28%|##8 | 853/3000 [08:04<49:09, 1.37s/it, lr: 1.0e-04 loss: 7.451e-01] my_first_lora_v1: 28%|##8 | 854/3000 [08:06<49:08, 1.37s/it, lr: 1.0e-04 loss: 5.891e-02] my_first_lora_v1: 28%|##8 | 854/3000 [08:06<49:08, 1.37s/it, lr: 1.0e-04 loss: 5.891e-02] my_first_lora_v1: 28%|##8 | 855/3000 [08:07<49:07, 1.37s/it, lr: 1.0e-04 loss: 7.075e-01] my_first_lora_v1: 28%|##8 | 855/3000 [08:07<49:07, 1.37s/it, lr: 1.0e-04 loss: 7.075e-01] my_first_lora_v1: 29%|##8 | 856/3000 [08:08<49:03, 1.37s/it, lr: 1.0e-04 loss: 4.187e-01] my_first_lora_v1: 29%|##8 | 856/3000 [08:08<49:03, 1.37s/it, lr: 1.0e-04 loss: 4.187e-01] my_first_lora_v1: 29%|##8 | 857/3000 [08:11<49:09, 1.38s/it, lr: 1.0e-04 loss: 3.419e-01] my_first_lora_v1: 29%|##8 | 857/3000 [08:11<49:09, 1.38s/it, lr: 1.0e-04 loss: 3.419e-01] my_first_lora_v1: 29%|##8 | 858/3000 [08:12<49:07, 1.38s/it, lr: 1.0e-04 loss: 9.005e-02] my_first_lora_v1: 29%|##8 | 858/3000 [08:12<49:07, 1.38s/it, lr: 1.0e-04 loss: 9.005e-02] my_first_lora_v1: 29%|##8 | 859/3000 [08:15<49:12, 1.38s/it, lr: 1.0e-04 loss: 3.912e-01] my_first_lora_v1: 29%|##8 | 859/3000 [08:15<49:12, 1.38s/it, lr: 1.0e-04 loss: 3.912e-01] my_first_lora_v1: 29%|##8 | 860/3000 [08:15<49:07, 1.38s/it, lr: 1.0e-04 loss: 7.401e-01] my_first_lora_v1: 29%|##8 | 860/3000 [08:15<49:07, 1.38s/it, lr: 1.0e-04 loss: 7.401e-01] my_first_lora_v1: 29%|##8 | 861/3000 [08:16<49:02, 1.38s/it, lr: 1.0e-04 loss: 3.819e-01] my_first_lora_v1: 29%|##8 | 861/3000 [08:16<49:02, 1.38s/it, lr: 1.0e-04 loss: 3.819e-01] my_first_lora_v1: 29%|##8 | 862/3000 [08:17<48:57, 1.37s/it, lr: 1.0e-04 loss: 4.961e-02] my_first_lora_v1: 29%|##8 | 862/3000 [08:17<48:57, 1.37s/it, lr: 1.0e-04 loss: 4.961e-02] my_first_lora_v1: 29%|##8 | 863/3000 [08:18<48:54, 1.37s/it, lr: 1.0e-04 loss: 7.606e-01] my_first_lora_v1: 29%|##8 | 863/3000 [08:18<48:54, 1.37s/it, lr: 1.0e-04 loss: 7.606e-01] my_first_lora_v1: 29%|##8 | 864/3000 [08:19<48:53, 1.37s/it, lr: 1.0e-04 loss: 6.691e-01] my_first_lora_v1: 29%|##8 | 864/3000 [08:19<48:53, 1.37s/it, lr: 1.0e-04 loss: 6.691e-01] my_first_lora_v1: 29%|##8 | 865/3000 [08:21<48:52, 1.37s/it, lr: 1.0e-04 loss: 4.769e-01] my_first_lora_v1: 29%|##8 | 865/3000 [08:21<48:52, 1.37s/it, lr: 1.0e-04 loss: 4.769e-01] my_first_lora_v1: 29%|##8 | 866/3000 [08:23<48:57, 1.38s/it, lr: 1.0e-04 loss: 6.946e-01] my_first_lora_v1: 29%|##8 | 866/3000 [08:23<48:57, 1.38s/it, lr: 1.0e-04 loss: 6.946e-01] my_first_lora_v1: 29%|##8 | 867/3000 [08:25<48:56, 1.38s/it, lr: 1.0e-04 loss: 3.681e-01] my_first_lora_v1: 29%|##8 | 867/3000 [08:25<48:56, 1.38s/it, lr: 1.0e-04 loss: 3.681e-01] my_first_lora_v1: 29%|##8 | 868/3000 [08:26<48:52, 1.38s/it, lr: 1.0e-04 loss: 7.548e-01] my_first_lora_v1: 29%|##8 | 868/3000 [08:26<48:52, 1.38s/it, lr: 1.0e-04 loss: 7.548e-01] my_first_lora_v1: 29%|##8 | 869/3000 [08:27<48:52, 1.38s/it, lr: 1.0e-04 loss: 2.875e-01] my_first_lora_v1: 29%|##8 | 869/3000 [08:27<48:52, 1.38s/it, lr: 1.0e-04 loss: 2.875e-01] my_first_lora_v1: 29%|##9 | 870/3000 [08:28<48:48, 1.38s/it, lr: 1.0e-04 loss: 3.588e-01] my_first_lora_v1: 29%|##9 | 870/3000 [08:28<48:48, 1.38s/it, lr: 1.0e-04 loss: 3.588e-01] my_first_lora_v1: 29%|##9 | 871/3000 [08:30<48:49, 1.38s/it, lr: 1.0e-04 loss: 2.876e-01] my_first_lora_v1: 29%|##9 | 871/3000 [08:30<48:49, 1.38s/it, lr: 1.0e-04 loss: 2.876e-01] my_first_lora_v1: 29%|##9 | 872/3000 [08:33<48:56, 1.38s/it, lr: 1.0e-04 loss: 2.593e-01] my_first_lora_v1: 29%|##9 | 872/3000 [08:33<48:56, 1.38s/it, lr: 1.0e-04 loss: 2.593e-01] my_first_lora_v1: 29%|##9 | 873/3000 [08:34<48:56, 1.38s/it, lr: 1.0e-04 loss: 3.852e-01] my_first_lora_v1: 29%|##9 | 873/3000 [08:34<48:56, 1.38s/it, lr: 1.0e-04 loss: 3.852e-01] my_first_lora_v1: 29%|##9 | 874/3000 [08:36<48:55, 1.38s/it, lr: 1.0e-04 loss: 2.421e-01] my_first_lora_v1: 29%|##9 | 874/3000 [08:36<48:55, 1.38s/it, lr: 1.0e-04 loss: 2.421e-01] my_first_lora_v1: 29%|##9 | 875/3000 [08:37<48:53, 1.38s/it, lr: 1.0e-04 loss: 5.154e-01] my_first_lora_v1: 29%|##9 | 875/3000 [08:37<48:53, 1.38s/it, lr: 1.0e-04 loss: 5.154e-01] my_first_lora_v1: 29%|##9 | 876/3000 [08:38<48:49, 1.38s/it, lr: 1.0e-04 loss: 1.294e-01] my_first_lora_v1: 29%|##9 | 876/3000 [08:38<48:49, 1.38s/it, lr: 1.0e-04 loss: 1.294e-01] my_first_lora_v1: 29%|##9 | 877/3000 [08:39<48:47, 1.38s/it, lr: 1.0e-04 loss: 4.738e-01] my_first_lora_v1: 29%|##9 | 877/3000 [08:39<48:47, 1.38s/it, lr: 1.0e-04 loss: 4.738e-01] my_first_lora_v1: 29%|##9 | 878/3000 [08:40<48:42, 1.38s/it, lr: 1.0e-04 loss: 5.126e-01] my_first_lora_v1: 29%|##9 | 878/3000 [08:40<48:42, 1.38s/it, lr: 1.0e-04 loss: 5.126e-01] my_first_lora_v1: 29%|##9 | 879/3000 [08:42<48:41, 1.38s/it, lr: 1.0e-04 loss: 4.088e-01] my_first_lora_v1: 29%|##9 | 879/3000 [08:42<48:41, 1.38s/it, lr: 1.0e-04 loss: 4.088e-01] my_first_lora_v1: 29%|##9 | 880/3000 [08:42<48:37, 1.38s/it, lr: 1.0e-04 loss: 6.670e-01] my_first_lora_v1: 29%|##9 | 880/3000 [08:42<48:37, 1.38s/it, lr: 1.0e-04 loss: 6.670e-01] my_first_lora_v1: 29%|##9 | 881/3000 [08:43<48:34, 1.38s/it, lr: 1.0e-04 loss: 6.760e-01] my_first_lora_v1: 29%|##9 | 881/3000 [08:43<48:34, 1.38s/it, lr: 1.0e-04 loss: 6.760e-01] my_first_lora_v1: 29%|##9 | 882/3000 [08:45<48:34, 1.38s/it, lr: 1.0e-04 loss: 7.422e-01] my_first_lora_v1: 29%|##9 | 882/3000 [08:45<48:34, 1.38s/it, lr: 1.0e-04 loss: 7.422e-01] my_first_lora_v1: 29%|##9 | 883/3000 [08:48<48:38, 1.38s/it, lr: 1.0e-04 loss: 5.037e-01] my_first_lora_v1: 29%|##9 | 883/3000 [08:48<48:38, 1.38s/it, lr: 1.0e-04 loss: 5.037e-01] my_first_lora_v1: 29%|##9 | 884/3000 [08:48<48:34, 1.38s/it, lr: 1.0e-04 loss: 2.921e-01] my_first_lora_v1: 29%|##9 | 884/3000 [08:48<48:34, 1.38s/it, lr: 1.0e-04 loss: 2.921e-01] my_first_lora_v1: 30%|##9 | 885/3000 [08:50<48:33, 1.38s/it, lr: 1.0e-04 loss: 7.193e-01] my_first_lora_v1: 30%|##9 | 885/3000 [08:50<48:33, 1.38s/it, lr: 1.0e-04 loss: 7.193e-01] my_first_lora_v1: 30%|##9 | 886/3000 [08:51<48:29, 1.38s/it, lr: 1.0e-04 loss: 2.153e-01] my_first_lora_v1: 30%|##9 | 886/3000 [08:51<48:29, 1.38s/it, lr: 1.0e-04 loss: 2.153e-01] my_first_lora_v1: 30%|##9 | 887/3000 [08:52<48:27, 1.38s/it, lr: 1.0e-04 loss: 1.661e-01] my_first_lora_v1: 30%|##9 | 887/3000 [08:52<48:27, 1.38s/it, lr: 1.0e-04 loss: 1.661e-01] my_first_lora_v1: 30%|##9 | 888/3000 [08:53<48:23, 1.37s/it, lr: 1.0e-04 loss: 4.055e-01] my_first_lora_v1: 30%|##9 | 888/3000 [08:53<48:23, 1.37s/it, lr: 1.0e-04 loss: 4.055e-01] my_first_lora_v1: 30%|##9 | 889/3000 [08:54<48:18, 1.37s/it, lr: 1.0e-04 loss: 3.834e-01] my_first_lora_v1: 30%|##9 | 889/3000 [08:54<48:18, 1.37s/it, lr: 1.0e-04 loss: 3.834e-01] my_first_lora_v1: 30%|##9 | 890/3000 [08:55<48:18, 1.37s/it, lr: 1.0e-04 loss: 7.956e-01] my_first_lora_v1: 30%|##9 | 890/3000 [08:55<48:18, 1.37s/it, lr: 1.0e-04 loss: 7.956e-01] my_first_lora_v1: 30%|##9 | 891/3000 [08:56<48:15, 1.37s/it, lr: 1.0e-04 loss: 1.739e-01] my_first_lora_v1: 30%|##9 | 891/3000 [08:56<48:15, 1.37s/it, lr: 1.0e-04 loss: 1.739e-01] my_first_lora_v1: 30%|##9 | 892/3000 [08:58<48:14, 1.37s/it, lr: 1.0e-04 loss: 4.931e-01] my_first_lora_v1: 30%|##9 | 892/3000 [08:58<48:14, 1.37s/it, lr: 1.0e-04 loss: 4.931e-01] my_first_lora_v1: 30%|##9 | 893/3000 [08:59<48:10, 1.37s/it, lr: 1.0e-04 loss: 6.295e-01] my_first_lora_v1: 30%|##9 | 893/3000 [08:59<48:10, 1.37s/it, lr: 1.0e-04 loss: 6.295e-01] my_first_lora_v1: 30%|##9 | 894/3000 [09:00<48:11, 1.37s/it, lr: 1.0e-04 loss: 3.367e-01] my_first_lora_v1: 30%|##9 | 894/3000 [09:00<48:11, 1.37s/it, lr: 1.0e-04 loss: 3.367e-01] my_first_lora_v1: 30%|##9 | 895/3000 [09:02<48:10, 1.37s/it, lr: 1.0e-04 loss: 1.682e-01] my_first_lora_v1: 30%|##9 | 895/3000 [09:02<48:10, 1.37s/it, lr: 1.0e-04 loss: 1.682e-01] my_first_lora_v1: 30%|##9 | 896/3000 [09:04<48:10, 1.37s/it, lr: 1.0e-04 loss: 3.344e-02] my_first_lora_v1: 30%|##9 | 896/3000 [09:04<48:10, 1.37s/it, lr: 1.0e-04 loss: 3.344e-02] my_first_lora_v1: 30%|##9 | 897/3000 [09:05<48:10, 1.37s/it, lr: 1.0e-04 loss: 1.519e-01] my_first_lora_v1: 30%|##9 | 897/3000 [09:05<48:10, 1.37s/it, lr: 1.0e-04 loss: 1.519e-01] my_first_lora_v1: 30%|##9 | 898/3000 [09:06<48:08, 1.37s/it, lr: 1.0e-04 loss: 7.297e-02] my_first_lora_v1: 30%|##9 | 898/3000 [09:06<48:08, 1.37s/it, lr: 1.0e-04 loss: 7.297e-02] my_first_lora_v1: 30%|##9 | 899/3000 [09:07<48:05, 1.37s/it, lr: 1.0e-04 loss: 1.408e-01] my_first_lora_v1: 30%|##9 | 899/3000 [09:07<48:05, 1.37s/it, lr: 1.0e-04 loss: 1.408e-01] my_first_lora_v1: 30%|### | 900/3000 [09:10<48:09, 1.38s/it, lr: 1.0e-04 loss: 2.773e-01] my_first_lora_v1: 30%|### | 900/3000 [09:10<48:09, 1.38s/it, lr: 1.0e-04 loss: 2.773e-01] my_first_lora_v1: 30%|### | 901/3000 [09:12<48:13, 1.38s/it, lr: 1.0e-04 loss: 2.801e-01] my_first_lora_v1: 30%|### | 901/3000 [09:12<48:13, 1.38s/it, lr: 1.0e-04 loss: 2.801e-01] my_first_lora_v1: 30%|### | 902/3000 [09:13<48:10, 1.38s/it, lr: 1.0e-04 loss: 4.051e-02] my_first_lora_v1: 30%|### | 902/3000 [09:13<48:10, 1.38s/it, lr: 1.0e-04 loss: 4.051e-02] my_first_lora_v1: 30%|### | 903/3000 [09:14<48:06, 1.38s/it, lr: 1.0e-04 loss: 6.774e-01] my_first_lora_v1: 30%|### | 903/3000 [09:14<48:06, 1.38s/it, lr: 1.0e-04 loss: 6.774e-01] my_first_lora_v1: 30%|### | 904/3000 [09:16<48:05, 1.38s/it, lr: 1.0e-04 loss: 3.572e-01] my_first_lora_v1: 30%|### | 904/3000 [09:16<48:05, 1.38s/it, lr: 1.0e-04 loss: 3.572e-01] my_first_lora_v1: 30%|### | 905/3000 [09:17<48:05, 1.38s/it, lr: 1.0e-04 loss: 4.718e-01] my_first_lora_v1: 30%|### | 905/3000 [09:17<48:05, 1.38s/it, lr: 1.0e-04 loss: 4.718e-01] my_first_lora_v1: 30%|### | 906/3000 [09:20<48:10, 1.38s/it, lr: 1.0e-04 loss: 5.179e-01] my_first_lora_v1: 30%|### | 906/3000 [09:20<48:10, 1.38s/it, lr: 1.0e-04 loss: 5.179e-01] my_first_lora_v1: 30%|### | 907/3000 [09:21<48:05, 1.38s/it, lr: 1.0e-04 loss: 2.355e-01] my_first_lora_v1: 30%|### | 907/3000 [09:21<48:05, 1.38s/it, lr: 1.0e-04 loss: 2.355e-01] my_first_lora_v1: 30%|### | 908/3000 [09:24<48:12, 1.38s/it, lr: 1.0e-04 loss: 7.177e-01] my_first_lora_v1: 30%|### | 908/3000 [09:24<48:12, 1.38s/it, lr: 1.0e-04 loss: 7.177e-01] my_first_lora_v1: 30%|### | 909/3000 [09:24<48:08, 1.38s/it, lr: 1.0e-04 loss: 1.590e-01] my_first_lora_v1: 30%|### | 909/3000 [09:24<48:08, 1.38s/it, lr: 1.0e-04 loss: 1.590e-01] my_first_lora_v1: 30%|### | 910/3000 [09:27<48:11, 1.38s/it, lr: 1.0e-04 loss: 1.831e-01] my_first_lora_v1: 30%|### | 910/3000 [09:27<48:11, 1.38s/it, lr: 1.0e-04 loss: 1.831e-01] my_first_lora_v1: 30%|### | 911/3000 [09:28<48:10, 1.38s/it, lr: 1.0e-04 loss: 6.762e-01] my_first_lora_v1: 30%|### | 911/3000 [09:28<48:10, 1.38s/it, lr: 1.0e-04 loss: 6.762e-01] my_first_lora_v1: 30%|### | 912/3000 [09:29<48:07, 1.38s/it, lr: 1.0e-04 loss: 3.250e-01] my_first_lora_v1: 30%|### | 912/3000 [09:29<48:07, 1.38s/it, lr: 1.0e-04 loss: 3.250e-01] my_first_lora_v1: 30%|### | 913/3000 [09:31<48:08, 1.38s/it, lr: 1.0e-04 loss: 2.467e-01] my_first_lora_v1: 30%|### | 913/3000 [09:31<48:08, 1.38s/it, lr: 1.0e-04 loss: 2.467e-01] my_first_lora_v1: 30%|### | 914/3000 [09:34<48:13, 1.39s/it, lr: 1.0e-04 loss: 4.906e-01] my_first_lora_v1: 30%|### | 914/3000 [09:34<48:13, 1.39s/it, lr: 1.0e-04 loss: 4.906e-01] my_first_lora_v1: 30%|### | 915/3000 [09:36<48:17, 1.39s/it, lr: 1.0e-04 loss: 2.559e-01] my_first_lora_v1: 30%|### | 915/3000 [09:36<48:17, 1.39s/it, lr: 1.0e-04 loss: 2.559e-01] my_first_lora_v1: 31%|### | 916/3000 [09:39<48:21, 1.39s/it, lr: 1.0e-04 loss: 5.839e-01] my_first_lora_v1: 31%|### | 916/3000 [09:39<48:21, 1.39s/it, lr: 1.0e-04 loss: 5.839e-01] my_first_lora_v1: 31%|### | 917/3000 [09:40<48:21, 1.39s/it, lr: 1.0e-04 loss: 1.403e-01] my_first_lora_v1: 31%|### | 917/3000 [09:40<48:21, 1.39s/it, lr: 1.0e-04 loss: 1.403e-01] my_first_lora_v1: 31%|### | 918/3000 [09:42<48:20, 1.39s/it, lr: 1.0e-04 loss: 3.964e-01] my_first_lora_v1: 31%|### | 918/3000 [09:42<48:20, 1.39s/it, lr: 1.0e-04 loss: 3.964e-01] my_first_lora_v1: 31%|### | 919/3000 [09:43<48:18, 1.39s/it, lr: 1.0e-04 loss: 1.053e-01] my_first_lora_v1: 31%|### | 919/3000 [09:43<48:18, 1.39s/it, lr: 1.0e-04 loss: 1.053e-01] my_first_lora_v1: 31%|### | 920/3000 [09:44<48:15, 1.39s/it, lr: 1.0e-04 loss: 2.439e-01] my_first_lora_v1: 31%|### | 920/3000 [09:44<48:15, 1.39s/it, lr: 1.0e-04 loss: 2.439e-01] my_first_lora_v1: 31%|### | 921/3000 [09:45<48:11, 1.39s/it, lr: 1.0e-04 loss: 7.083e-01] my_first_lora_v1: 31%|### | 921/3000 [09:45<48:11, 1.39s/it, lr: 1.0e-04 loss: 7.083e-01] my_first_lora_v1: 31%|### | 922/3000 [09:47<48:10, 1.39s/it, lr: 1.0e-04 loss: 1.755e-01] my_first_lora_v1: 31%|### | 922/3000 [09:47<48:10, 1.39s/it, lr: 1.0e-04 loss: 1.755e-01] my_first_lora_v1: 31%|### | 923/3000 [09:48<48:11, 1.39s/it, lr: 1.0e-04 loss: 1.955e-01] my_first_lora_v1: 31%|### | 923/3000 [09:48<48:11, 1.39s/it, lr: 1.0e-04 loss: 1.955e-01] my_first_lora_v1: 31%|### | 924/3000 [09:49<48:06, 1.39s/it, lr: 1.0e-04 loss: 8.467e-01] my_first_lora_v1: 31%|### | 924/3000 [09:49<48:06, 1.39s/it, lr: 1.0e-04 loss: 8.467e-01] my_first_lora_v1: 31%|### | 925/3000 [09:50<48:04, 1.39s/it, lr: 1.0e-04 loss: 5.646e-01] my_first_lora_v1: 31%|### | 925/3000 [09:50<48:04, 1.39s/it, lr: 1.0e-04 loss: 5.646e-01] my_first_lora_v1: 31%|### | 926/3000 [09:52<48:03, 1.39s/it, lr: 1.0e-04 loss: 2.950e-01] my_first_lora_v1: 31%|### | 926/3000 [09:52<48:03, 1.39s/it, lr: 1.0e-04 loss: 2.950e-01] my_first_lora_v1: 31%|### | 927/3000 [09:53<48:00, 1.39s/it, lr: 1.0e-04 loss: 5.339e-01] my_first_lora_v1: 31%|### | 927/3000 [09:53<48:00, 1.39s/it, lr: 1.0e-04 loss: 5.339e-01] my_first_lora_v1: 31%|### | 928/3000 [09:54<47:59, 1.39s/it, lr: 1.0e-04 loss: 5.271e-01] my_first_lora_v1: 31%|### | 928/3000 [09:54<47:59, 1.39s/it, lr: 1.0e-04 loss: 5.271e-01] my_first_lora_v1: 31%|### | 929/3000 [09:55<47:55, 1.39s/it, lr: 1.0e-04 loss: 5.380e-01] my_first_lora_v1: 31%|### | 929/3000 [09:55<47:55, 1.39s/it, lr: 1.0e-04 loss: 5.380e-01] my_first_lora_v1: 31%|###1 | 930/3000 [09:56<47:51, 1.39s/it, lr: 1.0e-04 loss: 3.219e-01] my_first_lora_v1: 31%|###1 | 930/3000 [09:56<47:51, 1.39s/it, lr: 1.0e-04 loss: 3.219e-01] my_first_lora_v1: 31%|###1 | 931/3000 [09:57<47:47, 1.39s/it, lr: 1.0e-04 loss: 2.540e-01] my_first_lora_v1: 31%|###1 | 931/3000 [09:57<47:47, 1.39s/it, lr: 1.0e-04 loss: 2.540e-01] my_first_lora_v1: 31%|###1 | 932/3000 [09:58<47:46, 1.39s/it, lr: 1.0e-04 loss: 6.687e-01] my_first_lora_v1: 31%|###1 | 932/3000 [09:58<47:46, 1.39s/it, lr: 1.0e-04 loss: 6.687e-01] my_first_lora_v1: 31%|###1 | 933/3000 [10:00<47:45, 1.39s/it, lr: 1.0e-04 loss: 2.376e-01] my_first_lora_v1: 31%|###1 | 933/3000 [10:00<47:45, 1.39s/it, lr: 1.0e-04 loss: 2.376e-01] my_first_lora_v1: 31%|###1 | 934/3000 [10:02<47:49, 1.39s/it, lr: 1.0e-04 loss: 1.193e-01] my_first_lora_v1: 31%|###1 | 934/3000 [10:02<47:49, 1.39s/it, lr: 1.0e-04 loss: 1.193e-01] my_first_lora_v1: 31%|###1 | 935/3000 [10:03<47:45, 1.39s/it, lr: 1.0e-04 loss: 2.103e-01] my_first_lora_v1: 31%|###1 | 935/3000 [10:03<47:45, 1.39s/it, lr: 1.0e-04 loss: 2.103e-01] my_first_lora_v1: 31%|###1 | 936/3000 [10:05<47:44, 1.39s/it, lr: 1.0e-04 loss: 6.821e-01] my_first_lora_v1: 31%|###1 | 936/3000 [10:05<47:44, 1.39s/it, lr: 1.0e-04 loss: 6.821e-01] my_first_lora_v1: 31%|###1 | 937/3000 [10:05<47:40, 1.39s/it, lr: 1.0e-04 loss: 4.715e-01] my_first_lora_v1: 31%|###1 | 937/3000 [10:05<47:40, 1.39s/it, lr: 1.0e-04 loss: 4.715e-01] my_first_lora_v1: 31%|###1 | 938/3000 [10:06<47:35, 1.39s/it, lr: 1.0e-04 loss: 2.452e-01] my_first_lora_v1: 31%|###1 | 938/3000 [10:06<47:35, 1.39s/it, lr: 1.0e-04 loss: 2.452e-01] my_first_lora_v1: 31%|###1 | 939/3000 [10:07<47:33, 1.38s/it, lr: 1.0e-04 loss: 2.101e-01] my_first_lora_v1: 31%|###1 | 939/3000 [10:07<47:33, 1.38s/it, lr: 1.0e-04 loss: 2.101e-01] my_first_lora_v1: 31%|###1 | 940/3000 [10:08<47:28, 1.38s/it, lr: 1.0e-04 loss: 1.695e-01] my_first_lora_v1: 31%|###1 | 940/3000 [10:08<47:28, 1.38s/it, lr: 1.0e-04 loss: 1.695e-01] my_first_lora_v1: 31%|###1 | 941/3000 [10:09<47:27, 1.38s/it, lr: 1.0e-04 loss: 8.414e-02] my_first_lora_v1: 31%|###1 | 941/3000 [10:09<47:27, 1.38s/it, lr: 1.0e-04 loss: 8.414e-02] my_first_lora_v1: 31%|###1 | 942/3000 [10:12<47:31, 1.39s/it, lr: 1.0e-04 loss: 0.000e+00] my_first_lora_v1: 31%|###1 | 942/3000 [10:12<47:31, 1.39s/it, lr: 1.0e-04 loss: 0.000e+00] my_first_lora_v1: 31%|###1 | 943/3000 [10:13<47:26, 1.38s/it, lr: 1.0e-04 loss: 8.472e-01] my_first_lora_v1: 31%|###1 | 943/3000 [10:13<47:26, 1.38s/it, lr: 1.0e-04 loss: 8.472e-01] my_first_lora_v1: 31%|###1 | 944/3000 [10:14<47:26, 1.38s/it, lr: 1.0e-04 loss: 2.562e-01] my_first_lora_v1: 31%|###1 | 944/3000 [10:14<47:26, 1.38s/it, lr: 1.0e-04 loss: 2.562e-01] my_first_lora_v1: 32%|###1 | 945/3000 [10:16<47:25, 1.38s/it, lr: 1.0e-04 loss: 6.161e-01] my_first_lora_v1: 32%|###1 | 945/3000 [10:16<47:25, 1.38s/it, lr: 1.0e-04 loss: 6.161e-01] my_first_lora_v1: 32%|###1 | 946/3000 [10:17<47:24, 1.38s/it, lr: 1.0e-04 loss: 7.055e-01] my_first_lora_v1: 32%|###1 | 946/3000 [10:17<47:24, 1.38s/it, lr: 1.0e-04 loss: 7.055e-01] my_first_lora_v1: 32%|###1 | 947/3000 [10:18<47:20, 1.38s/it, lr: 1.0e-04 loss: 1.373e-01] my_first_lora_v1: 32%|###1 | 947/3000 [10:18<47:20, 1.38s/it, lr: 1.0e-04 loss: 1.373e-01] my_first_lora_v1: 32%|###1 | 948/3000 [10:20<47:20, 1.38s/it, lr: 1.0e-04 loss: 2.256e-01] my_first_lora_v1: 32%|###1 | 948/3000 [10:20<47:20, 1.38s/it, lr: 1.0e-04 loss: 2.256e-01] my_first_lora_v1: 32%|###1 | 949/3000 [10:22<47:24, 1.39s/it, lr: 1.0e-04 loss: 7.218e-01] my_first_lora_v1: 32%|###1 | 949/3000 [10:22<47:24, 1.39s/it, lr: 1.0e-04 loss: 7.218e-01] my_first_lora_v1: 32%|###1 | 950/3000 [10:23<47:20, 1.39s/it, lr: 1.0e-04 loss: 6.546e-01] my_first_lora_v1: 32%|###1 | 950/3000 [10:23<47:20, 1.39s/it, lr: 1.0e-04 loss: 6.546e-01] my_first_lora_v1: 32%|###1 | 951/3000 [10:24<47:16, 1.38s/it, lr: 1.0e-04 loss: 2.870e-01] my_first_lora_v1: 32%|###1 | 951/3000 [10:24<47:16, 1.38s/it, lr: 1.0e-04 loss: 2.870e-01] my_first_lora_v1: 32%|###1 | 952/3000 [10:25<47:12, 1.38s/it, lr: 1.0e-04 loss: 2.939e-01] my_first_lora_v1: 32%|###1 | 952/3000 [10:25<47:12, 1.38s/it, lr: 1.0e-04 loss: 2.939e-01] my_first_lora_v1: 32%|###1 | 953/3000 [10:27<47:16, 1.39s/it, lr: 1.0e-04 loss: 3.440e-01] my_first_lora_v1: 32%|###1 | 953/3000 [10:27<47:16, 1.39s/it, lr: 1.0e-04 loss: 3.440e-01] my_first_lora_v1: 32%|###1 | 954/3000 [10:28<47:12, 1.38s/it, lr: 1.0e-04 loss: 3.997e-01] my_first_lora_v1: 32%|###1 | 954/3000 [10:28<47:12, 1.38s/it, lr: 1.0e-04 loss: 3.997e-01] my_first_lora_v1: 32%|###1 | 955/3000 [10:29<47:08, 1.38s/it, lr: 1.0e-04 loss: 4.828e-01] my_first_lora_v1: 32%|###1 | 955/3000 [10:29<47:08, 1.38s/it, lr: 1.0e-04 loss: 4.828e-01] my_first_lora_v1: 32%|###1 | 956/3000 [10:31<47:08, 1.38s/it, lr: 1.0e-04 loss: 6.906e-01] my_first_lora_v1: 32%|###1 | 956/3000 [10:31<47:08, 1.38s/it, lr: 1.0e-04 loss: 6.906e-01] my_first_lora_v1: 32%|###1 | 957/3000 [10:31<47:04, 1.38s/it, lr: 1.0e-04 loss: 3.691e-02] my_first_lora_v1: 32%|###1 | 957/3000 [10:31<47:04, 1.38s/it, lr: 1.0e-04 loss: 3.691e-02] my_first_lora_v1: 32%|###1 | 958/3000 [10:33<47:04, 1.38s/it, lr: 1.0e-04 loss: 4.953e-01] my_first_lora_v1: 32%|###1 | 958/3000 [10:33<47:04, 1.38s/it, lr: 1.0e-04 loss: 4.953e-01] my_first_lora_v1: 32%|###1 | 959/3000 [10:35<47:04, 1.38s/it, lr: 1.0e-04 loss: 3.416e-01] my_first_lora_v1: 32%|###1 | 959/3000 [10:35<47:04, 1.38s/it, lr: 1.0e-04 loss: 3.416e-01] my_first_lora_v1: 32%|###2 | 960/3000 [10:36<47:03, 1.38s/it, lr: 1.0e-04 loss: 5.321e-01] my_first_lora_v1: 32%|###2 | 960/3000 [10:36<47:03, 1.38s/it, lr: 1.0e-04 loss: 5.321e-01] my_first_lora_v1: 32%|###2 | 961/3000 [10:37<46:59, 1.38s/it, lr: 1.0e-04 loss: 7.913e-01] my_first_lora_v1: 32%|###2 | 961/3000 [10:37<46:59, 1.38s/it, lr: 1.0e-04 loss: 7.913e-01] my_first_lora_v1: 32%|###2 | 962/3000 [10:38<46:55, 1.38s/it, lr: 1.0e-04 loss: 4.750e-01] my_first_lora_v1: 32%|###2 | 962/3000 [10:38<46:55, 1.38s/it, lr: 1.0e-04 loss: 4.750e-01] my_first_lora_v1: 32%|###2 | 963/3000 [10:39<46:51, 1.38s/it, lr: 1.0e-04 loss: 8.596e-01] my_first_lora_v1: 32%|###2 | 963/3000 [10:39<46:51, 1.38s/it, lr: 1.0e-04 loss: 8.596e-01] my_first_lora_v1: 32%|###2 | 964/3000 [10:39<46:47, 1.38s/it, lr: 1.0e-04 loss: 7.645e-01] my_first_lora_v1: 32%|###2 | 964/3000 [10:39<46:47, 1.38s/it, lr: 1.0e-04 loss: 7.645e-01] my_first_lora_v1: 32%|###2 | 965/3000 [10:41<46:46, 1.38s/it, lr: 1.0e-04 loss: 1.359e-01] my_first_lora_v1: 32%|###2 | 965/3000 [10:41<46:46, 1.38s/it, lr: 1.0e-04 loss: 1.359e-01] my_first_lora_v1: 32%|###2 | 966/3000 [10:42<46:42, 1.38s/it, lr: 1.0e-04 loss: 6.627e-01] my_first_lora_v1: 