learning_rate: 0.0002
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
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
num_epochs: 5

Training Loss	Epoch	Step	Validation Loss
3.5665	0.3556	100	3.1386
3.0398	0.7111	200	3.0567
2.9252	1.064	300	3.0102
2.8475	1.4196	400	2.9824
2.8068	1.7751	500	2.9564
2.736	2.128	600	2.9535
2.6993	2.4836	700	2.9417
2.6785	2.8391	800	2.9309
2.6215	3.192	900	2.9332
2.575	3.5476	1000	2.9244
2.5789	3.9031	1100	2.9233
2.4963	4.256	1200	2.9345
2.5072	4.6116	1300	2.9338
2.4719	4.9671	1400	2.9338

Ratul-Chakraborty/pk-bloomz

pk-bloomz