Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +13 -0
- checkpoint-1000/config.json +41 -0
- checkpoint-1000/model.safetensors +3 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state.pth +0 -0
- checkpoint-1000/scheduler.pt +0 -0
- checkpoint-1000/special_tokens_map.json +7 -0
- checkpoint-1000/tokenizer.json +0 -0
- checkpoint-1000/tokenizer_config.json +56 -0
- checkpoint-1000/trainer_state.json +128 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1000/vocab.txt +0 -0
- checkpoint-1500/config.json +41 -0
- checkpoint-1500/model.safetensors +3 -0
- checkpoint-1500/optimizer.pt +3 -0
- checkpoint-1500/rng_state.pth +0 -0
- checkpoint-1500/scheduler.pt +0 -0
- checkpoint-1500/special_tokens_map.json +7 -0
- checkpoint-1500/tokenizer.json +0 -0
- checkpoint-1500/tokenizer_config.json +56 -0
- checkpoint-1500/trainer_state.json +175 -0
- checkpoint-1500/training_args.bin +3 -0
- checkpoint-1500/vocab.txt +0 -0
- checkpoint-2000/config.json +41 -0
- checkpoint-2000/model.safetensors +3 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/rng_state.pth +0 -0
- checkpoint-2000/scheduler.pt +0 -0
- checkpoint-2000/special_tokens_map.json +7 -0
- checkpoint-2000/tokenizer.json +0 -0
- checkpoint-2000/tokenizer_config.json +56 -0
- checkpoint-2000/trainer_state.json +222 -0
- checkpoint-2000/training_args.bin +3 -0
- checkpoint-2000/vocab.txt +0 -0
- checkpoint-2500/config.json +41 -0
- checkpoint-2500/model.safetensors +3 -0
- checkpoint-2500/optimizer.pt +3 -0
- checkpoint-2500/rng_state.pth +0 -0
- checkpoint-2500/scheduler.pt +0 -0
- checkpoint-2500/special_tokens_map.json +7 -0
- checkpoint-2500/tokenizer.json +0 -0
- checkpoint-2500/tokenizer_config.json +56 -0
- checkpoint-2500/trainer_state.json +269 -0
- checkpoint-2500/training_args.bin +3 -0
- checkpoint-2500/vocab.txt +0 -0
- checkpoint-3000/config.json +41 -0
- checkpoint-3000/model.safetensors +3 -0
- checkpoint-3000/optimizer.pt +3 -0
- checkpoint-3000/rng_state.pth +0 -0
- checkpoint-3000/scheduler.pt +0 -0
.gitattributes
CHANGED
|
@@ -4,3 +4,16 @@
|
|
| 4 |
results/checkpoint-4000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 5 |
results/checkpoint-4000/scheduler.pt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
基于BERT的情感分析系统.pptx filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
results/checkpoint-4000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 5 |
results/checkpoint-4000/scheduler.pt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
基于BERT的情感分析系统.pptx filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
checkpoint-1000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
checkpoint-1500/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
checkpoint-2000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
checkpoint-2500/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
checkpoint-3000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
checkpoint-3500/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
checkpoint-4000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
checkpoint-4500/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
checkpoint-500/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
checkpoint-5000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
checkpoint-5500/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
checkpoint-6000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
checkpoint-6500/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"directionality": "bidi",
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "negative",
|
| 14 |
+
"1": "neutral",
|
| 15 |
+
"2": "positive"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"negative": 0,
|
| 21 |
+
"neutral": 1,
|
| 22 |
+
"positive": 2
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "bert",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"pooler_fc_size": 768,
|
| 31 |
+
"pooler_num_attention_heads": 12,
|
| 32 |
+
"pooler_num_fc_layers": 3,
|
| 33 |
+
"pooler_size_per_head": 128,
|
| 34 |
+
"pooler_type": "first_token_transform",
|
| 35 |
+
"position_embedding_type": "absolute",
|
| 36 |
+
"problem_type": "single_label_classification",
|
| 37 |
+
"transformers_version": "4.57.3",
|
| 38 |
+
"type_vocab_size": 2,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 21128
|
| 41 |
+
}
|
checkpoint-1000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e583d628bf3f7664d535cf9ef598114a7c49fe257c7fe24c2c221b5f2233b850
|
| 3 |
+
size 409103316
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42f24930a75cafe396570302ac3432d90d46838277c4d457f1085f00561acef3
|
| 3 |
+
size 818320969
|
checkpoint-1000/rng_state.pth
ADDED
|
Binary file (14.4 kB). View file
