learning_rate: 0.0002
train_batch_size: 32
eval_batch_size: 32
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: cosine
num_epochs: 5
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
1.3577	0.0962	10	1.2713
1.3243	0.1923	20	1.2728
1.3107	0.2885	30	1.2959
1.312	0.3846	40	1.2748
1.3671	0.4808	50	1.3367
1.3327	0.5769	60	1.3070
1.3419	0.6731	70	1.3431
1.3405	0.7692	80	1.2734
1.2465	0.8654	90	1.2881
1.3376	0.9615	100	1.2953
1.2883	1.0577	110	1.2678
1.3219	1.1538	120	1.2775
1.2754	1.25	130	1.2876
1.293	1.3462	140	1.2705
1.2848	1.4423	150	1.2747
1.3346	1.5385	160	1.2852
1.3195	1.6346	170	1.2678
1.3516	1.7308	180	1.3041
1.3072	1.8269	190	1.2718
1.3103	1.9231	200	1.3155
1.338	2.0192	210	1.2849
1.3551	2.1154	220	1.2753
1.3342	2.2115	230	1.3073
1.3228	2.3077	240	1.2871
1.335	2.4038	250	1.2732
1.3218	2.5	260	1.2806
1.2967	2.5962	270	1.2738
1.2826	2.6923	280	1.2746
1.2718	2.7885	290	1.2680
1.2969	2.8846	300	1.2714
1.3147	2.9808	310	1.2699
1.253	3.0769	320	1.2703
1.3062	3.1731	330	1.2714
1.303	3.2692	340	1.2708
1.3001	3.3654	350	1.2814
1.3067	3.4615	360	1.2780
1.2818	3.5577	370	1.2708
1.3128	3.6538	380	1.2702
1.2715	3.75	390	1.2761
1.3178	3.8462	400	1.2673
1.2829	3.9423	410	1.2697
1.3103	4.0385	420	1.2723
1.3009	4.1346	430	1.2728
1.2902	4.2308	440	1.2697
1.3163	4.3269	450	1.2690
1.3005	4.4231	460	1.2689
1.3083	4.5192	470	1.2693
1.2759	4.6154	480	1.2690
1.2771	4.7115	490	1.2690
1.2882	4.8077	500	1.2691
1.2749	4.9038	510	1.2692
1.2892	5.0	520	1.2692

YuvrajSingh9886/roberta-base-Maradona

roberta-base-Maradona