32%|###2 | 966/3000 [10:42<46:42, 1.38s/it, lr: 1.0e-04 loss: 6.627e-01] my_first_lora_v1: 32%|###2 | 967/3000 [10:44<46:43, 1.38s/it, lr: 1.0e-04 loss: 7.190e-01] my_first_lora_v1: 32%|###2 | 967/3000 [10:44<46:43, 1.38s/it, lr: 1.0e-04 loss: 7.190e-01] my_first_lora_v1: 32%|###2 | 968/3000 [10:45<46:42, 1.38s/it, lr: 1.0e-04 loss: 4.024e-01] my_first_lora_v1: 32%|###2 | 968/3000 [10:45<46:42, 1.38s/it, lr: 1.0e-04 loss: 4.024e-01] my_first_lora_v1: 32%|###2 | 969/3000 [10:46<46:40, 1.38s/it, lr: 1.0e-04 loss: 5.737e-01] my_first_lora_v1: 32%|###2 | 969/3000 [10:46<46:40, 1.38s/it, lr: 1.0e-04 loss: 5.737e-01] my_first_lora_v1: 32%|###2 | 970/3000 [10:49<46:44, 1.38s/it, lr: 1.0e-04 loss: 7.809e-01] my_first_lora_v1: 32%|###2 | 970/3000 [10:49<46:44, 1.38s/it, lr: 1.0e-04 loss: 7.809e-01] my_first_lora_v1: 32%|###2 | 971/3000 [10:52<46:49, 1.38s/it, lr: 1.0e-04 loss: 8.050e-01] my_first_lora_v1: 32%|###2 | 971/3000 [10:52<46:49, 1.38s/it, lr: 1.0e-04 loss: 8.050e-01] my_first_lora_v1: 32%|###2 | 972/3000 [10:54<46:53, 1.39s/it, lr: 1.0e-04 loss: 7.440e-01] my_first_lora_v1: 32%|###2 | 972/3000 [10:54<46:53, 1.39s/it, lr: 1.0e-04 loss: 7.440e-01] my_first_lora_v1: 32%|###2 | 973/3000 [10:55<46:49, 1.39s/it, lr: 1.0e-04 loss: 7.767e-01] my_first_lora_v1: 32%|###2 | 973/3000 [10:55<46:49, 1.39s/it, lr: 1.0e-04 loss: 7.767e-01] my_first_lora_v1: 32%|###2 | 974/3000 [10:56<46:45, 1.38s/it, lr: 1.0e-04 loss: 5.474e-02] my_first_lora_v1: 32%|###2 | 974/3000 [10:56<46:45, 1.38s/it, lr: 1.0e-04 loss: 5.474e-02] my_first_lora_v1: 32%|###2 | 975/3000 [10:57<46:41, 1.38s/it, lr: 1.0e-04 loss: 6.995e-01] my_first_lora_v1: 32%|###2 | 975/3000 [10:57<46:41, 1.38s/it, lr: 1.0e-04 loss: 6.995e-01] my_first_lora_v1: 33%|###2 | 976/3000 [10:58<46:37, 1.38s/it, lr: 1.0e-04 loss: 5.459e-02] my_first_lora_v1: 33%|###2 | 976/3000 [10:58<46:37, 1.38s/it, lr: 1.0e-04 loss: 5.459e-02] my_first_lora_v1: 33%|###2 | 977/3000 [10:59<46:36, 1.38s/it, lr: 1.0e-04 loss: 8.099e-01] my_first_lora_v1: 33%|###2 | 977/3000 [10:59<46:36, 1.38s/it, lr: 1.0e-04 loss: 8.099e-01] my_first_lora_v1: 33%|###2 | 978/3000 [11:00<46:35, 1.38s/it, lr: 1.0e-04 loss: 1.368e-01] my_first_lora_v1: 33%|###2 | 978/3000 [11:00<46:35, 1.38s/it, lr: 1.0e-04 loss: 1.368e-01] my_first_lora_v1: 33%|###2 | 979/3000 [11:02<46:33, 1.38s/it, lr: 1.0e-04 loss: 2.497e-01] my_first_lora_v1: 33%|###2 | 979/3000 [11:02<46:33, 1.38s/it, lr: 1.0e-04 loss: 2.497e-01] my_first_lora_v1: 33%|###2 | 980/3000 [11:03<46:32, 1.38s/it, lr: 1.0e-04 loss: 3.070e-01] my_first_lora_v1: 33%|###2 | 980/3000 [11:03<46:32, 1.38s/it, lr: 1.0e-04 loss: 3.070e-01] my_first_lora_v1: 33%|###2 | 981/3000 [11:05<46:32, 1.38s/it, lr: 1.0e-04 loss: 5.004e-01] my_first_lora_v1: 33%|###2 | 981/3000 [11:05<46:32, 1.38s/it, lr: 1.0e-04 loss: 5.004e-01] my_first_lora_v1: 33%|###2 | 982/3000 [11:06<46:31, 1.38s/it, lr: 1.0e-04 loss: 9.291e-02] my_first_lora_v1: 33%|###2 | 982/3000 [11:06<46:31, 1.38s/it, lr: 1.0e-04 loss: 9.291e-02] my_first_lora_v1: 33%|###2 | 983/3000 [11:09<46:34, 1.39s/it, lr: 1.0e-04 loss: 6.770e-01] my_first_lora_v1: 33%|###2 | 983/3000 [11:09<46:34, 1.39s/it, lr: 1.0e-04 loss: 6.770e-01] my_first_lora_v1: 33%|###2 | 984/3000 [11:10<46:30, 1.38s/it, lr: 1.0e-04 loss: 8.318e-01] my_first_lora_v1: 33%|###2 | 984/3000 [11:10<46:30, 1.38s/it, lr: 1.0e-04 loss: 8.318e-01] my_first_lora_v1: 33%|###2 | 985/3000 [11:11<46:30, 1.38s/it, lr: 1.0e-04 loss: 1.961e-01] my_first_lora_v1: 33%|###2 | 985/3000 [11:11<46:30, 1.38s/it, lr: 1.0e-04 loss: 1.961e-01] my_first_lora_v1: 33%|###2 | 986/3000 [11:13<46:29, 1.39s/it, lr: 1.0e-04 loss: 7.607e-01] my_first_lora_v1: 33%|###2 | 986/3000 [11:13<46:29, 1.39s/it, lr: 1.0e-04 loss: 7.607e-01] my_first_lora_v1: 33%|###2 | 987/3000 [11:13<46:25, 1.38s/it, lr: 1.0e-04 loss: 1.941e-01] my_first_lora_v1: 33%|###2 | 987/3000 [11:13<46:25, 1.38s/it, lr: 1.0e-04 loss: 1.941e-01] my_first_lora_v1: 33%|###2 | 988/3000 [11:15<46:24, 1.38s/it, lr: 1.0e-04 loss: 5.636e-01] my_first_lora_v1: 33%|###2 | 988/3000 [11:15<46:24, 1.38s/it, lr: 1.0e-04 loss: 5.636e-01] my_first_lora_v1: 33%|###2 | 989/3000 [11:16<46:20, 1.38s/it, lr: 1.0e-04 loss: 4.558e-01] my_first_lora_v1: 33%|###2 | 989/3000 [11:16<46:20, 1.38s/it, lr: 1.0e-04 loss: 4.558e-01] my_first_lora_v1: 33%|###3 | 990/3000 [11:16<46:16, 1.38s/it, lr: 1.0e-04 loss: 1.128e-01] my_first_lora_v1: 33%|###3 | 990/3000 [11:16<46:16, 1.38s/it, lr: 1.0e-04 loss: 1.128e-01] my_first_lora_v1: 33%|###3 | 991/3000 [11:18<46:16, 1.38s/it, lr: 1.0e-04 loss: 4.744e-01] my_first_lora_v1: 33%|###3 | 991/3000 [11:18<46:16, 1.38s/it, lr: 1.0e-04 loss: 4.744e-01] my_first_lora_v1: 33%|###3 | 992/3000 [11:19<46:12, 1.38s/it, lr: 1.0e-04 loss: 6.998e-01] my_first_lora_v1: 33%|###3 | 992/3000 [11:19<46:12, 1.38s/it, lr: 1.0e-04 loss: 6.998e-01] my_first_lora_v1: 33%|###3 | 993/3000 [11:20<46:12, 1.38s/it, lr: 1.0e-04 loss: 5.854e-01] my_first_lora_v1: 33%|###3 | 993/3000 [11:20<46:12, 1.38s/it, lr: 1.0e-04 loss: 5.854e-01] my_first_lora_v1: 33%|###3 | 994/3000 [11:22<46:09, 1.38s/it, lr: 1.0e-04 loss: 7.393e-01] my_first_lora_v1: 33%|###3 | 994/3000 [11:22<46:09, 1.38s/it, lr: 1.0e-04 loss: 7.393e-01] my_first_lora_v1: 33%|###3 | 995/3000 [11:23<46:08, 1.38s/it, lr: 1.0e-04 loss: 4.387e-01] my_first_lora_v1: 33%|###3 | 995/3000 [11:23<46:08, 1.38s/it, lr: 1.0e-04 loss: 4.387e-01] my_first_lora_v1: 33%|###3 | 996/3000 [11:24<46:07, 1.38s/it, lr: 1.0e-04 loss: 6.597e-02] my_first_lora_v1: 33%|###3 | 996/3000 [11:24<46:07, 1.38s/it, lr: 1.0e-04 loss: 6.597e-02] my_first_lora_v1: 33%|###3 | 997/3000 [11:25<46:03, 1.38s/it, lr: 1.0e-04 loss: 7.478e-01] my_first_lora_v1: 33%|###3 | 997/3000 [11:25<46:03, 1.38s/it, lr: 1.0e-04 loss: 7.478e-01] my_first_lora_v1: 33%|###3 | 998/3000 [11:27<46:03, 1.38s/it, lr: 1.0e-04 loss: 1.331e-01] my_first_lora_v1: 33%|###3 | 998/3000 [11:27<46:03, 1.38s/it, lr: 1.0e-04 loss: 1.331e-01] my_first_lora_v1: 33%|###3 | 999/3000 [11:28<45:59, 1.38s/it, lr: 1.0e-04 loss: 4.012e-01] my_first_lora_v1: 33%|###3 | 999/3000 [11:28<45:59, 1.38s/it, lr: 1.0e-04 loss: 4.012e-01]
Saving at step 1000
Saved checkpoint to /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v1/my_first_lora_v1_000001000.safetensors
Saved optimizer to /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v1/optimizer.pt
Unloading assistant lora
Generating Images: 0%| | 0/5 [00:00<?, ?it/s] Generating Images: 0%| | 0/5 [00:00<?, ?it/s]
Generating Images: 20%|## | 1/5 [00:07<00:30, 7.66s/it] Generating Images: 20%|## | 1/5 [00:07<00:30, 7.66s/it]
Generating Images: 40%|#### | 2/5 [00:15<00:22, 7.64s/it] Generating Images: 40%|#### | 2/5 [00:15<00:22, 7.64s/it]
Generating Images: 60%|###### | 3/5 [00:23<00:15, 7.72s/it] Generating Images: 60%|###### | 3/5 [00:23<00:15, 7.72s/it]
Generating Images: 80%|######## | 4/5 [00:30<00:07, 7.66s/it] Generating Images: 80%|######## | 4/5 [00:30<00:07, 7.66s/it]
Generating Images: 100%|##########| 5/5 [00:38<00:00, 7.89s/it] Generating Images: 100%|##########| 5/5 [00:38<00:00, 7.89s/it]
Loading assistant lora
my_first_lora_v1: 33%|###3 | 1000/3000 [11:29<45:58, 1.38s/it, lr: 1.0e-04 loss: 6.882e-01] my_first_lora_v1: 33%|###3 | 1000/3000 [11:29<45:58, 1.38s/it, lr: 1.0e-04 loss: 6.882e-01] my_first_lora_v1: 33%|###3 | 1001/3000 [11:31<45:58, 1.38s/it, lr: 1.0e-04 loss: 4.435e-01] my_first_lora_v1: 33%|###3 | 1001/3000 [11:31<45:58, 1.38s/it, lr: 1.0e-04 loss: 4.435e-01] my_first_lora_v1: 33%|###3 | 1002/3000 [11:32<45:54, 1.38s/it, lr: 1.0e-04 loss: 1.086e-01] my_first_lora_v1: 33%|###3 | 1002/3000 [11:32<45:54, 1.38s/it, lr: 1.0e-04 loss: 1.086e-01] my_first_lora_v1: 33%|###3 | 1003/3000 [11:33<45:52, 1.38s/it, lr: 1.0e-04 loss: 5.860e-01] my_first_lora_v1: 33%|###3 | 1003/3000 [11:33<45:52, 1.38s/it, lr: 1.0e-04 loss: 5.860e-01] my_first_lora_v1: 33%|###3 | 1004/3000 [11:34<45:51, 1.38s/it, lr: 1.0e-04 loss: 2.182e-01] my_first_lora_v1: 33%|###3 | 1004/3000 [11:34<45:51, 1.38s/it, lr: 1.0e-04 loss: 2.182e-01] my_first_lora_v1: 34%|###3 | 1005/3000 [11:35<45:47, 1.38s/it, lr: 1.0e-04 loss: 5.299e-01] my_first_lora_v1: 34%|###3 | 1005/3000 [11:35<45:47, 1.38s/it, lr: 1.0e-04 loss: 5.299e-01] my_first_lora_v1: 34%|###3 | 1006/3000 [11:37<45:46, 1.38s/it, lr: 1.0e-04 loss: 6.166e-01] my_first_lora_v1: 34%|###3 | 1006/3000 [11:37<45:46, 1.38s/it, lr: 1.0e-04 loss: 6.166e-01] my_first_lora_v1: 34%|###3 | 1007/3000 [11:37<45:43, 1.38s/it, lr: 1.0e-04 loss: 2.695e-01] my_first_lora_v1: 34%|###3 | 1007/3000 [11:37<45:43, 1.38s/it, lr: 1.0e-04 loss: 2.695e-01] my_first_lora_v1: 34%|###3 | 1008/3000 [11:40<45:45, 1.38s/it, lr: 1.0e-04 loss: 3.703e-01] my_first_lora_v1: 34%|###3 | 1008/3000 [11:40<45:45, 1.38s/it, lr: 1.0e-04 loss: 3.703e-01] my_first_lora_v1: 34%|###3 | 1009/3000 [11:41<45:43, 1.38s/it, lr: 1.0e-04 loss: 4.145e-01] my_first_lora_v1: 34%|###3 | 1009/3000 [11:41<45:43, 1.38s/it, lr: 1.0e-04 loss: 4.145e-01] my_first_lora_v1: 34%|###3 | 1010/3000 [11:42<45:39, 1.38s/it, lr: 1.0e-04 loss: 5.111e-01] my_first_lora_v1: 34%|###3 | 1010/3000 [11:42<45:39, 1.38s/it, lr: 1.0e-04 loss: 5.111e-01] my_first_lora_v1: 34%|###3 | 1011/3000 [11:43<45:38, 1.38s/it, lr: 1.0e-04 loss: 2.336e-02] my_first_lora_v1: 34%|###3 | 1011/3000 [11:43<45:38, 1.38s/it, lr: 1.0e-04 loss: 2.336e-02] my_first_lora_v1: 34%|###3 | 1012/3000 [11:44<45:36, 1.38s/it, lr: 1.0e-04 loss: 7.194e-01] my_first_lora_v1: 34%|###3 | 1012/3000 [11:44<45:36, 1.38s/it, lr: 1.0e-04 loss: 7.194e-01] my_first_lora_v1: 34%|###3 | 1013/3000 [11:46<45:35, 1.38s/it, lr: 1.0e-04 loss: 1.337e-01] my_first_lora_v1: 34%|###3 | 1013/3000 [11:46<45:35, 1.38s/it, lr: 1.0e-04 loss: 1.337e-01] my_first_lora_v1: 34%|###3 | 1014/3000 [11:47<45:32, 1.38s/it, lr: 1.0e-04 loss: 3.623e-01] my_first_lora_v1: 34%|###3 | 1014/3000 [11:47<45:32, 1.38s/it, lr: 1.0e-04 loss: 3.623e-01] my_first_lora_v1: 34%|###3 | 1015/3000 [11:49<45:34, 1.38s/it, lr: 1.0e-04 loss: 6.181e-01] my_first_lora_v1: 34%|###3 | 1015/3000 [11:49<45:34, 1.38s/it, lr: 1.0e-04 loss: 6.181e-01] my_first_lora_v1: 34%|###3 | 1016/3000 [11:50<45:33, 1.38s/it, lr: 1.0e-04 loss: 7.498e-01] my_first_lora_v1: 34%|###3 | 1016/3000 [11:50<45:33, 1.38s/it, lr: 1.0e-04 loss: 7.498e-01] my_first_lora_v1: 34%|###3 | 1017/3000 [11:53<45:38, 1.38s/it, lr: 1.0e-04 loss: 6.586e-01] my_first_lora_v1: 34%|###3 | 1017/3000 [11:53<45:38, 1.38s/it, lr: 1.0e-04 loss: 6.586e-01] my_first_lora_v1: 34%|###3 | 1018/3000 [11:55<45:37, 1.38s/it, lr: 1.0e-04 loss: 2.391e-01] my_first_lora_v1: 34%|###3 | 1018/3000 [11:55<45:37, 1.38s/it, lr: 1.0e-04 loss: 2.391e-01] my_first_lora_v1: 34%|###3 | 1019/3000 [11:56<45:35, 1.38s/it, lr: 1.0e-04 loss: 9.690e-02] my_first_lora_v1: 34%|###3 | 1019/3000 [11:56<45:35, 1.38s/it, lr: 1.0e-04 loss: 9.690e-02] my_first_lora_v1: 34%|###4 | 1020/3000 [11:57<45:33, 1.38s/it, lr: 1.0e-04 loss: 7.304e-01] my_first_lora_v1: 34%|###4 | 1020/3000 [11:57<45:33, 1.38s/it, lr: 1.0e-04 loss: 7.304e-01] my_first_lora_v1: 34%|###4 | 1021/3000 [11:59<45:32, 1.38s/it, lr: 1.0e-04 loss: 6.743e-01] my_first_lora_v1: 34%|###4 | 1021/3000 [11:59<45:32, 1.38s/it, lr: 1.0e-04 loss: 6.743e-01] my_first_lora_v1: 34%|###4 | 1022/3000 [12:01<45:35, 1.38s/it, lr: 1.0e-04 loss: 2.434e-01] my_first_lora_v1: 34%|###4 | 1022/3000 [12:01<45:35, 1.38s/it, lr: 1.0e-04 loss: 2.434e-01] my_first_lora_v1: 34%|###4 | 1023/3000 [12:02<45:31, 1.38s/it, lr: 1.0e-04 loss: 6.719e-01] my_first_lora_v1: 34%|###4 | 1023/3000 [12:02<45:31, 1.38s/it, lr: 1.0e-04 loss: 6.719e-01] my_first_lora_v1: 34%|###4 | 1024/3000 [12:04<45:30, 1.38s/it, lr: 1.0e-04 loss: 2.111e-01] my_first_lora_v1: 34%|###4 | 1024/3000 [12:04<45:30, 1.38s/it, lr: 1.0e-04 loss: 2.111e-01] my_first_lora_v1: 34%|###4 | 1025/3000 [12:05<45:28, 1.38s/it, lr: 1.0e-04 loss: 7.357e-01] my_first_lora_v1: 34%|###4 | 1025/3000 [12:05<45:28, 1.38s/it, lr: 1.0e-04 loss: 7.357e-01] my_first_lora_v1: 34%|###4 | 1026/3000 [12:07<45:28, 1.38s/it, lr: 1.0e-04 loss: 3.247e-01] my_first_lora_v1: 34%|###4 | 1026/3000 [12:07<45:28, 1.38s/it, lr: 1.0e-04 loss: 3.247e-01] my_first_lora_v1: 34%|###4 | 1027/3000 [12:07<45:25, 1.38s/it, lr: 1.0e-04 loss: 1.340e-01] my_first_lora_v1: 34%|###4 | 1027/3000 [12:07<45:25, 1.38s/it, lr: 1.0e-04 loss: 1.340e-01] my_first_lora_v1: 34%|###4 | 1028/3000 [12:09<45:23, 1.38s/it, lr: 1.0e-04 loss: 4.555e-01] my_first_lora_v1: 34%|###4 | 1028/3000 [12:09<45:23, 1.38s/it, lr: 1.0e-04 loss: 4.555e-01] my_first_lora_v1: 34%|###4 | 1029/3000 [12:11<45:23, 1.38s/it, lr: 1.0e-04 loss: 2.846e-01] my_first_lora_v1: 34%|###4 | 1029/3000 [12:11<45:23, 1.38s/it, lr: 1.0e-04 loss: 2.846e-01] my_first_lora_v1: 34%|###4 | 1030/3000 [12:13<45:27, 1.38s/it, lr: 1.0e-04 loss: 1.121e-01] my_first_lora_v1: 34%|###4 | 1030/3000 [12:13<45:27, 1.38s/it, lr: 1.0e-04 loss: 1.121e-01] my_first_lora_v1: 34%|###4 | 1031/3000 [12:15<45:26, 1.38s/it, lr: 1.0e-04 loss: 6.456e-01] my_first_lora_v1: 34%|###4 | 1031/3000 [12:15<45:26, 1.38s/it, lr: 1.0e-04 loss: 6.456e-01] my_first_lora_v1: 34%|###4 | 1032/3000 [12:17<45:28, 1.39s/it, lr: 1.0e-04 loss: 2.994e-02] my_first_lora_v1: 34%|###4 | 1032/3000 [12:17<45:28, 1.39s/it, lr: 1.0e-04 loss: 2.994e-02] my_first_lora_v1: 34%|###4 | 1033/3000 [12:19<45:30, 1.39s/it, lr: 1.0e-04 loss: 7.105e-01] my_first_lora_v1: 34%|###4 | 1033/3000 [12:19<45:30, 1.39s/it, lr: 1.0e-04 loss: 7.105e-01] my_first_lora_v1: 34%|###4 | 1034/3000 [12:21<45:28, 1.39s/it, lr: 1.0e-04 loss: 1.502e-01] my_first_lora_v1: 34%|###4 | 1034/3000 [12:21<45:28, 1.39s/it, lr: 1.0e-04 loss: 1.502e-01] my_first_lora_v1: 34%|###4 | 1035/3000 [12:22<45:25, 1.39s/it, lr: 1.0e-04 loss: 2.568e-01] my_first_lora_v1: 34%|###4 | 1035/3000 [12:22<45:25, 1.39s/it, lr: 1.0e-04 loss: 2.568e-01] my_first_lora_v1: 35%|###4 | 1036/3000 [12:22<45:22, 1.39s/it, lr: 1.0e-04 loss: 6.832e-01] my_first_lora_v1: 35%|###4 | 1036/3000 [12:22<45:22, 1.39s/it, lr: 1.0e-04 loss: 6.832e-01] my_first_lora_v1: 35%|###4 | 1037/3000 [12:24<45:21, 1.39s/it, lr: 1.0e-04 loss: 1.666e-01] my_first_lora_v1: 35%|###4 | 1037/3000 [12:24<45:21, 1.39s/it, lr: 1.0e-04 loss: 1.666e-01] my_first_lora_v1: 35%|###4 | 1038/3000 [12:25<45:18, 1.39s/it, lr: 1.0e-04 loss: 3.530e-01] my_first_lora_v1: 35%|###4 | 1038/3000 [12:25<45:18, 1.39s/it, lr: 1.0e-04 loss: 3.530e-01] my_first_lora_v1: 35%|###4 | 1039/3000 [12:26<45:14, 1.38s/it, lr: 1.0e-04 loss: 5.447e-01] my_first_lora_v1: 35%|###4 | 1039/3000 [12:26<45:14, 1.38s/it, lr: 1.0e-04 loss: 5.447e-01] my_first_lora_v1: 35%|###4 | 1040/3000 [12:27<45:14, 1.39s/it, lr: 1.0e-04 loss: 2.928e-01] my_first_lora_v1: 35%|###4 | 1040/3000 [12:27<45:14, 1.39s/it, lr: 1.0e-04 loss: 2.928e-01] my_first_lora_v1: 35%|###4 | 1041/3000 [12:29<45:13, 1.39s/it, lr: 1.0e-04 loss: 6.003e-01] my_first_lora_v1: 35%|###4 | 1041/3000 [12:29<45:13, 1.39s/it, lr: 1.0e-04 loss: 6.003e-01] my_first_lora_v1: 35%|###4 | 1042/3000 [12:30<45:09, 1.38s/it, lr: 1.0e-04 loss: 9.666e-02] my_first_lora_v1: 35%|###4 | 1042/3000 [12:30<45:09, 1.38s/it, lr: 1.0e-04 loss: 9.666e-02] my_first_lora_v1: 35%|###4 | 1043/3000 [12:30<45:06, 1.38s/it, lr: 1.0e-04 loss: 3.081e-01] my_first_lora_v1: 35%|###4 | 1043/3000 [12:30<45:06, 1.38s/it, lr: 1.0e-04 loss: 3.081e-01] my_first_lora_v1: 35%|###4 | 1044/3000 [12:31<45:02, 1.38s/it, lr: 1.0e-04 loss: 4.336e-01] my_first_lora_v1: 35%|###4 | 1044/3000 [12:31<45:02, 1.38s/it, lr: 1.0e-04 loss: 4.336e-01] my_first_lora_v1: 35%|###4 | 1045/3000 [12:34<45:04, 1.38s/it, lr: 1.0e-04 loss: 1.331e-01] my_first_lora_v1: 35%|###4 | 1045/3000 [12:34<45:04, 1.38s/it, lr: 1.0e-04 loss: 1.331e-01] my_first_lora_v1: 35%|###4 | 1046/3000 [12:35<45:03, 1.38s/it, lr: 1.0e-04 loss: 5.924e-01] my_first_lora_v1: 35%|###4 | 1046/3000 [12:35<45:03, 1.38s/it, lr: 1.0e-04 loss: 5.924e-01] my_first_lora_v1: 35%|###4 | 1047/3000 [12:36<45:02, 1.38s/it, lr: 1.0e-04 loss: 5.162e-01] my_first_lora_v1: 35%|###4 | 1047/3000 [12:36<45:02, 1.38s/it, lr: 1.0e-04 loss: 5.162e-01] my_first_lora_v1: 35%|###4 | 1048/3000 [12:37<44:58, 1.38s/it, lr: 1.0e-04 loss: 2.806e-01] my_first_lora_v1: 35%|###4 | 1048/3000 [12:37<44:58, 1.38s/it, lr: 1.0e-04 loss: 2.806e-01] my_first_lora_v1: 35%|###4 | 1049/3000 [12:39<44:57, 1.38s/it, lr: 1.0e-04 loss: 3.953e-01] my_first_lora_v1: 35%|###4 | 1049/3000 [12:39<44:57, 1.38s/it, lr: 1.0e-04 loss: 3.953e-01] my_first_lora_v1: 35%|###5 | 1050/3000 [12:40<44:57, 1.38s/it, lr: 1.0e-04 loss: 6.982e-01] my_first_lora_v1: 35%|###5 | 1050/3000 [12:40<44:57, 1.38s/it, lr: 1.0e-04 loss: 6.982e-01] my_first_lora_v1: 35%|###5 | 1051/3000 [12:41<44:54, 1.38s/it, lr: 1.0e-04 loss: 3.078e-01] my_first_lora_v1: 35%|###5 | 1051/3000 [12:41<44:54, 1.38s/it, lr: 1.0e-04 loss: 3.078e-01] my_first_lora_v1: 35%|###5 | 1052/3000 [12:43<44:53, 1.38s/it, lr: 1.0e-04 loss: 2.074e-01] my_first_lora_v1: 35%|###5 | 1052/3000 [12:43<44:53, 1.38s/it, lr: 1.0e-04 loss: 2.074e-01] my_first_lora_v1: 35%|###5 | 1053/3000 [12:45<44:55, 1.38s/it, lr: 1.0e-04 loss: 5.903e-01] my_first_lora_v1: 35%|###5 | 1053/3000 [12:45<44:55, 1.38s/it, lr: 1.0e-04 loss: 5.903e-01] my_first_lora_v1: 35%|###5 | 1054/3000 [12:46<44:53, 1.38s/it, lr: 1.0e-04 loss: 7.765e-01] my_first_lora_v1: 35%|###5 | 1054/3000 [12:46<44:53, 1.38s/it, lr: 1.0e-04 loss: 7.765e-01] my_first_lora_v1: 35%|###5 | 1055/3000 [12:47<44:49, 1.38s/it, lr: 1.0e-04 loss: 8.337e-01] my_first_lora_v1: 35%|###5 | 1055/3000 [12:47<44:49, 1.38s/it, lr: 1.0e-04 loss: 8.337e-01] my_first_lora_v1: 35%|###5 | 1056/3000 [12:48<44:47, 1.38s/it, lr: 1.0e-04 loss: 1.324e-01] my_first_lora_v1: 35%|###5 | 1056/3000 [12:48<44:47, 1.38s/it, lr: 1.0e-04 loss: 1.324e-01] my_first_lora_v1: 35%|###5 | 1057/3000 [12:49<44:44, 1.38s/it, lr: 1.0e-04 loss: 1.657e-01] my_first_lora_v1: 35%|###5 | 1057/3000 [12:49<44:44, 1.38s/it, lr: 1.0e-04 loss: 1.657e-01] my_first_lora_v1: 35%|###5 | 1058/3000 [12:52<44:47, 1.38s/it, lr: 1.0e-04 loss: 5.748e-01] my_first_lora_v1: 35%|###5 | 1058/3000 [12:52<44:47, 1.38s/it, lr: 1.0e-04 loss: 5.748e-01] my_first_lora_v1: 35%|###5 | 1059/3000 [12:53<44:46, 1.38s/it, lr: 1.0e-04 loss: 1.983e-02] my_first_lora_v1: 35%|###5 | 1059/3000 [12:53<44:46, 1.38s/it, lr: 1.0e-04 loss: 1.983e-02] my_first_lora_v1: 35%|###5 | 1060/3000 [12:54<44:43, 1.38s/it, lr: 1.0e-04 loss: 6.799e-01] my_first_lora_v1: 35%|###5 | 1060/3000 [12:54<44:43, 1.38s/it, lr: 1.0e-04 loss: 6.799e-01] my_first_lora_v1: 35%|###5 | 1061/3000 [12:55<44:39, 1.38s/it, lr: 1.0e-04 loss: 4.355e-01] my_first_lora_v1: 35%|###5 | 1061/3000 [12:55<44:39, 1.38s/it, lr: 1.0e-04 loss: 4.355e-01] my_first_lora_v1: 35%|###5 | 1062/3000 [12:56<44:37, 1.38s/it, lr: 1.0e-04 loss: 1.005e-01] my_first_lora_v1: 35%|###5 | 1062/3000 [12:56<44:37, 1.38s/it, lr: 1.0e-04 loss: 1.005e-01] my_first_lora_v1: 35%|###5 | 1063/3000 [12:58<44:39, 1.38s/it, lr: 1.0e-04 loss: 7.141e-01] my_first_lora_v1: 35%|###5 | 1063/3000 [12:58<44:39, 1.38s/it, lr: 1.0e-04 loss: 7.141e-01] my_first_lora_v1: 35%|###5 | 1064/3000 [13:00<44:37, 1.38s/it, lr: 1.0e-04 loss: 3.161e-01] my_first_lora_v1: 35%|###5 | 1064/3000 [13:00<44:37, 1.38s/it, lr: 1.0e-04 loss: 3.161e-01] my_first_lora_v1: 36%|###5 | 1065/3000 [13:01<44:35, 1.38s/it, lr: 1.0e-04 loss: 8.334e-01] my_first_lora_v1: 36%|###5 | 1065/3000 [13:01<44:35, 1.38s/it, lr: 1.0e-04 loss: 8.334e-01] my_first_lora_v1: 36%|###5 | 1066/3000 [13:02<44:34, 1.38s/it, lr: 1.0e-04 loss: 3.886e-01] my_first_lora_v1: 36%|###5 | 1066/3000 [13:02<44:34, 1.38s/it, lr: 1.0e-04 loss: 3.886e-01] my_first_lora_v1: 36%|###5 | 1067/3000 [13:04<44:33, 1.38s/it, lr: 1.0e-04 loss: 3.041e-01] my_first_lora_v1: 36%|###5 | 1067/3000 [13:04<44:33, 1.38s/it, lr: 1.0e-04 loss: 3.041e-01] my_first_lora_v1: 36%|###5 | 1068/3000 [13:04<44:30, 1.38s/it, lr: 1.0e-04 loss: 5.104e-01] my_first_lora_v1: 36%|###5 | 1068/3000 [13:04<44:30, 1.38s/it, lr: 1.0e-04 loss: 5.104e-01] my_first_lora_v1: 36%|###5 | 1069/3000 [13:05<44:26, 1.38s/it, lr: 1.0e-04 loss: 3.674e-01] my_first_lora_v1: 36%|###5 | 1069/3000 [13:05<44:26, 1.38s/it, lr: 1.0e-04 loss: 3.674e-01] my_first_lora_v1: 36%|###5 | 1070/3000 [13:06<44:24, 1.38s/it, lr: 1.0e-04 loss: 7.694e-01] my_first_lora_v1: 36%|###5 | 1070/3000 [13:06<44:24, 1.38s/it, lr: 1.0e-04 loss: 7.694e-01] my_first_lora_v1: 36%|###5 | 1071/3000 [13:08<44:23, 1.38s/it, lr: 1.0e-04 loss: 2.841e-01] my_first_lora_v1: 36%|###5 | 1071/3000 [13:08<44:23, 1.38s/it, lr: 1.0e-04 loss: 2.841e-01] my_first_lora_v1: 36%|###5 | 1072/3000 [13:09<44:19, 1.38s/it, lr: 1.0e-04 loss: 7.847e-01] my_first_lora_v1: 