You can deploy this model and start earning money today!

xiulinyang/
gpt2_mini_baby_30M_32768_42

Name: gpt2_mini_baby_30M_32768_42
Availability: InStock

Views

No views yet

gpt2_mini_baby_30M_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
6.3592	0.73	2000	6.5099	0.1705
4.6975	1.46	4000	5.5909	0.2060
4.341	2.19	6000	5.2411	0.2183
4.1307	2.93	8000	4.9924	0.2344
3.9425	3.66	10000	4.7904	0.2493
3.7927	4.39	12000	4.6244	0.2609
3.6714	5.12	14000	4.4828	0.2711
3.5653	5.85	16000	4.3561	0.2801
3.4674	6.58	18000	4.2592	0.2871
3.3755	7.32	20000	4.1754	0.2958
3.3145	8.05	22000	4.1103	0.3018
3.2534	8.78	24000	4.0454	0.3076
3.1873	9.51	26000	3.9979	0.3115
3.1397	10.24	28000	3.9587	0.3162
3.1173	10.97	30000	3.9136	0.3209
3.0769	11.7	32000	3.8934	0.3229
3.0338	12.44	34000	3.8709	0.3253
2.9993	13.17	36000	3.8487	0.3277
2.9957	13.9	38000	3.8201	0.3299
2.9653	14.63	40000	3.8136	0.3319
2.9251	15.36	42000	3.7927	0.3333
2.9193	16.09	44000	3.7771	0.3358
2.896	16.83	46000	3.7666	0.3368
2.8698	17.56	48000	3.7607	0.3383
2.8435	18.29	50000	3.7521	0.3393
2.8516	19.02	52000	3.7389	0.3410
2.8278	19.75	54000	3.7367	0.3415
2.801	20.48	56000	3.7265	0.3425
2.799	21.21	58000	3.7257	0.3432
2.7908	21.95	60000	3.7205	0.3439
2.7781	22.68	62000	3.7144	0.3451
2.7552	23.41	64000	3.7128	0.3453
2.7582	24.14	66000	3.7122	0.3459
2.7501	24.87	68000	3.7043	0.3470
2.7315	25.6	70000	3.7079	0.3472
2.7157	26.34	72000	3.7017	0.3478
2.7273	27.07	74000	3.7003	0.3478
2.7143	27.8	76000	3.6962	0.3487
2.698	28.53	78000	3.6957	0.3488
2.6875	29.26	80000	3.6947	0.3493
2.7015	29.99	82000	3.6917	0.3493
2.6808	30.72	84000	3.6937	0.3501
2.6621	31.46	86000	3.6907	0.3501
2.6745	32.19	88000	3.6928	0.3502
2.6681	32.92	90000	3.6855	0.3508
2.6545	33.65	92000	3.6860	0.3511
2.6436	34.38	94000	3.6858	0.3512
2.6483	35.11	96000	3.6835	0.3514
2.6385	35.84	98000	3.6808	0.3518
2.6388	36.58	100000	3.6819	0.3519