|
|
|
checkpoint-1000/scheduler.pt
ADDED
|
Binary file (1.45 kB). View file
|
|
|
checkpoint-1000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
checkpoint-1000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "BertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,128 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 1000,
|
| 3 |
+
"best_metric": 0.7448374295446439,
|
| 4 |
+
"best_model_checkpoint": "/Users/wangyiqiu/Desktop/program/\u795e\u7ecf\u7f51\u7edc\u62d3\u6251/results/checkpoint-1000",
|
| 5 |
+
"epoch": 0.06317119393556538,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.006317119393556538,
|
| 14 |
+
"grad_norm": 13.061114311218262,
|
| 15 |
+
"learning_rate": 4.169298799747316e-07,
|
| 16 |
+
"loss": 1.354,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.012634238787113077,
|
| 21 |
+
"grad_norm": 13.682186126708984,
|
| 22 |
+
"learning_rate": 8.380711728785009e-07,
|
| 23 |
+
"loss": 1.0853,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.018951358180669616,
|
| 28 |
+
"grad_norm": 4.851679801940918,
|
| 29 |
+
"learning_rate": 1.2592124657822702e-06,
|
| 30 |
+
"loss": 0.9111,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.025268477574226154,
|
| 35 |
+
"grad_norm": 5.82253360748291,
|
| 36 |
+
"learning_rate": 1.6803537586860393e-06,
|
| 37 |
+
"loss": 0.7179,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.03158559696778269,
|
| 42 |
+
"grad_norm": 5.032683372497559,
|
| 43 |
+
"learning_rate": 2.1014950515898086e-06,
|
| 44 |
+
"loss": 0.6422,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03158559696778269,
|
| 49 |
+
"eval_accuracy": 0.7368075050637859,
|
| 50 |
+
"eval_f1": 0.7170832086299176,
|
| 51 |
+
"eval_loss": 0.6070035696029663,
|
| 52 |
+
"eval_precision": 0.7218199142709759,
|
| 53 |
+
"eval_recall": 0.7368075050637859,
|
| 54 |
+
"eval_runtime": 582.5178,
|
| 55 |
+
"eval_samples_per_second": 96.619,
|
| 56 |
+
"eval_steps_per_second": 3.02,
|
| 57 |
+
"step": 500
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.03790271636133923,
|
| 61 |
+
"grad_norm": 7.424877166748047,
|
| 62 |
+
"learning_rate": 2.5226363444935774e-06,
|
| 63 |
+
"loss": 0.6155,
|
| 64 |
+
"step": 600
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.04421983575489577,
|
| 68 |
+
"grad_norm": 16.976255416870117,
|
| 69 |
+
"learning_rate": 2.943777637397347e-06,
|
| 70 |
+
"loss": 0.5944,
|
| 71 |
+
"step": 700
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.05053695514845231,
|
| 75 |
+
"grad_norm": 9.103567123413086,
|
| 76 |
+
"learning_rate": 3.3649189303011164e-06,
|
| 77 |
+
"loss": 0.5812,
|
| 78 |
+
"step": 800
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.056854074542008845,
|
| 82 |
+
"grad_norm": 7.061375617980957,
|
| 83 |
+
"learning_rate": 3.7860602232048853e-06,
|
| 84 |
+
"loss": 0.5965,
|
| 85 |
+
"step": 900
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.06317119393556538,
|
| 89 |
+
"grad_norm": 6.224503040313721,
|
| 90 |
+
"learning_rate": 4.207201516108655e-06,
|
| 91 |
+
"loss": 0.5553,
|
| 92 |
+
"step": 1000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.06317119393556538,
|
| 96 |
+
"eval_accuracy": 0.7581642443409972,
|
| 97 |
+
"eval_f1": 0.7448374295446439,
|
| 98 |
+
"eval_loss": 0.5610596537590027,
|
| 99 |
+
"eval_precision": 0.7461287482946488,
|
| 100 |
+
"eval_recall": 0.7581642443409972,
|
| 101 |
+
"eval_runtime": 584.5541,
|
| 102 |
+
"eval_samples_per_second": 96.282,
|
| 103 |
+
"eval_steps_per_second": 3.009,
|
| 104 |
+
"step": 1000
|
| 105 |
+
}
|
| 106 |
+
],
|
| 107 |
+
"logging_steps": 100,
|
| 108 |
+
"max_steps": 47490,
|
| 109 |
+
"num_input_tokens_seen": 0,
|
| 110 |
+
"num_train_epochs": 3,
|
| 111 |
+
"save_steps": 500,
|
| 112 |
+
"stateful_callbacks": {
|
| 113 |
+
"TrainerControl": {
|
| 114 |
+
"args": {
|
| 115 |
+
"should_epoch_stop": false,
|
| 116 |
+
"should_evaluate": false,
|
| 117 |
+
"should_log": false,
|
| 118 |
+
"should_save": true,
|
| 119 |
+
"should_training_stop": false
|
| 120 |
+
},
|
| 121 |
+
"attributes": {}
|
| 122 |
+
}
|
| 123 |
+
},
|
| 124 |
+
"total_flos": 2104907341824000.0,
|
| 125 |
+
"train_batch_size": 32,
|
| 126 |
+
"trial_name": null,
|
| 127 |
+
"trial_params": null
|
| 128 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88724115c05a14013e1bf5182b6efa00270cfee7c30485da6eb058c6d09f75a8
|
| 3 |
+
size 5805
|
checkpoint-1000/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1500/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"directionality": "bidi",
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "negative",
|
| 14 |
+
"1": "neutral",
|
| 15 |
+
