Model description

More information needed

Intended uses & limitations

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 0.0004
train_batch_size: 4
eval_batch_size: 4
seed: 1337
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: polynomial
training_steps: 6450

Training Loss	Epoch	Step	Validation Loss
54.5306	1.0	129	47.6483
42.7396	2.0	258	34.9192
38.1013	3.0	387	31.6591
32.8585	4.0	516	33.2288
30.481	5.0	645	31.1107
29.7583	6.0	774	33.4640
26.7225	7.0	903	28.5952
26.0046	8.0	1032	29.7853
24.8025	9.0	1161	28.1448
24.0444	10.0	1290	29.0327
23.1171	11.0	1419	27.7611
22.0008	12.0	1548	27.4982
22.4006	13.0	1677	28.5804
20.6462	14.0	1806	26.5733
20.1936	15.0	1935	27.0318
19.4983	16.0	2064	26.2896
19.4915	17.0	2193	27.2829
18.8834	18.0	2322	27.4219
17.7948	19.0	2451	26.9262
17.7806	20.0	2580	28.1830
17.3828	21.0	2709	26.5501
16.7812	22.0	2838	27.7953
16.5225	23.0	2967	26.7844
16.6727	24.0	3096	29.3165
15.9375	25.0	3225	29.3433
15.554	26.0	3354	27.7353
15.3216	27.0	3483	28.5868
15.2336	28.0	3612	30.1337
14.4484	29.0	3741	29.4535
14.5668	30.0	3870	29.9552
14.2886	31.0	3999	30.3295
13.9594	32.0	4128	30.9996
13.3464	33.0	4257	29.5446
14.3524	34.0	4386	30.5839
13.7015	35.0	4515	31.6050
13.1693	36.0	4644	30.4525
13.0106	37.0	4773	30.8857
13.4503	38.0	4902	33.0173
12.885	39.0	5031	33.0191
12.4798	40.0	5160	32.4086
12.569	41.0	5289	35.1227
12.2572	42.0	5418	33.3447
12.1342	43.0	5547	34.8180
12.6542	44.0	5676	34.2102
11.9929	45.0	5805	35.5142
11.2777	46.0	5934	36.4062
12.3835	47.0	6063	36.1198
11.4719	48.0	6192	36.6292
12.1422	49.0	6321	36.8263
11.636	50.0	6450	36.5817