learning_rate: 2e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
4.2281	0.3193	500	4.0769
4.1077	0.6385	1000	4.0222
4.0667	0.9578	1500	3.9898
4.0905	1.2765	2000	3.9738
4.008	1.5957	2500	3.9561
4.0071	1.9150	3000	3.9448
3.9696	2.2337	3500	3.9376
3.9984	2.5530	4000	3.9289
3.9279	2.8722	4500	3.9212
3.9569	3.1909	5000	3.9181
3.9598	3.5102	5500	3.9154
3.9403	3.8294	6000	3.9126
3.908	4.1481	6500	3.9117
3.9344	4.4674	7000	3.9109
3.9645	4.7867	7500	3.9105

kriteekathapa/gpt2-poems-finetuned-v1

gpt2-poems-finetuned-v1