"2": "positive"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"negative": 0,
|
| 21 |
+
"neutral": 1,
|
| 22 |
+
"positive": 2
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "bert",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"pooler_fc_size": 768,
|
| 31 |
+
"pooler_num_attention_heads": 12,
|
| 32 |
+
"pooler_num_fc_layers": 3,
|
| 33 |
+
"pooler_size_per_head": 128,
|
| 34 |
+
"pooler_type": "first_token_transform",
|
| 35 |
+
"position_embedding_type": "absolute",
|
| 36 |
+
"problem_type": "single_label_classification",
|
| 37 |
+
"transformers_version": "4.57.3",
|
| 38 |
+
"type_vocab_size": 2,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 21128
|
| 41 |
+
}
|
checkpoint-1500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4209fdfbb0289e0649ee9e29950a97c6f5f549a5f73c74da86f22954d84d3c6b
|
| 3 |
+
size 409103316
|
checkpoint-1500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2c6935f688f73008b30e77553a70ce309f0077be2763f4129a83cf96713d28a
|
| 3 |
+
size 818320969
|
checkpoint-1500/rng_state.pth
ADDED
|
Binary file (14.4 kB). View file
|
|
|
checkpoint-1500/scheduler.pt
ADDED
|
Binary file (1.45 kB). View file
|
|
|
checkpoint-1500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
checkpoint-1500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "BertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
checkpoint-1500/trainer_state.json
ADDED
|
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 1500,
|
| 3 |
+
"best_metric": 0.7632915279870514,
|
| 4 |
+
"best_model_checkpoint": "/Users/wangyiqiu/Desktop/program/\u795e\u7ecf\u7f51\u7edc\u62d3\u6251/results/checkpoint-1500",
|
| 5 |
+
"epoch": 0.09475679090334807,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.006317119393556538,
|
| 14 |
+
"grad_norm": 13.061114311218262,
|
| 15 |
+
"learning_rate": 4.169298799747316e-07,
|
| 16 |
+
"loss": 1.354,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.012634238787113077,
|
| 21 |
+
"grad_norm": 13.682186126708984,
|
| 22 |
+
"learning_rate": 8.380711728785009e-07,
|
| 23 |
+
"loss": 1.0853,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.018951358180669616,
|
| 28 |
+
"grad_norm": 4.851679801940918,
|
| 29 |
+
"learning_rate": 1.2592124657822702e-06,
|
| 30 |
+
"loss": 0.9111,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.025268477574226154,
|
| 35 |
+
"grad_norm": 5.82253360748291,
|
| 36 |
+
"learning_rate": 1.6803537586860393e-06,
|
| 37 |
+
"loss": 0.7179,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.03158559696778269,
|
| 42 |
+
"grad_norm": 5.032683372497559,
|
| 43 |
+
"learning_rate": 2.1014950515898086e-06,
|
| 44 |
+
"loss": 0.6422,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03158559696778269,
|
| 49 |
+
"eval_accuracy": 0.7368075050637859,
|
| 50 |
+
"eval_f1": 0.7170832086299176,
|
| 51 |
+
"eval_loss": 0.6070035696029663,
|
| 52 |
+
"eval_precision": 0.7218199142709759,
|
| 53 |
+
"eval_recall": 0.7368075050637859,
|
| 54 |
+
"eval_runtime": 582.5178,
|
| 55 |
+
"eval_samples_per_second": 96.619,
|
| 56 |
+
"eval_steps_per_second": 3.02,
|
| 57 |
+
"step": 500
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.03790271636133923,
|
| 61 |
+
"grad_norm": 7.424877166748047,
|
| 62 |
+
"learning_rate": 2.5226363444935774e-06,
|
| 63 |
+
"loss": 0.6155,
|
| 64 |
+
"step": 600
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.04421983575489577,
|
| 68 |
+
"grad_norm": 16.976255416870117,
|
| 69 |
+
"learning_rate": 2.943777637397347e-06,
|
| 70 |
+
"loss": 0.5944,
|
| 71 |
+
"step": 700
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.05053695514845231,
|
| 75 |
+
"grad_norm": 9.103567123413086,
|
| 76 |
+
"learning_rate": 3.3649189303011164e-06,
|
| 77 |
+
"loss": 0.5812,
|
| 78 |
+
"step": 800
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.056854074542008845,
|
| 82 |
+
"grad_norm": 7.061375617980957,
|
| 83 |
+
"learning_rate": 3.7860602232048853e-06,
|
| 84 |
+
"loss": 0.5965,
|
| 85 |
+
"step": 900
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.06317119393556538,
|
| 89 |
+
"grad_norm": 6.224503040313721,
|
| 90 |
+
"learning_rate": 4.207201516108655e-06,
|
| 91 |
+
"loss": 0.5553,
|
| 92 |
+
"step": 1000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.06317119393556538,
|
| 96 |
+
"eval_accuracy": 0.7581642443409972,
|
| 97 |
+
"eval_f1": 0.7448374295446439,
|
| 98 |
+
"eval_loss": 0.5610596537590027,
|
| 99 |
+
"eval_precision": 0.7461287482946488,
|
| 100 |
+
"eval_recall": 0.7581642443409972,
|
| 101 |
+
"eval_runtime": 584.5541,
|
| 102 |
+
"eval_samples_per_second": 96.282,
|
| 103 |
+
"eval_steps_per_second": 3.009,
|
| 104 |
+
