9f129d61-8632-45c9-849d-b9e5ac8f6b93

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: 0.6775

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: 0.000212
• 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	0.0003	1	5.4387
1.4398	0.0173	50	1.6982
0.938	0.0345	100	1.2479
0.8383	0.0518	150	1.1411
0.6159	0.0690	200	0.9577
0.7404	0.0863	250	0.9037
0.5642	0.1035	300	0.8304
0.578	0.1208	350	0.7515
0.6018	0.1380	400	0.6989
0.5285	0.1553	450	0.6766
0.5686	0.1725	500	0.6775

Framework versions

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