MedQA_L3_1000steps_1e7rate_SFT

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7486

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: 1e-07
• train_batch_size: 2
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss
1.774	0.0489	50	1.7867
1.7099	0.0977	100	1.6989
1.5873	0.1466	150	1.5668
1.4721	0.1954	200	1.4501
1.3469	0.2443	250	1.3336
1.2381	0.2931	300	1.2152
1.1195	0.3420	350	1.1046
1.0094	0.3908	400	1.0086
0.9372	0.4397	450	0.9280
0.8756	0.4885	500	0.8669
0.8221	0.5374	550	0.8219
0.8048	0.5862	600	0.7900
0.7759	0.6351	650	0.7691
0.7465	0.6839	700	0.7568
0.7426	0.7328	750	0.7506
0.7462	0.7816	800	0.7488
0.7764	0.8305	850	0.7486
0.7327	0.8793	900	0.7486
0.7316	0.9282	950	0.7486
0.7478	0.9770	1000	0.7486

Framework versions

• Transformers 4.41.0
• Pytorch 2.0.0+cu117
• Datasets 2.19.1
• Tokenizers 0.19.1