"step": 1000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.06948831332912192,
|
| 108 |
+
"grad_norm": 6.321476459503174,
|
| 109 |
+
"learning_rate": 4.628342809012423e-06,
|
| 110 |
+
"loss": 0.592,
|
| 111 |
+
"step": 1100
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.07580543272267846,
|
| 115 |
+
"grad_norm": 8.201200485229492,
|
| 116 |
+
"learning_rate": 5.0494841019161935e-06,
|
| 117 |
+
"loss": 0.5518,
|
| 118 |
+
"step": 1200
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.082122552116235,
|
| 122 |
+
"grad_norm": 6.514477729797363,
|
| 123 |
+
"learning_rate": 5.470625394819963e-06,
|
| 124 |
+
"loss": 0.5897,
|
| 125 |
+
"step": 1300
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.08843967150979154,
|
| 129 |
+
"grad_norm": 8.077017784118652,
|
| 130 |
+
"learning_rate": 5.891766687723732e-06,
|
| 131 |
+
"loss": 0.5476,
|
| 132 |
+
"step": 1400
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.09475679090334807,
|
| 136 |
+
"grad_norm": 9.256704330444336,
|
| 137 |
+
"learning_rate": 6.3129079806275005e-06,
|
| 138 |
+
"loss": 0.5263,
|
| 139 |
+
"step": 1500
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.09475679090334807,
|
| 143 |
+
"eval_accuracy": 0.7675278064034683,
|
| 144 |
+
"eval_f1": 0.7632915279870514,
|
| 145 |
+
"eval_loss": 0.5426821112632751,
|
| 146 |
+
"eval_precision": 0.760979358962669,
|
| 147 |
+
"eval_recall": 0.7675278064034683,
|
| 148 |
+
"eval_runtime": 587.2504,
|
| 149 |
+
"eval_samples_per_second": 95.84,
|
| 150 |
+
"eval_steps_per_second": 2.995,
|
| 151 |
+
"step": 1500
|
| 152 |
+
}
|
| 153 |
+
],
|
| 154 |
+
"logging_steps": 100,
|
| 155 |
+
"max_steps": 47490,
|
| 156 |
+
"num_input_tokens_seen": 0,
|
| 157 |
+
"num_train_epochs": 3,
|
| 158 |
+
"save_steps": 500,
|
| 159 |
+
"stateful_callbacks": {
|
| 160 |
+
"TrainerControl": {
|
| 161 |
+
"args": {
|
| 162 |
+
"should_epoch_stop": false,
|
| 163 |
+
"should_evaluate": false,
|
| 164 |
+
"should_log": false,
|
| 165 |
+
"should_save": true,
|
| 166 |
+
"should_training_stop": false
|
| 167 |
+
},
|
| 168 |
+
"attributes": {}
|
| 169 |
+
}
|
| 170 |
+
},
|
| 171 |
+
"total_flos": 3157361012736000.0,
|
| 172 |
+
"train_batch_size": 32,
|
| 173 |
+
"trial_name": null,
|
| 174 |
+
"trial_params": null
|
| 175 |
+
}
|
checkpoint-1500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88724115c05a14013e1bf5182b6efa00270cfee7c30485da6eb058c6d09f75a8
|
| 3 |
+
size 5805
|
checkpoint-1500/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2000/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"directionality": "bidi",
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "negative",
|
| 14 |
+
"1": "neutral",
|
| 15 |
+
"2": "positive"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"negative": 0,
|
| 21 |
+
"neutral": 1,
|
| 22 |
+
"positive": 2
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "bert",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"pooler_fc_size": 768,
|
| 31 |
+
"pooler_num_attention_heads": 12,
|
| 32 |
+
"pooler_num_fc_layers": 3,
|
| 33 |
+
"pooler_size_per_head": 128,
|
| 34 |
+
"pooler_type": "first_token_transform",
|
| 35 |
+
"position_embedding_type": "absolute",
|
| 36 |
+
"problem_type": "single_label_classification",
|
| 37 |
+
"transformers_version": "4.57.3",
|
| 38 |
+
"type_vocab_size": 2,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 21128
|
| 41 |
+
}
|
checkpoint-2000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4ea44ef70cf8d03e38dc4bd19e0395e151e76ca0ec086f9b64a9bafbffe8634
|
| 3 |
+
size 409103316
|
checkpoint-2000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bb16411239bf92da62b02a0c869901a9e3f917e66b5d90f3980cbdd70d7dfd2
|
| 3 |
+
size 818320969
|
checkpoint-2000/rng_state.pth
ADDED
|
Binary file (14.4 kB). View file
|
|
|
checkpoint-2000/scheduler.pt
ADDED
|
Binary file (1.45 kB). View file
|
|
|
checkpoint-2000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
checkpoint-2000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "BertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
checkpoint-2000/trainer_state.json
ADDED
|
@@ -0,0 +1,222 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 2000,
|
| 3 |
+
"best_metric": 0.7644619158467771,
|
| 4 |
+
"best_model_checkpoint": "/Users/wangyiqiu/Desktop/program/\u795e\u7ecf\u7f51\u7edc\u62d3\u6251/results/checkpoint-2000",
|
| 5 |
+
"epoch": 0.12634238787113075,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.006317119393556538,
|
| 14 |
+
"grad_norm": 13.061114311218262,
|
| 15 |
+
"learning_rate": 4.169298799747316e-07,
|
| 16 |
+
"loss": 1.354,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.012634238787113077,
|
| 21 |