36%|###5 | 1072/3000 [13:09<44:19, 1.38s/it, lr: 1.0e-04 loss: 7.847e-01] my_first_lora_v1: 36%|###5 | 1073/3000 [13:10<44:18, 1.38s/it, lr: 1.0e-04 loss: 3.965e-01] my_first_lora_v1: 36%|###5 | 1073/3000 [13:10<44:18, 1.38s/it, lr: 1.0e-04 loss: 3.965e-01] my_first_lora_v1: 36%|###5 | 1074/3000 [13:11<44:14, 1.38s/it, lr: 1.0e-04 loss: 4.115e-01] my_first_lora_v1: 36%|###5 | 1074/3000 [13:11<44:14, 1.38s/it, lr: 1.0e-04 loss: 4.115e-01] my_first_lora_v1: 36%|###5 | 1075/3000 [13:12<44:11, 1.38s/it, lr: 1.0e-04 loss: 6.654e-01] my_first_lora_v1: 36%|###5 | 1075/3000 [13:12<44:11, 1.38s/it, lr: 1.0e-04 loss: 6.654e-01] my_first_lora_v1: 36%|###5 | 1076/3000 [13:14<44:14, 1.38s/it, lr: 1.0e-04 loss: 3.505e-01] my_first_lora_v1: 36%|###5 | 1076/3000 [13:14<44:14, 1.38s/it, lr: 1.0e-04 loss: 3.505e-01] my_first_lora_v1: 36%|###5 | 1077/3000 [13:17<44:18, 1.38s/it, lr: 1.0e-04 loss: 3.768e-01] my_first_lora_v1: 36%|###5 | 1077/3000 [13:17<44:18, 1.38s/it, lr: 1.0e-04 loss: 3.768e-01] my_first_lora_v1: 36%|###5 | 1078/3000 [13:18<44:14, 1.38s/it, lr: 1.0e-04 loss: 4.036e-01] my_first_lora_v1: 36%|###5 | 1078/3000 [13:18<44:14, 1.38s/it, lr: 1.0e-04 loss: 4.036e-01] my_first_lora_v1: 36%|###5 | 1079/3000 [13:20<44:16, 1.38s/it, lr: 1.0e-04 loss: 6.275e-01] my_first_lora_v1: 36%|###5 | 1079/3000 [13:20<44:16, 1.38s/it, lr: 1.0e-04 loss: 6.275e-01] my_first_lora_v1: 36%|###6 | 1080/3000 [13:21<44:14, 1.38s/it, lr: 1.0e-04 loss: 1.567e-01] my_first_lora_v1: 36%|###6 | 1080/3000 [13:21<44:14, 1.38s/it, lr: 1.0e-04 loss: 1.567e-01] my_first_lora_v1: 36%|###6 | 1081/3000 [13:22<44:11, 1.38s/it, lr: 1.0e-04 loss: 2.091e-01] my_first_lora_v1: 36%|###6 | 1081/3000 [13:22<44:11, 1.38s/it, lr: 1.0e-04 loss: 2.091e-01] my_first_lora_v1: 36%|###6 | 1082/3000 [13:24<44:10, 1.38s/it, lr: 1.0e-04 loss: 3.811e-01] my_first_lora_v1: 36%|###6 | 1082/3000 [13:24<44:10, 1.38s/it, lr: 1.0e-04 loss: 3.811e-01] my_first_lora_v1: 36%|###6 | 1083/3000 [13:25<44:09, 1.38s/it, lr: 1.0e-04 loss: 6.828e-01] my_first_lora_v1: 36%|###6 | 1083/3000 [13:25<44:09, 1.38s/it, lr: 1.0e-04 loss: 6.828e-01] my_first_lora_v1: 36%|###6 | 1084/3000 [13:26<44:06, 1.38s/it, lr: 1.0e-04 loss: 6.794e-01] my_first_lora_v1: 36%|###6 | 1084/3000 [13:26<44:06, 1.38s/it, lr: 1.0e-04 loss: 6.794e-01] my_first_lora_v1: 36%|###6 | 1085/3000 [13:27<44:03, 1.38s/it, lr: 1.0e-04 loss: 2.768e-01] my_first_lora_v1: 36%|###6 | 1085/3000 [13:27<44:03, 1.38s/it, lr: 1.0e-04 loss: 2.768e-01] my_first_lora_v1: 36%|###6 | 1086/3000 [13:28<43:59, 1.38s/it, lr: 1.0e-04 loss: 1.249e-01] my_first_lora_v1: 36%|###6 | 1086/3000 [13:28<43:59, 1.38s/it, lr: 1.0e-04 loss: 1.249e-01] my_first_lora_v1: 36%|###6 | 1087/3000 [13:29<43:56, 1.38s/it, lr: 1.0e-04 loss: 5.723e-01] my_first_lora_v1: 36%|###6 | 1087/3000 [13:29<43:56, 1.38s/it, lr: 1.0e-04 loss: 5.723e-01] my_first_lora_v1: 36%|###6 | 1088/3000 [13:29<43:53, 1.38s/it, lr: 1.0e-04 loss: 5.886e-01] my_first_lora_v1: 36%|###6 | 1088/3000 [13:29<43:53, 1.38s/it, lr: 1.0e-04 loss: 5.886e-01] my_first_lora_v1: 36%|###6 | 1089/3000 [13:30<43:50, 1.38s/it, lr: 1.0e-04 loss: 5.642e-01] my_first_lora_v1: 36%|###6 | 1089/3000 [13:30<43:50, 1.38s/it, lr: 1.0e-04 loss: 5.642e-01] my_first_lora_v1: 36%|###6 | 1090/3000 [13:32<43:49, 1.38s/it, lr: 1.0e-04 loss: 1.653e-01] my_first_lora_v1: 36%|###6 | 1090/3000 [13:32<43:49, 1.38s/it, lr: 1.0e-04 loss: 1.653e-01] my_first_lora_v1: 36%|###6 | 1091/3000 [13:34<43:49, 1.38s/it, lr: 1.0e-04 loss: 7.691e-01] my_first_lora_v1: 36%|###6 | 1091/3000 [13:34<43:49, 1.38s/it, lr: 1.0e-04 loss: 7.691e-01] my_first_lora_v1: 36%|###6 | 1092/3000 [13:35<43:48, 1.38s/it, lr: 1.0e-04 loss: 3.489e-02] my_first_lora_v1: 36%|###6 | 1092/3000 [13:35<43:48, 1.38s/it, lr: 1.0e-04 loss: 3.489e-02] my_first_lora_v1: 36%|###6 | 1093/3000 [13:38<43:50, 1.38s/it, lr: 1.0e-04 loss: 7.164e-01] my_first_lora_v1: 36%|###6 | 1093/3000 [13:38<43:50, 1.38s/it, lr: 1.0e-04 loss: 7.164e-01] my_first_lora_v1: 36%|###6 | 1094/3000 [13:40<43:53, 1.38s/it, lr: 1.0e-04 loss: 1.727e-01] my_first_lora_v1: 36%|###6 | 1094/3000 [13:40<43:53, 1.38s/it, lr: 1.0e-04 loss: 1.727e-01] my_first_lora_v1: 36%|###6 | 1095/3000 [13:43<43:55, 1.38s/it, lr: 1.0e-04 loss: 7.057e-01] my_first_lora_v1: 36%|###6 | 1095/3000 [13:43<43:55, 1.38s/it, lr: 1.0e-04 loss: 7.057e-01] my_first_lora_v1: 37%|###6 | 1096/3000 [13:43<43:52, 1.38s/it, lr: 1.0e-04 loss: 1.368e-01] my_first_lora_v1: 37%|###6 | 1096/3000 [13:43<43:52, 1.38s/it, lr: 1.0e-04 loss: 1.368e-01] my_first_lora_v1: 37%|###6 | 1097/3000 [13:44<43:49, 1.38s/it, lr: 1.0e-04 loss: 1.730e-01] my_first_lora_v1: 37%|###6 | 1097/3000 [13:44<43:49, 1.38s/it, lr: 1.0e-04 loss: 1.730e-01] my_first_lora_v1: 37%|###6 | 1098/3000 [13:45<43:45, 1.38s/it, lr: 1.0e-04 loss: 3.743e-01] my_first_lora_v1: 37%|###6 | 1098/3000 [13:45<43:45, 1.38s/it, lr: 1.0e-04 loss: 3.743e-01] my_first_lora_v1: 37%|###6 | 1099/3000 [13:46<43:42, 1.38s/it, lr: 1.0e-04 loss: 4.777e-01] my_first_lora_v1: 37%|###6 | 1099/3000 [13:46<43:42, 1.38s/it, lr: 1.0e-04 loss: 4.777e-01] my_first_lora_v1: 37%|###6 | 1100/3000 [13:47<43:39, 1.38s/it, lr: 1.0e-04 loss: 2.063e-01] my_first_lora_v1: 37%|###6 | 1100/3000 [13:47<43:39, 1.38s/it, lr: 1.0e-04 loss: 2.063e-01] my_first_lora_v1: 37%|###6 | 1101/3000 [13:47<43:36, 1.38s/it, lr: 1.0e-04 loss: 4.325e-01] my_first_lora_v1: 37%|###6 | 1101/3000 [13:47<43:36, 1.38s/it, lr: 1.0e-04 loss: 4.325e-01] my_first_lora_v1: 37%|###6 | 1102/3000 [13:48<43:33, 1.38s/it, lr: 1.0e-04 loss: 7.364e-01] my_first_lora_v1: 37%|###6 | 1102/3000 [13:48<43:33, 1.38s/it, lr: 1.0e-04 loss: 7.364e-01] my_first_lora_v1: 37%|###6 | 1103/3000 [13:50<43:32, 1.38s/it, lr: 1.0e-04 loss: 3.995e-02] my_first_lora_v1: 37%|###6 | 1103/3000 [13:50<43:32, 1.38s/it, lr: 1.0e-04 loss: 3.995e-02] my_first_lora_v1: 37%|###6 | 1104/3000 [13:51<43:31, 1.38s/it, lr: 1.0e-04 loss: 2.744e-01] my_first_lora_v1: 37%|###6 | 1104/3000 [13:51<43:31, 1.38s/it, lr: 1.0e-04 loss: 2.744e-01] my_first_lora_v1: 37%|###6 | 1105/3000 [13:52<43:29, 1.38s/it, lr: 1.0e-04 loss: 4.526e-01] my_first_lora_v1: 37%|###6 | 1105/3000 [13:52<43:29, 1.38s/it, lr: 1.0e-04 loss: 4.526e-01] my_first_lora_v1: 37%|###6 | 1106/3000 [13:53<43:25, 1.38s/it, lr: 1.0e-04 loss: 6.501e-01] my_first_lora_v1: 37%|###6 | 1106/3000 [13:53<43:25, 1.38s/it, lr: 1.0e-04 loss: 6.501e-01] my_first_lora_v1: 37%|###6 | 1107/3000 [13:55<43:24, 1.38s/it, lr: 1.0e-04 loss: 4.412e-01] my_first_lora_v1: 37%|###6 | 1107/3000 [13:55<43:24, 1.38s/it, lr: 1.0e-04 loss: 4.412e-01] my_first_lora_v1: 37%|###6 | 1108/3000 [13:57<43:24, 1.38s/it, lr: 1.0e-04 loss: 3.849e-01] my_first_lora_v1: 37%|###6 | 1108/3000 [13:57<43:24, 1.38s/it, lr: 1.0e-04 loss: 3.849e-01] my_first_lora_v1: 37%|###6 | 1109/3000 [13:58<43:23, 1.38s/it, lr: 1.0e-04 loss: 6.944e-01] my_first_lora_v1: 37%|###6 | 1109/3000 [13:58<43:23, 1.38s/it, lr: 1.0e-04 loss: 6.944e-01] my_first_lora_v1: 37%|###7 | 1110/3000 [14:01<43:26, 1.38s/it, lr: 1.0e-04 loss: 6.844e-01] my_first_lora_v1: 37%|###7 | 1110/3000 [14:01<43:26, 1.38s/it, lr: 1.0e-04 loss: 6.844e-01] my_first_lora_v1: 37%|###7 | 1111/3000 [14:02<43:25, 1.38s/it, lr: 1.0e-04 loss: 4.928e-02] my_first_lora_v1: 37%|###7 | 1111/3000 [14:02<43:25, 1.38s/it, lr: 1.0e-04 loss: 4.928e-02] my_first_lora_v1: 37%|###7 | 1112/3000 [14:03<43:23, 1.38s/it, lr: 1.0e-04 loss: 2.821e-01] my_first_lora_v1: 37%|###7 | 1112/3000 [14:03<43:23, 1.38s/it, lr: 1.0e-04 loss: 2.821e-01] my_first_lora_v1: 37%|###7 | 1113/3000 [14:05<43:22, 1.38s/it, lr: 1.0e-04 loss: 1.244e-01] my_first_lora_v1: 37%|###7 | 1113/3000 [14:05<43:22, 1.38s/it, lr: 1.0e-04 loss: 1.244e-01] my_first_lora_v1: 37%|###7 | 1114/3000 [14:06<43:19, 1.38s/it, lr: 1.0e-04 loss: 6.100e-01] my_first_lora_v1: 37%|###7 | 1114/3000 [14:06<43:19, 1.38s/it, lr: 1.0e-04 loss: 6.100e-01] my_first_lora_v1: 37%|###7 | 1115/3000 [14:06<43:15, 1.38s/it, lr: 1.0e-04 loss: 4.644e-01] my_first_lora_v1: 37%|###7 | 1115/3000 [14:06<43:15, 1.38s/it, lr: 1.0e-04 loss: 4.644e-01] my_first_lora_v1: 37%|###7 | 1116/3000 [14:07<43:12, 1.38s/it, lr: 1.0e-04 loss: 5.306e-01] my_first_lora_v1: 37%|###7 | 1116/3000 [14:07<43:12, 1.38s/it, lr: 1.0e-04 loss: 5.306e-01] my_first_lora_v1: 37%|###7 | 1117/3000 [14:08<43:09, 1.38s/it, lr: 1.0e-04 loss: 5.285e-01] my_first_lora_v1: 37%|###7 | 1117/3000 [14:08<43:09, 1.38s/it, lr: 1.0e-04 loss: 5.285e-01] my_first_lora_v1: 37%|###7 | 1118/3000 [14:09<43:06, 1.37s/it, lr: 1.0e-04 loss: 1.487e-01] my_first_lora_v1: 37%|###7 | 1118/3000 [14:09<43:06, 1.37s/it, lr: 1.0e-04 loss: 1.487e-01] my_first_lora_v1: 37%|###7 | 1119/3000 [14:10<43:05, 1.37s/it, lr: 1.0e-04 loss: 2.441e-01] my_first_lora_v1: 37%|###7 | 1119/3000 [14:10<43:05, 1.37s/it, lr: 1.0e-04 loss: 2.441e-01] my_first_lora_v1: 37%|###7 | 1120/3000 [14:13<43:07, 1.38s/it, lr: 1.0e-04 loss: 7.113e-01] my_first_lora_v1: 37%|###7 | 1120/3000 [14:13<43:07, 1.38s/it, lr: 1.0e-04 loss: 7.113e-01] my_first_lora_v1: 37%|###7 | 1121/3000 [14:14<43:05, 1.38s/it, lr: 1.0e-04 loss: 3.057e-01] my_first_lora_v1: 37%|###7 | 1121/3000 [14:14<43:05, 1.38s/it, lr: 1.0e-04 loss: 3.057e-01] my_first_lora_v1: 37%|###7 | 1122/3000 [14:16<43:04, 1.38s/it, lr: 1.0e-04 loss: 2.588e-01] my_first_lora_v1: 37%|###7 | 1122/3000 [14:16<43:04, 1.38s/it, lr: 1.0e-04 loss: 2.588e-01] my_first_lora_v1: 37%|###7 | 1123/3000 [14:19<43:08, 1.38s/it, lr: 1.0e-04 loss: 5.854e-01] my_first_lora_v1: 37%|###7 | 1123/3000 [14:19<43:08, 1.38s/it, lr: 1.0e-04 loss: 5.854e-01] my_first_lora_v1: 37%|###7 | 1124/3000 [14:20<43:06, 1.38s/it, lr: 1.0e-04 loss: 4.792e-01] my_first_lora_v1: 37%|###7 | 1124/3000 [14:20<43:06, 1.38s/it, lr: 1.0e-04 loss: 4.792e-01] my_first_lora_v1: 38%|###7 | 1125/3000 [14:21<43:05, 1.38s/it, lr: 1.0e-04 loss: 4.865e-01] my_first_lora_v1: 38%|###7 | 1125/3000 [14:21<43:05, 1.38s/it, lr: 1.0e-04 loss: 4.865e-01] my_first_lora_v1: 38%|###7 | 1126/3000 [14:22<43:02, 1.38s/it, lr: 1.0e-04 loss: 8.646e-02] my_first_lora_v1: 38%|###7 | 1126/3000 [14:22<43:02, 1.38s/it, lr: 1.0e-04 loss: 8.646e-02] my_first_lora_v1: 38%|###7 | 1127/3000 [14:24<43:01, 1.38s/it, lr: 1.0e-04 loss: 5.088e-01] my_first_lora_v1: 38%|###7 | 1127/3000 [14:24<43:01, 1.38s/it, lr: 1.0e-04 loss: 5.088e-01] my_first_lora_v1: 38%|###7 | 1128/3000 [14:24<42:58, 1.38s/it, lr: 1.0e-04 loss: 4.467e-01] my_first_lora_v1: 38%|###7 | 1128/3000 [14:24<42:58, 1.38s/it, lr: 1.0e-04 loss: 4.467e-01] my_first_lora_v1: 38%|###7 | 1129/3000 [14:25<42:54, 1.38s/it, lr: 1.0e-04 loss: 6.790e-01] my_first_lora_v1: 38%|###7 | 1129/3000 [14:25<42:54, 1.38s/it, lr: 1.0e-04 loss: 6.790e-01] my_first_lora_v1: 38%|###7 | 1130/3000 [14:26<42:52, 1.38s/it, lr: 1.0e-04 loss: 7.327e-01] my_first_lora_v1: 38%|###7 | 1130/3000 [14:26<42:52, 1.38s/it, lr: 1.0e-04 loss: 7.327e-01] my_first_lora_v1: 38%|###7 | 1131/3000 [14:28<42:52, 1.38s/it, lr: 1.0e-04 loss: 4.748e-01] my_first_lora_v1: 38%|###7 | 1131/3000 [14:28<42:52, 1.38s/it, lr: 1.0e-04 loss: 4.748e-01] my_first_lora_v1: 38%|###7 | 1132/3000 [14:29<42:49, 1.38s/it, lr: 1.0e-04 loss: 6.413e-01] my_first_lora_v1: 38%|###7 | 1132/3000 [14:29<42:49, 1.38s/it, lr: 1.0e-04 loss: 6.413e-01] my_first_lora_v1: 38%|###7 | 1133/3000 [14:30<42:47, 1.38s/it, lr: 1.0e-04 loss: 5.106e-01] my_first_lora_v1: 38%|###7 | 1133/3000 [14:30<42:47, 1.38s/it, lr: 1.0e-04 loss: 5.106e-01] my_first_lora_v1: 38%|###7 | 1134/3000 [14:32<42:46, 1.38s/it, lr: 1.0e-04 loss: 4.816e-01] my_first_lora_v1: 38%|###7 | 1134/3000 [14:32<42:46, 1.38s/it, lr: 1.0e-04 loss: 4.816e-01] my_first_lora_v1: 38%|###7 | 1135/3000 [14:33<42:44, 1.38s/it, lr: 1.0e-04 loss: 7.296e-01] my_first_lora_v1: 38%|###7 | 1135/3000 [14:33<42:44, 1.38s/it, lr: 1.0e-04 loss: 7.296e-01] my_first_lora_v1: 38%|###7 | 1136/3000 [14:34<42:41, 1.37s/it, lr: 1.0e-04 loss: 4.335e-01] my_first_lora_v1: 38%|###7 | 1136/3000 [14:34<42:41, 1.37s/it, lr: 1.0e-04 loss: 4.335e-01] my_first_lora_v1: 38%|###7 | 1137/3000 [14:35<42:40, 1.37s/it, lr: 1.0e-04 loss: 5.200e-01] my_first_lora_v1: 38%|###7 | 1137/3000 [14:35<42:40, 1.37s/it, lr: 1.0e-04 loss: 5.200e-01] my_first_lora_v1: 38%|###7 | 1138/3000 [14:36<42:39, 1.37s/it, lr: 1.0e-04 loss: 5.628e-01] my_first_lora_v1: 38%|###7 | 1138/3000 [14:36<42:39, 1.37s/it, lr: 1.0e-04 loss: 5.628e-01] my_first_lora_v1: 38%|###7 | 1139/3000 [14:38<42:38, 1.37s/it, lr: 1.0e-04 loss: 7.181e-01] my_first_lora_v1: 38%|###7 | 1139/3000 [14:38<42:38, 1.37s/it, lr: 1.0e-04 loss: 7.181e-01] my_first_lora_v1: 38%|###8 | 1140/3000 [14:40<42:39, 1.38s/it, lr: 1.0e-04 loss: 5.369e-01] my_first_lora_v1: 38%|###8 | 1140/3000 [14:40<42:39, 1.38s/it, lr: 1.0e-04 loss: 5.369e-01] my_first_lora_v1: 38%|###8 | 1141/3000 [14:43<42:41, 1.38s/it, lr: 1.0e-04 loss: 2.166e-01] my_first_lora_v1: 38%|###8 | 1141/3000 [14:43<42:41, 1.38s/it, lr: 1.0e-04 loss: 2.166e-01] my_first_lora_v1: 38%|###8 | 1142/3000 [14:44<42:40, 1.38s/it, lr: 1.0e-04 loss: 2.046e-01] my_first_lora_v1: 38%|###8 | 1142/3000 [14:44<42:40, 1.38s/it, lr: 1.0e-04 loss: 2.046e-01] my_first_lora_v1: 38%|###8 | 1143/3000 [14:46<42:39, 1.38s/it, lr: 1.0e-04 loss: 2.152e-01] my_first_lora_v1: 38%|###8 | 1143/3000 [14:46<42:39, 1.38s/it, lr: 1.0e-04 loss: 2.152e-01] my_first_lora_v1: 38%|###8 | 1144/3000 [14:47<42:36, 1.38s/it, lr: 1.0e-04 loss: 2.808e-01] my_first_lora_v1: 38%|###8 | 1144/3000 [14:47<42:36, 1.38s/it, lr: 1.0e-04 loss: 2.808e-01] my_first_lora_v1: 38%|###8 | 1145/3000 [14:47<42:33, 1.38s/it, lr: 1.0e-04 loss: 5.414e-01] my_first_lora_v1: 38%|###8 | 1145/3000 [14:47<42:33, 1.38s/it, lr: 1.0e-04 loss: 5.414e-01] my_first_lora_v1: 38%|###8 | 1146/3000 [14:48<42:30, 1.38s/it, lr: 1.0e-04 loss: 2.386e-01] my_first_lora_v1: 38%|###8 | 1146/3000 [14:48<42:30, 1.38s/it, lr: 1.0e-04 loss: 2.386e-01] my_first_lora_v1: 38%|###8 | 1147/3000 [14:49<42:27, 1.37s/it, lr: 1.0e-04 loss: 5.682e-01] my_first_lora_v1: 38%|###8 | 1147/3000 [14:49<42:27, 1.37s/it, lr: 1.0e-04 loss: 5.682e-01] my_first_lora_v1: 38%|###8 | 1148/3000 [14:50<42:24, 1.37s/it, lr: 1.0e-04 loss: 7.420e-01] my_first_lora_v1: 38%|###8 | 1148/3000 [14:50<42:24, 1.37s/it, lr: 1.0e-04 loss: 7.420e-01] my_first_lora_v1: 38%|###8 | 1149/3000 [14:51<42:23, 1.37s/it, lr: 1.0e-04 loss: 7.811e-01] my_first_lora_v1: 38%|###8 | 1149/3000 [14:51<42:23, 1.37s/it, lr: 1.0e-04 loss: 7.811e-01] my_first_lora_v1: 38%|###8 | 1150/3000 [14:52<42:20, 1.37s/it, lr: 1.0e-04 loss: 2.606e-01] my_first_lora_v1: 38%|###8 | 1150/3000 [14:52<42:20, 1.37s/it, lr: 1.0e-04 loss: 2.606e-01] my_first_lora_v1: 38%|###8 | 1151/3000 [14:53<42:18, 1.37s/it, lr: 1.0e-04 loss: 5.638e-01] my_first_lora_v1: 38%|###8 | 1151/3000 [14:53<42:18, 1.37s/it, lr: 1.0e-04 loss: 5.638e-01] my_first_lora_v1: 38%|###8 | 1152/3000 [14:54<42:15, 1.37s/it, lr: 1.0e-04 loss: 6.752e-01] my_first_lora_v1: 38%|###8 | 1152/3000 [14:54<42:15, 1.37s/it, lr: 1.0e-04 loss: 6.752e-01] my_first_lora_v1: 38%|###8 | 1153/3000 [14:56<42:17, 1.37s/it, lr: 1.0e-04 loss: 7.152e-01] my_first_lora_v1: 38%|###8 | 1153/3000 [14:56<42:17, 1.37s/it, lr: 1.0e-04 loss: 7.152e-01] my_first_lora_v1: 38%|###8 | 1154/3000 [14:57<42:14, 1.37s/it, lr: 1.0e-04 loss: 4.694e-01] my_first_lora_v1: 38%|###8 | 1154/3000 [14:57<42:14, 1.37s/it, lr: 1.0e-04 loss: 4.694e-01] my_first_lora_v1: 38%|###8 | 1155/3000 [14:58<42:11, 1.37s/it, lr: 1.0e-04 loss: 2.927e-01] my_first_lora_v1: 38%|###8 | 1155/3000 [14:58<42:11, 1.37s/it, lr: 1.0e-04 loss: 2.927e-01] my_first_lora_v1: 39%|###8 | 1156/3000 [14:59<42:08, 1.37s/it, lr: 1.0e-04 loss: 8.123e-01] my_first_lora_v1: 39%|###8 | 1156/3000 [14:59<42:08, 1.37s/it, lr: 1.0e-04 loss: 8.123e-01] my_first_lora_v1: 39%|###8 | 1157/3000 [15:01<42:07, 1.37s/it, lr: 1.0e-04 loss: 8.373e-01] my_first_lora_v1: 39%|###8 | 1157/3000 [15:01<42:07, 1.37s/it, lr: 1.0e-04 loss: 8.373e-01] my_first_lora_v1: 39%|###8 | 1158/3000 [15:02<42:05, 1.37s/it, lr: 1.0e-04 loss: 1.446e-01] my_first_lora_v1: 39%|###8 | 1158/3000 [15:02<42:05, 1.37s/it, lr: 1.0e-04 loss: 1.446e-01] my_first_lora_v1: 39%|###8 | 1159/3000 [15:04<42:05, 1.37s/it, lr: 1.0e-04 loss: 7.285e-01] my_first_lora_v1: 39%|###8 | 1159/3000 [15:04<42:05, 1.37s/it, lr: 1.0e-04 loss: 7.285e-01] my_first_lora_v1: 39%|###8 | 1160/3000 [15:05<42:04, 1.37s/it, lr: 1.0e-04 loss: 9.380e-01] my_first_lora_v1: 39%|###8 | 1160/3000 [15:05<42:04, 1.37s/it, lr: 1.0e-04 loss: 9.380e-01] my_first_lora_v1: 39%|###8 | 1161/3000 [15:06<42:01, 1.37s/it, lr: 1.0e-04 loss: 7.447e-01] my_first_lora_v1: 39%|###8 | 1161/3000 [15:06<42:01, 1.37s/it, lr: 1.0e-04 loss: 7.447e-01] my_first_lora_v1: 39%|###8 | 1162/3000 [15:07<42:00, 1.37s/it, lr: 1.0e-04 loss: 4.619e-02] my_first_lora_v1: 39%|###8 | 1162/3000 [15:07<42:00, 1.37s/it, lr: 1.0e-04 loss: 4.619e-02] my_first_lora_v1: 39%|###8 | 1163/3000 [15:08<41:57, 1.37s/it, lr: 1.0e-04 loss: 4.555e-01] my_first_lora_v1: 39%|###8 | 1163/3000 [15:08<41:57, 1.37s/it, lr: 1.0e-04 loss: 4.555e-01] my_first_lora_v1: 39%|###8 | 1164/3000 [15:11<42:00, 1.37s/it, lr: 1.0e-04 loss: 5.940e-01] my_first_lora_v1: 39%|###8 | 1164/3000 [15:11<42:00, 1.37s/it, lr: 1.0e-04 loss: 5.940e-01] my_first_lora_v1: 39%|###8 | 1165/3000 [15:12<41:57, 1.37s/it, lr: 1.0e-04 loss: 3.840e-01] my_first_lora_v1: 39%|###8 | 1165/3000 [15:12<41:57, 1.37s/it, lr: 1.0e-04 loss: 3.840e-01] my_first_lora_v1: 39%|###8 | 1166/3000 [15:13<41:54, 1.37s/it, lr: 1.0e-04 loss: 6.224e-01] my_first_lora_v1: 39%|###8 | 1166/3000 [15:13<41:54, 1.37s/it, lr: 1.0e-04 loss: 6.224e-01] my_first_lora_v1: 39%|###8 | 1167/3000 [15:14<41:53, 1.37s/it, lr: 1.0e-04 loss: 7.851e-01] my_first_lora_v1: 39%|###8 | 1167/3000 [15:14<41:53, 1.37s/it, lr: 1.0e-04 loss: 7.851e-01] my_first_lora_v1: 39%|###8 | 1168/3000 [15:15<41:50, 1.37s/it, lr: 1.0e-04 loss: 5.509e-01] my_first_lora_v1: 39%|###8 | 1168/3000 [15:15<41:50, 1.37s/it, lr: 1.0e-04 loss: 5.509e-01] my_first_lora_v1: 39%|###8 | 1169/3000 [15:17<41:49, 1.37s/it, lr: 1.0e-04 loss: 2.413e-01] my_first_lora_v1: 39%|###8 | 1169/3000 [15:17<41:49, 1.37s/it, lr: 1.0e-04 loss: 2.413e-01] my_first_lora_v1: 39%|###9 | 1170/3000 [15:17<41:46, 1.37s/it, lr: 1.0e-04 loss: 8.638e-01] my_first_lora_v1: 39%|###9 | 1170/3000 [15:17<41:46, 1.37s/it, lr: 1.0e-04 loss: 8.638e-01] my_first_lora_v1: 39%|###9 | 1171/3000 [15:19<41:45, 1.37s/it, lr: 1.0e-04 loss: 3.489e-01] my_first_lora_v1: 39%|###9 | 1171/3000 [15:19<41:45, 1.37s/it, lr: 1.0e-04 loss: 3.489e-01] my_first_lora_v1: 39%|###9 | 1172/3000 [15:19<41:42, 1.37s/it, lr: 1.0e-04 loss: 4.231e-01] my_first_lora_v1: 39%|###9 | 1172/3000 [15:19<41:42, 1.37s/it, lr: 1.0e-04 loss: 4.231e-01] my_first_lora_v1: 39%|###9 | 1173/3000 [15:20<41:39, 1.37s/it, lr: 1.0e-04 loss: 4.254e-01] my_first_lora_v1: 39%|###9 | 1173/3000 [15:20<41:39, 1.37s/it, lr: 1.0e-04 loss: 4.254e-01] my_first_lora_v1: 39%|###9 | 1174/3000 [15:22<41:38, 1.37s/it, lr: 1.0e-04 loss: 7.445e-01] my_first_lora_v1: 39%|###9 | 1174/3000 [15:22<41:38, 1.37s/it, lr: 1.0e-04 loss: 7.445e-01] my_first_lora_v1: 39%|###9 | 1175/3000 [15:25<41:41, 1.37s/it, lr: 1.0e-04 loss: 4.640e-01] my_first_lora_v1: 39%|###9 | 1175/3000 [15:25<41:41, 1.37s/it, lr: 1.0e-04 loss: 4.640e-01] my_first_lora_v1: 39%|###9 | 1176/3000 [15:26<41:39, 1.37s/it, lr: 1.0e-04 loss: 2.098e-01] my_first_lora_v1: 39%|###9 | 1176/3000 [15:26<41:39, 1.37s/it, lr: 1.0e-04 loss: 2.098e-01] my_first_lora_v1: 39%|###9 | 1177/3000 [15:27<41:37, 1.37s/it, lr: 1.0e-04 loss: 4.960e-01] my_first_lora_v1: 39%|###9 | 1177/3000 [15:27<41:37, 1.37s/it, lr: 1.0e-04 loss: 4.960e-01] my_first_lora_v1: 39%|###9 | 1178/3000 [15:28<41:36, 1.37s/it, lr: 1.0e-04 loss: 2.339e-01] my_first_lora_v1: 39%|###9 | 1178/3000 [15:28<41:36, 1.37s/it, lr: 1.0e-04 loss: 2.339e-01] my_first_lora_v1: 39%|###9 | 1179/3000 [15:29<41:33, 1.37s/it, lr: 1.0e-04 loss: 3.877e-01] my_first_lora_v1: 39%|###9 | 1179/3000 [15:29<41:33, 1.37s/it, lr: 1.0e-04 loss: 3.877e-01] my_first_lora_v1: 39%|###9 | 1180/3000 [15:30<41:30, 1.37s/it, lr: 1.0e-04 loss: 7.127e-01] my_first_lora_v1: 39%|###9 | 1180/3000 [15:30<41:30, 1.37s/it, lr: 1.0e-04 loss: 7.127e-01] my_first_lora_v1: 39%|###9 | 1181/3000 [15:31<41:28, 1.37s/it, lr: 1.0e-04 loss: 7.669e-01] my_first_lora_v1: 39%|###9 | 1181/3000 [15:31<41:28, 1.37s/it, lr: 1.0e-04 loss: 7.669e-01] my_first_lora_v1: 39%|###9 | 1182/3000 [15:33<41:27, 1.37s/it, lr: 1.0e-04 loss: 5.629e-01] my_first_lora_v1: 39%|###9 | 1182/3000 [15:33<41:27, 1.37s/it, lr: 1.0e-04 loss: 5.629e-01] my_first_lora_v1: 39%|###9 | 1183/3000 [15:33<41:24, 1.37s/it, lr: 1.0e-04 