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_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 9

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0128	0.5714	400	0.9888	0.5866
0.9791	1.1429	800	0.8602	0.6831
0.8077	1.7143	1200	0.8283	0.7246
0.2678	2.2857	1600	0.8748	0.7260
0.6564	2.8571	2000	0.7661	0.7568
0.1334	3.4286	2400	0.7627	0.7711
0.2002	4.0	2800	0.7838	0.7754
0.4461	4.5714	3200	0.8242	0.7854
0.0927	5.1429	3600	0.8513	0.7797
0.6988	5.7143	4000	0.8268	0.7911
0.468	6.2857	4400	0.9100	0.7797
1.7041	6.8571	4800	0.8209	0.8011
0.561	7.4286	5200	0.8592	0.7983
0.4816	8.0	5600	0.8902	0.7990
0.5653	8.5714	6000	0.8957	0.8026

auditi31/HuBERT-LARGE-F5-New

HuBERT-LARGE-F5-New