Llama2-7B-Medical-Finetune_V2/README.md

base_model, tags, model-index

base_model	tags	model-index
meta-llama/Llama-2-7b-chat-hf	trl sft generated_from_trainer	name results Llama2-7B-Medical-Finetune_V2

Llama2-7B-Medical-Finetune_V2

This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0369

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: 0.00025
• train_batch_size: 26
• eval_batch_size: 26
• seed: 42
• gradient_accumulation_steps: 26
• total_train_batch_size: 676
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.2907	0.3	100	1.1620
1.1355	0.59	200	1.1211
1.1063	0.89	300	1.0957
1.0724	1.19	400	1.0780
1.0489	1.49	500	1.0633
1.0359	1.78	600	1.0512
1.0228	2.08	700	1.0447
0.9924	2.38	800	1.0401
0.9906	2.68	900	1.0375
0.9863	2.97	1000	1.0369

Framework versions

• Transformers 4.35.2
• Pytorch 2.2.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.1