learning_rate: 5e-05
train_batch_size: 14
eval_batch_size: 8
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: 1

Training Loss	Epoch	Step	Validation Loss
11.081	0.0161	1	7.6957
7.2974	0.0323	2	4.3568
4.4097	0.0484	3	1.9400
1.9547	0.0645	4	0.8222
0.8794	0.0806	5	0.4759
0.516	0.0968	6	0.4206
0.4622	0.1129	7	0.4044
0.4349	0.1290	8	0.3880
0.4338	0.1452	9	0.3734
0.4054	0.1613	10	0.3620
0.3903	0.1774	11	0.3544
0.3927	0.1935	12	0.3486
0.3585	0.2097	13	0.3433
0.3877	0.2258	14	0.3381
0.3611	0.2419	15	0.3329
0.3164	0.2581	16	0.3279
0.3437	0.2742	17	0.3234
0.305	0.2903	18	0.3193
0.326	0.3065	19	0.3157
0.2885	0.3226	20	0.3127
0.3415	0.3387	21	0.3101
0.2878	0.3548	22	0.3077
0.3514	0.3710	23	0.3055
0.3326	0.3871	24	0.3035
0.3211	0.4032	25	0.3016
0.339	0.4194	26	0.2999
0.2991	0.4355	27	0.2984
0.3143	0.4516	28	0.2971
0.3136	0.4677	29	0.2959
0.3053	0.4839	30	0.2948
0.2874	0.5	31	0.2938
0.2973	0.5161	32	0.2929
0.3325	0.5323	33	0.2920
0.2851	0.5484	34	0.2912
0.32	0.5645	35	0.2905
0.2977	0.5806	36	0.2897
0.3346	0.5968	37	0.2890
0.2807	0.6129	38	0.2884
0.2835	0.6290	39	0.2877
0.3279	0.6452	40	0.2871
0.341	0.6613	41	0.2866
0.2772	0.6774	42	0.2861
0.2953	0.6935	43	0.2857
0.3148	0.7097	44	0.2853
0.2989	0.7258	45	0.2849
0.3328	0.7419	46	0.2845
0.2642	0.7581	47	0.2842
0.2524	0.7742	48	0.2839
0.3357	0.7903	49	0.2836
0.2786	0.8065	50	0.2834
0.2984	0.8226	51	0.2831
0.2667	0.8387	52	0.2829
0.33	0.8548	53	0.2827
0.3078	0.8710	54	0.2826
0.3182	0.8871	55	0.2824
0.2762	0.9032	56	0.2823
0.2946	0.9194	57	0.2821
0.2842	0.9355	58	0.2820
0.2594	0.9516	59	0.2820
0.2544	0.9677	60	0.2819
0.3066	0.9839	61	0.2819
0.2675	1.0	62	0.2818

estradax/gpt2-finetuned-qna-crypto

gpt2-finetuned-qna-crypto