learning_rate: 5e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
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: 8.0
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
1.6429	0.1095	200	1.5249
1.5576	0.2189	400	1.4750
1.5404	0.3284	600	1.4393
1.5029	0.4379	800	1.4116
1.4252	0.5473	1000	1.3929
1.4361	0.6568	1200	1.3649
1.3958	0.7663	1400	1.3523
1.4064	0.8758	1600	1.3419
1.3853	0.9852	1800	1.3217
1.3707	1.0947	2000	1.3137
1.3580	1.2042	2200	1.3013
1.3785	1.3136	2400	1.2921
1.3552	1.4231	2600	1.2855
1.3694	1.5326	2800	1.2751
1.3128	1.6420	3000	1.2692
1.3424	1.7515	3200	1.2673
1.3293	1.8610	3400	1.2614
1.3435	1.9704	3600	1.2524
1.2980	2.0799	3800	1.2489

jeanmidev/trackmania-tmnf-distilgpt2-v2

trackmania-tmnf-distilgpt2-v2