+
"grad_norm": 13.682186126708984,
|
| 22 |
+
"learning_rate": 8.380711728785009e-07,
|
| 23 |
+
"loss": 1.0853,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.018951358180669616,
|
| 28 |
+
"grad_norm": 4.851679801940918,
|
| 29 |
+
"learning_rate": 1.2592124657822702e-06,
|
| 30 |
+
"loss": 0.9111,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.025268477574226154,
|
| 35 |
+
"grad_norm": 5.82253360748291,
|
| 36 |
+
"learning_rate": 1.6803537586860393e-06,
|
| 37 |
+
"loss": 0.7179,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.03158559696778269,
|
| 42 |
+
"grad_norm": 5.032683372497559,
|
| 43 |
+
"learning_rate": 2.1014950515898086e-06,
|
| 44 |
+
"loss": 0.6422,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03158559696778269,
|
| 49 |
+
"eval_accuracy": 0.7368075050637859,
|
| 50 |
+
"eval_f1": 0.7170832086299176,
|
| 51 |
+
"eval_loss": 0.6070035696029663,
|
| 52 |
+
"eval_precision": 0.7218199142709759,
|
| 53 |
+
"eval_recall": 0.7368075050637859,
|
| 54 |
+
"eval_runtime": 582.5178,
|
| 55 |
+
"eval_samples_per_second": 96.619,
|
| 56 |
+
"eval_steps_per_second": 3.02,
|
| 57 |
+
"step": 500
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.03790271636133923,
|
| 61 |
+
"grad_norm": 7.424877166748047,
|
| 62 |
+
"learning_rate": 2.5226363444935774e-06,
|
| 63 |
+
"loss": 0.6155,
|
| 64 |
+
"step": 600
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.04421983575489577,
|
| 68 |
+
"grad_norm": 16.976255416870117,
|
| 69 |
+
"learning_rate": 2.943777637397347e-06,
|
| 70 |
+
"loss": 0.5944,
|
| 71 |
+
"step": 700
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.05053695514845231,
|
| 75 |
+
"grad_norm": 9.103567123413086,
|
| 76 |
+
"learning_rate": 3.3649189303011164e-06,
|
| 77 |
+
"loss": 0.5812,
|
| 78 |
+
"step": 800
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.056854074542008845,
|
| 82 |
+
"grad_norm": 7.061375617980957,
|
| 83 |
+
"learning_rate": 3.7860602232048853e-06,
|
| 84 |
+
"loss": 0.5965,
|
| 85 |
+
"step": 900
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.06317119393556538,
|
| 89 |
+
"grad_norm": 6.224503040313721,
|
| 90 |
+
"learning_rate": 4.207201516108655e-06,
|
| 91 |
+
"loss": 0.5553,
|
| 92 |
+
"step": 1000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.06317119393556538,
|
| 96 |
+
"eval_accuracy": 0.7581642443409972,
|
| 97 |
+
"eval_f1": 0.7448374295446439,
|
| 98 |
+
"eval_loss": 0.5610596537590027,
|
| 99 |
+
"eval_precision": 0.7461287482946488,
|
| 100 |
+
"eval_recall": 0.7581642443409972,
|
| 101 |
+
"eval_runtime": 584.5541,
|
| 102 |
+
"eval_samples_per_second": 96.282,
|
| 103 |
+
"eval_steps_per_second": 3.009,
|
| 104 |
+
"step": 1000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.06948831332912192,
|
| 108 |
+
"grad_norm": 6.321476459503174,
|
| 109 |
+
"learning_rate": 4.628342809012423e-06,
|
| 110 |
+
"loss": 0.592,
|
| 111 |
+
"step": 1100
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.07580543272267846,
|
| 115 |
+
"grad_norm": 8.201200485229492,
|
| 116 |
+
"learning_rate": 5.0494841019161935e-06,
|
| 117 |
+
"loss": 0.5518,
|
| 118 |
+
"step": 1200
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.082122552116235,
|
| 122 |
+
"grad_norm": 6.514477729797363,
|
| 123 |
+
"learning_rate": 5.470625394819963e-06,
|
| 124 |
+
"loss": 0.5897,
|
| 125 |
+
"step": 1300
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.08843967150979154,
|
| 129 |
+
"grad_norm": 8.077017784118652,
|
| 130 |
+
"learning_rate": 5.891766687723732e-06,
|
| 131 |
+
"loss": 0.5476,
|
| 132 |
+
"step": 1400
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.09475679090334807,
|
| 136 |
+
"grad_norm": 9.256704330444336,
|
| 137 |
+
"learning_rate": 6.3129079806275005e-06,
|
| 138 |
+
"loss": 0.5263,
|
| 139 |
+
"step": 1500
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.09475679090334807,
|
| 143 |
+
"eval_accuracy": 0.7675278064034683,
|
| 144 |
+
"eval_f1": 0.7632915279870514,
|
| 145 |
+
"eval_loss": 0.5426821112632751,
|
| 146 |
+
"eval_precision": 0.760979358962669,
|
| 147 |
+
"eval_recall": 0.7675278064034683,
|
| 148 |
+
"eval_runtime": 587.2504,
|
| 149 |
+
"eval_samples_per_second": 95.84,
|
| 150 |
+
"eval_steps_per_second": 2.995,
|
| 151 |
+
"step": 1500
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.10107391029690461,
|
| 155 |
+
"grad_norm": 6.117814064025879,
|
| 156 |
+
"learning_rate": 6.73404927353127e-06,
|
| 157 |
+
"loss": 0.5563,
|
| 158 |
+
"step": 1600
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.10739102969046115,
|
| 162 |
+
"grad_norm": 9.015992164611816,
|
| 163 |
+
"learning_rate": 7.15519056643504e-06,
|
| 164 |
