4a2ae7ad-1989-4607-8533-8d14ef4b1dd0

This model is a fine-tuned version of JackFram/llama-68m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.4074

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: 0.000204
• train_batch_size: 4
• eval_batch_size: 4
• seed: 40
• 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: 254

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0039	1	4.9531
3.2081	0.1969	50	3.3028
2.6354	0.3937	100	2.7675
2.2916	0.5906	150	2.5760
2.3519	0.7874	200	2.4549
2.2586	0.9843	250	2.4074

Framework versions

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