You can deploy this model and start earning money today!

xiulinyang/
gpt2_mini_baby_50M_32768_42

Name: gpt2_mini_baby_50M_32768_42
Availability: InStock

Views

No views yet

gpt2_mini_baby_50M_32768_42

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

Training Loss	Epoch	Step	Validation Loss	Accuracy
6.4363	0.43	2000	6.5555	0.1669
4.7651	0.87	4000	5.6007	0.2050
4.4184	1.3	6000	5.2506	0.2163
4.2102	1.73	8000	5.0149	0.2299
4.0321	2.17	10000	4.7996	0.2476
3.8932	2.6	12000	4.6323	0.2602
3.7622	3.03	14000	4.4786	0.2716
3.6542	3.47	16000	4.3621	0.2799
3.5581	3.9	18000	4.2604	0.2874
3.4727	4.33	20000	4.1735	0.2954
3.4029	4.77	22000	4.0963	0.3022
3.3365	5.2	24000	4.0384	0.3082
3.2935	5.64	26000	3.9855	0.3137
3.2385	6.07	28000	3.9292	0.3187
3.1984	6.5	30000	3.8944	0.3215
3.1741	6.94	32000	3.8659	0.3250
3.1333	7.37	34000	3.8328	0.3277
3.1123	7.8	36000	3.8142	0.3298
3.0711	8.24	38000	3.7918	0.3312
3.0716	8.67	40000	3.7729	0.3334
3.0384	9.1	42000	3.7552	0.3357
3.0178	9.54	44000	3.7382	0.3377
3.0097	9.97	46000	3.7170	0.3397
2.9748	10.4	48000	3.7111	0.3406
2.975	10.84	50000	3.6924	0.3427
2.9429	11.27	52000	3.6832	0.3442
2.9481	11.7	54000	3.6742	0.3447
2.9206	12.14	56000	3.6676	0.3456
2.9138	12.57	58000	3.6554	0.3472
2.9262	13.0	60000	3.6539	0.3481
2.8956	13.44	62000	3.6439	0.3489
2.9017	13.87	64000	3.6371	0.3502
2.8628	14.3	66000	3.6371	0.3495
2.8775	14.74	68000	3.6237	0.3517
2.8611	15.17	70000	3.6270	0.3509
2.8581	15.6	72000	3.6171	0.3520
2.8557	16.04	74000	3.6136	0.3531
2.8383	16.47	76000	3.6082	0.3529
2.8463	16.91	78000	3.6040	0.3539
2.8209	17.34	80000	3.6049	0.3542
2.8257	17.77	82000	3.6000	0.3546
2.8111	18.21	84000	3.5972	0.3554
2.8092	18.64	86000	3.5951	0.3556
2.8098	19.07	88000	3.5931	0.3556
2.7985	19.51	90000	3.5923	0.3568
2.8038	19.94	92000	3.5834	0.3571
2.7879	20.37	94000	3.5829	0.3572
2.7898	20.81	96000	3.5804	0.3576
2.776	21.24	98000	3.5801	0.3577
2.7778	21.67	100000	3.5788	0.3578