loss: 1.420e-01] my_first_lora_v1: 39%|###9 | 1183/3000 [15:33<41:24, 1.37s/it, lr: 1.0e-04 loss: 1.420e-01] my_first_lora_v1: 39%|###9 | 1184/3000 [15:34<41:22, 1.37s/it, lr: 1.0e-04 loss: 1.374e-01] my_first_lora_v1: 39%|###9 | 1184/3000 [15:34<41:22, 1.37s/it, lr: 1.0e-04 loss: 1.374e-01] my_first_lora_v1: 40%|###9 | 1185/3000 [15:35<41:19, 1.37s/it, lr: 1.0e-04 loss: 1.541e-01] my_first_lora_v1: 40%|###9 | 1185/3000 [15:35<41:19, 1.37s/it, lr: 1.0e-04 loss: 1.541e-01] my_first_lora_v1: 40%|###9 | 1186/3000 [15:37<41:19, 1.37s/it, lr: 1.0e-04 loss: 3.175e-01] my_first_lora_v1: 40%|###9 | 1186/3000 [15:37<41:19, 1.37s/it, lr: 1.0e-04 loss: 3.175e-01] my_first_lora_v1: 40%|###9 | 1187/3000 [15:38<41:17, 1.37s/it, lr: 1.0e-04 loss: 3.921e-01] my_first_lora_v1: 40%|###9 | 1187/3000 [15:38<41:17, 1.37s/it, lr: 1.0e-04 loss: 3.921e-01] my_first_lora_v1: 40%|###9 | 1188/3000 [15:39<41:14, 1.37s/it, lr: 1.0e-04 loss: 5.688e-01] my_first_lora_v1: 40%|###9 | 1188/3000 [15:39<41:14, 1.37s/it, lr: 1.0e-04 loss: 5.688e-01] my_first_lora_v1: 40%|###9 | 1189/3000 [15:41<41:13, 1.37s/it, lr: 1.0e-04 loss: 7.364e-01] my_first_lora_v1: 40%|###9 | 1189/3000 [15:41<41:13, 1.37s/it, lr: 1.0e-04 loss: 7.364e-01] my_first_lora_v1: 40%|###9 | 1190/3000 [15:43<41:15, 1.37s/it, lr: 1.0e-04 loss: 2.812e-01] my_first_lora_v1: 40%|###9 | 1190/3000 [15:43<41:15, 1.37s/it, lr: 1.0e-04 loss: 2.812e-01] my_first_lora_v1: 40%|###9 | 1191/3000 [15:44<41:13, 1.37s/it, lr: 1.0e-04 loss: 3.454e-01] my_first_lora_v1: 40%|###9 | 1191/3000 [15:44<41:13, 1.37s/it, lr: 1.0e-04 loss: 3.454e-01] my_first_lora_v1: 40%|###9 | 1192/3000 [15:45<41:10, 1.37s/it, lr: 1.0e-04 loss: 1.960e-01] my_first_lora_v1: 40%|###9 | 1192/3000 [15:45<41:10, 1.37s/it, lr: 1.0e-04 loss: 1.960e-01] my_first_lora_v1: 40%|###9 | 1193/3000 [15:47<41:09, 1.37s/it, lr: 1.0e-04 loss: 5.765e-01] my_first_lora_v1: 40%|###9 | 1193/3000 [15:47<41:09, 1.37s/it, lr: 1.0e-04 loss: 5.765e-01] my_first_lora_v1: 40%|###9 | 1194/3000 [15:47<41:06, 1.37s/it, lr: 1.0e-04 loss: 4.991e-01] my_first_lora_v1: 40%|###9 | 1194/3000 [15:47<41:06, 1.37s/it, lr: 1.0e-04 loss: 4.991e-01] my_first_lora_v1: 40%|###9 | 1195/3000 [15:50<41:07, 1.37s/it, lr: 1.0e-04 loss: 0.000e+00] my_first_lora_v1: 40%|###9 | 1195/3000 [15:50<41:07, 1.37s/it, lr: 1.0e-04 loss: 0.000e+00] my_first_lora_v1: 40%|###9 | 1196/3000 [15:51<41:07, 1.37s/it, lr: 1.0e-04 loss: 2.710e-01] my_first_lora_v1: 40%|###9 | 1196/3000 [15:51<41:07, 1.37s/it, lr: 1.0e-04 loss: 2.710e-01] my_first_lora_v1: 40%|###9 | 1197/3000 [15:53<41:06, 1.37s/it, lr: 1.0e-04 loss: 1.609e-01] my_first_lora_v1: 40%|###9 | 1197/3000 [15:53<41:06, 1.37s/it, lr: 1.0e-04 loss: 1.609e-01] my_first_lora_v1: 40%|###9 | 1198/3000 [15:55<41:07, 1.37s/it, lr: 1.0e-04 loss: 3.839e-01] my_first_lora_v1: 40%|###9 | 1198/3000 [15:55<41:07, 1.37s/it, lr: 1.0e-04 loss: 3.839e-01] my_first_lora_v1: 40%|###9 | 1199/3000 [15:58<41:09, 1.37s/it, lr: 1.0e-04 loss: 6.675e-01] my_first_lora_v1: 40%|###9 | 1199/3000 [15:58<41:09, 1.37s/it, lr: 1.0e-04 loss: 6.675e-01] my_first_lora_v1: 40%|#### | 1200/3000 [15:59<41:06, 1.37s/it, lr: 1.0e-04 loss: 4.353e-01] my_first_lora_v1: 40%|#### | 1200/3000 [15:59<41:06, 1.37s/it, lr: 1.0e-04 loss: 4.353e-01] my_first_lora_v1: 40%|#### | 1201/3000 [16:00<41:04, 1.37s/it, lr: 1.0e-04 loss: 6.206e-01] my_first_lora_v1: 40%|#### | 1201/3000 [16:00<41:04, 1.37s/it, lr: 1.0e-04 loss: 6.206e-01] my_first_lora_v1: 40%|#### | 1202/3000 [16:01<41:03, 1.37s/it, lr: 1.0e-04 loss: 1.812e-01] my_first_lora_v1: 40%|#### | 1202/3000 [16:01<41:03, 1.37s/it, lr: 1.0e-04 loss: 1.812e-01] my_first_lora_v1: 40%|#### | 1203/3000 [16:03<41:02, 1.37s/it, lr: 1.0e-04 loss: 2.006e-02] my_first_lora_v1: 40%|#### | 1203/3000 [16:03<41:02, 1.37s/it, lr: 1.0e-04 loss: 2.006e-02] my_first_lora_v1: 40%|#### | 1204/3000 [16:04<40:59, 1.37s/it, lr: 1.0e-04 loss: 3.094e-01] my_first_lora_v1: 40%|#### | 1204/3000 [16:04<40:59, 1.37s/it, lr: 1.0e-04 loss: 3.094e-01] my_first_lora_v1: 40%|#### | 1205/3000 [16:06<41:01, 1.37s/it, lr: 1.0e-04 loss: 8.399e-01] my_first_lora_v1: 40%|#### | 1205/3000 [16:06<41:01, 1.37s/it, lr: 1.0e-04 loss: 8.399e-01] my_first_lora_v1: 40%|#### | 1206/3000 [16:08<41:00, 1.37s/it, lr: 1.0e-04 loss: 1.208e-01] my_first_lora_v1: 40%|#### | 1206/3000 [16:08<41:00, 1.37s/it, lr: 1.0e-04 loss: 1.208e-01] my_first_lora_v1: 40%|#### | 1207/3000 [16:09<40:59, 1.37s/it, lr: 1.0e-04 loss: 4.830e-01] my_first_lora_v1: 40%|#### | 1207/3000 [16:09<40:59, 1.37s/it, lr: 1.0e-04 loss: 4.830e-01] my_first_lora_v1: 40%|#### | 1208/3000 [16:12<41:01, 1.37s/it, lr: 1.0e-04 loss: 5.515e-01] my_first_lora_v1: 40%|#### | 1208/3000 [16:12<41:01, 1.37s/it, lr: 1.0e-04 loss: 5.515e-01] my_first_lora_v1: 40%|#### | 1209/3000 [16:13<40:58, 1.37s/it, lr: 1.0e-04 loss: 1.590e-01] my_first_lora_v1: 40%|#### | 1209/3000 [16:13<40:58, 1.37s/it, lr: 1.0e-04 loss: 1.590e-01] my_first_lora_v1: 40%|#### | 1210/3000 [16:14<40:55, 1.37s/it, lr: 1.0e-04 loss: 5.743e-01] my_first_lora_v1: 40%|#### | 1210/3000 [16:14<40:55, 1.37s/it, lr: 1.0e-04 loss: 5.743e-01] my_first_lora_v1: 40%|#### | 1211/3000 [16:14<40:52, 1.37s/it, lr: 1.0e-04 loss: 7.515e-01] my_first_lora_v1: 40%|#### | 1211/3000 [16:14<40:52, 1.37s/it, lr: 1.0e-04 loss: 7.515e-01] my_first_lora_v1: 40%|#### | 1212/3000 [16:16<40:52, 1.37s/it, lr: 1.0e-04 loss: 7.097e-01] my_first_lora_v1: 40%|#### | 1212/3000 [16:16<40:52, 1.37s/it, lr: 1.0e-04 loss: 7.097e-01] my_first_lora_v1: 40%|#### | 1213/3000 [16:18<40:51, 1.37s/it, lr: 1.0e-04 loss: 4.800e-01] my_first_lora_v1: 40%|#### | 1213/3000 [16:18<40:51, 1.37s/it, lr: 1.0e-04 loss: 4.800e-01] my_first_lora_v1: 40%|#### | 1214/3000 [16:20<40:52, 1.37s/it, lr: 1.0e-04 loss: 7.453e-02] my_first_lora_v1: 40%|#### | 1214/3000 [16:20<40:52, 1.37s/it, lr: 1.0e-04 loss: 7.453e-02] my_first_lora_v1: 40%|#### | 1215/3000 [16:21<40:49, 1.37s/it, lr: 1.0e-04 loss: 6.938e-01] my_first_lora_v1: 40%|#### | 1215/3000 [16:21<40:49, 1.37s/it, lr: 1.0e-04 loss: 6.938e-01] my_first_lora_v1: 41%|#### | 1216/3000 [16:22<40:48, 1.37s/it, lr: 1.0e-04 loss: 7.584e-01] my_first_lora_v1: 41%|#### | 1216/3000 [16:22<40:48, 1.37s/it, lr: 1.0e-04 loss: 7.584e-01] my_first_lora_v1: 41%|#### | 1217/3000 [16:23<40:46, 1.37s/it, lr: 1.0e-04 loss: 4.762e-01] my_first_lora_v1: 41%|#### | 1217/3000 [16:23<40:46, 1.37s/it, lr: 1.0e-04 loss: 4.762e-01] my_first_lora_v1: 41%|#### | 1218/3000 [16:25<40:45, 1.37s/it, lr: 1.0e-04 loss: 5.336e-01] my_first_lora_v1: 41%|#### | 1218/3000 [16:25<40:45, 1.37s/it, lr: 1.0e-04 loss: 5.336e-01] my_first_lora_v1: 41%|#### | 1219/3000 [16:25<40:42, 1.37s/it, lr: 1.0e-04 loss: 2.912e-01] my_first_lora_v1: 41%|#### | 1219/3000 [16:25<40:42, 1.37s/it, lr: 1.0e-04 loss: 2.912e-01] my_first_lora_v1: 41%|#### | 1220/3000 [16:27<40:40, 1.37s/it, lr: 1.0e-04 loss: 1.818e-01] my_first_lora_v1: 41%|#### | 1220/3000 [16:27<40:40, 1.37s/it, lr: 1.0e-04 loss: 1.818e-01] my_first_lora_v1: 41%|#### | 1221/3000 [16:28<40:38, 1.37s/it, lr: 1.0e-04 loss: 7.058e-01] my_first_lora_v1: 41%|#### | 1221/3000 [16:28<40:38, 1.37s/it, lr: 1.0e-04 loss: 7.058e-01] my_first_lora_v1: 41%|#### | 1222/3000 [16:28<40:35, 1.37s/it, lr: 1.0e-04 loss: 4.646e-01] my_first_lora_v1: 41%|#### | 1222/3000 [16:28<40:35, 1.37s/it, lr: 1.0e-04 loss: 4.646e-01] my_first_lora_v1: 41%|#### | 1223/3000 [16:30<40:33, 1.37s/it, lr: 1.0e-04 loss: 6.253e-01] my_first_lora_v1: 41%|#### | 1223/3000 [16:30<40:33, 1.37s/it, lr: 1.0e-04 loss: 6.253e-01] my_first_lora_v1: 41%|#### | 1224/3000 [16:31<40:31, 1.37s/it, lr: 1.0e-04 loss: 3.690e-01] my_first_lora_v1: 41%|#### | 1224/3000 [16:31<40:31, 1.37s/it, lr: 1.0e-04 loss: 3.690e-01] my_first_lora_v1: 41%|#### | 1225/3000 [16:31<40:28, 1.37s/it, lr: 1.0e-04 loss: 2.435e-01] my_first_lora_v1: 41%|#### | 1225/3000 [16:31<40:28, 1.37s/it, lr: 1.0e-04 loss: 2.435e-01] my_first_lora_v1: 41%|#### | 1226/3000 [16:33<40:26, 1.37s/it, lr: 1.0e-04 loss: 4.573e-01] my_first_lora_v1: 41%|#### | 1226/3000 [16:33<40:26, 1.37s/it, lr: 1.0e-04 loss: 4.573e-01] my_first_lora_v1: 41%|#### | 1227/3000 [16:35<40:28, 1.37s/it, lr: 1.0e-04 loss: 1.725e-01] my_first_lora_v1: 41%|#### | 1227/3000 [16:35<40:28, 1.37s/it, lr: 1.0e-04 loss: 1.725e-01] my_first_lora_v1: 41%|#### | 1228/3000 [16:37<40:27, 1.37s/it, lr: 1.0e-04 loss: 7.221e-01] my_first_lora_v1: 41%|#### | 1228/3000 [16:37<40:27, 1.37s/it, lr: 1.0e-04 loss: 7.221e-01] my_first_lora_v1: 41%|#### | 1229/3000 [16:38<40:24, 1.37s/it, lr: 1.0e-04 loss: 3.074e-01] my_first_lora_v1: 41%|#### | 1229/3000 [16:38<40:24, 1.37s/it, lr: 1.0e-04 loss: 3.074e-01] my_first_lora_v1: 41%|####1 | 1230/3000 [16:39<40:22, 1.37s/it, lr: 1.0e-04 loss: 6.535e-01] my_first_lora_v1: 41%|####1 | 1230/3000 [16:39<40:22, 1.37s/it, lr: 1.0e-04 loss: 6.535e-01] my_first_lora_v1: 41%|####1 | 1231/3000 [16:40<40:20, 1.37s/it, lr: 1.0e-04 loss: 7.400e-01] my_first_lora_v1: 41%|####1 | 1231/3000 [16:40<40:20, 1.37s/it, lr: 1.0e-04 loss: 7.400e-01] my_first_lora_v1: 41%|####1 | 1232/3000 [16:41<40:18, 1.37s/it, lr: 1.0e-04 loss: 3.777e-01] my_first_lora_v1: 41%|####1 | 1232/3000 [16:41<40:18, 1.37s/it, lr: 1.0e-04 loss: 3.777e-01] my_first_lora_v1: 41%|####1 | 1233/3000 [16:42<40:17, 1.37s/it, lr: 1.0e-04 loss: 1.118e-01] my_first_lora_v1: 41%|####1 | 1233/3000 [16:42<40:17, 1.37s/it, lr: 1.0e-04 loss: 1.118e-01] my_first_lora_v1: 41%|####1 | 1234/3000 [16:43<40:14, 1.37s/it, lr: 1.0e-04 loss: 2.582e-01] my_first_lora_v1: 41%|####1 | 1234/3000 [16:43<40:14, 1.37s/it, lr: 1.0e-04 loss: 2.582e-01] my_first_lora_v1: 41%|####1 | 1235/3000 [16:45<40:13, 1.37s/it, lr: 1.0e-04 loss: 1.796e-01] my_first_lora_v1: 41%|####1 | 1235/3000 [16:45<40:13, 1.37s/it, lr: 1.0e-04 loss: 1.796e-01] my_first_lora_v1: 41%|####1 | 1236/3000 [16:46<40:12, 1.37s/it, lr: 1.0e-04 loss: 1.520e-01] my_first_lora_v1: 41%|####1 | 1236/3000 [16:46<40:12, 1.37s/it, lr: 1.0e-04 loss: 1.520e-01] my_first_lora_v1: 41%|####1 | 1237/3000 [16:48<40:11, 1.37s/it, lr: 1.0e-04 loss: 6.551e-01] my_first_lora_v1: 41%|####1 | 1237/3000 [16:48<40:11, 1.37s/it, lr: 1.0e-04 loss: 6.551e-01] my_first_lora_v1: 41%|####1 | 1238/3000 [16:49<40:09, 1.37s/it, lr: 1.0e-04 loss: 3.932e-01] my_first_lora_v1: 41%|####1 | 1238/3000 [16:49<40:09, 1.37s/it, lr: 1.0e-04 loss: 3.932e-01] my_first_lora_v1: 41%|####1 | 1239/3000 [16:50<40:08, 1.37s/it, lr: 1.0e-04 loss: 7.243e-01] my_first_lora_v1: 41%|####1 | 1239/3000 [16:50<40:08, 1.37s/it, lr: 1.0e-04 loss: 7.243e-01] my_first_lora_v1: 41%|####1 | 1240/3000 [16:52<40:07, 1.37s/it, lr: 1.0e-04 loss: 5.903e-01] my_first_lora_v1: 41%|####1 | 1240/3000 [16:52<40:07, 1.37s/it, lr: 1.0e-04 loss: 5.903e-01] my_first_lora_v1: 41%|####1 | 1241/3000 [16:53<40:05, 1.37s/it, lr: 1.0e-04 loss: 1.867e-01] my_first_lora_v1: 41%|####1 | 1241/3000 [16:53<40:05, 1.37s/it, lr: 1.0e-04 loss: 1.867e-01] my_first_lora_v1: 41%|####1 | 1242/3000 [16:55<40:06, 1.37s/it, lr: 1.0e-04 loss: 1.301e-01] my_first_lora_v1: 41%|####1 | 1242/3000 [16:55<40:06, 1.37s/it, lr: 1.0e-04 loss: 1.301e-01] my_first_lora_v1: 41%|####1 | 1243/3000 [16:56<40:03, 1.37s/it, lr: 1.0e-04 loss: 4.292e-01] my_first_lora_v1: 41%|####1 | 1243/3000 [16:56<40:03, 1.37s/it, lr: 1.0e-04 loss: 4.292e-01] my_first_lora_v1: 41%|####1 | 1244/3000 [16:58<40:02, 1.37s/it, lr: 1.0e-04 loss: 1.040e-01] my_first_lora_v1: 41%|####1 | 1244/3000 [16:58<40:02, 1.37s/it, lr: 1.0e-04 loss: 1.040e-01] my_first_lora_v1: 42%|####1 | 1245/3000 [16:59<40:00, 1.37s/it, lr: 1.0e-04 loss: 2.127e-01] my_first_lora_v1: 42%|####1 | 1245/3000 [16:59<40:00, 1.37s/it, lr: 1.0e-04 loss: 2.127e-01] my_first_lora_v1: 42%|####1 | 1246/3000 [16:59<39:58, 1.37s/it, lr: 1.0e-04 loss: 5.859e-02] my_first_lora_v1: 42%|####1 | 1246/3000 [16:59<39:58, 1.37s/it, lr: 1.0e-04 loss: 5.859e-02] my_first_lora_v1: 42%|####1 | 1247/3000 [17:01<39:56, 1.37s/it, lr: 1.0e-04 loss: 1.336e-01] my_first_lora_v1: 42%|####1 | 1247/3000 [17:01<39:56, 1.37s/it, lr: 1.0e-04 loss: 1.336e-01] my_first_lora_v1: 42%|####1 | 1248/3000 [17:03<39:57, 1.37s/it, lr: 1.0e-04 loss: 1.015e-01] my_first_lora_v1: 42%|####1 | 1248/3000 [17:03<39:57, 1.37s/it, lr: 1.0e-04 loss: 1.015e-01] my_first_lora_v1: 42%|####1 | 1249/3000 [17:06<39:59, 1.37s/it, lr: 1.0e-04 loss: 4.302e-01] my_first_lora_v1: 42%|####1 | 1249/3000 [17:06<39:59, 1.37s/it, lr: 1.0e-04 loss: 4.302e-01]
Saving at step 1250
Saved checkpoint to /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v1/my_first_lora_v1_000001250.safetensors
Saved optimizer to /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v1/optimizer.pt
Removing old save: /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v1/my_first_lora_v1_000000250.safetensors
Unloading assistant lora
Generating Images: 0%| | 0/5 [00:00<?, ?it/s] Generating Images: 0%| | 0/5 [00:00<?, ?it/s]
Generating Images: 20%|## | 1/5 [00:07<00:30, 7.64s/it] Generating Images: 20%|## | 1/5 [00:07<00:30, 7.64s/it]
Generating Images: 40%|#### | 2/5 [00:15<00:22, 7.61s/it] Generating Images: 40%|#### | 2/5 [00:15<00:22, 7.61s/it]
Generating Images: 60%|###### | 3/5 [00:22<00:15, 7.68s/it] Generating Images: 60%|###### | 3/5 [00:22<00:15, 7.68s/it]
Generating Images: 80%|######## | 4/5 [00:30<00:07, 7.64s/it] Generating Images: 80%|######## | 4/5 [00:30<00:07, 7.64s/it]
Generating Images: 100%|##########| 5/5 [00:38<00:00, 7.86s/it] Generating Images: 100%|##########| 5/5 [00:38<00:00, 7.86s/it]
Loading assistant lora
my_first_lora_v1: 42%|####1 | 1250/3000 [17:08<40:00, 1.37s/it, lr: 1.0e-04 loss: 5.166e-01] my_first_lora_v1: 42%|####1 | 1250/3000 [17:08<40:00, 1.37s/it, lr: 1.0e-04 loss: 5.166e-01] my_first_lora_v1: 42%|####1 | 1251/3000 [17:10<39:59, 1.37s/it, lr: 1.0e-04 loss: 6.882e-01] my_first_lora_v1: 42%|####1 | 1251/3000 [17:10<39:59, 1.37s/it, lr: 1.0e-04 loss: 6.882e-01] my_first_lora_v1: 42%|####1 | 1252/3000 [17:11<39:56, 1.37s/it, lr: 1.0e-04 loss: 5.041e-01] my_first_lora_v1: 42%|####1 | 1252/3000 [17:11<39:56, 1.37s/it, lr: 1.0e-04 loss: 5.041e-01] my_first_lora_v1: 42%|####1 | 1253/3000 [17:12<39:55, 1.37s/it, lr: 1.0e-04 loss: 5.455e-01] my_first_lora_v1: 42%|####1 | 1253/3000 [17:12<39:55, 1.37s/it, lr: 1.0e-04 loss: 5.455e-01] my_first_lora_v1: 42%|####1 | 1254/3000 [17:15<39:57, 1.37s/it, lr: 1.0e-04 loss: 5.043e-01] my_first_lora_v1: 42%|####1 | 1254/3000 [17:15<39:57, 1.37s/it, lr: 1.0e-04 loss: 5.043e-01] my_first_lora_v1: 42%|####1 | 1255/3000 [17:16<39:56, 1.37s/it, lr: 1.0e-04 loss: 1.640e-01] my_first_lora_v1: 42%|####1 | 1255/3000 [17:16<39:56, 1.37s/it, lr: 1.0e-04 loss: 1.640e-01] my_first_lora_v1: 42%|####1 | 1256/3000 [17:18<39:55, 1.37s/it, lr: 1.0e-04 loss: 1.612e-01] my_first_lora_v1: 42%|####1 | 1256/3000 [17:18<39:55, 1.37s/it, lr: 1.0e-04 loss: 1.612e-01] my_first_lora_v1: 42%|####1 | 1257/3000 [17:20<39:56, 1.38s/it, lr: 1.0e-04 loss: 5.207e-01] my_first_lora_v1: 42%|####1 | 1257/3000 [17:20<39:56, 1.38s/it, lr: 1.0e-04 loss: 5.207e-01] my_first_lora_v1: 42%|####1 | 1258/3000 [17:23<39:58, 1.38s/it, lr: 1.0e-04 loss: 7.872e-01] my_first_lora_v1: 42%|####1 | 1258/3000 [17:23<39:58, 1.38s/it, lr: 1.0e-04 loss: 7.872e-01] my_first_lora_v1: 42%|####1 | 1259/3000 [17:25<39:57, 1.38s/it, lr: 1.0e-04 loss: 6.748e-01] my_first_lora_v1: 42%|####1 | 1259/3000 [17:25<39:57, 1.38s/it, lr: 1.0e-04 loss: 6.748e-01] my_first_lora_v1: 42%|####2 | 1260/3000 [17:26<39:55, 1.38s/it, lr: 1.0e-04 loss: 5.888e-01] my_first_lora_v1: 42%|####2 | 1260/3000 [17:26<39:55, 1.38s/it, lr: 1.0e-04 loss: 5.888e-01] my_first_lora_v1: 42%|####2 | 1261/3000 [17:27<39:53, 1.38s/it, lr: 1.0e-04 loss: 3.161e-01] my_first_lora_v1: 42%|####2 | 1261/3000 [17:27<39:53, 1.38s/it, lr: 1.0e-04 loss: 3.161e-01] my_first_lora_v1: 42%|####2 | 1262/3000 [17:29<39:54, 1.38s/it, lr: 1.0e-04 loss: 3.088e-01] my_first_lora_v1: 42%|####2 | 1262/3000 [17:29<39:54, 1.38s/it, lr: 1.0e-04 loss: 3.088e-01] my_first_lora_v1: 42%|####2 | 1263/3000 [17:31<39:53, 1.38s/it, lr: 1.0e-04 loss: 5.549e-01] my_first_lora_v1: 42%|####2 | 1263/3000 [17:31<39:53, 1.38s/it, lr: 1.0e-04 loss: 5.549e-01] my_first_lora_v1: 42%|####2 | 1264/3000 [17:32<39:52, 1.38s/it, lr: 1.0e-04 loss: 6.927e-01] my_first_lora_v1: 42%|####2 | 1264/3000 [17:32<39:52, 1.38s/it, lr: 1.0e-04 loss: 6.927e-01] my_first_lora_v1: 42%|####2 | 1265/3000 [17:34<39:51, 1.38s/it, lr: 1.0e-04 loss: 5.848e-01] my_first_lora_v1: 42%|####2 | 1265/3000 [17:34<39:51, 1.38s/it, lr: 1.0e-04 loss: 5.848e-01] my_first_lora_v1: 42%|####2 | 1266/3000 [17:35<39:48, 1.38s/it, lr: 1.0e-04 loss: 7.298e-01] my_first_lora_v1: 42%|####2 | 1266/3000 [17:35<39:48, 1.38s/it, lr: 1.0e-04 loss: 7.298e-01] my_first_lora_v1: 42%|####2 | 1267/3000 [17:36<39:46, 1.38s/it, lr: 1.0e-04 loss: 1.784e-01] my_first_lora_v1: 42%|####2 | 1267/3000 [17:36<39:46, 1.38s/it, lr: 1.0e-04 loss: 1.784e-01] my_first_lora_v1: 42%|####2 | 1268/3000 [17:37<39:45, 1.38s/it, lr: 1.0e-04 loss: 8.301e-02] my_first_lora_v1: 42%|####2 | 1268/3000 [17:37<39:45, 1.38s/it, lr: 1.0e-04 loss: 8.301e-02] my_first_lora_v1: 42%|####2 | 1269/3000 [17:38<39:42, 1.38s/it, lr: 1.0e-04 loss: 3.528e-01] my_first_lora_v1: 42%|####2 | 1269/3000 [17:38<39:42, 1.38s/it, lr: 1.0e-04 loss: 3.528e-01] my_first_lora_v1: 42%|####2 | 1270/3000 [17:40<39:41, 1.38s/it, lr: 1.0e-04 loss: 7.051e-01] my_first_lora_v1: 42%|####2 | 1270/3000 [17:40<39:41, 1.38s/it, lr: 1.0e-04 loss: 7.051e-01] my_first_lora_v1: 42%|####2 | 1271/3000 [17:40<39:38, 1.38s/it, lr: 1.0e-04 loss: 6.355e-01] my_first_lora_v1: 42%|####2 | 1271/3000 [17:40<39:38, 1.38s/it, lr: 1.0e-04 loss: 6.355e-01] my_first_lora_v1: 42%|####2 | 1272/3000 [17:43<39:40, 1.38s/it, lr: 1.0e-04 loss: 5.592e-01] my_first_lora_v1: 42%|####2 | 1272/3000 [17:43<39:40, 1.38s/it, lr: 1.0e-04 loss: 5.592e-01] my_first_lora_v1: 42%|####2 | 1273/3000 [17:44<39:37, 1.38s/it, lr: 1.0e-04 loss: 4.536e-01] my_first_lora_v1: 42%|####2 | 1273/3000 [17:44<39:37, 1.38s/it, lr: 1.0e-04 loss: 4.536e-01] my_first_lora_v1: 42%|####2 | 1274/3000 [17:45<39:36, 1.38s/it, lr: 1.0e-04 loss: 3.452e-01] my_first_lora_v1: 42%|####2 | 1274/3000 [17:45<39:36, 1.38s/it, lr: 1.0e-04 loss: 3.452e-01] my_first_lora_v1: 42%|####2 | 1275/3000 [17:46<39:34, 1.38s/it, lr: 1.0e-04 loss: 2.974e-01] my_first_lora_v1: 42%|####2 | 1275/3000 [17:46<39:34, 1.38s/it, lr: 1.0e-04 loss: 2.974e-01] my_first_lora_v1: 43%|####2 | 1276/3000 [17:47<39:32, 1.38s/it, lr: 1.0e-04 loss: 4.870e-01] my_first_lora_v1: 43%|####2 | 1276/3000 [17:47<39:32, 1.38s/it, lr: 1.0e-04 loss: 4.870e-01] my_first_lora_v1: 43%|####2 | 1277/3000 [17:48<39:29, 1.38s/it, lr: 1.0e-04 loss: 8.158e-01] my_first_lora_v1: 43%|####2 | 1277/3000 [17:48<39:29, 1.38s/it, lr: 1.0e-04 loss: 8.158e-01] my_first_lora_v1: 43%|####2 | 1278/3000 [17:50<39:28, 1.38s/it, lr: 1.0e-04 loss: 6.733e-01] my_first_lora_v1: 43%|####2 | 1278/3000 [17:50<39:28, 1.38s/it, lr: 1.0e-04 loss: 6.733e-01] my_first_lora_v1: 43%|####2 | 1279/3000 [17:51<39:27, 1.38s/it, lr: 1.0e-04 loss: 2.821e-01] my_first_lora_v1: 43%|####2 | 1279/3000 [17:51<39:27, 1.38s/it, lr: 1.0e-04 loss: 2.821e-01] my_first_lora_v1: 43%|####2 | 1280/3000 [17:52<39:25, 1.38s/it, lr: 1.0e-04 loss: 3.515e-02] my_first_lora_v1: 43%|####2 | 1280/3000 [17:52<39:25, 1.38s/it, lr: 1.0e-04 loss: 3.515e-02] my_first_lora_v1: 43%|####2 | 1281/3000 [17:53<39:23, 1.37s/it, lr: 1.0e-04 loss: 5.788e-01] my_first_lora_v1: 43%|####2 | 1281/3000 [17:53<39:23, 1.37s/it, lr: 1.0e-04 loss: 5.788e-01] my_first_lora_v1: 43%|####2 | 1282/3000 [17:54<39:20, 1.37s/it, lr: 1.0e-04 loss: 4.022e-01] my_first_lora_v1: 43%|####2 | 1282/3000 [17:54<39:20, 1.37s/it, lr: 1.0e-04 loss: 4.022e-01] my_first_lora_v1: 43%|####2 | 1283/3000 [17:55<39:17, 1.37s/it, lr: 1.0e-04 loss: 7.534e-01] my_first_lora_v1: 43%|####2 | 1283/3000 [17:55<39:17, 1.37s/it, lr: 1.0e-04 loss: 7.534e-01] my_first_lora_v1: 43%|####2 | 1284/3000 [17:56<39:15, 1.37s/it, lr: 1.0e-04 loss: 7.651e-01] my_first_lora_v1: 43%|####2 | 1284/3000 [17:56<39:15, 1.37s/it, lr: 1.0e-04 loss: 7.651e-01] my_first_lora_v1: 43%|####2 | 1285/3000 [17:56<39:12, 1.37s/it, lr: 1.0e-04 loss: 5.098e-01] my_first_lora_v1: 43%|####2 | 1285/3000 [17:56<39:12, 1.37s/it, lr: 1.0e-04 loss: 5.098e-01] my_first_lora_v1: 43%|####2 | 1286/3000 [17:57<39:10, 1.37s/it, lr: 1.0e-04 loss: 1.174e-01] my_first_lora_v1: 43%|####2 | 1286/3000 [17:57<39:10, 1.37s/it, lr: 1.0e-04 loss: 1.174e-01] my_first_lora_v1: 43%|####2 | 1287/3000 [17:59<39:08, 1.37s/it, lr: 1.0e-04 loss: 2.157e-01] my_first_lora_v1: 43%|####2 | 1287/3000 [17:59<39:08, 