+
"loss": 0.5622,
|
| 165 |
+
"step": 1700
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.11370814908401769,
|
| 169 |
+
"grad_norm": 8.684099197387695,
|
| 170 |
+
"learning_rate": 7.576331859338809e-06,
|
| 171 |
+
"loss": 0.5483,
|
| 172 |
+
"step": 1800
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.12002526847757422,
|
| 176 |
+
"grad_norm": 5.517951488494873,
|
| 177 |
+
"learning_rate": 7.997473152242578e-06,
|
| 178 |
+
"loss": 0.5467,
|
| 179 |
+
"step": 1900
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.12634238787113075,
|
| 183 |
+
"grad_norm": 4.840009689331055,
|
| 184 |
+
"learning_rate": 8.418614445146347e-06,
|
| 185 |
+
"loss": 0.5472,
|
| 186 |
+
"step": 2000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.12634238787113075,
|
| 190 |
+
"eval_accuracy": 0.7682740485412743,
|
| 191 |
+
"eval_f1": 0.7644619158467771,
|
| 192 |
+
"eval_loss": 0.5479554533958435,
|
| 193 |
+
"eval_precision": 0.7616941910129872,
|
| 194 |
+
"eval_recall": 0.7682740485412743,
|
| 195 |
+
"eval_runtime": 594.3974,
|
| 196 |
+
"eval_samples_per_second": 94.687,
|
| 197 |
+
"eval_steps_per_second": 2.959,
|
| 198 |
+
"step": 2000
|
| 199 |
+
}
|
| 200 |
+
],
|
| 201 |
+
"logging_steps": 100,
|
| 202 |
+
"max_steps": 47490,
|
| 203 |
+
"num_input_tokens_seen": 0,
|
| 204 |
+
"num_train_epochs": 3,
|
| 205 |
+
"save_steps": 500,
|
| 206 |
+
"stateful_callbacks": {
|
| 207 |
+
"TrainerControl": {
|
| 208 |
+
"args": {
|
| 209 |
+
"should_epoch_stop": false,
|
| 210 |
+
"should_evaluate": false,
|
| 211 |
+
"should_log": false,
|
| 212 |
+
"should_save": true,
|
| 213 |
+
"should_training_stop": false
|
| 214 |
+
},
|
| 215 |
+
"attributes": {}
|
| 216 |
+
}
|
| 217 |
+
},
|
| 218 |
+
"total_flos": 4209814683648000.0,
|
| 219 |
+
"train_batch_size": 32,
|
| 220 |
+
"trial_name": null,
|
| 221 |
+
"trial_params": null
|
| 222 |
+
}
|
checkpoint-2000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88724115c05a14013e1bf5182b6efa00270cfee7c30485da6eb058c6d09f75a8
|
| 3 |
+
size 5805
|
checkpoint-2000/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2500/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"directionality": "bidi",
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "negative",
|
| 14 |
+
"1": "neutral",
|
| 15 |
+
"2": "positive"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"negative": 0,
|
| 21 |
+
"neutral": 1,
|
| 22 |
+
"positive": 2
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "bert",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"pooler_fc_size": 768,
|
| 31 |
+
"pooler_num_attention_heads": 12,
|
| 32 |
+
"pooler_num_fc_layers": 3,
|
| 33 |
+
"pooler_size_per_head": 128,
|
| 34 |
+
"pooler_type": "first_token_transform",
|
| 35 |
+
"position_embedding_type": "absolute",
|
| 36 |
+
"problem_type": "single_label_classification",
|
| 37 |
+
"transformers_version": "4.57.3",
|
| 38 |
+
"type_vocab_size": 2,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 21128
|
| 41 |
+
}
|
checkpoint-2500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a65784efe8a30dcba18ab4014fe925034545bd17cb304dbd85a3e45f1ee18b8
|
| 3 |
+
size 409103316
|
checkpoint-2500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d1420b60e06ba0d05e36c8a399cface5b24ca58c2dca60adf781f4a8d792a2b
|
| 3 |
+
size 818320969
|
checkpoint-2500/rng_state.pth
ADDED
|
Binary file (14.4 kB). View file
|
|
|
checkpoint-2500/scheduler.pt
ADDED
|
Binary file (1.45 kB). View file
|
|
|
checkpoint-2500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
checkpoint-2500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "BertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
checkpoint-2500/trainer_state.json
ADDED
|
@@ -0,0 +1,269 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 2500,
|
| 3 |
+
"best_metric": 0.7701652961241094,
|
| 4 |
+
"best_model_checkpoint": "/Users/wangyiqiu/Desktop/program/\u795e\u7ecf\u7f51\u7edc\u62d3\u6251/results/checkpoint-2500",
|
| 5 |
+
"epoch": 0.15792798483891346,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.006317119393556538,
|
| 14 |
+
"grad_norm": 13.061114311218262,
|
| 15 |
+
"learning_rate": 4.169298799747316e-07,
|
| 16 |
+
"loss": 1.354,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.012634238787113077,
|
| 21 |
+
"grad_norm": 13.682186126708984,
|
| 22 |
+
"learning_rate": 8.380711728785009e-07,
|
| 23 |
+
"loss": 1.0853,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.018951358180669616,
|
| 28 |
+
"grad_norm": 4.851679801940918,
|
| 29 |
+
"learning_rate": 1.2592124657822702e-06,
|
| 30 |
+
"loss": 0.9111,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.025268477574226154,
