FleetAI/fleet-sft-wallst-fostgres-Qwen3-32B

fleet-sft-full

This model is a fine-tuned version of Qwen/Qwen3-32B on the fleet_trajectories_train dataset. It achieves the following results on the evaluation set:

• Loss: 0.6065

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• total_eval_batch_size: 8
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0	0	1.0228
0.8247	0.0826	10	0.7420
0.7588	0.1652	20	0.6738
0.6626	0.2478	30	0.6482
0.6548	0.3304	40	0.6332
0.6488	0.4130	50	0.6242
0.6595	0.4956	60	0.6179
0.6359	0.5782	70	0.6137
0.6445	0.6608	80	0.6109
0.6231	0.7434	90	0.6087
0.6402	0.8260	100	0.6073
0.6321	0.9086	110	0.6066
0.6315	0.9912	120	0.6065

Framework versions

• Transformers 4.52.4
• Pytorch 2.10.0+cu128
• Datasets 3.6.0
• Tokenizers 0.21.1