You can deploy this model and start earning money today!

xiulinyang/
gpt2_small_baby_30M_32768_42f

Name: gpt2_small_baby_30M_32768_42f
Availability: InStock

Views

No views yet

gpt2_small_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
5.2872	0.72	2000	6.0570	0.2003
4.334	1.43	4000	5.4283	0.2172
4.0686	2.15	6000	5.1254	0.2404
3.8075	2.87	8000	4.8579	0.2623
3.6521	3.58	10000	4.6789	0.2783
3.5305	4.3	12000	4.5519	0.2889
3.4468	5.02	14000	4.4641	0.2968
3.3796	5.73	16000	4.3670	0.3039
3.3147	6.45	18000	4.2983	0.3093
3.2597	7.17	20000	4.2740	0.3121
3.2291	7.89	22000	4.2016	0.3168
3.1771	8.6	24000	4.1468	0.3194
3.126	9.32	26000	4.1398	0.3218
3.1267	10.04	28000	4.1255	0.3254
3.091	10.75	30000	4.0887	0.3277
3.0477	11.47	32000	4.0975	0.3282
3.0239	12.19	34000	4.1045	0.3305
3.0259	12.9	36000	4.0838	0.3307
2.9827	13.62	38000	4.0775	0.3312
2.9339	14.34	40000	4.1023	0.3316
2.9511	15.05	42000	4.0809	0.3337
2.9149	15.77	44000	4.0616	0.3354
2.8589	16.49	46000	4.0982	0.3358
2.8362	17.2	48000	4.0864	0.3345
2.8479	17.92	50000	4.0667	0.3364