1.37s/it, lr: 1.0e-04 loss: 2.157e-01] my_first_lora_v1: 43%|####2 | 1288/3000 [17:59<39:06, 1.37s/it, lr: 1.0e-04 loss: 6.754e-01] my_first_lora_v1: 43%|####2 | 1288/3000 [17:59<39:06, 1.37s/it, lr: 1.0e-04 loss: 6.754e-01] my_first_lora_v1: 43%|####2 | 1289/3000 [18:01<39:04, 1.37s/it, lr: 1.0e-04 loss: 5.162e-01] my_first_lora_v1: 43%|####2 | 1289/3000 [18:01<39:04, 1.37s/it, lr: 1.0e-04 loss: 5.162e-01] my_first_lora_v1: 43%|####3 | 1290/3000 [18:02<39:02, 1.37s/it, lr: 1.0e-04 loss: 2.875e-01] my_first_lora_v1: 43%|####3 | 1290/3000 [18:02<39:02, 1.37s/it, lr: 1.0e-04 loss: 2.875e-01] my_first_lora_v1: 43%|####3 | 1291/3000 [18:03<39:00, 1.37s/it, lr: 1.0e-04 loss: 1.467e-01] my_first_lora_v1: 43%|####3 | 1291/3000 [18:03<39:00, 1.37s/it, lr: 1.0e-04 loss: 1.467e-01] my_first_lora_v1: 43%|####3 | 1292/3000 [18:04<38:59, 1.37s/it, lr: 1.0e-04 loss: 5.125e-01] my_first_lora_v1: 43%|####3 | 1292/3000 [18:04<38:59, 1.37s/it, lr: 1.0e-04 loss: 5.125e-01] my_first_lora_v1: 43%|####3 | 1293/3000 [18:07<39:00, 1.37s/it, lr: 1.0e-04 loss: 7.247e-02] my_first_lora_v1: 43%|####3 | 1293/3000 [18:07<39:00, 1.37s/it, lr: 1.0e-04 loss: 7.247e-02] my_first_lora_v1: 43%|####3 | 1294/3000 [18:08<38:57, 1.37s/it, lr: 1.0e-04 loss: 1.652e-01] my_first_lora_v1: 43%|####3 | 1294/3000 [18:08<38:57, 1.37s/it, lr: 1.0e-04 loss: 1.652e-01] my_first_lora_v1: 43%|####3 | 1295/3000 [18:10<38:58, 1.37s/it, lr: 1.0e-04 loss: 3.965e-01] my_first_lora_v1: 43%|####3 | 1295/3000 [18:10<38:58, 1.37s/it, lr: 1.0e-04 loss: 3.965e-01] my_first_lora_v1: 43%|####3 | 1296/3000 [18:12<38:58, 1.37s/it, lr: 1.0e-04 loss: 7.099e-01] my_first_lora_v1: 43%|####3 | 1296/3000 [18:12<38:58, 1.37s/it, lr: 1.0e-04 loss: 7.099e-01] my_first_lora_v1: 43%|####3 | 1297/3000 [18:13<38:55, 1.37s/it, lr: 1.0e-04 loss: 5.503e-01] my_first_lora_v1: 43%|####3 | 1297/3000 [18:13<38:55, 1.37s/it, lr: 1.0e-04 loss: 5.503e-01] my_first_lora_v1: 43%|####3 | 1298/3000 [18:14<38:54, 1.37s/it, lr: 1.0e-04 loss: 6.029e-01] my_first_lora_v1: 43%|####3 | 1298/3000 [18:14<38:54, 1.37s/it, lr: 1.0e-04 loss: 6.029e-01] my_first_lora_v1: 43%|####3 | 1299/3000 [18:15<38:52, 1.37s/it, lr: 1.0e-04 loss: 6.398e-02] my_first_lora_v1: 43%|####3 | 1299/3000 [18:15<38:52, 1.37s/it, lr: 1.0e-04 loss: 6.398e-02] my_first_lora_v1: 43%|####3 | 1300/3000 [18:18<38:54, 1.37s/it, lr: 1.0e-04 loss: 8.200e-01] my_first_lora_v1: 43%|####3 | 1300/3000 [18:18<38:54, 1.37s/it, lr: 1.0e-04 loss: 8.200e-01] my_first_lora_v1: 43%|####3 | 1301/3000 [18:19<38:51, 1.37s/it, lr: 1.0e-04 loss: 7.997e-01] my_first_lora_v1: 43%|####3 | 1301/3000 [18:19<38:51, 1.37s/it, lr: 1.0e-04 loss: 7.997e-01] my_first_lora_v1: 43%|####3 | 1302/3000 [18:20<38:49, 1.37s/it, lr: 1.0e-04 loss: 3.925e-01] my_first_lora_v1: 43%|####3 | 1302/3000 [18:20<38:49, 1.37s/it, lr: 1.0e-04 loss: 3.925e-01] my_first_lora_v1: 43%|####3 | 1303/3000 [18:22<38:50, 1.37s/it, lr: 1.0e-04 loss: 1.174e-01] my_first_lora_v1: 43%|####3 | 1303/3000 [18:22<38:50, 1.37s/it, lr: 1.0e-04 loss: 1.174e-01] my_first_lora_v1: 43%|####3 | 1304/3000 [18:24<38:49, 1.37s/it, lr: 1.0e-04 loss: 3.208e-01] my_first_lora_v1: 43%|####3 | 1304/3000 [18:24<38:49, 1.37s/it, lr: 1.0e-04 loss: 3.208e-01] my_first_lora_v1: 44%|####3 | 1305/3000 [18:25<38:47, 1.37s/it, lr: 1.0e-04 loss: 7.666e-01] my_first_lora_v1: 44%|####3 | 1305/3000 [18:25<38:47, 1.37s/it, lr: 1.0e-04 loss: 7.666e-01] my_first_lora_v1: 44%|####3 | 1306/3000 [18:27<38:48, 1.37s/it, lr: 1.0e-04 loss: 2.462e-01] my_first_lora_v1: 44%|####3 | 1306/3000 [18:27<38:48, 1.37s/it, lr: 1.0e-04 loss: 2.462e-01] my_first_lora_v1: 44%|####3 | 1307/3000 [18:28<38:46, 1.37s/it, lr: 1.0e-04 loss: 2.212e-01] my_first_lora_v1: 44%|####3 | 1307/3000 [18:28<38:46, 1.37s/it, lr: 1.0e-04 loss: 2.212e-01] my_first_lora_v1: 44%|####3 | 1308/3000 [18:29<38:43, 1.37s/it, lr: 1.0e-04 loss: 7.236e-01] my_first_lora_v1: 44%|####3 | 1308/3000 [18:29<38:43, 1.37s/it, lr: 1.0e-04 loss: 7.236e-01] my_first_lora_v1: 44%|####3 | 1309/3000 [18:30<38:40, 1.37s/it, lr: 1.0e-04 loss: 1.399e-01] my_first_lora_v1: 44%|####3 | 1309/3000 [18:30<38:40, 1.37s/it, lr: 1.0e-04 loss: 1.399e-01] my_first_lora_v1: 44%|####3 | 1310/3000 [18:31<38:38, 1.37s/it, lr: 1.0e-04 loss: 6.153e-01] my_first_lora_v1: 44%|####3 | 1310/3000 [18:31<38:38, 1.37s/it, lr: 1.0e-04 loss: 6.153e-01] my_first_lora_v1: 44%|####3 | 1311/3000 [18:32<38:37, 1.37s/it, lr: 1.0e-04 loss: 1.957e-01] my_first_lora_v1: 44%|####3 | 1311/3000 [18:32<38:37, 1.37s/it, lr: 1.0e-04 loss: 1.957e-01] my_first_lora_v1: 44%|####3 | 1312/3000 [18:33<38:35, 1.37s/it, lr: 1.0e-04 loss: 5.573e-01] my_first_lora_v1: 44%|####3 | 1312/3000 [18:33<38:35, 1.37s/it, lr: 1.0e-04 loss: 5.573e-01] my_first_lora_v1: 44%|####3 | 1313/3000 [18:35<38:33, 1.37s/it, lr: 1.0e-04 loss: 4.850e-01] my_first_lora_v1: 44%|####3 | 1313/3000 [18:35<38:33, 1.37s/it, lr: 1.0e-04 loss: 4.850e-01] my_first_lora_v1: 44%|####3 | 1314/3000 [18:36<38:32, 1.37s/it, lr: 1.0e-04 loss: 6.973e-01] my_first_lora_v1: 44%|####3 | 1314/3000 [18:36<38:32, 1.37s/it, lr: 1.0e-04 loss: 6.973e-01] my_first_lora_v1: 44%|####3 | 1315/3000 [18:37<38:31, 1.37s/it, lr: 1.0e-04 loss: 6.761e-01] my_first_lora_v1: 44%|####3 | 1315/3000 [18:37<38:31, 1.37s/it, lr: 1.0e-04 loss: 6.761e-01] my_first_lora_v1: 44%|####3 | 1316/3000 [18:39<38:30, 1.37s/it, lr: 1.0e-04 loss: 6.082e-01] my_first_lora_v1: 44%|####3 | 1316/3000 [18:39<38:30, 1.37s/it, lr: 1.0e-04 loss: 6.082e-01] my_first_lora_v1: 44%|####3 | 1317/3000 [18:40<38:28, 1.37s/it, lr: 1.0e-04 loss: 2.170e-01] my_first_lora_v1: 44%|####3 | 1317/3000 [18:40<38:28, 1.37s/it, lr: 1.0e-04 loss: 2.170e-01] my_first_lora_v1: 44%|####3 | 1318/3000 [18:41<38:25, 1.37s/it, lr: 1.0e-04 loss: 2.250e-01] my_first_lora_v1: 44%|####3 | 1318/3000 [18:41<38:25, 1.37s/it, lr: 1.0e-04 loss: 2.250e-01] my_first_lora_v1: 44%|####3 | 1319/3000 [18:43<38:25, 1.37s/it, lr: 1.0e-04 loss: 1.346e-01] my_first_lora_v1: 44%|####3 | 1319/3000 [18:43<38:25, 1.37s/it, lr: 1.0e-04 loss: 1.346e-01] my_first_lora_v1: 44%|####4 | 1320/3000 [18:43<38:22, 1.37s/it, lr: 1.0e-04 loss: 5.608e-01] my_first_lora_v1: 44%|####4 | 1320/3000 [18:43<38:22, 1.37s/it, lr: 1.0e-04 loss: 5.608e-01] my_first_lora_v1: 44%|####4 | 1321/3000 [18:45<38:21, 1.37s/it, lr: 1.0e-04 loss: 2.176e-01] my_first_lora_v1: 44%|####4 | 1321/3000 [18:45<38:21, 1.37s/it, lr: 1.0e-04 loss: 2.176e-01] my_first_lora_v1: 44%|####4 | 1322/3000 [18:47<38:20, 1.37s/it, lr: 1.0e-04 loss: 5.082e-01] my_first_lora_v1: 44%|####4 | 1322/3000 [18:47<38:20, 1.37s/it, lr: 1.0e-04 loss: 5.082e-01] my_first_lora_v1: 44%|####4 | 1323/3000 [18:47<38:18, 1.37s/it, lr: 1.0e-04 loss: 2.431e-01] my_first_lora_v1: 44%|####4 | 1323/3000 [18:47<38:18, 1.37s/it, lr: 1.0e-04 loss: 2.431e-01] my_first_lora_v1: 44%|####4 | 1324/3000 [18:50<38:18, 1.37s/it, lr: 1.0e-04 loss: 6.395e-01] my_first_lora_v1: 44%|####4 | 1324/3000 [18:50<38:18, 1.37s/it, lr: 1.0e-04 loss: 6.395e-01] my_first_lora_v1: 44%|####4 | 1325/3000 [18:51<38:17, 1.37s/it, lr: 1.0e-04 loss: 4.692e-02] my_first_lora_v1: 44%|####4 | 1325/3000 [18:51<38:17, 1.37s/it, lr: 1.0e-04 loss: 4.692e-02] my_first_lora_v1: 44%|####4 | 1326/3000 [18:53<38:16, 1.37s/it, lr: 1.0e-04 loss: 1.644e-01] my_first_lora_v1: 44%|####4 | 1326/3000 [18:53<38:16, 1.37s/it, lr: 1.0e-04 loss: 1.644e-01] my_first_lora_v1: 44%|####4 | 1327/3000 [18:54<38:15, 1.37s/it, lr: 1.0e-04 loss: 4.196e-02] my_first_lora_v1: 44%|####4 | 1327/3000 [18:54<38:15, 1.37s/it, lr: 1.0e-04 loss: 4.196e-02] my_first_lora_v1: 44%|####4 | 1328/3000 [18:57<38:16, 1.37s/it, lr: 1.0e-04 loss: 6.773e-01] my_first_lora_v1: 44%|####4 | 1328/3000 [18:57<38:16, 1.37s/it, lr: 1.0e-04 loss: 6.773e-01] my_first_lora_v1: 44%|####4 | 1329/3000 [18:58<38:14, 1.37s/it, lr: 1.0e-04 loss: 4.237e-01] my_first_lora_v1: 44%|####4 | 1329/3000 [18:58<38:14, 1.37s/it, lr: 1.0e-04 loss: 4.237e-01] my_first_lora_v1: 44%|####4 | 1330/3000 [18:59<38:11, 1.37s/it, lr: 1.0e-04 loss: 1.276e-01] my_first_lora_v1: 44%|####4 | 1330/3000 [18:59<38:11, 1.37s/it, lr: 1.0e-04 loss: 1.276e-01] my_first_lora_v1: 44%|####4 | 1331/3000 [19:00<38:10, 1.37s/it, lr: 1.0e-04 loss: 1.219e-01] my_first_lora_v1: 44%|####4 | 1331/3000 [19:00<38:10, 1.37s/it, lr: 1.0e-04 loss: 1.219e-01] my_first_lora_v1: 44%|####4 | 1332/3000 [19:01<38:07, 1.37s/it, lr: 1.0e-04 loss: 7.166e-01] my_first_lora_v1: 44%|####4 | 1332/3000 [19:01<38:07, 1.37s/it, lr: 1.0e-04 loss: 7.166e-01] my_first_lora_v1: 44%|####4 | 1333/3000 [19:02<38:06, 1.37s/it, lr: 1.0e-04 loss: 2.528e-01] my_first_lora_v1: 44%|####4 | 1333/3000 [19:02<38:06, 1.37s/it, lr: 1.0e-04 loss: 2.528e-01] my_first_lora_v1: 44%|####4 | 1334/3000 [19:03<38:04, 1.37s/it, lr: 1.0e-04 loss: 1.734e-01] my_first_lora_v1: 44%|####4 | 1334/3000 [19:03<38:04, 1.37s/it, lr: 1.0e-04 loss: 1.734e-01] my_first_lora_v1: 44%|####4 | 1335/3000 [19:04<38:02, 1.37s/it, lr: 1.0e-04 loss: 2.243e-01] my_first_lora_v1: 44%|####4 | 1335/3000 [19:04<38:02, 1.37s/it, lr: 1.0e-04 loss: 2.243e-01] my_first_lora_v1: 45%|####4 | 1336/3000 [19:07<38:03, 1.37s/it, lr: 1.0e-04 loss: 5.087e-01] my_first_lora_v1: 45%|####4 | 1336/3000 [19:07<38:03, 1.37s/it, lr: 1.0e-04 loss: 5.087e-01] my_first_lora_v1: 45%|####4 | 1337/3000 [19:08<38:02, 1.37s/it, lr: 1.0e-04 loss: 1.962e-01] my_first_lora_v1: 45%|####4 | 1337/3000 [19:08<38:02, 1.37s/it, lr: 1.0e-04 loss: 1.962e-01] my_first_lora_v1: 45%|####4 | 1338/3000 [19:09<38:00, 1.37s/it, lr: 1.0e-04 loss: 3.741e-01] my_first_lora_v1: 45%|####4 | 1338/3000 [19:09<38:00, 1.37s/it, lr: 1.0e-04 loss: 3.741e-01] my_first_lora_v1: 45%|####4 | 1339/3000 [19:10<37:57, 1.37s/it, lr: 1.0e-04 loss: 5.185e-01] my_first_lora_v1: 45%|####4 | 1339/3000 [19:10<37:57, 1.37s/it, lr: 1.0e-04 loss: 5.185e-01] my_first_lora_v1: 45%|####4 | 1340/3000 [19:12<37:58, 1.37s/it, lr: 1.0e-04 loss: 5.323e-01] my_first_lora_v1: 45%|####4 | 1340/3000 [19:12<37:58, 1.37s/it, lr: 1.0e-04 loss: 5.323e-01] my_first_lora_v1: 45%|####4 | 1341/3000 [19:14<37:57, 1.37s/it, lr: 1.0e-04 loss: 2.115e-01] my_first_lora_v1: 45%|####4 | 1341/3000 [19:14<37:57, 1.37s/it, lr: 1.0e-04 loss: 2.115e-01] my_first_lora_v1: 45%|####4 | 1342/3000 [19:16<37:57, 1.37s/it, lr: 1.0e-04 loss: 6.943e-01] my_first_lora_v1: 45%|####4 | 1342/3000 [19:16<37:57, 1.37s/it, lr: 1.0e-04 loss: 6.943e-01] my_first_lora_v1: 45%|####4 | 1343/3000 [19:18<37:57, 1.37s/it, lr: 1.0e-04 loss: 4.088e-01] my_first_lora_v1: 45%|####4 | 1343/3000 [19:18<37:57, 1.37s/it, lr: 1.0e-04 loss: 4.088e-01] my_first_lora_v1: 45%|####4 | 1344/3000 [19:20<37:56, 1.37s/it, lr: 1.0e-04 loss: 4.823e-02] my_first_lora_v1: 45%|####4 | 1344/3000 [19:20<37:56, 1.37s/it, lr: 1.0e-04 loss: 4.823e-02] my_first_lora_v1: 45%|####4 | 1345/3000 [19:21<37:54, 1.37s/it, lr: 1.0e-04 loss: 4.794e-01] my_first_lora_v1: 45%|####4 | 1345/3000 [19:21<37:54, 1.37s/it, lr: 1.0e-04 loss: 4.794e-01] my_first_lora_v1: 45%|####4 | 1346/3000 [19:22<37:52, 1.37s/it, lr: 1.0e-04 loss: 5.742e-01] my_first_lora_v1: 45%|####4 | 1346/3000 [19:22<37:52, 1.37s/it, lr: 1.0e-04 loss: 5.742e-01] my_first_lora_v1: 45%|####4 | 1347/3000 [19:24<37:51, 1.37s/it, lr: 1.0e-04 loss: 6.867e-01] my_first_lora_v1: 45%|####4 | 1347/3000 [19:24<37:51, 1.37s/it, lr: 1.0e-04 loss: 6.867e-01] my_first_lora_v1: 45%|####4 | 1348/3000 [19:25<37:50, 1.37s/it, lr: 1.0e-04 loss: 1.272e-01] my_first_lora_v1: 45%|####4 | 1348/3000 [19:25<37:50, 1.37s/it, lr: 1.0e-04 loss: 1.272e-01] my_first_lora_v1: 45%|####4 | 1349/3000 [19:26<37:48, 1.37s/it, lr: 1.0e-04 loss: 2.750e-01] my_first_lora_v1: 45%|####4 | 1349/3000 [19:26<37:48, 1.37s/it, lr: 1.0e-04 loss: 2.750e-01] my_first_lora_v1: 45%|####5 | 1350/3000 [19:28<37:47, 1.37s/it, lr: 1.0e-04 loss: 5.667e-01] my_first_lora_v1: 45%|####5 | 1350/3000 [19:28<37:47, 1.37s/it, lr: 1.0e-04 loss: 5.667e-01] my_first_lora_v1: 45%|####5 | 1351/3000 [19:30<37:48, 1.38s/it, lr: 1.0e-04 loss: 1.351e-01] my_first_lora_v1: 45%|####5 | 1351/3000 [19:30<37:48, 1.38s/it, lr: 1.0e-04 loss: 1.351e-01] my_first_lora_v1: 45%|####5 | 1352/3000 [19:32<37:47, 1.38s/it, lr: 1.0e-04 loss: 6.863e-01] my_first_lora_v1: 45%|####5 | 1352/3000 [19:32<37:47, 1.38s/it, lr: 1.0e-04 loss: 6.863e-01] my_first_lora_v1: 45%|####5 | 1353/3000 [19:33<37:44, 1.38s/it, lr: 1.0e-04 loss: 2.457e-01] my_first_lora_v1: 45%|####5 | 1353/3000 [19:33<37:44, 1.38s/it, lr: 1.0e-04 loss: 2.457e-01] my_first_lora_v1: 45%|####5 | 1354/3000 [19:35<37:45, 1.38s/it, lr: 1.0e-04 loss: 3.144e-01] my_first_lora_v1: 45%|####5 | 1354/3000 [19:35<37:45, 1.38s/it, lr: 1.0e-04 loss: 3.144e-01] my_first_lora_v1: 45%|####5 | 1355/3000 [19:37<37:45, 1.38s/it, lr: 1.0e-04 loss: 1.871e-01] my_first_lora_v1: 45%|####5 | 1355/3000 [19:37<37:45, 1.38s/it, lr: 1.0e-04 loss: 1.871e-01] my_first_lora_v1: 45%|####5 | 1356/3000 [19:38<37:42, 1.38s/it, lr: 1.0e-04 loss: 3.590e-01] my_first_lora_v1: 45%|####5 | 1356/3000 [19:38<37:42, 1.38s/it, lr: 1.0e-04 loss: 3.590e-01] my_first_lora_v1: 45%|####5 | 1357/3000 [19:39<37:41, 1.38s/it, lr: 1.0e-04 loss: 1.372e-01] my_first_lora_v1: 45%|####5 | 1357/3000 [19:39<37:41, 1.38s/it, lr: 1.0e-04 loss: 1.372e-01] my_first_lora_v1: 45%|####5 | 1358/3000 [19:40<37:39, 1.38s/it, lr: 1.0e-04 loss: 4.424e-01] my_first_lora_v1: 45%|####5 | 1358/3000 [19:40<37:39, 1.38s/it, lr: 1.0e-04 loss: 4.424e-01] my_first_lora_v1: 45%|####5 | 1359/3000 [19:42<37:38, 1.38s/it, lr: 1.0e-04 loss: 5.893e-02] my_first_lora_v1: 45%|####5 | 1359/3000 [19:42<37:38, 1.38s/it, lr: 1.0e-04 loss: 5.893e-02] my_first_lora_v1: 45%|####5 | 1360/3000 [19:44<37:38, 1.38s/it, lr: 1.0e-04 loss: 5.031e-01] my_first_lora_v1: 45%|####5 | 1360/3000 [19:44<37:38, 1.38s/it, lr: 1.0e-04 loss: 5.031e-01] my_first_lora_v1: 45%|####5 | 1361/3000 [19:46<37:39, 1.38s/it, lr: 1.0e-04 loss: 3.202e-01] my_first_lora_v1: 45%|####5 | 1361/3000 [19:46<37:39, 1.38s/it, lr: 1.0e-04 loss: 3.202e-01] my_first_lora_v1: 45%|####5 | 1362/3000 [19:48<37:37, 1.38s/it, lr: 1.0e-04 loss: 6.788e-01] my_first_lora_v1: 45%|####5 | 1362/3000 [19:48<37:37, 1.38s/it, lr: 1.0e-04 loss: 6.788e-01] my_first_lora_v1: 45%|####5 | 1363/3000 [19:49<37:35, 1.38s/it, lr: 1.0e-04 loss: 1.073e-01] my_first_lora_v1: 45%|####5 | 1363/3000 [19:49<37:35, 1.38s/it, lr: 1.0e-04 loss: 1.073e-01] my_first_lora_v1: 45%|####5 | 1364/3000 [19:50<37:34, 1.38s/it, lr: 1.0e-04 loss: 4.433e-01] my_first_lora_v1: 45%|####5 | 1364/3000 [19:50<37:34, 1.38s/it, lr: 1.0e-04 loss: 4.433e-01] my_first_lora_v1: 46%|####5 | 1365/3000 [19:51<37:32, 1.38s/it, lr: 1.0e-04 loss: 5.320e-01] my_first_lora_v1: 46%|####5 | 1365/3000 [19:51<37:32, 1.38s/it, lr: 1.0e-04 loss: 5.320e-01] my_first_lora_v1: 46%|####5 | 1366/3000 [19:53<37:32, 1.38s/it, lr: 1.0e-04 loss: 6.698e-01] my_first_lora_v1: 46%|####5 | 1366/3000 [19:53<37:32, 1.38s/it, lr: 1.0e-04 loss: 6.698e-01] my_first_lora_v1: 46%|####5 | 1367/3000 [19:55<37:31, 1.38s/it, lr: 1.0e-04 loss: 6.748e-01] my_first_lora_v1: 46%|####5 | 1367/3000 [19:55<37:31, 1.38s/it, lr: 1.0e-04 loss: 6.748e-01] my_first_lora_v1: 46%|####5 | 1368/3000 [19:56<37:29, 1.38s/it, lr: 1.0e-04 loss: 5.337e-01] my_first_lora_v1: 46%|####5 | 1368/3000 [19:56<37:29, 1.38s/it, lr: 1.0e-04 loss: 5.337e-01] my_first_lora_v1: 46%|####5 | 1369/3000 [19:58<37:28, 1.38s/it, lr: 1.0e-04 loss: 5.616e-01] my_first_lora_v1: 46%|####5 | 1369/3000 [19:58<37:28, 1.38s/it, lr: 1.0e-04 loss: 5.616e-01] my_first_lora_v1: 46%|####5 | 1370/3000 [19:59<37:27, 1.38s/it, lr: 1.0e-04 loss: 3.846e-01] my_first_lora_v1: 46%|####5 | 1370/3000 [19:59<37:27, 1.38s/it, lr: 1.0e-04 loss: 3.846e-01] my_first_lora_v1: 46%|####5 | 1371/3000 [20:00<37:25, 1.38s/it, lr: 1.0e-04 loss: 4.444e-01] my_first_lora_v1: 46%|####5 | 1371/3000 [20:00<37:25, 1.38s/it, lr: 1.0e-04 loss: 4.444e-01] my_first_lora_v1: 46%|####5 | 1372/3000 [20:02<37:24, 1.38s/it, lr: 1.0e-04 loss: 5.504e-01] my_first_lora_v1: 46%|####5 | 1372/3000 [20:02<37:24, 1.38s/it, lr: 1.0e-04 loss: 5.504e-01] my_first_lora_v1: 46%|####5 | 1373/3000 [20:02<37:21, 1.38s/it, lr: 1.0e-04 loss: 4.690e-01] my_first_lora_v1: 46%|####5 | 1373/3000 [20:02<37:21, 1.38s/it, lr: 1.0e-04 loss: 4.690e-01] my_first_lora_v1: 46%|####5 | 1374/3000 [20:04<37:20, 1.38s/it, lr: 1.0e-04 loss: 8.313e-01] my_first_lora_v1: 46%|####5 | 1374/3000 [20:04<37:20, 1.38s/it, lr: 1.0e-04 loss: 8.313e-01] my_first_lora_v1: 46%|####5 | 1375/3000 [20:05<37:19, 1.38s/it, lr: 1.0e-04 loss: 7.127e-01] my_first_lora_v1: 46%|####5 | 1375/3000 [20:05<37:19, 1.38s/it, lr: 1.0e-04 loss: 7.127e-01] my_first_lora_v1: 46%|####5 | 1376/3000 [20:06<37:16, 1.38s/it, lr: 1.0e-04 loss: 3.989e-01] my_first_lora_v1: 46%|####5 | 1376/3000 [20:06<37:16, 1.38s/it, lr: 1.0e-04 loss: 3.989e-01] my_first_lora_v1: 46%|####5 | 1377/3000 [20:07<37:14, 1.38s/it, lr: 1.0e-04 loss: 3.660e-01] my_first_lora_v1: 46%|####5 | 1377/3000 [20:07<37:14, 1.38s/it, lr: 1.0e-04 loss: 3.660e-01] my_first_lora_v1: 46%|####5 | 1378/3000 [20:08<37:11, 1.38s/it, lr: 1.0e-04 loss: 6.550e-01] my_first_lora_v1: 46%|####5 | 1378/3000 [20:08<37:11, 1.38s/it, lr: 1.0e-04 loss: 6.550e-01] my_first_lora_v1: 46%|####5 | 1379/3000 [20:08<37:09, 1.38s/it, lr: 1.0e-04 loss: 2.923e-01] my_first_lora_v1: 46%|####5 | 1379/3000 [20:08<37:09, 1.38s/it, lr: 1.0e-04 loss: 2.923e-01] my_first_lora_v1: 46%|####6 | 1380/3000 [20:10<37:08, 1.38s/it, lr: 1.0e-04 loss: 9.783e-02] my_first_lora_v1: 46%|####6 | 1380/3000 [20:10<37:08, 1.38s/it, lr: 1.0e-04 loss: 9.783e-02] my_first_lora_v1: 46%|####6 | 1381/3000 [20:11<37:06, 1.38s/it, lr: 1.0e-04 loss: 4.694e-01] my_first_lora_v1: 46%|####6 | 1381/3000 [20:11<37:06, 1.38s/it, lr: 1.0e-04 loss: 4.694e-01] my_first_lora_v1: 46%|####6 | 1382/3000 [20:14<37:07, 1.38s/it, lr: 1.0e-04 loss: 1.585e-01] my_first_lora_v1: 46%|####6 | 1382/3000 [20:14<37:07, 1.38s/it, lr: 1.0e-04 loss: 1.585e-01] my_first_lora_v1: 46%|####6 | 1383/3000 [20:15<37:05, 1.38s/it, lr: 1.0e-04 loss: 3.810e-01] my_first_lora_v1: 46%|####6 | 1383/3000 [20:15<37:05, 1.38s/it, lr: 1.0e-04 loss: 3.810e-01] my_first_lora_v1: 46%|####6 | 1384/3000 [20:15<37:02, 1.38s/it, lr: 1.0e-04 loss: 7.127e-01] my_first_lora_v1: 46%|####6 | 1384/3000 [20:15<37:02, 1.38s/it, lr: 1.0e-04 loss: 7.127e-01] my_first_lora_v1: 46%|####6 | 1385/3000 [20:16<37:00, 1.37s/it, lr: 1.0e-04 loss: 3.334e-02] my_first_lora_v1: 46%|####6 | 1385/3000 [20:16<37:00, 1.37s/it, lr: 1.0e-04 loss: 3.334e-02] my_first_lora_v1: 46%|####6 | 1386/3000 [20:18<36:59, 1.37s/it, lr: 1.0e-04 loss: 5.902e-01] my_first_lora_v1: 46%|####6 | 1386/3000 [20:18<36:59, 1.37s/it, lr: 1.0e-04 loss: 5.902e-01] my_first_lora_v1: 46%|####6 | 1387/3000 [20:19<36:57, 1.37s/it, lr: 1.0e-04 loss: 9.864e-02] my_first_lora_v1: 46%|####6 | 1387/3000 [20:19<36:57, 1.37s/it, lr: 1.0e-04 loss: 9.864e-02] my_first_lora_v1: 46%|####6 | 1388/3000 [20:20<36:56, 1.37s/it, lr: 1.0e-04 loss: 2.995e-01] my_first_lora_v1: 46%|####6 | 1388/3000 [20:20<36:56, 1.37s/it, lr: 1.0e-04 loss: 2.995e-01] my_first_lora_v1: 46%|####6 | 1389/3000 [20:21<36:54, 1.37s/it, lr: 1.0e-04 loss: 5.590e-01] my_first_lora_v1: 46%|####6 | 1389/3000 [20:21<36:54, 1.37s/it, lr: 1.0e-04 loss: 5.590e-01] my_first_lora_v1: 46%|####6 | 1390/3000 [20:24<36:55, 1.38s/it, lr: 1.0e-04 loss: 8.289e-01] my_first_lora_v1: 46%|####6 | 1390/3000 [20:24<36:55, 1.38s/it, lr: 1.0e-04 loss: 8.289e-01] my_first_lora_v1: 46%|####6 | 1391/3000 [20:27<36:56, 1.38s/it, lr: 1.0e-04 loss: 1.600e-01] my_first_lora_v1: 46%|####6 | 1391/3000 [20:27<36:56, 1.38s/it, lr: 1.0e-04 loss: 1.600e-01] my_first_lora_v1: 46%|####6 | 1392/3000 [20:29<36:56, 1.38s/it, lr: 1.0e-04 loss: 5.606e-01] my_first_lora_v1: 46%|####6 | 1392/3000 [20:29<36:56, 1.38s/it, lr: 1.0e-04 loss: 5.606e-01] my_first_lora_v1: 46%|####6 | 1393/3000 [20:30<36:54, 1.38s/it, lr: 1.0e-04 loss: 2.748e-01] my_first_lora_v1: 46%|####6 | 1393/3000 [20:30<36:54, 1.38s/it, lr: 1.0e-04 loss: 2.748e-01] my_first_lora_v1: 46%|####6 | 1394/3000 [20:32<36:53, 1.38s/it, lr: 1.0e-04 loss: 7.029e-01] my_first_lora_v1: 46%|####6 | 1394/3000 [20:32<36:53, 1.38s/it, lr: 1.0e-04 loss: 7.029e-01] my_first_lora_v1: 46%|####6 | 1395/3000 [20:35<36:54, 1.38s/it, lr: 1.0e-04 loss: 5.655e-02] my_first_lora_v1: 46%|####6 | 1395/3000 [20:35<36:54, 1.38s/it, lr: 1.0e-04 loss: 5.655e-02] my_first_lora_v1: 47%|####6 | 1396/3000 [20:36<36:53, 1.38s/it, lr: 1.0e-04 loss: 5.928e-01] my_first_lora_v1: 47%|####6 | 1396/3000 [20:36<36:53, 1.38s/it, lr: 1.0e-04 loss: 5.928e-01] my_first_lora_v1: 47%|####6 | 1397/3000 [20:37<36:50, 1.38s/it, lr: 1.0e-04 loss: 