learning_rate: 2e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
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: linear
num_epochs: 18
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
3.8855	1.0	53	3.3830
3.4777	2.0	106	3.2701
3.3303	3.0	159	3.0544
3.1507	4.0	212	3.1233
3.0755	5.0	265	2.9944
2.9621	6.0	318	2.9380
2.8887	7.0	371	2.7652
2.7405	8.0	424	2.7211
2.6984	9.0	477	2.6333
2.6866	10.0	530	2.5593
2.6092	11.0	583	2.6409
2.606	12.0	636	2.7579
2.6133	13.0	689	2.5129
2.5196	14.0	742	2.5859
2.5082	15.0	795	2.5665
2.4753	16.0	848	2.4857
2.4284	17.0	901	2.5324
2.4461	18.0	954	2.3652

adity12345/chakma-lm

chakma-lm