e71f3d12-3439-4358-879a-3311ff89a029

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: 11.9184

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: 0.000203
• 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	11.9326
11.9259	0.0118	50	11.9237
11.9206	0.0235	100	11.9212
11.9201	0.0353	150	11.9209
11.9218	0.0470	200	11.9201
11.9193	0.0588	250	11.9196
11.9197	0.0705	300	11.9190
11.9186	0.0823	350	11.9187
11.9207	0.0941	400	11.9185
11.9188	0.1058	450	11.9185
11.9168	0.1176	500	11.9184

Framework versions

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