learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
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: 23

Training Loss	Epoch	Step	Validation Loss
2.1297	1.0	1512	4.6129
1.8735	2.0	3024	4.2815
1.7233	3.0	4536	4.0705
1.6162	4.0	6048	3.9392
1.5457	5.0	7560	3.8424
1.4936	6.0	9072	3.7552
1.434	7.0	10584	3.7105
1.4082	8.0	12096	3.6719
1.3684	9.0	13608	3.6305
1.3299	10.0	15120	3.6176
1.2918	11.0	16632	3.5734
1.274	12.0	18144	3.5631
1.2425	13.0	19656	3.5680
1.2353	14.0	21168	3.5422
1.2091	15.0	22680	3.5249
1.1957	16.0	24192	3.5243
1.175	17.0	25704	3.5308
1.1616	18.0	27216	3.5351
1.1337	19.0	28728	3.5258
1.1318	20.0	30240	3.5298
1.126	21.0	31752	3.5283
1.1242	22.0	33264	3.5191
1.1109	23.0	34776	3.5242

Danteindrex/gpt2-dantegpt3

gpt2-dantegpt3