|
| 35 |
+
"grad_norm": 5.82253360748291,
|
| 36 |
+
"learning_rate": 1.6803537586860393e-06,
|
| 37 |
+
"loss": 0.7179,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.03158559696778269,
|
| 42 |
+
"grad_norm": 5.032683372497559,
|
| 43 |
+
"learning_rate": 2.1014950515898086e-06,
|
| 44 |
+
"loss": 0.6422,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03158559696778269,
|
| 49 |
+
"eval_accuracy": 0.7368075050637859,
|
| 50 |
+
"eval_f1": 0.7170832086299176,
|
| 51 |
+
"eval_loss": 0.6070035696029663,
|
| 52 |
+
"eval_precision": 0.7218199142709759,
|
| 53 |
+
"eval_recall": 0.7368075050637859,
|
| 54 |
+
"eval_runtime": 582.5178,
|
| 55 |
+
"eval_samples_per_second": 96.619,
|
| 56 |
+
"eval_steps_per_second": 3.02,
|
| 57 |
+
"step": 500
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.03790271636133923,
|
| 61 |
+
"grad_norm": 7.424877166748047,
|
| 62 |
+
"learning_rate": 2.5226363444935774e-06,
|
| 63 |
+
"loss": 0.6155,
|
| 64 |
+
"step": 600
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.04421983575489577,
|
| 68 |
+
"grad_norm": 16.976255416870117,
|
| 69 |
+
"learning_rate": 2.943777637397347e-06,
|
| 70 |
+
"loss": 0.5944,
|
| 71 |
+
"step": 700
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.05053695514845231,
|
| 75 |
+
"grad_norm": 9.103567123413086,
|
| 76 |
+
"learning_rate": 3.3649189303011164e-06,
|
| 77 |
+
"loss": 0.5812,
|
| 78 |
+
"step": 800
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.056854074542008845,
|
| 82 |
+
"grad_norm": 7.061375617980957,
|
| 83 |
+
"learning_rate": 3.7860602232048853e-06,
|
| 84 |
+
"loss": 0.5965,
|
| 85 |
+
"step": 900
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.06317119393556538,
|
| 89 |
+
"grad_norm": 6.224503040313721,
|
| 90 |
+
"learning_rate": 4.207201516108655e-06,
|
| 91 |
+
"loss": 0.5553,
|
| 92 |
+
"step": 1000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.06317119393556538,
|
| 96 |
+
"eval_accuracy": 0.7581642443409972,
|
| 97 |
+
"eval_f1": 0.7448374295446439,
|
| 98 |
+
"eval_loss": 0.5610596537590027,
|
| 99 |
+
"eval_precision": 0.7461287482946488,
|
| 100 |
+
"eval_recall": 0.7581642443409972,
|
| 101 |
+
"eval_runtime": 584.5541,
|
| 102 |
+
"eval_samples_per_second": 96.282,
|
| 103 |
+
"eval_steps_per_second": 3.009,
|
| 104 |
+
"step": 1000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.06948831332912192,
|
| 108 |
+
"grad_norm": 6.321476459503174,
|
| 109 |
+
"learning_rate": 4.628342809012423e-06,
|
| 110 |
+
"loss": 0.592,
|
| 111 |
+
"step": 1100
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.07580543272267846,
|
| 115 |
+
"grad_norm": 8.201200485229492,
|
| 116 |
+
"learning_rate": 5.0494841019161935e-06,
|
| 117 |
+
"loss": 0.5518,
|
| 118 |
+
"step": 1200
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.082122552116235,
|
| 122 |
+
"grad_norm": 6.514477729797363,
|
| 123 |
+
"learning_rate": 5.470625394819963e-06,
|
| 124 |
+
"loss": 0.5897,
|
| 125 |
+
"step": 1300
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.08843967150979154,
|
| 129 |
+
"grad_norm": 8.077017784118652,
|
| 130 |
+
"learning_rate": 5.891766687723732e-06,
|
| 131 |
+
"loss": 0.5476,
|
| 132 |
+
"step": 1400
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.09475679090334807,
|
| 136 |
+
"grad_norm": 9.256704330444336,
|
| 137 |
+
"learning_rate": 6.3129079806275005e-06,
|
| 138 |
+
"loss": 0.5263,
|
| 139 |
+
"step": 1500
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.09475679090334807,
|
| 143 |
+
"eval_accuracy": 0.7675278064034683,
|
| 144 |
+
"eval_f1": 0.7632915279870514,
|
| 145 |
+
"eval_loss": 0.5426821112632751,
|
| 146 |
+
"eval_precision": 0.760979358962669,
|
| 147 |
+
"eval_recall": 0.7675278064034683,
|
| 148 |
+
"eval_runtime": 587.2504,
|
| 149 |
+
"eval_samples_per_second": 95.84,
|
| 150 |
+
"eval_steps_per_second": 2.995,
|
| 151 |
+
"step": 1500
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.10107391029690461,
|
| 155 |
+
"grad_norm": 6.117814064025879,
|
| 156 |
+
"learning_rate": 6.73404927353127e-06,
|
| 157 |
+
"loss": 0.5563,
|
| 158 |
+
"step": 1600
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.10739102969046115,
|
| 162 |
+
"grad_norm": 9.015992164611816,
|
| 163 |
+
"learning_rate": 7.15519056643504e-06,
|
| 164 |
+
"loss": 0.5622,
|
| 165 |
+
"step": 1700
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.11370814908401769,
|
| 169 |
+
"grad_norm": 8.684099197387695,
|
| 170 |
+
"learning_rate": 7.576331859338809e-06,
|
| 171 |
+
"loss": 0.5483,
|
| 172 |
+
"step": 1800
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.12002526847757422,
|
| 176 |
+
"grad_norm": 5.517951488494873,
