7b-claude-32k-20250419_153234-2ep

This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2495

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: 1e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 8
• total_eval_batch_size: 8
• optimizer: Use adamw_torch with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.2938	0.1408	10	0.3067
0.2167	0.2817	20	0.2746
0.2339	0.4225	30	0.2653
0.3247	0.5634	40	0.2608
0.2055	0.7042	50	0.2564
0.2555	0.8451	60	0.2536
0.2486	0.9859	70	0.2510
0.254	1.1268	80	0.2533
0.188	1.2676	90	0.2525
0.2137	1.4085	100	0.2502
0.2181	1.5493	110	0.2500
0.2752	1.6901	120	0.2501
0.1925	1.8310	130	0.2497
0.1969	1.9718	140	0.2495

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1