5.902e-01] my_first_lora_v1: 47%|####6 | 1397/3000 [20:37<36:50, 1.38s/it, lr: 1.0e-04 loss: 5.902e-01] my_first_lora_v1: 47%|####6 | 1398/3000 [20:37<36:48, 1.38s/it, lr: 1.0e-04 loss: 7.002e-01] my_first_lora_v1: 47%|####6 | 1398/3000 [20:37<36:48, 1.38s/it, lr: 1.0e-04 loss: 7.002e-01] my_first_lora_v1: 47%|####6 | 1399/3000 [20:39<36:47, 1.38s/it, lr: 1.0e-04 loss: 4.702e-01] my_first_lora_v1: 47%|####6 | 1399/3000 [20:39<36:47, 1.38s/it, lr: 1.0e-04 loss: 4.702e-01] my_first_lora_v1: 47%|####6 | 1400/3000 [20:42<36:48, 1.38s/it, lr: 1.0e-04 loss: 5.952e-01] my_first_lora_v1: 47%|####6 | 1400/3000 [20:42<36:48, 1.38s/it, lr: 1.0e-04 loss: 5.952e-01] my_first_lora_v1: 47%|####6 | 1401/3000 [20:43<36:47, 1.38s/it, lr: 1.0e-04 loss: 3.206e-02] my_first_lora_v1: 47%|####6 | 1401/3000 [20:43<36:47, 1.38s/it, lr: 1.0e-04 loss: 3.206e-02] my_first_lora_v1: 47%|####6 | 1402/3000 [20:45<36:46, 1.38s/it, lr: 1.0e-04 loss: 1.513e-01] my_first_lora_v1: 47%|####6 | 1402/3000 [20:45<36:46, 1.38s/it, lr: 1.0e-04 loss: 1.513e-01] my_first_lora_v1: 47%|####6 | 1403/3000 [20:46<36:44, 1.38s/it, lr: 1.0e-04 loss: 3.216e-01] my_first_lora_v1: 47%|####6 | 1403/3000 [20:46<36:44, 1.38s/it, lr: 1.0e-04 loss: 3.216e-01] my_first_lora_v1: 47%|####6 | 1404/3000 [20:47<36:42, 1.38s/it, lr: 1.0e-04 loss: 7.683e-02] my_first_lora_v1: 47%|####6 | 1404/3000 [20:47<36:42, 1.38s/it, lr: 1.0e-04 loss: 7.683e-02] my_first_lora_v1: 47%|####6 | 1405/3000 [20:48<36:40, 1.38s/it, lr: 1.0e-04 loss: 5.552e-01] my_first_lora_v1: 47%|####6 | 1405/3000 [20:48<36:40, 1.38s/it, lr: 1.0e-04 loss: 5.552e-01] my_first_lora_v1: 47%|####6 | 1406/3000 [20:49<36:38, 1.38s/it, lr: 1.0e-04 loss: 2.708e-01] my_first_lora_v1: 47%|####6 | 1406/3000 [20:49<36:38, 1.38s/it, lr: 1.0e-04 loss: 2.708e-01] my_first_lora_v1: 47%|####6 | 1407/3000 [20:51<36:37, 1.38s/it, lr: 1.0e-04 loss: 1.417e-01] my_first_lora_v1: 47%|####6 | 1407/3000 [20:51<36:37, 1.38s/it, lr: 1.0e-04 loss: 1.417e-01] my_first_lora_v1: 47%|####6 | 1408/3000 [20:52<36:36, 1.38s/it, lr: 1.0e-04 loss: 6.863e-01] my_first_lora_v1: 47%|####6 | 1408/3000 [20:52<36:36, 1.38s/it, lr: 1.0e-04 loss: 6.863e-01] my_first_lora_v1: 47%|####6 | 1409/3000 [20:54<36:34, 1.38s/it, lr: 1.0e-04 loss: 4.912e-01] my_first_lora_v1: 47%|####6 | 1409/3000 [20:54<36:34, 1.38s/it, lr: 1.0e-04 loss: 4.912e-01] my_first_lora_v1: 47%|####6 | 1410/3000 [20:54<36:32, 1.38s/it, lr: 1.0e-04 loss: 5.966e-01] my_first_lora_v1: 47%|####6 | 1410/3000 [20:54<36:32, 1.38s/it, lr: 1.0e-04 loss: 5.966e-01] my_first_lora_v1: 47%|####7 | 1411/3000 [20:56<36:31, 1.38s/it, lr: 1.0e-04 loss: 5.653e-01] my_first_lora_v1: 47%|####7 | 1411/3000 [20:56<36:31, 1.38s/it, lr: 1.0e-04 loss: 5.653e-01] my_first_lora_v1: 47%|####7 | 1412/3000 [20:58<36:31, 1.38s/it, lr: 1.0e-04 loss: 3.396e-01] my_first_lora_v1: 47%|####7 | 1412/3000 [20:58<36:31, 1.38s/it, lr: 1.0e-04 loss: 3.396e-01] my_first_lora_v1: 47%|####7 | 1413/3000 [20:59<36:29, 1.38s/it, lr: 1.0e-04 loss: 2.432e-02] my_first_lora_v1: 47%|####7 | 1413/3000 [20:59<36:29, 1.38s/it, lr: 1.0e-04 loss: 2.432e-02] my_first_lora_v1: 47%|####7 | 1414/3000 [21:00<36:27, 1.38s/it, lr: 1.0e-04 loss: 4.542e-01] my_first_lora_v1: 47%|####7 | 1414/3000 [21:00<36:27, 1.38s/it, lr: 1.0e-04 loss: 4.542e-01] my_first_lora_v1: 47%|####7 | 1415/3000 [21:01<36:24, 1.38s/it, lr: 1.0e-04 loss: 5.163e-02] my_first_lora_v1: 47%|####7 | 1415/3000 [21:01<36:24, 1.38s/it, lr: 1.0e-04 loss: 5.163e-02] my_first_lora_v1: 47%|####7 | 1416/3000 [21:01<36:22, 1.38s/it, lr: 1.0e-04 loss: 9.211e-01] my_first_lora_v1: 47%|####7 | 1416/3000 [21:01<36:22, 1.38s/it, lr: 1.0e-04 loss: 9.211e-01] my_first_lora_v1: 47%|####7 | 1417/3000 [21:02<36:19, 1.38s/it, lr: 1.0e-04 loss: 3.551e-01] my_first_lora_v1: 47%|####7 | 1417/3000 [21:02<36:19, 1.38s/it, lr: 1.0e-04 loss: 3.551e-01] my_first_lora_v1: 47%|####7 | 1418/3000 [21:05<36:20, 1.38s/it, lr: 1.0e-04 loss: 2.500e-01] my_first_lora_v1: 47%|####7 | 1418/3000 [21:05<36:20, 1.38s/it, lr: 1.0e-04 loss: 2.500e-01] my_first_lora_v1: 47%|####7 | 1419/3000 [21:05<36:17, 1.38s/it, lr: 1.0e-04 loss: 3.287e-01] my_first_lora_v1: 47%|####7 | 1419/3000 [21:05<36:17, 1.38s/it, lr: 1.0e-04 loss: 3.287e-01] my_first_lora_v1: 47%|####7 | 1420/3000 [21:07<36:16, 1.38s/it, lr: 1.0e-04 loss: 6.637e-01] my_first_lora_v1: 47%|####7 | 1420/3000 [21:07<36:16, 1.38s/it, lr: 1.0e-04 loss: 6.637e-01] my_first_lora_v1: 47%|####7 | 1421/3000 [21:08<36:14, 1.38s/it, lr: 1.0e-04 loss: 7.824e-01] my_first_lora_v1: 47%|####7 | 1421/3000 [21:08<36:14, 1.38s/it, lr: 1.0e-04 loss: 7.824e-01] my_first_lora_v1: 47%|####7 | 1422/3000 [21:09<36:12, 1.38s/it, lr: 1.0e-04 loss: 3.812e-01] my_first_lora_v1: 47%|####7 | 1422/3000 [21:09<36:12, 1.38s/it, lr: 1.0e-04 loss: 3.812e-01] my_first_lora_v1: 47%|####7 | 1423/3000 [21:10<36:09, 1.38s/it, lr: 1.0e-04 loss: 7.437e-01] my_first_lora_v1: 47%|####7 | 1423/3000 [21:10<36:09, 1.38s/it, lr: 1.0e-04 loss: 7.437e-01] my_first_lora_v1: 47%|####7 | 1424/3000 [21:11<36:08, 1.38s/it, lr: 1.0e-04 loss: 7.622e-02] my_first_lora_v1: 47%|####7 | 1424/3000 [21:11<36:08, 1.38s/it, lr: 1.0e-04 loss: 7.622e-02] my_first_lora_v1: 48%|####7 | 1425/3000 [21:12<36:06, 1.38s/it, lr: 1.0e-04 loss: 5.685e-01] my_first_lora_v1: 48%|####7 | 1425/3000 [21:12<36:06, 1.38s/it, lr: 1.0e-04 loss: 5.685e-01] my_first_lora_v1: 48%|####7 | 1426/3000 [21:13<36:04, 1.38s/it, lr: 1.0e-04 loss: 2.620e-01] my_first_lora_v1: 48%|####7 | 1426/3000 [21:13<36:04, 1.38s/it, lr: 1.0e-04 loss: 2.620e-01] my_first_lora_v1: 48%|####7 | 1427/3000 [21:14<36:03, 1.38s/it, lr: 1.0e-04 loss: 2.841e-01] my_first_lora_v1: 48%|####7 | 1427/3000 [21:14<36:03, 1.38s/it, lr: 1.0e-04 loss: 2.841e-01] my_first_lora_v1: 48%|####7 | 1428/3000 [21:15<36:00, 1.37s/it, lr: 1.0e-04 loss: 1.562e-01] my_first_lora_v1: 48%|####7 | 1428/3000 [21:15<36:00, 1.37s/it, lr: 1.0e-04 loss: 1.562e-01] my_first_lora_v1: 48%|####7 | 1429/3000 [21:18<36:01, 1.38s/it, lr: 1.0e-04 loss: 2.350e-01] my_first_lora_v1: 48%|####7 | 1429/3000 [21:18<36:01, 1.38s/it, lr: 1.0e-04 loss: 2.350e-01] my_first_lora_v1: 48%|####7 | 1430/3000 [21:19<35:59, 1.38s/it, lr: 1.0e-04 loss: 7.147e-01] my_first_lora_v1: 48%|####7 | 1430/3000 [21:19<35:59, 1.38s/it, lr: 1.0e-04 loss: 7.147e-01] my_first_lora_v1: 48%|####7 | 1431/3000 [21:20<35:57, 1.37s/it, lr: 1.0e-04 loss: 2.000e-01] my_first_lora_v1: 48%|####7 | 1431/3000 [21:20<35:57, 1.37s/it, lr: 1.0e-04 loss: 2.000e-01] my_first_lora_v1: 48%|####7 | 1432/3000 [21:20<35:54, 1.37s/it, lr: 1.0e-04 loss: 3.348e-01] my_first_lora_v1: 48%|####7 | 1432/3000 [21:20<35:54, 1.37s/it, lr: 1.0e-04 loss: 3.348e-01] my_first_lora_v1: 48%|####7 | 1433/3000 [21:21<35:52, 1.37s/it, lr: 1.0e-04 loss: 6.991e-01] my_first_lora_v1: 48%|####7 | 1433/3000 [21:21<35:52, 1.37s/it, lr: 1.0e-04 loss: 6.991e-01] my_first_lora_v1: 48%|####7 | 1434/3000 [21:23<35:51, 1.37s/it, lr: 1.0e-04 loss: 3.894e-01] my_first_lora_v1: 48%|####7 | 1434/3000 [21:23<35:51, 1.37s/it, lr: 1.0e-04 loss: 3.894e-01] my_first_lora_v1: 48%|####7 | 1435/3000 [21:24<35:49, 1.37s/it, lr: 1.0e-04 loss: 2.284e-01] my_first_lora_v1: 48%|####7 | 1435/3000 [21:24<35:49, 1.37s/it, lr: 1.0e-04 loss: 2.284e-01] my_first_lora_v1: 48%|####7 | 1436/3000 [21:24<35:46, 1.37s/it, lr: 1.0e-04 loss: 4.074e-01] my_first_lora_v1: 48%|####7 | 1436/3000 [21:24<35:46, 1.37s/it, lr: 1.0e-04 loss: 4.074e-01] my_first_lora_v1: 48%|####7 | 1437/3000 [21:25<35:44, 1.37s/it, lr: 1.0e-04 loss: 5.960e-01] my_first_lora_v1: 48%|####7 | 1437/3000 [21:25<35:44, 1.37s/it, lr: 1.0e-04 loss: 5.960e-01] my_first_lora_v1: 48%|####7 | 1438/3000 [21:26<35:42, 1.37s/it, lr: 1.0e-04 loss: 7.489e-02] my_first_lora_v1: 48%|####7 | 1438/3000 [21:26<35:42, 1.37s/it, lr: 1.0e-04 loss: 7.489e-02] my_first_lora_v1: 48%|####7 | 1439/3000 [21:27<35:40, 1.37s/it, lr: 1.0e-04 loss: 9.289e-01] my_first_lora_v1: 48%|####7 | 1439/3000 [21:27<35:40, 1.37s/it, lr: 1.0e-04 loss: 9.289e-01] my_first_lora_v1: 48%|####8 | 1440/3000 [21:29<35:39, 1.37s/it, lr: 1.0e-04 loss: 2.869e-01] my_first_lora_v1: 48%|####8 | 1440/3000 [21:29<35:39, 1.37s/it, lr: 1.0e-04 loss: 2.869e-01] my_first_lora_v1: 48%|####8 | 1441/3000 [21:30<35:38, 1.37s/it, lr: 1.0e-04 loss: 4.880e-01] my_first_lora_v1: 48%|####8 | 1441/3000 [21:30<35:38, 1.37s/it, lr: 1.0e-04 loss: 4.880e-01] my_first_lora_v1: 48%|####8 | 1442/3000 [21:31<35:36, 1.37s/it, lr: 1.0e-04 loss: 6.788e-01] my_first_lora_v1: 48%|####8 | 1442/3000 [21:31<35:36, 1.37s/it, lr: 1.0e-04 loss: 6.788e-01] my_first_lora_v1: 48%|####8 | 1443/3000 [21:32<35:34, 1.37s/it, lr: 1.0e-04 loss: 1.321e-01] my_first_lora_v1: 48%|####8 | 1443/3000 [21:32<35:34, 1.37s/it, lr: 1.0e-04 loss: 1.321e-01] my_first_lora_v1: 48%|####8 | 1444/3000 [21:33<35:32, 1.37s/it, lr: 1.0e-04 loss: 4.914e-01] my_first_lora_v1: 48%|####8 | 1444/3000 [21:33<35:32, 1.37s/it, lr: 1.0e-04 loss: 4.914e-01] my_first_lora_v1: 48%|####8 | 1445/3000 [21:34<35:30, 1.37s/it, lr: 1.0e-04 loss: 6.705e-01] my_first_lora_v1: 48%|####8 | 1445/3000 [21:34<35:30, 1.37s/it, lr: 1.0e-04 loss: 6.705e-01] my_first_lora_v1: 48%|####8 | 1446/3000 [21:35<35:28, 1.37s/it, lr: 1.0e-04 loss: 5.507e-01] my_first_lora_v1: 48%|####8 | 1446/3000 [21:35<35:28, 1.37s/it, lr: 1.0e-04 loss: 5.507e-01] my_first_lora_v1: 48%|####8 | 1447/3000 [21:37<35:27, 1.37s/it, lr: 1.0e-04 loss: 7.381e-02] my_first_lora_v1: 48%|####8 | 1447/3000 [21:37<35:27, 1.37s/it, lr: 1.0e-04 loss: 7.381e-02] my_first_lora_v1: 48%|####8 | 1448/3000 [21:38<35:25, 1.37s/it, lr: 1.0e-04 loss: 6.705e-01] my_first_lora_v1: 48%|####8 | 1448/3000 [21:38<35:25, 1.37s/it, lr: 1.0e-04 loss: 6.705e-01] my_first_lora_v1: 48%|####8 | 1449/3000 [21:38<35:22, 1.37s/it, lr: 1.0e-04 loss: 7.753e-01] my_first_lora_v1: 48%|####8 | 1449/3000 [21:38<35:22, 1.37s/it, lr: 1.0e-04 loss: 7.753e-01] my_first_lora_v1: 48%|####8 | 1450/3000 [21:39<35:20, 1.37s/it, lr: 1.0e-04 loss: 1.233e-01] my_first_lora_v1: 48%|####8 | 1450/3000 [21:39<35:20, 1.37s/it, lr: 1.0e-04 loss: 1.233e-01] my_first_lora_v1: 48%|####8 | 1451/3000 [21:42<35:21, 1.37s/it, lr: 1.0e-04 loss: 3.711e-01] my_first_lora_v1: 48%|####8 | 1451/3000 [21:42<35:21, 1.37s/it, lr: 1.0e-04 loss: 3.711e-01] my_first_lora_v1: 48%|####8 | 1452/3000 [21:45<35:22, 1.37s/it, lr: 1.0e-04 loss: 7.459e-01] my_first_lora_v1: 48%|####8 | 1452/3000 [21:45<35:22, 1.37s/it, lr: 1.0e-04 loss: 7.459e-01] my_first_lora_v1: 48%|####8 | 1453/3000 [21:46<35:21, 1.37s/it, lr: 1.0e-04 loss: 5.653e-01] my_first_lora_v1: 48%|####8 | 1453/3000 [21:46<35:21, 1.37s/it, lr: 1.0e-04 loss: 5.653e-01] my_first_lora_v1: 48%|####8 | 1454/3000 [21:47<35:18, 1.37s/it, lr: 1.0e-04 loss: 7.045e-01] my_first_lora_v1: 48%|####8 | 1454/3000 [21:47<35:18, 1.37s/it, lr: 1.0e-04 loss: 7.045e-01] my_first_lora_v1: 48%|####8 | 1455/3000 [21:48<35:16, 1.37s/it, lr: 1.0e-04 loss: 3.860e-01] my_first_lora_v1: 48%|####8 | 1455/3000 [21:48<35:16, 1.37s/it, lr: 1.0e-04 loss: 3.860e-01] my_first_lora_v1: 49%|####8 | 1456/3000 [21:49<35:15, 1.37s/it, lr: 1.0e-04 loss: 3.826e-01] my_first_lora_v1: 49%|####8 | 1456/3000 [21:49<35:15, 1.37s/it, lr: 1.0e-04 loss: 3.826e-01] my_first_lora_v1: 49%|####8 | 1457/3000 [21:50<35:13, 1.37s/it, lr: 1.0e-04 loss: 1.741e-01] my_first_lora_v1: 49%|####8 | 1457/3000 [21:50<35:13, 1.37s/it, lr: 1.0e-04 loss: 1.741e-01] my_first_lora_v1: 49%|####8 | 1458/3000 [21:52<35:12, 1.37s/it, lr: 1.0e-04 loss: 1.596e-01] my_first_lora_v1: 49%|####8 | 1458/3000 [21:52<35:12, 1.37s/it, lr: 1.0e-04 loss: 1.596e-01] my_first_lora_v1: 49%|####8 | 1459/3000 [21:54<35:12, 1.37s/it, lr: 1.0e-04 loss: 5.785e-02] my_first_lora_v1: 49%|####8 | 1459/3000 [21:54<35:12, 1.37s/it, lr: 1.0e-04 loss: 5.785e-02] my_first_lora_v1: 49%|####8 | 1460/3000 [21:56<35:11, 1.37s/it, lr: 1.0e-04 loss: 3.971e-02] my_first_lora_v1: 49%|####8 | 1460/3000 [21:56<35:11, 1.37s/it, lr: 1.0e-04 loss: 3.971e-02] my_first_lora_v1: 49%|####8 | 1461/3000 [21:56<35:09, 1.37s/it, lr: 1.0e-04 loss: 1.054e-01] my_first_lora_v1: 49%|####8 | 1461/3000 [21:56<35:09, 1.37s/it, lr: 1.0e-04 loss: 1.054e-01] my_first_lora_v1: 49%|####8 | 1462/3000 [21:58<35:07, 1.37s/it, lr: 1.0e-04 loss: 5.343e-01] my_first_lora_v1: 49%|####8 | 1462/3000 [21:58<35:07, 1.37s/it, lr: 1.0e-04 loss: 5.343e-01] my_first_lora_v1: 49%|####8 | 1463/3000 [21:59<35:05, 1.37s/it, lr: 1.0e-04 loss: 4.388e-01] my_first_lora_v1: 49%|####8 | 1463/3000 [21:59<35:05, 1.37s/it, lr: 1.0e-04 loss: 4.388e-01] my_first_lora_v1: 49%|####8 | 1464/3000 [22:00<35:03, 1.37s/it, lr: 1.0e-04 loss: 5.831e-01] my_first_lora_v1: 49%|####8 | 1464/3000 [22:00<35:03, 1.37s/it, lr: 1.0e-04 loss: 5.831e-01] my_first_lora_v1: 49%|####8 | 1465/3000 [22:01<35:02, 1.37s/it, lr: 1.0e-04 loss: 7.314e-01] my_first_lora_v1: 49%|####8 | 1465/3000 [22:01<35:02, 1.37s/it, lr: 1.0e-04 loss: 7.314e-01] my_first_lora_v1: 49%|####8 | 1466/3000 [22:03<35:01, 1.37s/it, lr: 1.0e-04 loss: 4.618e-01] my_first_lora_v1: 49%|####8 | 1466/3000 [22:03<35:01, 1.37s/it, lr: 1.0e-04 loss: 4.618e-01] my_first_lora_v1: 49%|####8 | 1467/3000 [22:04<34:59, 1.37s/it, lr: 1.0e-04 loss: 2.076e-01] my_first_lora_v1: 49%|####8 | 1467/3000 [22:04<34:59, 1.37s/it, lr: 1.0e-04 loss: 2.076e-01] my_first_lora_v1: 49%|####8 | 1468/3000 [22:05<34:57, 1.37s/it, lr: 1.0e-04 loss: 6.245e-01] my_first_lora_v1: 49%|####8 | 1468/3000 [22:05<34:57, 1.37s/it, lr: 1.0e-04 loss: 6.245e-01] my_first_lora_v1: 49%|####8 | 1469/3000 [22:06<34:55, 1.37s/it, lr: 1.0e-04 loss: 1.418e-01] my_first_lora_v1: 49%|####8 | 1469/3000 [22:06<34:55, 1.37s/it, lr: 1.0e-04 loss: 1.418e-01] my_first_lora_v1: 49%|####9 | 1470/3000 [22:06<34:53, 1.37s/it, lr: 1.0e-04 loss: 5.311e-01] my_first_lora_v1: 49%|####9 | 1470/3000 [22:06<34:53, 1.37s/it, lr: 1.0e-04 loss: 5.311e-01] my_first_lora_v1: 49%|####9 | 1471/3000 [22:07<34:50, 1.37s/it, lr: 1.0e-04 loss: 1.261e-01] my_first_lora_v1: 49%|####9 | 1471/3000 [22:07<34:50, 1.37s/it, lr: 1.0e-04 loss: 1.261e-01] my_first_lora_v1: 49%|####9 | 1472/3000 [22:08<34:48, 1.37s/it, lr: 1.0e-04 loss: 3.205e-01] my_first_lora_v1: 49%|####9 | 1472/3000 [22:08<34:48, 1.37s/it, lr: 1.0e-04 loss: 3.205e-01] my_first_lora_v1: 49%|####9 | 1473/3000 [22:09<34:46, 1.37s/it, lr: 1.0e-04 loss: 3.295e-01] my_first_lora_v1: 49%|####9 | 1473/3000 [22:09<34:46, 1.37s/it, lr: 1.0e-04 loss: 3.295e-01] my_first_lora_v1: 49%|####9 | 1474/3000 [22:11<34:45, 1.37s/it, lr: 1.0e-04 loss: 2.444e-01] my_first_lora_v1: 49%|####9 | 1474/3000 [22:11<34:45, 1.37s/it, lr: 1.0e-04 loss: 2.444e-01] my_first_lora_v1: 49%|####9 | 1475/3000 [22:12<34:44, 1.37s/it, lr: 1.0e-04 loss: 3.121e-01] my_first_lora_v1: 49%|####9 | 1475/3000 [22:12<34:44, 1.37s/it, lr: 1.0e-04 loss: 3.121e-01] my_first_lora_v1: 49%|####9 | 1476/3000 [22:14<34:44, 1.37s/it, lr: 1.0e-04 loss: 6.963e-01] my_first_lora_v1: 49%|####9 | 1476/3000 [22:14<34:44, 1.37s/it, lr: 1.0e-04 loss: 6.963e-01] my_first_lora_v1: 49%|####9 | 1477/3000 [22:16<34:42, 1.37s/it, lr: 1.0e-04 loss: 5.540e-01] my_first_lora_v1: 49%|####9 | 1477/3000 [22:16<34:42, 1.37s/it, lr: 1.0e-04 loss: 5.540e-01] my_first_lora_v1: 49%|####9 | 1478/3000 [22:17<34:42, 1.37s/it, lr: 1.0e-04 loss: 4.985e-01] my_first_lora_v1: 49%|####9 | 1478/3000 [22:17<34:42, 1.37s/it, lr: 1.0e-04 loss: 4.985e-01] my_first_lora_v1: 49%|####9 | 1479/3000 [22:18<34:40, 1.37s/it, lr: 1.0e-04 loss: 5.057e-01] my_first_lora_v1: 49%|####9 | 1479/3000 [22:18<34:40, 1.37s/it, lr: 1.0e-04 loss: 5.057e-01] my_first_lora_v1: 49%|####9 | 1480/3000 [22:19<34:37, 1.37s/it, lr: 1.0e-04 loss: 6.623e-01] my_first_lora_v1: 49%|####9 | 1480/3000 [22:19<34:37, 1.37s/it, lr: 1.0e-04 loss: 6.623e-01] my_first_lora_v1: 49%|####9 | 1481/3000 [22:21<34:36, 1.37s/it, lr: 1.0e-04 loss: 5.157e-01] my_first_lora_v1: 49%|####9 | 1481/3000 [22:21<34:36, 1.37s/it, lr: 1.0e-04 loss: 5.157e-01] my_first_lora_v1: 49%|####9 | 1482/3000 [22:22<34:36, 1.37s/it, lr: 1.0e-04 loss: 2.039e-01] my_first_lora_v1: 49%|####9 | 1482/3000 [22:22<34:36, 1.37s/it, lr: 1.0e-04 loss: 2.039e-01] my_first_lora_v1: 49%|####9 | 1483/3000 [22:23<34:33, 1.37s/it, lr: 1.0e-04 loss: 6.831e-02] my_first_lora_v1: 49%|####9 | 1483/3000 [22:23<34:33, 1.37s/it, lr: 1.0e-04 loss: 6.831e-02] my_first_lora_v1: 49%|####9 | 1484/3000 [22:24<34:32, 1.37s/it, lr: 1.0e-04 loss: 2.641e-01] my_first_lora_v1: 49%|####9 | 1484/3000 [22:24<34:32, 1.37s/it, lr: 1.0e-04 loss: 2.641e-01] my_first_lora_v1: 50%|####9 | 1485/3000 [22:27<34:33, 1.37s/it, lr: 1.0e-04 loss: 4.526e-01] my_first_lora_v1: 50%|####9 | 1485/3000 [22:27<34:33, 1.37s/it, lr: 1.0e-04 loss: 4.526e-01] my_first_lora_v1: 50%|####9 | 1486/3000 [22:28<34:30, 1.37s/it, lr: 1.0e-04 loss: 8.409e-02] my_first_lora_v1: 50%|####9 | 1486/3000 [22:28<34:30, 1.37s/it, lr: 1.0e-04 loss: 8.409e-02] my_first_lora_v1: 50%|####9 | 1487/3000 [22:31<34:31, 1.37s/it, lr: 1.0e-04 loss: 1.373e-01] my_first_lora_v1: 50%|####9 | 1487/3000 [22:31<34:31, 1.37s/it, lr: 1.0e-04 loss: 1.373e-01] my_first_lora_v1: 50%|####9 | 1488/3000 [22:32<34:29, 1.37s/it, lr: 1.0e-04 loss: 8.173e-01] my_first_lora_v1: 50%|####9 | 1488/3000 [22:32<34:29, 1.37s/it, lr: 1.0e-04 loss: 8.173e-01] my_first_lora_v1: 50%|####9 | 1489/3000 [22:33<34:28, 1.37s/it, lr: 1.0e-04 loss: 1.191e-01] my_first_lora_v1: 50%|####9 | 1489/3000 [22:33<34:28, 1.37s/it, lr: 1.0e-04 loss: 1.191e-01] my_first_lora_v1: 50%|####9 | 1490/3000 [22:34<34:26, 1.37s/it, lr: 1.0e-04 loss: 3.415e-01] my_first_lora_v1: 50%|####9 | 1490/3000 [22:34<34:26, 1.37s/it, lr: 1.0e-04 loss: 3.415e-01] my_first_lora_v1: 50%|####9 | 1491/3000 [22:36<34:25, 1.37s/it, lr: 1.0e-04 loss: 7.931e-01] my_first_lora_v1: 50%|####9 | 1491/3000 [22:36<34:25, 1.37s/it, lr: 1.0e-04 loss: 7.931e-01] my_first_lora_v1: 50%|####9 | 1492/3000 [22:39<34:25, 1.37s/it, lr: 1.0e-04 loss: 6.485e-02] my_first_lora_v1: 50%|####9 | 1492/3000 [22:39<34:25, 1.37s/it, lr: 1.0e-04 loss: 6.485e-02] my_first_lora_v1: 50%|####9 | 1493/3000 [22:39<34:23, 1.37s/it, lr: 1.0e-04 loss: 2.209e-01] my_first_lora_v1: 50%|####9 | 1493/3000 [22:39<34:23, 1.37s/it, lr: 1.0e-04 loss: 2.209e-01] my_first_lora_v1: 50%|####9 | 1494/3000 [22:41<34:22, 1.37s/it, lr: 1.0e-04 loss: 6.166e-01] my_first_lora_v1: 50%|####9 | 1494/3000 [22:41<34:22, 1.37s/it, lr: 1.0e-04 loss: 6.166e-01] my_first_lora_v1: 50%|####9 | 1495/3000 [22:42<34:21, 1.37s/it, lr: 1.0e-04 loss: 2.655e-01] my_first_lora_v1: 50%|####9 | 1495/3000 [22:42<34:21, 1.37s/it, lr: 1.0e-04 loss: 2.655e-01] my_first_lora_v1: 50%|####9 | 1496/3000 [22:44<34:19, 1.37s/it, lr: 1.0e-04 loss: 7.797e-01] my_first_lora_v1: 50%|####9 | 1496/3000 [22:44<34:19, 1.37s/it, lr: 1.0e-04 loss: 7.797e-01] my_first_lora_v1: 50%|####9 | 1497/3000 [22:46<34:20, 1.37s/it, lr: 1.0e-04 loss: 2.526e-01] my_first_lora_v1: 50%|####9 | 1497/3000 [22:46<34:20, 1.37s/it, lr: 1.0e-04 loss: 2.526e-01] my_first_lora_v1: 50%|####9 | 1498/3000 [22:47<34:18, 1.37s/it, lr: 1.0e-04 loss: 7.837e-01] my_first_lora_v1: 50%|####9 | 1498/3000 [22:47<34:18, 1.37s/it, lr: 1.0e-04 loss: 7.837e-01] my_first_lora_v1: 50%|####9 | 1499/3000 [22:50<34:18, 1.37s/it, lr: 1.0e-04 loss: 1.359e-01] my_first_lora_v1: 50%|####9 | 1499/3000 [22:50<34:18, 1.37s/it, lr: 1.0e-04 loss: 1.359e-01]
Saving at step 1500
Saved checkpoint to /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v1/my_first_lora_v1_000001500.safetensors
Saved optimizer to /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v1/optimizer.pt
Removing old save: /teamspace/studios/this_studio/ai-toolkit/output/my_first_lora_v1/my_first_lora_v1_000000500.safetensors
Unloading assistant lora
Generating Images: 0%| | 0/5 [00:00<?, ?it/s] Generating Images: 0%| | 0/5 [00:00<?, ?it/s]
Generating Images: 20%|## | 1/5 [00:07<00:30, 7.60s/it] Generating Images: 20%|## | 1/5 [00:07<00:30, 7.60s/it]
Generating Images: 40%|#### | 2/5 [00:15<00:22, 7.57s/it] Generating Images: 40%|#### | 2/5 [00:15<00:22, 7.57s/it]
Generating Images: 60%|###### | 3/5 [00:22<00:15, 7.66s/it] Generating Images: 60%|###### | 3/5 [00:22<00:15, 7.66s/it]
Generating Images: 80%|######## | 4/5 [00:30<00:07, 7.62s/it] Generating Images: 80%|######## | 4/5 [00:30<00:07, 7.62s/it]
Generating Images: 100%|##########| 5/5 [00:38<00:00, 7.84s/it] Generating Images: 100%|##########| 5/5 [00:38<00:00, 7.84s/it]
Loading assistant lora