|
| 177 |
+
"learning_rate": 7.997473152242578e-06,
|
| 178 |
+
"loss": 0.5467,
|
| 179 |
+
"step": 1900
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.12634238787113075,
|
| 183 |
+
"grad_norm": 4.840009689331055,
|
| 184 |
+
"learning_rate": 8.418614445146347e-06,
|
| 185 |
+
"loss": 0.5472,
|
| 186 |
+
"step": 2000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.12634238787113075,
|
| 190 |
+
"eval_accuracy": 0.7682740485412743,
|
| 191 |
+
"eval_f1": 0.7644619158467771,
|
| 192 |
+
"eval_loss": 0.5479554533958435,
|
| 193 |
+
"eval_precision": 0.7616941910129872,
|
| 194 |
+
"eval_recall": 0.7682740485412743,
|
| 195 |
+
"eval_runtime": 594.3974,
|
| 196 |
+
"eval_samples_per_second": 94.687,
|
| 197 |
+
"eval_steps_per_second": 2.959,
|
| 198 |
+
"step": 2000
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.1326595072646873,
|
| 202 |
+
"grad_norm": 9.188036918640137,
|
| 203 |
+
"learning_rate": 8.839755738050117e-06,
|
| 204 |
+
"loss": 0.5436,
|
| 205 |
+
"step": 2100
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.13897662665824384,
|
| 209 |
+
"grad_norm": 5.845507621765137,
|
| 210 |
+
"learning_rate": 9.260897030953885e-06,
|
| 211 |
+
"loss": 0.5684,
|
| 212 |
+
"step": 2200
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.14529374605180037,
|
| 216 |
+
"grad_norm": 6.014614105224609,
|
| 217 |
+
"learning_rate": 9.682038323857656e-06,
|
| 218 |
+
"loss": 0.5268,
|
| 219 |
+
"step": 2300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.15161086544535693,
|
| 223 |
+
"grad_norm": 5.183818817138672,
|
| 224 |
+
"learning_rate": 1.0103179616761426e-05,
|
| 225 |
+
"loss": 0.5505,
|
| 226 |
+
"step": 2400
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.15792798483891346,
|
| 230 |
+
"grad_norm": 4.270262718200684,
|
| 231 |
+
"learning_rate": 1.0524320909665192e-05,
|
| 232 |
+
"loss": 0.5327,
|
| 233 |
+
"step": 2500
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.15792798483891346,
|
| 237 |
+
"eval_accuracy": 0.7718631178707225,
|
| 238 |
+
"eval_f1": 0.7701652961241094,
|
| 239 |
+
"eval_loss": 0.538950502872467,
|
| 240 |
+
"eval_precision": 0.7692113501499637,
|
| 241 |
+
"eval_recall": 0.7718631178707225,
|
| 242 |
+
"eval_runtime": 598.0361,
|
| 243 |
+
"eval_samples_per_second": 94.111,
|
| 244 |
+
"eval_steps_per_second": 2.941,
|
| 245 |
+
"step": 2500
|
| 246 |
+
}
|
| 247 |
+
],
|
| 248 |
+
"logging_steps": 100,
|
| 249 |
+
"max_steps": 47490,
|
| 250 |
+
"num_input_tokens_seen": 0,
|
| 251 |
+
"num_train_epochs": 3,
|
| 252 |
+
"save_steps": 500,
|
| 253 |
+
"stateful_callbacks": {
|
| 254 |
+
"TrainerControl": {
|
| 255 |
+
"args": {
|
| 256 |
+
"should_epoch_stop": false,
|
| 257 |
+
"should_evaluate": false,
|
| 258 |
+
"should_log": false,
|
| 259 |
+
"should_save": true,
|
| 260 |
+
"should_training_stop": false
|
| 261 |
+
},
|
| 262 |
+
"attributes": {}
|
| 263 |
+
}
|
| 264 |
+
},
|
| 265 |
+
"total_flos": 5262268354560000.0,
|
| 266 |
+
"train_batch_size": 32,
|
| 267 |
+
"trial_name": null,
|
| 268 |
+
"trial_params": null
|
| 269 |
+
}
|
checkpoint-2500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88724115c05a14013e1bf5182b6efa00270cfee7c30485da6eb058c6d09f75a8
|
| 3 |
+
size 5805
|
checkpoint-2500/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-3000/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"directionality": "bidi",
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "negative",
|
| 14 |
+
"1": "neutral",
|
| 15 |
+
"2": "positive"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"negative": 0,
|
| 21 |
+
"neutral": 1,
|
| 22 |
+
"positive": 2
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "bert",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"pooler_fc_size": 768,
|
| 31 |
+
"pooler_num_attention_heads": 12,
|
| 32 |
+
"pooler_num_fc_layers": 3,
|
| 33 |
+
"pooler_size_per_head": 128,
|
| 34 |
+
"pooler_type": "first_token_transform",
|
| 35 |
+
"position_embedding_type": "absolute",
|
| 36 |
+
"problem_type": "single_label_classification",
|
| 37 |
+
"transformers_version": "4.57.3",
|
| 38 |
+
"type_vocab_size": 2,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 21128
|
| 41 |
+
}
|
checkpoint-3000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ce0f10418c09aad543969f7b335b600bc4485c0894c8752b10067c20058c90e
|
| 3 |
+
size 409103316
|
checkpoint-3000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e18d3d6e0e530bc9fd092dde6f6e67f21536e58d7cb195ac7cb5a2475b38081c
|
| 3 |
+
size 818320969
|
checkpoint-3000/rng_state.pth
ADDED
|
Binary file (14.4 kB). View file
|
|
|
checkpoint-3000/scheduler.pt
ADDED
|
Binary file (1.45 kB). View file
|
|
|