learning_rate: 5e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Use 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
training_steps: 7200
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
18.6462	0.025	180	4.6356	0.0178
18.5586	1.0250	360	4.6307	0.0178
18.5336	2.0249	540	4.6175	0.0178
18.4061	3.0250	721	4.6010	0.0237
18.4296	4.025	901	4.6124	0.0178
18.2093	5.0250	1081	4.5984	0.0325
18.0237	6.0249	1261	4.5540	0.0148
17.4151	7.0250	1442	4.4870	0.0237
16.8583	8.025	1622	4.3815	0.0266
16.1956	9.0250	1802	4.2802	0.0414
15.5695	10.0249	1982	4.1388	0.0473
14.5735	11.0250	2163	3.9890	0.0710
13.4312	12.025	2343	3.7280	0.1065
12.0333	13.0250	2523	3.5096	0.1686
10.5096	14.0249	2703	3.3636	0.1805
8.9214	15.0250	2884	3.1767	0.2337
7.4521	16.025	3064	2.9754	0.2781
6.1617	17.0250	3244	2.8687	0.2781
4.9368	18.0249	3424	2.7472	0.3343
3.7959	19.0250	3605	2.5918	0.3639
2.8585	20.025	3785	2.6698	0.3432
2.1971	21.0250	3965	2.5368	0.3935
1.6464	22.0249	4145	2.5242	0.3935
1.1763	23.0250	4326	2.4909	0.4142
0.9575	24.025	4506	2.4721	0.4260
0.6456	25.0250	4686	2.4560	0.4083
0.4699	26.0249	4866	2.4103	0.4053
0.3633	27.0250	5047	2.4689	0.4379
0.2726	28.025	5227	2.3656	0.4379
0.2045	29.0250	5407	2.4719	0.4467
0.1629	30.0249	5587	2.4916	0.4438
0.1193	31.0250	5768	2.4569	0.4438
0.1116	32.025	5948	2.5053	0.4527
0.0723	33.0250	6128	2.5459	0.4556
0.0818	34.0249	6308	2.5362	0.4645
0.0586	35.0250	6489	2.5750	0.4467
0.0651	36.025	6669	2.5845	0.4527
0.061	37.0250	6849	2.5880	0.4586
0.0664	38.0249	7029	2.5688	0.4734
0.0414	39.0236	7200	2.5702	0.4645

Shawon16/videoMAE_base_wlasl_100_40ep_coR_p10

videoMAE_base_wlasl_100_40ep_coR_p10