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	Dummy	Validation Loss
53.0042	1.0	129	1.0	41.6702
41.5032	2.0	258	1.0	35.3152
37.8318	3.0	387	1.0	33.2929
33.1734	4.0	516	1.0	31.6052
31.0889	5.0	645	1.0	32.0792
30.5091	6.0	774	1.0	29.4252
27.7742	7.0	903	1.0	29.3660
27.1136	8.0	1032	1.0	28.6043
25.1614	9.0	1161	1.0	28.0848
24.7794	10.0	1290	1.0	28.1507
23.636	11.0	1419	1.0	28.3853
22.7494	12.0	1548	1.0	27.2592
22.7129	13.0	1677	1.0	29.8838
21.1747	14.0	1806	1.0	28.1624
20.9589	15.0	1935	1.0	27.9121
20.2591	16.0	2064	1.0	26.6467
20.1436	17.0	2193	1.0	26.9901
19.5047	18.0	2322	1.0	29.2895
18.4257	19.0	2451	1.0	27.0489
18.6316	20.0	2580	1.0	27.3730
18.037	21.0	2709	1.0	28.0853
17.6324	22.0	2838	1.0	26.6344
17.19	23.0	2967	1.0	28.1709
17.5784	24.0	3096	1.0	26.3646
16.3714	25.0	3225	1.0	28.6477
16.2177	26.0	3354	1.0	29.9328
15.8326	27.0	3483	1.0	27.1418
15.7345	28.0	3612	1.0	28.5265
14.918	29.0	3741	1.0	30.8378
15.2316	30.0	3870	1.0	28.5173
14.6576	31.0	3999	1.0	29.0688
14.5837	32.0	4128	1.0	29.7354
13.7819	33.0	4257	1.0	28.6140
14.851	34.0	4386	1.0	30.7131
14.1454	35.0	4515	1.0	29.3673
13.5445	36.0	4644	1.0	30.1412
13.3725	37.0	4773	1.0	29.7489
13.8976	38.0	4902	1.0	32.2482
13.2317	39.0	5031	1.0	33.3837
12.8382	40.0	5160	1.0	31.9261
12.8798	41.0	5289	1.0	31.0644
12.5615	42.0	5418	1.0	32.6052
12.4595	43.0	5547	1.0	32.6710
12.9861	44.0	5676	1.0	32.3271
12.3429	45.0	5805	1.0	33.1802
11.6031	46.0	5934	1.0	33.3981
12.7182	47.0	6063	1.0	33.2806
11.8251	48.0	6192	1.0	33.9491
12.4439	49.0	6321	1.0	33.4338
11.9834	50.0	6450	1.0	33.8444