my_first_lora_v1: 50%|##### | 1500/3000 [22:51<34:17, 1.37s/it, lr: 1.0e-04 loss: 1.894e-01] my_first_lora_v1: 50%|##### | 1500/3000 [22:51<34:17, 1.37s/it, lr: 1.0e-04 loss: 1.894e-01] my_first_lora_v1: 50%|##### | 1501/3000 [22:52<34:15, 1.37s/it, lr: 1.0e-04 loss: 6.234e-01] my_first_lora_v1: 50%|##### | 1501/3000 [22:52<34:15, 1.37s/it, lr: 1.0e-04 loss: 6.234e-01] my_first_lora_v1: 50%|##### | 1502/3000 [22:53<34:12, 1.37s/it, lr: 1.0e-04 loss: 1.957e-01] my_first_lora_v1: 50%|##### | 1502/3000 [22:53<34:12, 1.37s/it, lr: 1.0e-04 loss: 1.957e-01] my_first_lora_v1: 50%|##### | 1503/3000 [22:53<34:10, 1.37s/it, lr: 1.0e-04 loss: 3.647e-01] my_first_lora_v1: 50%|##### | 1503/3000 [22:53<34:10, 1.37s/it, lr: 1.0e-04 loss: 3.647e-01] my_first_lora_v1: 50%|##### | 1504/3000 [22:55<34:09, 1.37s/it, lr: 1.0e-04 loss: 6.984e-01] my_first_lora_v1: 50%|##### | 1504/3000 [22:55<34:09, 1.37s/it, lr: 1.0e-04 loss: 6.984e-01] my_first_lora_v1: 50%|##### | 1505/3000 [22:56<34:07, 1.37s/it, lr: 1.0e-04 loss: 3.091e-01] my_first_lora_v1: 50%|##### | 1505/3000 [22:56<34:07, 1.37s/it, lr: 1.0e-04 loss: 3.091e-01] my_first_lora_v1: 50%|##### | 1506/3000 [22:57<34:06, 1.37s/it, lr: 1.0e-04 loss: 3.012e-01] my_first_lora_v1: 50%|##### | 1506/3000 [22:57<34:06, 1.37s/it, lr: 1.0e-04 loss: 3.012e-01] my_first_lora_v1: 50%|##### | 1507/3000 [22:58<34:03, 1.37s/it, lr: 1.0e-04 loss: 5.505e-01] my_first_lora_v1: 50%|##### | 1507/3000 [22:58<34:03, 1.37s/it, lr: 1.0e-04 loss: 5.505e-01] my_first_lora_v1: 50%|##### | 1508/3000 [22:59<34:02, 1.37s/it, lr: 1.0e-04 loss: 6.647e-01] my_first_lora_v1: 50%|##### | 1508/3000 [22:59<34:02, 1.37s/it, lr: 1.0e-04 loss: 6.647e-01] my_first_lora_v1: 50%|##### | 1509/3000 [23:00<34:00, 1.37s/it, lr: 1.0e-04 loss: 3.354e-01] my_first_lora_v1: 50%|##### | 1509/3000 [23:00<34:00, 1.37s/it, lr: 1.0e-04 loss: 3.354e-01] my_first_lora_v1: 50%|##### | 1510/3000 [23:01<33:57, 1.37s/it, lr: 1.0e-04 loss: 3.887e-01] my_first_lora_v1: 50%|##### | 1510/3000 [23:01<33:57, 1.37s/it, lr: 1.0e-04 loss: 3.887e-01] my_first_lora_v1: 50%|##### | 1511/3000 [23:02<33:56, 1.37s/it, lr: 1.0e-04 loss: 1.341e-01] my_first_lora_v1: 50%|##### | 1511/3000 [23:02<33:56, 1.37s/it, lr: 1.0e-04 loss: 1.341e-01] my_first_lora_v1: 50%|##### | 1512/3000 [23:03<33:54, 1.37s/it, lr: 1.0e-04 loss: 5.167e-01] my_first_lora_v1: 50%|##### | 1512/3000 [23:03<33:54, 1.37s/it, lr: 1.0e-04 loss: 5.167e-01] my_first_lora_v1: 50%|##### | 1513/3000 [23:05<33:53, 1.37s/it, lr: 1.0e-04 loss: 6.445e-01] my_first_lora_v1: 50%|##### | 1513/3000 [23:05<33:53, 1.37s/it, lr: 1.0e-04 loss: 6.445e-01] my_first_lora_v1: 50%|##### | 1514/3000 [23:06<33:52, 1.37s/it, lr: 1.0e-04 loss: 3.242e-01] my_first_lora_v1: 50%|##### | 1514/3000 [23:06<33:52, 1.37s/it, lr: 1.0e-04 loss: 3.242e-01] my_first_lora_v1: 50%|##### | 1515/3000 [23:08<33:50, 1.37s/it, lr: 1.0e-04 loss: 8.191e-01] my_first_lora_v1: 50%|##### | 1515/3000 [23:08<33:50, 1.37s/it, lr: 1.0e-04 loss: 8.191e-01] my_first_lora_v1: 51%|##### | 1516/3000 [23:09<33:49, 1.37s/it, lr: 1.0e-04 loss: 3.694e-01] my_first_lora_v1: 51%|##### | 1516/3000 [23:09<33:49, 1.37s/it, lr: 1.0e-04 loss: 3.694e-01] my_first_lora_v1: 51%|##### | 1517/3000 [23:10<33:47, 1.37s/it, lr: 1.0e-04 loss: 4.301e-01] my_first_lora_v1: 51%|##### | 1517/3000 [23:10<33:47, 1.37s/it, lr: 1.0e-04 loss: 4.301e-01] my_first_lora_v1: 51%|##### | 1518/3000 [23:11<33:46, 1.37s/it, lr: 1.0e-04 loss: 5.555e-01] my_first_lora_v1: 51%|##### | 1518/3000 [23:11<33:46, 1.37s/it, lr: 1.0e-04 loss: 5.555e-01] my_first_lora_v1: 51%|##### | 1519/3000 [23:14<33:46, 1.37s/it, lr: 1.0e-04 loss: 3.421e-01] my_first_lora_v1: 51%|##### | 1519/3000 [23:14<33:46, 1.37s/it, lr: 1.0e-04 loss: 3.421e-01] my_first_lora_v1: 51%|##### | 1520/3000 [23:15<33:45, 1.37s/it, lr: 1.0e-04 loss: 6.401e-01] my_first_lora_v1: 51%|##### | 1520/3000 [23:15<33:45, 1.37s/it, lr: 1.0e-04 loss: 6.401e-01] my_first_lora_v1: 51%|##### | 1521/3000 [23:17<33:43, 1.37s/it, lr: 1.0e-04 loss: 1.683e-01] my_first_lora_v1: 51%|##### | 1521/3000 [23:17<33:43, 1.37s/it, lr: 1.0e-04 loss: 1.683e-01] my_first_lora_v1: 51%|##### | 1522/3000 [23:17<33:41, 1.37s/it, lr: 1.0e-04 loss: 3.717e-01] my_first_lora_v1: 51%|##### | 1522/3000 [23:17<33:41, 1.37s/it, lr: 1.0e-04 loss: 3.717e-01] my_first_lora_v1: 51%|##### | 1523/3000 [23:18<33:39, 1.37s/it, lr: 1.0e-04 loss: 3.241e-01] my_first_lora_v1: 51%|##### | 1523/3000 [23:18<33:39, 1.37s/it, lr: 1.0e-04 loss: 3.241e-01] my_first_lora_v1: 51%|##### | 1524/3000 [23:20<33:38, 1.37s/it, lr: 1.0e-04 loss: 3.873e-01] my_first_lora_v1: 51%|##### | 1524/3000 [23:20<33:38, 1.37s/it, lr: 1.0e-04 loss: 3.873e-01] my_first_lora_v1: 51%|##### | 1525/3000 [23:21<33:36, 1.37s/it, lr: 1.0e-04 loss: 7.185e-01] my_first_lora_v1: 51%|##### | 1525/3000 [23:21<33:36, 1.37s/it, lr: 1.0e-04 loss: 7.185e-01] my_first_lora_v1: 51%|##### | 1526/3000 [23:23<33:35, 1.37s/it, lr: 1.0e-04 loss: 6.919e-01] my_first_lora_v1: 51%|##### | 1526/3000 [23:23<33:35, 1.37s/it, lr: 1.0e-04 loss: 6.919e-01] my_first_lora_v1: 51%|##### | 1527/3000 [23:24<33:33, 1.37s/it, lr: 1.0e-04 loss: 6.898e-01] my_first_lora_v1: 51%|##### | 1527/3000 [23:24<33:33, 1.37s/it, lr: 1.0e-04 loss: 6.898e-01] my_first_lora_v1: 51%|##### | 1528/3000 [23:27<33:34, 1.37s/it, lr: 1.0e-04 loss: 2.459e-01] my_first_lora_v1: 51%|##### | 1528/3000 [23:27<33:34, 1.37s/it, lr: 1.0e-04 loss: 2.459e-01] my_first_lora_v1: 51%|##### | 1529/3000 [23:28<33:32, 1.37s/it, lr: 1.0e-04 loss: 1.769e-01] my_first_lora_v1: 51%|##### | 1529/3000 [23:28<33:32, 1.37s/it, lr: 1.0e-04 loss: 1.769e-01] my_first_lora_v1: 51%|#####1 | 1530/3000 [23:29<33:31, 1.37s/it, lr: 1.0e-04 loss: 1.962e-01] my_first_lora_v1: 51%|#####1 | 1530/3000 [23:29<33:31, 1.37s/it, lr: 1.0e-04 loss: 1.962e-01] my_first_lora_v1: 51%|#####1 | 1531/3000 [23:31<33:31, 1.37s/it, lr: 1.0e-04 loss: 6.755e-01] my_first_lora_v1: 51%|#####1 | 1531/3000 [23:31<33:31, 1.37s/it, lr: 1.0e-04 loss: 6.755e-01] my_first_lora_v1: 51%|#####1 | 1532/3000 [23:33<33:30, 1.37s/it, lr: 1.0e-04 loss: 6.149e-01] my_first_lora_v1: 51%|#####1 | 1532/3000 [23:33<33:30, 1.37s/it, lr: 1.0e-04 loss: 6.149e-01] my_first_lora_v1: 51%|#####1 | 1533/3000 [23:34<33:29, 1.37s/it, lr: 1.0e-04 loss: 6.073e-01] my_first_lora_v1: 51%|#####1 | 1533/3000 [23:34<33:29, 1.37s/it, lr: 1.0e-04 loss: 6.073e-01] my_first_lora_v1: 51%|#####1 | 1534/3000 [23:37<33:29, 1.37s/it, lr: 1.0e-04 loss: 1.656e-01] my_first_lora_v1: 51%|#####1 | 1534/3000 [23:37<33:29, 1.37s/it, lr: 1.0e-04 loss: 1.656e-01] my_first_lora_v1: 51%|#####1 | 1535/3000 [23:38<33:28, 1.37s/it, lr: 1.0e-04 loss: 3.432e-01] my_first_lora_v1: 51%|#####1 | 1535/3000 [23:38<33:28, 1.37s/it, lr: 1.0e-04 loss: 3.432e-01] my_first_lora_v1: 51%|#####1 | 1536/3000 [23:40<33:26, 1.37s/it, lr: 1.0e-04 loss: 3.913e-01] my_first_lora_v1: 51%|#####1 | 1536/3000 [23:40<33:26, 1.37s/it, lr: 1.0e-04 loss: 3.913e-01] my_first_lora_v1: 51%|#####1 | 1537/3000 [23:40<33:24, 1.37s/it, lr: 1.0e-04 loss: 6.479e-01] my_first_lora_v1: 51%|#####1 | 1537/3000 [23:40<33:24, 1.37s/it, lr: 1.0e-04 loss: 6.479e-01] my_first_lora_v1: 51%|#####1 | 1538/3000 [23:41<33:22, 1.37s/it, lr: 1.0e-04 loss: 5.159e-01] my_first_lora_v1: 51%|#####1 | 1538/3000 [23:41<33:22, 1.37s/it, lr: 1.0e-04 loss: 5.159e-01] my_first_lora_v1: 51%|#####1 | 1539/3000 [23:43<33:21, 1.37s/it, lr: 1.0e-04 loss: 7.125e-01] my_first_lora_v1: 51%|#####1 | 1539/3000 [23:43<33:21, 1.37s/it, lr: 1.0e-04 loss: 7.125e-01] my_first_lora_v1: 51%|#####1 | 1540/3000 [23:44<33:19, 1.37s/it, lr: 1.0e-04 loss: 2.597e-01] my_first_lora_v1: 51%|#####1 | 1540/3000 [23:44<33:19, 1.37s/it, lr: 1.0e-04 loss: 2.597e-01] my_first_lora_v1: 51%|#####1 | 1541/3000 [23:47<33:20, 1.37s/it, lr: 1.0e-04 loss: 9.476e-01] my_first_lora_v1: 51%|#####1 | 1541/3000 [23:47<33:20, 1.37s/it, lr: 1.0e-04 loss: 9.476e-01] my_first_lora_v1: 51%|#####1 | 1542/3000 [23:48<33:18, 1.37s/it, lr: 1.0e-04 loss: 6.179e-01] my_first_lora_v1: 51%|#####1 | 1542/3000 [23:48<33:18, 1.37s/it, lr: 1.0e-04 loss: 6.179e-01] my_first_lora_v1: 51%|#####1 | 1543/3000 [23:50<33:18, 1.37s/it, lr: 1.0e-04 loss: 3.842e-01] my_first_lora_v1: 51%|#####1 | 1543/3000 [23:50<33:18, 1.37s/it, lr: 1.0e-04 loss: 3.842e-01] my_first_lora_v1: 51%|#####1 | 1544/3000 [23:51<33:16, 1.37s/it, lr: 1.0e-04 loss: 8.497e-01] my_first_lora_v1: 51%|#####1 | 1544/3000 [23:51<33:16, 1.37s/it, lr: 1.0e-04 loss: 8.497e-01] my_first_lora_v1: 52%|#####1 | 1545/3000 [23:52<33:14, 1.37s/it, lr: 1.0e-04 loss: 6.706e-01] my_first_lora_v1: 52%|#####1 | 1545/3000 [23:52<33:14, 1.37s/it, lr: 1.0e-04 loss: 6.706e-01] my_first_lora_v1: 52%|#####1 | 1546/3000 [23:55<33:15, 1.37s/it, lr: 1.0e-04 loss: 3.954e-01] my_first_lora_v1: 52%|#####1 | 1546/3000 [23:55<33:15, 1.37s/it, lr: 1.0e-04 loss: 3.954e-01] my_first_lora_v1: 52%|#####1 | 1547/3000 [23:57<33:15, 1.37s/it, lr: 1.0e-04 loss: 7.281e-01] my_first_lora_v1: 52%|#####1 | 1547/3000 [23:57<33:15, 1.37s/it, lr: 1.0e-04 loss: 7.281e-01] my_first_lora_v1: 52%|#####1 | 1548/3000 [23:58<33:13, 1.37s/it, lr: 1.0e-04 loss: 7.181e-02] my_first_lora_v1: 52%|#####1 | 1548/3000 [23:58<33:13, 1.37s/it, lr: 1.0e-04 loss: 7.181e-02] my_first_lora_v1: 52%|#####1 | 1549/3000 [24:00<33:13, 1.37s/it, lr: 1.0e-04 loss: 6.121e-01] my_first_lora_v1: 52%|#####1 | 1549/3000 [24:00<33:13, 1.37s/it, lr: 1.0e-04 loss: 6.121e-01] my_first_lora_v1: 52%|#####1 | 1550/3000 [24:02<33:11, 1.37s/it, lr: 1.0e-04 loss: 8.242e-01] my_first_lora_v1: 52%|#####1 | 1550/3000 [24:02<33:11, 1.37s/it, lr: 1.0e-04 loss: 8.242e-01] my_first_lora_v1: 52%|#####1 | 1551/3000 [24:03<33:10, 1.37s/it, lr: 1.0e-04 loss: 1.321e-01] my_first_lora_v1: 52%|#####1 | 1551/3000 [24:03<33:10, 1.37s/it, lr: 1.0e-04 loss: 1.321e-01] my_first_lora_v1: 52%|#####1 | 1552/3000 [24:05<33:08, 1.37s/it, lr: 1.0e-04 loss: 3.841e-01] my_first_lora_v1: 52%|#####1 | 1552/3000 [24:05<33:08, 1.37s/it, lr: 1.0e-04 loss: 3.841e-01] my_first_lora_v1: 52%|#####1 | 1553/3000 [24:06<33:08, 1.37s/it, lr: 1.0e-04 loss: 4.759e-01] my_first_lora_v1: 52%|#####1 | 1553/3000 [24:06<33:08, 1.37s/it, lr: 1.0e-04 loss: 4.759e-01] my_first_lora_v1: 52%|#####1 | 1554/3000 [24:07<33:06, 1.37s/it, lr: 1.0e-04 loss: 7.439e-01] my_first_lora_v1: 52%|#####1 | 1554/3000 [24:07<33:06, 1.37s/it, lr: 1.0e-04 loss: 7.439e-01] my_first_lora_v1: 52%|#####1 | 1555/3000 [24:08<33:04, 1.37s/it, lr: 1.0e-04 loss: 2.892e-01] my_first_lora_v1: 52%|#####1 | 1555/3000 [24:08<33:04, 1.37s/it, lr: 1.0e-04 loss: 2.892e-01] my_first_lora_v1: 52%|#####1 | 1556/3000 [24:10<33:02, 1.37s/it, lr: 1.0e-04 loss: 5.147e-01] my_first_lora_v1: 52%|#####1 | 1556/3000 [24:10<33:02, 1.37s/it, lr: 1.0e-04 loss: 5.147e-01] my_first_lora_v1: 52%|#####1 | 1557/3000 [24:12<33:02, 1.37s/it, lr: 1.0e-04 loss: 6.499e-01] my_first_lora_v1: 52%|#####1 | 1557/3000 [24:12<33:02, 1.37s/it, lr: 1.0e-04 loss: 6.499e-01] my_first_lora_v1: 52%|#####1 | 1558/3000 [24:13<33:00, 1.37s/it, lr: 1.0e-04 loss: 3.058e-01] my_first_lora_v1: 52%|#####1 | 1558/3000 [24:13<33:00, 1.37s/it, lr: 1.0e-04 loss: 3.058e-01] my_first_lora_v1: 52%|#####1 | 1559/3000 [24:14<32:59, 1.37s/it, lr: 1.0e-04 loss: 3.045e-01] my_first_lora_v1: 52%|#####1 | 1559/3000 [24:14<32:59, 1.37s/it, lr: 1.0e-04 loss: 3.045e-01] my_first_lora_v1: 52%|#####2 | 1560/3000 [24:15<32:57, 1.37s/it, lr: 1.0e-04 loss: 6.626e-01] my_first_lora_v1: 52%|#####2 | 1560/3000 [24:15<32:57, 1.37s/it, lr: 1.0e-04 loss: 6.626e-01] my_first_lora_v1: 52%|#####2 | 1561/3000 [24:17<32:56, 1.37s/it, lr: 1.0e-04 loss: 7.112e-01] my_first_lora_v1: 52%|#####2 | 1561/3000 [24:17<32:56, 1.37s/it, lr: 1.0e-04 loss: 7.112e-01] my_first_lora_v1: 52%|#####2 | 1562/3000 [24:17<32:54, 1.37s/it, lr: 1.0e-04 loss: 4.845e-01] my_first_lora_v1: 52%|#####2 | 1562/3000 [24:17<32:54, 1.37s/it, lr: 1.0e-04 loss: 4.845e-01] my_first_lora_v1: 52%|#####2 | 1563/3000 [24:18<32:51, 1.37s/it, lr: 1.0e-04 loss: 7.464e-01] my_first_lora_v1: 52%|#####2 | 1563/3000 [24:18<32:51, 1.37s/it, lr: 1.0e-04 loss: 7.464e-01] my_first_lora_v1: 52%|#####2 | 1564/3000 [24:19<32:49, 1.37s/it, lr: 1.0e-04 loss: 5.240e-01] my_first_lora_v1: 52%|#####2 | 1564/3000 [24:19<32:49, 1.37s/it, lr: 1.0e-04 loss: 5.240e-01] my_first_lora_v1: 52%|#####2 | 1565/3000 [24:21<32:48, 1.37s/it, lr: 1.0e-04 loss: 7.162e-01] my_first_lora_v1: 52%|#####2 | 1565/3000 [24:21<32:48, 1.37s/it, lr: 1.0e-04 loss: 7.162e-01] my_first_lora_v1: 52%|#####2 | 1566/3000 [24:23<32:48, 1.37s/it, lr: 1.0e-04 loss: 3.018e-01] my_first_lora_v1: 52%|#####2 | 1566/3000 [24:23<32:48, 1.37s/it, lr: 1.0e-04 loss: 3.018e-01] my_first_lora_v1: 52%|#####2 | 1567/3000 [24:26<32:49, 1.37s/it, lr: 1.0e-04 loss: 5.676e-01] my_first_lora_v1: 52%|#####2 | 1567/3000 [24:26<32:49, 1.37s/it, lr: 1.0e-04 loss: 5.676e-01] my_first_lora_v1: 52%|#####2 | 1568/3000 [24:27<32:47, 1.37s/it, lr: 1.0e-04 loss: 1.341e-01] my_first_lora_v1: 52%|#####2 | 1568/3000 [24:27<32:47, 1.37s/it, lr: 1.0e-04 loss: 1.341e-01] my_first_lora_v1: 52%|#####2 | 1569/3000 [24:29<32:46, 1.37s/it, lr: 1.0e-04 loss: 1.067e-01] my_first_lora_v1: 52%|#####2 | 1569/3000 [24:29<32:46, 1.37s/it, lr: 1.0e-04 loss: 1.067e-01] my_first_lora_v1: 52%|#####2 | 1570/3000 [24:30<32:44, 1.37s/it, lr: 1.0e-04 loss: 6.186e-01] my_first_lora_v1: 52%|#####2 | 1570/3000 [24:30<32:44, 1.37s/it, lr: 1.0e-04 loss: 6.186e-01] my_first_lora_v1: 52%|#####2 | 1571/3000 [24:31<32:42, 1.37s/it, lr: 1.0e-04 loss: 4.355e-01] my_first_lora_v1: 52%|#####2 | 1571/3000 [24:31<32:42, 1.37s/it, lr: 1.0e-04 loss: 4.355e-01] my_first_lora_v1: 52%|#####2 | 1572/3000 [24:32<32:41, 1.37s/it, lr: 1.0e-04 loss: 5.165e-01] my_first_lora_v1: 52%|#####2 | 1572/3000 [24:32<32:41, 1.37s/it, lr: 1.0e-04 loss: 5.165e-01] my_first_lora_v1: 52%|#####2 | 1573/3000 [24:35<32:42, 1.38s/it, lr: 1.0e-04 loss: 1.078e-02] my_first_lora_v1: 52%|#####2 | 1573/3000 [24:35<32:42, 1.38s/it, lr: 1.0e-04 loss: 1.078e-02] my_first_lora_v1: 52%|#####2 | 1574/3000 [24:36<32:40, 1.37s/it, lr: 1.0e-04 loss: 4.429e-01] my_first_lora_v1: 52%|#####2 | 1574/3000 [24:36<32:40, 1.37s/it, lr: 1.0e-04 loss: 4.429e-01] my_first_lora_v1: 52%|#####2 | 1575/3000 [24:38<32:39, 1.38s/it, lr: 1.0e-04 loss: 6.965e-02] my_first_lora_v1: 52%|#####2 | 1575/3000 [24:38<32:39, 1.38s/it, lr: 1.0e-04 loss: 6.965e-02] my_first_lora_v1: 53%|#####2 | 1576/3000 [24:39<32:37, 1.37s/it, lr: 1.0e-04 loss: 7.875e-01] my_first_lora_v1: 53%|#####2 | 1576/3000 [24:39<32:37, 1.37s/it, lr: 1.0e-04 loss: 7.875e-01] my_first_lora_v1: 53%|#####2 | 1577/3000 [24:40<32:36, 1.38s/it, lr: 1.0e-04 loss: 5.679e-02] my_first_lora_v1: 53%|#####2 | 1577/3000 [24:40<32:36, 1.38s/it, lr: 1.0e-04 loss: 5.679e-02] my_first_lora_v1: 53%|#####2 | 1578/3000 [24:41<32:34, 1.37s/it, lr: 1.0e-04 loss: 7.070e-01] my_first_lora_v1: 53%|#####2 | 1578/3000 [24:41<32:34, 1.37s/it, lr: 1.0e-04 loss: 7.070e-01] my_first_lora_v1: 53%|#####2 | 1579/3000 [24:44<32:34, 1.38s/it, lr: 1.0e-04 loss: 5.842e-01] my_first_lora_v1: 53%|#####2 | 1579/3000 [24:44<32:34, 1.38s/it, lr: 1.0e-04 loss: 5.842e-01] my_first_lora_v1: 53%|#####2 | 1580/3000 [24:45<32:32, 1.38s/it, lr: 1.0e-04 loss: 6.365e-01] my_first_lora_v1: 53%|#####2 | 1580/3000 [24:45<32:32, 1.38s/it, lr: 1.0e-04 loss: 6.365e-01] my_first_lora_v1: 53%|#####2 | 1581/3000 [24:46<32:31, 1.38s/it, lr: 1.0e-04 loss: 5.611e-01] my_first_lora_v1: 53%|#####2 | 1581/3000 [24:46<32:31, 1.38s/it, lr: 1.0e-04 loss: 5.611e-01] my_first_lora_v1: 53%|#####2 | 1582/3000 [24:47<32:30, 1.38s/it, lr: 1.0e-04 loss: 1.096e-01] my_first_lora_v1: 53%|#####2 | 1582/3000 [24:47<32:30, 1.38s/it, lr: 1.0e-04 loss: 1.096e-01] my_first_lora_v1: 53%|#####2 | 1583/3000 [24:48<32:27, 1.37s/it, lr: 1.0e-04 loss: 4.378e-01] my_first_lora_v1: 53%|#####2 | 1583/3000 [24:48<32:27, 1.37s/it, lr: 1.0e-04 loss: 4.378e-01] my_first_lora_v1: 53%|#####2 | 1584/3000 [24:50<32:26, 1.37s/it, lr: 1.0e-04 loss: 2.966e-02] my_first_lora_v1: 53%|#####2 | 1584/3000 [24:50<32:26, 1.37s/it, lr: 1.0e-04 loss: 2.966e-02] my_first_lora_v1: 53%|#####2 | 1585/3000 [24:51<32:24, 1.37s/it, lr: 1.0e-04 loss: 4.682e-01] my_first_lora_v1: 53%|#####2 | 1585/3000 [24:51<32:24, 1.37s/it, lr: 1.0e-04 loss: 4.682e-01] my_first_lora_v1: 53%|#####2 | 1586/3000 [24:52<32:23, 1.37s/it, lr: 1.0e-04 loss: 9.319e-02] my_first_lora_v1: 53%|#####2 | 1586/3000 [24:52<32:23, 1.37s/it, lr: 1.0e-04 loss: 9.319e-02] my_first_lora_v1: 53%|#####2 | 1587/3000 [24:53<32:21, 1.37s/it, lr: 1.0e-04 loss: 1.385e-01] my_first_lora_v1: 53%|#####2 | 1587/3000 [24:53<32:21, 1.37s/it, lr: 1.0e-04 loss: 1.385e-01] my_first_lora_v1: 53%|#####2 | 1588/3000 [24:54<32:19, 1.37s/it, lr: 1.0e-04 loss: 6.382e-01] my_first_lora_v1: 53%|#####2 | 1588/3000 [24:54<32:19, 1.37s/it, lr: 1.0e-04 loss: 6.382e-01] my_first_lora_v1: 53%|#####2 | 1589/3000 [24:55<32:17, 1.37s/it, lr: 1.0e-04 loss: 6.125e-01] my_first_lora_v1: 53%|#####2 | 1589/3000 [24:55<32:17, 1.37s/it, lr: 1.0e-04 loss: 6.125e-01] my_first_lora_v1: 53%|#####3 | 1590/3000 [24:56<32:16, 1.37s/it, lr: 1.0e-04 loss: 7.834e-01] my_first_lora_v1: 53%|#####3 | 1590/3000 [24:56<32:16, 1.37s/it, lr: 1.0e-04 loss: 7.834e-01] my_first_lora_v1: 53%|#####3 | 1591/3000 [24:59<32:16, 1.37s/it, lr: 1.0e-04 loss: 6.387e-01] my_first_lora_v1: 53%|#####3 | 1591/3000 [24:59<32:16, 1.37s/it, lr: 1.0e-04 loss: 6.387e-01] my_first_lora_v1: 53%|#####3 | 1592/3000 [25:01<32:15, 1.37s/it, lr: 1.0e-04 loss: 5.776e-01] my_first_lora_v1: 53%|#####3 | 1592/3000 [25:01<32:15, 1.37s/it, lr: 1.0e-04 loss: 5.776e-01] my_first_lora_v1: 53%|#####3 | 1593/3000 [25:02<32:13, 1.37s/it, lr: 1.0e-04 loss: 4.603e-01] my_first_lora_v1: 53%|#####3 | 1593/3000 [25:02<32:13, 1.37s/it, lr: 1.0e-04 loss: 4.603e-01] my_first_lora_v1: 53%|#####3 | 1594/3000 [25:03<32:11, 1.37s/it, lr: 1.0e-04 loss: 6.460e-01] my_first_lora_v1: 53%|#####3 | 1594/3000 [25:03<32:11, 1.37s/it, lr: 1.0e-04 loss: 6.460e-01] my_first_lora_v1: 53%|#####3 | 1595/3000 [25:04<32:10, 1.37s/it, lr: 1.0e-04 loss: 6.003e-01] my_first_lora_v1: 53%|#####3 | 1595/3000 [25:04<32:10, 1.37s/it, lr: 1.0e-04 loss: 6.003e-01] my_first_lora_v1: 53%|#####3 | 1596/3000 [25:05<32:08, 1.37s/it, lr: 1.0e-04 loss: 4.919e-01] my_first_lora_v1: 53%|#####3 | 1596/3000 [25:05<32:08, 1.37s/it, lr: 1.0e-04 loss: 4.919e-01] my_first_lora_v1: 53%|#####3 | 1597/3000 [25:07<32:07, 1.37s/it, lr: 1.0e-04 loss: 5.424e-01] my_first_lora_v1: 53%|#####3 | 1597/3000 [25:07<32:07, 1.37s/it, lr: 1.0e-04 loss: 5.424e-01] my_first_lora_v1: 53%|#####3 | 1598/3000 [25:10<32:08, 1.38s/it, lr: 1.0e-04 loss: 6.893e-01] my_first_lora_v1: 53%|#####3 | 1598/3000 [25:10<32:08, 1.38s/it, lr: 1.0e-04 loss: 6.893e-01] my_first_lora_v1: 53%|#####3 | 1599/3000 [25:11<32:06, 1.37s/it, lr: 1.0e-04 loss: 7.623e-01] my_first_lora_v1: 53%|#####3 | 1599/3000 [25:11<32:06, 1.37s/it, lr: 1.0e-04 loss: 7.623e-01] my_first_lora_v1: 53%|#####3 | 1600/3000 [25:12<32:05, 1.38s/it, lr: 1.0e-04 loss: 2.200e-01] my_first_lora_v1: 53%|#####3 | 1600/3000 [25:12<32:05, 1.38s/it, lr: 1.0e-04 loss: 2.200e-01] my_first_lora_v1: 53%|#####3 | 1601/3000 [25:13<32:02, 1.37s/it, lr: 1.0e-04 loss: 1.694e-01] my_first_lora_v1: 53%|#####3 | 1601/3000 [25:13<32:02, 1.37s/it, lr: 1.0e-04 loss: 1.694e-01] my_first_lora_v1: 53%|#####3 | 1602/3000 [25:14<32:01, 1.37s/it, lr: 1.0e-04 loss: 6.665e-01] my_first_lora_v1: 53%|#####3 | 1602/3000 [25:14<32:01, 1.37s/it, lr: 1.0e-04 loss: 6.665e-01] my_first_lora_v1: 53%|#####3 | 1603/3000 [25:17<32:02, 1.38s/it, lr: 1.0e-04 loss: 4.397e-01] my_first_lora_v1: 53%|#####3 | 1603/3000 [25:17<32:02, 1.38s/it, lr: 1.0e-04 loss: 4.397e-01] my_first_lora_v1: 53%|#####3 | 1604/3000 [25:19<32:00, 1.38s/it, lr: 1.0e-04 loss: 4.701e-01] my_first_lora_v1: 53%|#####3 | 1604/3000 [25:19<32:00, 1.38s/it, lr: 1.0e-04 loss: 4.701e-01] my_first_lora_v1: 54%|#####3 | 1605/3000 [25:20<31:59, 1.38s/it, lr: 1.0e-04 loss: 6.284e-01] my_first_lora_v1: 54%|#####3 | 1605/3000 [25:20<31:59, 1.38s/it, lr: 1.0e-04 loss: 6.284e-01] my_first_lora_v1: 54%|#####3 | 1606/3000 [25:23<32:00, 1.38s/it, lr: 1.0e-04 loss: 4.574e-01] my_first_lora_v1: 54%|#####3 | 1606/3000 [25:23<32:00, 1.38s/it, lr: 1.0e-04 loss: 4.574e-01] my_first_lora_v1: 54%|#####3 | 1607/3000 [25:25<31:59, 1.38s/it, lr: 1.0e-04 loss: 7.024e-02] my_first_lora_v1: 54%|#####3 | 1607/3000 [25:25<31:59, 1.38s/it, lr: 1.0e-04 loss: 7.024e-02] my_first_lora_v1: 54%|#####3 | 1608/3000 [25:27<31:58, 1.38s/it, lr: 1.0e-04 loss: 7.772e-01] my_first_lora_v1: 54%|#####3 | 1608/3000 [25:27<31:58, 1.38s/it, lr: 1.0e-04 loss: 7.772e-01] my_first_lora_v1: 54%|#####3 | 1609/3000 [25:27<31:56, 1.38s/it, lr: 1.0e-04 loss: 4.692e-01] my_first_lora_v1: 54%|#####3 | 1609/3000 [25:27<31:56, 1.38s/it, lr: 1.0e-04 loss: 4.692e-01] my_first_lora_v1: 54%|#####3 | 1610/3000 [25:29<31:55, 1.38s/it, lr: 1.0e-04 loss: 6.482e-01] my_first_lora_v1: 54%|#####3 | 1610/3000 [25:29<31:55, 1.38s/it, lr: 1.0e-04 loss: 6.482e-01] my_first_lora_v1: 54%|#####3 | 1611/3000 [25:31<31:54, 1.38s/it, lr: 1.0e-04 loss: 3.325e-01] my_first_lora_v1: 54%|#####3 | 1611/3000 [25:31<31:54, 1.38s/it, lr: 1.0e-04 loss: 3.325e-01] my_first_lora_v1: 54%|#####3 | 1612/3000 [25:32<31:52, 1.38s/it, lr: 1.0e-04 loss: 4.065e-01] my_first_lora_v1: 54%|#####3 | 1612/3000 [25:32<31:52, 1.38s/it, lr: 1.0e-04 loss: 4.065e-01] my_first_lora_v1: 54%|#####3 | 1613/3000 [25:32<31:50, 1.38s/it, lr: 1.0e-04 loss: 6.760e-01] my_first_lora_v1: 54%|#####3 | 1613/3000 [25:32<31:50, 1.38s/it, lr: 1.0e-04 loss: 6.760e-01] my_first_lora_v1: 54%|#####3 | 1614/3000 [25:34<31:48, 1.38s/it, lr: 1.0e-04 loss: 6.483e-01] my_first_lora_v1: 54%|#####3 | 1614/3000 [25:34<31:48, 1.38s/it, lr: 1.0e-04 loss: 6.483e-01] my_first_lora_v1: 54%|#####3 | 1615/3000 [25:35<31:47, 1.38s/it, lr: 1.0e-04 loss: 7.037e-01] my_first_lora_v1: 54%|#####3 | 1615/3000 [25:35<31:47, 1.38s/it, lr: 1.0e-04 loss: 7.037e-01] my_first_lora_v1: 54%|#####3 | 1616/3000 [25:36<31:45, 1.38s/it, lr: 1.0e-04 loss: 3.511e-01] my_first_lora_v1: 54%|#####3 | 1616/3000 [25:36<31:45, 1.38s/it, lr: 1.0e-04 loss: 3.511e-01] my_first_lora_v1: 54%|#####3 | 1617/3000 [25:37<31:43, 1.38s/it, lr: 1.0e-04 loss: 1.377e-01] my_first_lora_v1: 54%|#####3 | 1617/3000 [25:37<31:43, 1.38s/it, lr: 1.0e-04 loss: 1.377e-01] my_first_lora_v1: 54%|#####3 | 1618/3000 [25:38<31:41, 1.38s/it, lr: 1.0e-04 loss: 1.865e-01] my_first_lora_v1: 54%|#####3 | 1618/3000 [25:38<31:41, 1.38s/it, lr: 1.0e-04 loss: 1.865e-01] my_first_lora_v1: 54%|#####3 | 1619/3000 [25:39<31:39, 1.38s/it, lr: 1.0e-04 loss: 7.003e-01] my_first_lora_v1: 54%|#####3 | 1619/3000 [25:39<31:39, 1.38s/it, lr: 1.0e-04 loss: 7.003e-01] my_first_lora_v1: 54%|#####4 | 1620/3000 [25:41<31:39, 1.38s/it, lr: 1.0e-04 loss: 2.635e-01] my_first_lora_v1: 54%|#####4 | 1620/3000 [25:41<31:39, 1.38s/it, lr: 1.0e-04 loss: 2.635e-01] my_first_lora_v1: 54%|#####4 | 1621/3000 [25:42<31:38, 1.38s/it, lr: 1.0e-04 loss: 5.947e-02] my_first_lora_v1: 54%|#####4 | 1621/3000 [25:42<31:38, 1.38s/it, lr: 1.0e-04 loss: 5.947e-02] my_first_lora_v1: 54%|#####4 | 1622/3000 [25:45<31:37, 1.38s/it, lr: 1.0e-04 loss: 1.662e-01] my_first_lora_v1: 54%|#####4 | 1622/3000 [25:45<31:37, 1.38s/it, lr: 1.0e-04 loss: 1.662e-01] my_first_lora_v1: 54%|#####4 | 1623/3000 [25:46<31:36, 1.38s/it, lr: 1.0e-04 loss: 8.375e-01] my_first_lora_v1: 54%|#####4 | 1623/3000 [25:46<31:36, 1.38s/it, lr: 1.0e-04 loss: 8.375e-01] my_first_lora_v1: 54%|#####4 | 1624/3000 [25:49<31:37, 1.38s/it, lr: 1.0e-04 loss: 1.600e-02] my_first_lora_v1: 54%|#####4 | 1624/3000 [25:49<31:37, 1.38s/it, lr: 1.0e-04 loss: 1.600e-02] my_first_lora_v1: 54%|#####4 | 1625/3000 [25:51<31:35, 1.38s/it, lr: 1.0e-04 loss: 3.974e-01] my_first_lora_v1: 54%|#####4 | 1625/3000 [25:51<31:35, 1.38s/it, lr: 1.0e-04 loss: 3.974e-01] my_first_lora_v1: 54%|#####4 | 1626/3000 [25:52<31:34, 1.38s/it, lr: 1.0e-04 loss: 1.682e-01] my_first_lora_v1: 54%|#####4 | 1626/3000 [25:52<31:34, 1.38s/it, lr: 1.0e-04 loss: 1.682e-01] my_first_lora_v1: 54%|#####4 | 1627/3000 [25:53<31:32, 1.38s/it, lr: 1.0e-04 loss: 6.981e-01] my_first_lora_v1: 54%|#####4 | 1627/3000 [25:53<31:32, 1.38s/it, lr: 1.0e-04 loss: 6.981e-01] my_first_lora_v1: 54%|#####4 | 1628/3000 [25:53<31:30, 1.38s/it, lr: 1.0e-04 loss: 1.369e-01] my_first_lora_v1: 54%|#####4 | 1628/3000 [25:53<31:30, 1.38s/it, lr: 1.0e-04 loss: 1.369e-01] my_first_lora_v1: 54%|#####4 | 1629/3000 [25:55<31:28, 1.38s/it, lr: 1.0e-04 loss: 5.469e-01] my_first_lora_v1: 54%|#####4 | 1629/3000 [25:55<31:28, 1.38s/it, lr: 1.0e-04 loss: 5.469e-01] my_first_lora_v1: 54%|#####4 | 1630/3000 [25:56<31:27, 1.38s/it, lr: 1.0e-04 loss: 6.361e-01] my_first_lora_v1: 54%|#####4 | 1630/3000 [25:56<31:27, 1.38s/it, lr: 1.0e-04 loss: 6.361e-01] my_first_lora_v1: 54%|#####4 | 1631/3000 [25:58<31:25, 1.38s/it, lr: 1.0e-04 loss: 6.984e-01] my_first_lora_v1: 54%|#####4 | 1631/3000 [25:58<31:25, 1.38s/it, lr: 1.0e-04 loss: 6.984e-01] my_first_lora_v1: 54%|#####4 | 1632/3000 [25:59<31:24, 1.38s/it, lr: 1.0e-04 loss: 1.181e-01] my_first_lora_v1: 54%|#####4 | 1632/3000 [25:59<31:24, 1.38s/it, lr: 1.0e-04 loss: 1.181e-01] my_first_lora_v1: 54%|#####4 | 1633/3000 [26:00<31:22, 1.38s/it, lr: 1.0e-04 loss: 3.023e-01] my_first_lora_v1: 54%|#####4 | 1633/3000 [26:00<31:22, 1.38s/it, lr: 1.0e-04 loss: 3.023e-01] my_first_lora_v1: 54%|#####4 | 1634/3000 [26:03<31:23, 1.38s/it, lr: 1.0e-04 loss: 5.096e-01] my_first_lora_v1: 54%|#####4 | 1634/3000 [26:03<31:23, 1.38s/it, lr: 1.0e-04 loss: 5.096e-01] my_first_lora_v1: 55%|#####4 | 1635/3000 [26:05<31:22, 1.38s/it, lr: 1.0e-04 loss: 1.112e-01] my_first_lora_v1: 55%|#####4 | 1635/3000 [26:05<31:22, 1.38s/it, lr: 1.0e-04 loss: 1.112e-01] my_first_lora_v1: 55%|#####4 | 1636/3000 [26:06<31:20, 1.38s/it, lr: 1.0e-04 loss: 5.650e-01] my_first_lora_v1: 55%|#####4 | 1636/3000 [26:06<31:20, 1.38s/it, lr: 1.0e-04 loss: 5.650e-01] my_first_lora_v1: 55%|#####4 | 1637/3000 [26:07<31:19, 1.38s/it, lr: 1.0e-04 loss: 7.129e-01] my_first_lora_v1: 55%|#####4 | 1637/3000 [26:07<31:19, 1.38s/it, lr: 1.0e-04 loss: 7.129e-01] my_first_lora_v1: 55%|#####4 | 1638/3000 [26:08<31:17, 1.38s/it, lr: 1.0e-04 loss: 3.271e-01] my_first_lora_v1: 55%|#####4 | 1638/3000 [26:08<31:17, 1.38s/it, lr: 1.0e-04 loss: 3.271e-01] my_first_lora_v1: 55%|#####4 | 1639/3000 [26:09<31:15, 1.38s/it, lr: 1.0e-04 loss: 6.171e-01] my_first_lora_v1: 55%|#####4 | 1639/3000 [26:09<31:15, 1.38s/it, lr: 1.0e-04 loss: 6.171e-01] my_first_lora_v1: 55%|#####4 | 1640/3000 [26:10<31:14, 1.38s/it, lr: 1.0e-04 loss: 1.518e-02] my_first_lora_v1: 55%|#####4 | 1640/3000 [26:10<31:14, 1.38s/it, lr: 1.0e-04 loss: 1.518e-02] my_first_lora_v1: 55%|#####4 | 1641/3000 [26:11<31:12, 1.38s/it, lr: 1.0e-04 loss: 2.514e-02] my_first_lora_v1: 55%|#####4 | 1641/3000 [26:11<31:12, 1.38s/it, lr: 1.0e-04 loss: 2.514e-02] my_first_lora_v1: 55%|#####4 | 1642/3000 [26:14<31:11, 1.38s/it, lr: 1.0e-04 loss: 1.832e-01] my_first_lora_v1: 55%|#####4 | 1642/3000 [26:14<31:11, 1.38s/it, lr: 1.0e-04 loss: 1.832e-01] my_first_lora_v1: 55%|#####4 | 1643/3000 [26:15<31:10, 1.38s/it, lr: 1.0e-04 loss: 2.544e-01] my_first_lora_v1: 55%|#####4 | 1643/3000 [26:15<31:10, 1.38s/it, lr: 1.0e-04 loss: 2.544e-01] my_first_lora_v1: 55%|#####4 | 1644/3000 [26:16<31:09, 1.38s/it, lr: 1.0e-04 loss: 7.899e-01] my_first_lora_v1: 55%|#####4 | 1644/3000 [26:16<31:09, 1.38s/it, lr: 1.0e-04 loss: 7.899e-01] my_first_lora_v1: 55%|#####4 | 1645/3000 [26:18<31:08, 1.38s/it, lr: 1.0e-04 loss: 3.497e-01] my_first_lora_v1: 55%|#####4 | 1645/3000 [26:18<31:08, 1.38s/it, lr: 1.0e-04 loss: 3.497e-01] my_first_lora_v1: 55%|#####4 | 1646/3000 [26:20<31:06, 1.38s/it, lr: 1.0e-04 loss: 9.459e-02] my_first_lora_v1: 55%|#####4 | 1646/3000 [26:20<31:06, 1.38s/it, lr: 1.0e-04 loss: 9.459e-02] my_first_lora_v1: 55%|#####4 | 1647/3000 [26:20<31:04, 1.38s/it, lr: 1.0e-04 loss: 5.754e-01] my_first_lora_v1: 55%|#####4 | 1647/3000 [26:20<31:04, 1.38s/it, lr: 1.0e-04 loss: 5.754e-01] my_first_lora_v1: 55%|#####4 | 1648/3000 [26:22<31:03, 1.38s/it, lr: 1.0e-04 loss: 5.524e-01] my_first_lora_v1: 55%|#####4 | 1648/3000 [26:22<31:03, 1.38s/it, lr: 1.0e-04 loss: 5.524e-01] my_first_lora_v1: 55%|#####4 | 1649/3000 [26:23<31:02, 1.38s/it, lr: 1.0e-04 loss: 2.102e-01] my_first_lora_v1: 55%|#####4 | 1649/3000 [26:23<31:02, 1.38s/it, lr: 1.0e-04 loss: 2.102e-01] my_first_lora_v1: 55%|#####5 | 1650/3000 [26:25<31:00, 1.38s/it, lr: 1.0e-04 loss: 4.277e-01] my_first_lora_v1: 55%|#####5 | 1650/3000 [26:25<31:00, 1.38s/it, lr: 1.0e-04 loss: 4.277e-01] my_first_lora_v1: 55%|#####5 | 1651/3000 [26:26<30:59, 1.38s/it, lr: 1.0e-04 loss: 2.039e-01] my_first_lora_v1: 55%|#####5 | 1651/3000 [26:26<30:59, 1.38s/it, lr: 1.0e-04 loss: 2.039e-01] my_first_lora_v1: 55%|#####5 | 1652/3000 [26:28<30:58, 1.38s/it, lr: 1.0e-04 loss: 1.620e-01] my_first_lora_v1: 55%|#####5 | 1652/3000 [26:28<30:58, 1.38s/it, lr: 1.0e-04 loss: 1.620e-01] my_first_lora_v1: 55%|#####5 | 1653/3000 [26:29<30:57, 1.38s/it, lr: 1.0e-04 loss: 2.018e-02] my_first_lora_v1: 55%|#####5 | 1653/3000 [26:29<30:57, 1.38s/it, lr: 1.0e-04 loss: 2.018e-02] my_first_lora_v1: 55%|#####5 | 1654/3000 [26:31<30:55, 1.38s/it, lr: 1.0e-04 loss: 1.986e-01] my_first_lora_v1: 55%|#####5 | 1654/3000 [26:31<30:55, 1.38s/it, lr: 1.0e-04 loss: 1.986e-01] my_first_lora_v1: 55%|#####5 | 1655/3000 [26:32<30:54, 1.38s/it, lr: 1.0e-04 loss: 8.064e-01] my_first_lora_v1: 55%|#####5 | 1655/3000 [26:32<30:54, 1.38s/it, lr: 1.0e-04 loss: 8.064e-01] my_first_lora_v1: 55%|#####5 | 1656/3000 [26:32<30:52, 1.38s/it, lr: 1.0e-04 loss: 6.646e-01] my_first_lora_v1: 55%|#####5 | 1656/3000 [26:32<30:52, 1.38s/it, lr: 1.0e-04 loss: 6.646e-01] my_first_lora_v1: 55%|#####5 | 1657/3000 [26:34<30:50, 1.38s/it, lr: 1.0e-04 loss: 2.283e-01] my_first_lora_v1: 55%|#####5 | 1657/3000 [26:34<30:50, 1.38s/it, lr: 1.0e-04 loss: 2.283e-01] my_first_lora_v1: 55%|#####5 | 1658/3000 [26:35<30:49, 1.38s/it, lr: 1.0e-04 loss: 7.123e-01] my_first_lora_v1: 55%|#####5 | 1658/3000 [26:35<30:49, 1.38s/it, lr: 1.0e-04 loss: 7.123e-01] my_first_lora_v1: 55%|#####5 | 1659/3000 [26:38<30:49, 1.38s/it, lr: 1.0e-04 loss: 6.699e-01] my_first_lora_v1: 55%|#####5 | 1659/3000 [26:38<30:49, 1.38s/it, lr: 1.0e-04 loss: 6.699e-01] my_first_lora_v1: 55%|#####5 | 1660/3000 [26:39<30:47, 1.38s/it, lr: 1.0e-04 loss: 1.480e-01] my_first_lora_v1: 55%|#####5 | 1660/3000 [26:39<30:47, 1.38s/it, lr: 1.0e-04 loss: 1.480e-01] my_first_lora_v1: 55%|#####5 | 1661/3000 [26:39<30:45, 1.38s/it, lr: 1.0e-04 loss: 7.075e-01] my_first_lora_v1: 55%|#####5 | 1661/3000 [26:39<30:45, 1.38s/it, lr: 1.0e-04 loss: 7.075e-01] my_first_lora_v1: 55%|#####5 | 1662/3000 [26:40<30:43, 1.38s/it, lr: 1.0e-04 loss: 6.643e-01] my_first_lora_v1: 55%|#####5 | 1662/3000 [26:40<30:43, 1.38s/it, lr: 1.0e-04 loss: 6.643e-01] my_first_lora_v1: 55%|#####5 | 1663/3000 [26:42<30:42, 1.38s/it, lr: 1.0e-04 loss: 7.425e-01] my_first_lora_v1: 55%|#####5 | 1663/3000 [26:42<30:42, 1.38s/it, lr: 1.0e-04 loss: 7.425e-01] my_first_lora_v1: 55%|#####5 | 1664/3000 [26:43<30:40, 1.38s/it, lr: 1.0e-04 loss: 5.709e-01] my_first_lora_v1: 55%|#####5 | 1664/3000 [26:43<30:40, 1.38s/it, lr: 1.0e-04 loss: 5.709e-01] my_first_lora_v1: 56%|#####5 | 1665/3000 [26:45<30:39, 1.38s/it, lr: 1.0e-04 loss: 6.821e-01] my_first_lora_v1: 56%|#####5 | 1665/3000 [26:45<30:39, 1.38s/it, lr: 1.0e-04 loss: 6.821e-01] my_first_lora_v1: 56%|#####5 | 1666/3000 [26:46<30:38, 1.38s/it, lr: 1.0e-04 loss: 1.025e-02] my_first_lora_v1: 56%|#####5 | 1666/3000 [26:46<30:38, 1.38s/it, lr: 1.0e-04 loss: 1.025e-02] my_first_lora_v1: 56%|#####5 | 1667/3000 [26:47<30:36, 1.38s/it, lr: 1.0e-04 loss: 4.604e-01] my_first_lora_v1: 56%|#####5 | 1667/3000 [26:47<30:36, 1.38s/it, lr: 1.0e-04 loss: 4.604e-01] my_first_lora_v1: 56%|#####5 | 1668/3000 [26:50<30:36, 1.38s/it, lr: 1.0e-04 loss: 5.385e-01] my_first_lora_v1: 56%|#####5 | 1668/3000 [26:50<30:36, 1.38s/it, lr: 1.0e-04 loss: 5.385e-01] my_first_lora_v1: 56%|#####5 | 1669/3000 [26:50<30:34, 1.38s/it, lr: 1.0e-04 loss: 7.227e-01] my_first_lora_v1: 56%|#####5 | 1669/3000 [26:50<30:34, 1.38s/it, lr: 1.0e-04 loss: 7.227e-01] my_first_lora_v1: 56%|#####5 | 1670/3000 [26:52<30:33, 1.38s/it, lr: 1.0e-04 loss: 6.492e-01] my_first_lora_v1: 56%|#####5 | 1670/3000 [26:52<30:33, 1.38s/it, lr: 1.0e-04 loss: 6.492e-01] my_first_lora_v1: 56%|#####5 | 1671/3000 [26:53<30:31, 1.38s/it, lr: 1.0e-04 loss: 5.481e-01] my_first_lora_v1: 56%|#####5 | 1671/3000 [26:53<30:31, 1.38s/it, lr: 1.0e-04 loss: 5.481e-01] my_first_lora_v1: 56%|#####5 | 1672/3000 [26:54<30:29, 1.38s/it, lr: 1.0e-04 loss: 4.455e-01] my_first_lora_v1: 56%|#####5 | 1672/3000 [26:54<30:29, 1.38s/it, lr: 1.0e-04 loss: 4.455e-01] my_first_lora_v1: 56%|#####5 | 1673/3000 [26:56<30:28, 1.38s/it, lr: 1.0e-04 loss: 1.362e-01] my_first_lora_v1: 56%|#####5 | 1673/3000 [26:56<30:28, 1.38s/it, lr: 1.0e-04 loss: 1.362e-01] my_first_lora_v1: 56%|#####5 | 1674/3000 [26:57<30:27, 1.38s/it, lr: 1.0e-04 loss: 7.900e-01] my_first_lora_v1: 56%|#####5 | 1674/3000 [26:57<30:27, 1.38s/it, lr: 1.0e-04 loss: 7.900e-01] my_first_lora_v1: 56%|#####5 | 1675/3000 [26:58<30:25, 1.38s/it, lr: 1.0e-04 loss: 7.724e-01] my_first_lora_v1: 56%|#####5 | 1675/3000 [26:58<30:25, 1.38s/it, lr: 1.0e-04 loss: 7.724e-01] my_first_lora_v1: 56%|#####5 | 1676/3000 [27:00<30:24, 1.38s/it, lr: 1.0e-04 loss: 3.438e-01] my_first_lora_v1: 56%|#####5 | 1676/3000 [27:00<30:24, 1.38s/it, lr: 1.0e-04 loss: 3.438e-01] my_first_lora_v1: 56%|#####5 | 1677/3000 [27:01<30:22, 1.38s/it, lr: 1.0e-04 loss: 7.775e-01] my_first_lora_v1: 56%|#####5 | 1677/3000 [27:01<30:22, 1.38s/it, lr: 1.0e-04 loss: 7.775e-01] my_first_lora_v1: 56%|#####5 | 1678/3000 [27:01<30:20, 1.38s/it, lr: 1.0e-04 loss: 1.559e-01] my_first_lora_v1: 56%|#####5 | 1678/3000 [27:01<30:20, 1.38s/it, lr: 1.0e-04 loss: 1.559e-01] my_first_lora_v1: 56%|#####5 | 1679/3000 [27:03<30:18, 1.38s/it, lr: 1.0e-04 loss: 6.623e-01] my_first_lora_v1: 56%|#####5 | 1679/3000 [27:03<30:18, 1.38s/it, lr: 1.0e-04 loss: 6.623e-01] my_first_lora_v1: 56%|#####6 | 1680/3000 [27:05<30:18, 1.38s/it, lr: 1.0e-04 loss: 6.165e-01] my_first_lora_v1: 56%|#####6 | 1680/3000 [27:05<30:18, 1.38s/it, lr: 1.0e-04 loss: 6.165e-01] my_first_lora_v1: 56%|#####6 | 1681/3000 [27:07<30:17, 1.38s/it, lr: 1.0e-04 loss: 3.361e-01] my_first_lora_v1: 56%|#####6 | 1681/3000 [27:07<30:17, 1.38s/it, lr: 1.0e-04 loss: 3.361e-01] my_first_lora_v1: 56%|#####6 | 1682/3000 [27:10<30:17, 1.38s/it, lr: 1.0e-04 loss: 5.716e-01] my_first_lora_v1: 56%|#####6 | 1682/3000 [27:10<30:17, 1.38s/it, lr: 1.0e-04 loss: 5.716e-01] my_first_lora_v1: 56%|#####6 | 1683/3000 [27:12<30:17, 1.38s/it, lr: 1.0e-04 loss: 4.503e-01] my_first_lora_v1: 56%|#####6 | 1683/3000 [27:12<30:17, 1.38s/it, lr: 1.0e-04 loss: 4.503e-01] my_first_lora_v1: 56%|#####6 | 1684/3000 [27:15<30:18, 1.38s/it, lr: 1.0e-04 loss: 7.848e-01] my_first_lora_v1: 56%|#####6 | 1684/3000 [27:15<30:18, 1.38s/it, lr: 1.0e-04 loss: 7.848e-01] my_first_lora_v1: 56%|#####6 | 1685/3000 [27:16<30:16, 1.38s/it, lr: 1.0e-04 loss: 6.930e-01] my_first_lora_v1: 56%|#####6 | 1685/3000 [27:16<30:16, 1.38s/it, lr: 1.0e-04 loss: 6.930e-01] my_first_lora_v1: 56%|#####6 | 1686/3000 [27:18<30:14, 1.38s/it, lr: 1.0e-04 loss: 1.314e-01] my_first_lora_v1: 56%|#####6 | 1686/3000 [27:18<30:14, 1.38s/it, lr: 1.0e-04 loss: 1.314e-01] my_first_lora_v1: 56%|#####6 | 1687/3000 [27:20<30:14, 1.38s/it, lr: 1.0e-04 loss: 1.953e-01] my_first_lora_v1: 56%|#####6 | 1687/3000 [27:20<30:14, 1.38s/it, lr: 1.0e-04 loss: 1.953e-01] my_first_lora_v1: 56%|#####6 | 1688/3000 [27:21<30:12, 1.38s/it, lr: 1.0e-04 loss: 4.856e-01] my_first_lora_v1: 56%|#####6 | 1688/3000 [27:21<30:12, 1.38s/it, lr: 1.0e-04 loss: 4.856e-01] my_first_lora_v1: 56%|#####6 | 1689/3000 [27:22<30:10, 1.38s/it, lr: 1.0e-04 loss: 2.753e-01] my_first_lora_v1: 56%|#####6 | 1689/3000 [27:22<30:10, 1.38s/it, lr: 1.0e-04 loss: 2.753e-01] my_first_lora_v1: 56%|#####6 | 1690/3000 [27:23<30:08, 1.38s/it, lr: 1.0e-04 loss: 8.486e-01] my_first_lora_v1: 56%|#####6 | 1690/3000 [27:23<30:08, 1.38s/it, lr: 1.0e-04 loss: 8.486e-01] my_first_lora_v1: 56%|#####6 | 1691/3000 [27:24<30:07, 1.38s/it, lr: 1.0e-04 loss: 7.480e-01] my_first_lora_v1: 56%|#####6 | 1691/3000 [27:24<30:07, 1.38s/it, lr: 1.0e-04 loss: 7.480e-01] my_first_lora_v1: 56%|#####6 | 1692/3000 [27:25<30:05, 1.38s/it, lr: 1.0e-04 loss: 5.114e-01] my_first_lora_v1: 56%|#####6 | 1692/3000 [27:25<30:05, 1.38s/it, lr: 1.0e-04 loss: 5.114e-01] my_first_lora_v1: 56%|#####6 | 1693/3000 [27:27<30:05, 1.38s/it, lr: 1.0e-04 loss: 2.156e-01] my_first_lora_v1: 56%|#####6 | 1693/3000 [27:27<30:05, 1.38s/it, lr: 1.0e-04 loss: 2.156e-01] my_first_lora_v1: 56%|#####6 | 1694/3000 [27:29<30:03, 1.38s/it, lr: 1.0e-04 loss: 5.603e-01] my_first_lora_v1: 56%|#####6 | 1694/3000 [27:29<30:03, 1.38s/it, lr: 1.0e-04 loss: 5.603e-01] my_first_lora_v1: 56%|#####6 | 1695/3000 [27:30<30:02, 1.38s/it, lr: 1.0e-04 loss: 1.857e-01] my_first_lora_v1: 56%|#####6 | 1695/3000 [27:30<30:02, 1.38s/it, lr: 1.0e-04 loss: 1.857e-01] my_first_lora_v1: 57%|#####6 | 1696/3000 [27:31<30:00, 1.38s/it, lr: 1.0e-04 loss: 5.089e-01] my_first_lora_v1: 57%|#####6 | 1696/3000 [27:31<30:00, 1.38s/it, lr: 1.0e-04 loss: 5.089e-01] my_first_lora_v1: 57%|#####6 | 1697/3000 [27:32<29:58, 1.38s/it, lr: 1.0e-04 loss: 4.974e-01] my_first_lora_v1: 57%|#####6 | 1697/3000 [27:32<29:58, 1.38s/it, lr: 1.0e-04 loss: 4.974e-01] my_first_lora_v1: 57%|#####6 | 1698/3000 [27:33<29:57, 1.38s/it, lr: 1.0e-04 loss: 5.969e-01] my_first_lora_v1: 57%|#####6 | 1698/3000 [27:33<29:57, 1.38s/it, lr: 1.0e-04 loss: 5.969e-01] my_first_lora_v1: 57%|#####6 | 1699/3000 [27:34<29:54, 1.38s/it, lr: 1.0e-04 loss: 4.020e-01] my_first_lora_v1: 57%|#####6 | 1699/3000 [27:34<29:54, 1.38s/it, lr: 1.0e-04 loss: 4.020e-01] my_first_lora_v1: 57%|#####6 | 1700/3000 [27:35<29:53, 1.38s/it, lr: 1.0e-04 loss: 8.486e-01] my_first_lora_v1: 57%|#####6 | 1700/3000 [27:35<29:53, 1.38s/it, lr: 1.0e-04 loss: 8.486e-01] my_first_lora_v1: 57%|#####6 | 1701/3000 [27:36<29:51, 1.38s/it, lr: 1.0e-04 loss: 8.487e-01] my_first_lora_v1: 57%|#####6 | 1701/3000 [27:36<29:51, 1.38s/it, lr: 1.0e-04 loss: 8.487e-01] my_first_lora_v1: 57%|#####6 | 1702/3000 [27:37<29:49, 1.38s/it, lr: 1.0e-04 loss: 3.960e-01] my_first_lora_v1: 57%|#####6 | 1702/3000 [27:37<29:49, 1.38s/it, lr: 1.0e-04 loss: 3.960e-01] my_first_lora_v1: 57%|#####6 | 1703/3000 [27:38<29:47, 1.38s/it, lr: 1.0e-04 loss: 6.447e-01] my_first_lora_v1: 57%|#####6 | 1703/3000 [27:38<29:47, 1.38s/it, lr: 1.0e-04 loss: 6.447e-01] my_first_lora_v1: 57%|#####6 | 1704/3000 [27:39<29:46, 1.38s/it, lr: 1.0e-04 loss: 7.591e-01] my_first_lora_v1: 57%|#####6 | 1704/3000 [27:39<29:46, 1.38s/it, lr: 1.0e-04 loss: 7.591e-01] my_first_lora_v1: 57%|#####6 | 1705/3000 [27:41<29:45, 1.38s/it, lr: 1.0e-04 loss: 6.579e-01] my_first_lora_v1: 57%|#####6 | 1705/3000 [27:41<29:45, 1.38s/it, lr: 1.0e-04 loss: 6.579e-01] my_first_lora_v1: 57%|#####6 | 1706/3000 [27:42<29:43, 1.38s/it, lr: 1.0e-04 loss: 6.341e-01] my_first_lora_v1: 57%|#####6 | 1706/3000 [27:42<29:43, 1.38s/it, lr: 1.0e-04 loss: 6.341e-01] my_first_lora_v1: 57%|#####6 | 1707/3000 [27:42<29:41, 1.38s/it, lr: 1.0e-04 loss: 6.808e-01] my_first_lora_v1: 57%|#####6 | 1707/3000 [27:42<29:41, 1.38s/it, lr: 1.0e-04 loss: 6.808e-01]Error running job: Job stopped
========================================
Result:
- 0 completed jobs
- 1 failure
========================================
Traceback (most recent call last):
Traceback (most recent call last):
File "/teamspace/studios/this_studio/ai-toolkit/run.py", line 120, in <module>
File "/teamspace/studios/this_studio/ai-toolkit/run.py", line 120, in <module>
main()main()
File "/teamspace/studios/this_studio/ai-toolkit/run.py", line 108, in main
File "/teamspace/studios/this_studio/ai-toolkit/run.py", line 108, in main
raise eraise e
File "/teamspace/studios/this_studio/ai-toolkit/run.py", line 96, in main
File "/teamspace/studios/this_studio/ai-toolkit/run.py", line 96, in main
job.run()job.run()
File "/teamspace/studios/this_studio/ai-toolkit/jobs/ExtensionJob.py", line 22, in run
File "/teamspace/studios/this_studio/ai-toolkit/jobs/ExtensionJob.py", line 22, in run
process.run()process.run()
File "/teamspace/studios/this_studio/ai-toolkit/jobs/process/BaseSDTrainProcess.py", line 2353, in run
File "/teamspace/studios/this_studio/ai-toolkit/jobs/process/BaseSDTrainProcess.py", line 2353, in run
self.end_step_hook()self.end_step_hook()
File "/teamspace/studios/this_studio/ai-toolkit/extensions_built_in/sd_trainer/DiffusionTrainer.py", line 264, in end_step_hook
File "/teamspace/studios/this_studio/ai-toolkit/extensions_built_in/sd_trainer/DiffusionTrainer.py", line 264, in end_step_hook
self.maybe_stop()self.maybe_stop()
File "/teamspace/studios/this_studio/ai-toolkit/extensions_built_in/sd_trainer/DiffusionTrainer.py", line 147, in maybe_stop
File "/teamspace/studios/this_studio/ai-toolkit/extensions_built_in/sd_trainer/DiffusionTrainer.py", line 147, in maybe_stop
raise Exception("Job stopped")raise Exception("Job stopped")
ExceptionException: : Job stoppedJob stopped
my_first_lora_v1: 57%|#####6 | 1708/3000 [27:44<29:40, 1.38s/it, lr: 1.0e-04 loss: 6.808e-01] my_first_lora_v1: 57%|#####6 | 1708/3000 [27:44<29:40, 1.38s/it, lr: 1.0e-04 loss: 6.808e-01]