learning_rate: 3e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
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: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 35

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6905	1.0	23	0.6771	0.6
0.6385	2.0	46	0.5943	0.8222
0.491	3.0	69	0.3933	0.8667
0.35	4.0	92	0.2666	0.9333
0.2083	5.0	115	0.3853	0.8444
0.3464	6.0	138	0.2196	0.9333
0.0422	7.0	161	0.1174	0.9556
0.2935	8.0	184	0.3703	0.9111
0.0515	9.0	207	0.9962	0.7333
0.3358	10.0	230	0.2761	0.8889
0.0196	11.0	253	0.2279	0.9333
0.0138	12.0	276	0.1856	0.9556
0.3315	13.0	299	0.1883	0.9556
0.0481	14.0	322	0.2053	0.9556
0.1142	15.0	345	0.2177	0.9556
0.2434	16.0	368	0.2406	0.9333
0.0062	17.0	391	0.3580	0.9111
0.0052	18.0	414	0.2707	0.9333
0.1469	19.0	437	0.2602	0.9333
0.1411	20.0	460	0.2330	0.9556
0.1344	21.0	483	0.3096	0.9333
0.0855	22.0	506	0.3254	0.9333
0.0031	23.0	529	0.4003	0.9111
0.0027	24.0	552	0.3630	0.9333
0.0023	25.0	575	0.3692	0.9333
0.0024	26.0	598	0.3698	0.9333
0.0022	27.0	621	0.3709	0.9333
0.0022	28.0	644	0.3691	0.9333
0.0021	29.0	667	0.3770	0.9333
0.0018	30.0	690	0.3772	0.9333
0.002	31.0	713	0.3779	0.9333
0.0019	32.0	736	0.3779	0.9333
0.0019	33.0	759	0.3777	0.9333
0.0019	33.4889	770	0.3777	0.9333

Orama123/my_15Apr_model

my_15Apr_model