e90b6e86-f65f-4cda-8aef-716b152cf55d

This model is a fine-tuned version of fxmarty/tiny-dummy-qwen2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 11.9142

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: 0.000213
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0002	1	11.9320
11.9221	0.0104	50	11.9214
11.9183	0.0209	100	11.9194
11.9153	0.0313	150	11.9168
11.9133	0.0417	200	11.9155
11.9131	0.0522	250	11.9150
11.9128	0.0626	300	11.9147
11.9109	0.0731	350	11.9144
11.9118	0.0835	400	11.9143
11.9132	0.0939	450	11.9142
11.9107	0.1044	500	11.9142

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1