learning_rate: 5e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 4
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 200
num_epochs: 3
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
2.1439	0.1686	500	1.9988
1.919	0.3372	1000	1.7011
1.6665	0.5057	1500	1.5434
1.4834	0.6743	2000	1.4272
1.4149	0.8429	2500	1.3405
1.3279	1.0115	3000	1.2766
1.1643	1.1800	3500	1.2236
1.151	1.3486	4000	1.1806
1.1403	1.5172	4500	1.1421
1.0784	1.6858	5000	1.1136
1.0303	1.8543	5500	1.0795
0.8385	2.0229	6000	1.0726
0.8542	2.1915	6500	1.0580
0.7797	2.3601	7000	1.0466
0.8073	2.5287	7500	1.0307
0.7923	2.6972	8000	1.0134
0.7565	2.8658	8500	1.0069

ars1m/medical_chatbot_model

medical_chatbot_model