learning_rate: 5e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
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
lr_scheduler_warmup_steps: 100
num_epochs: 15
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Per	F1
10644.2969	1.0	104	1769.8489	1.0	0.0
3574.9772	2.0	208	1750.3961	1.0	0.0
3545.2557	3.0	312	1695.6754	1.0	0.0
2887.0763	4.0	416	950.4882	0.5267	0.6152
1578.4336	5.0	520	499.5067	0.2055	0.8318
992.7874	6.0	624	359.3315	0.1425	0.8840
744.5349	7.0	728	302.4440	0.1241	0.9000
610.2494	8.0	832	276.7447	0.1087	0.9108
528.7354	9.0	936	261.9057	0.1062	0.9128
471.6001	10.0	1040	248.0333	0.1025	0.9159
436.0370	11.0	1144	245.9362	0.0987	0.9189
405.6233	12.0	1248	236.4591	0.0979	0.9194
388.4592	13.0	1352	237.1770	0.0960	0.9208
373.4797	14.0	1456	232.7693	0.0940	0.9224
362.8645	15.0	1560	232.5266	0.0944	0.9222

waelhasan/wav2vec2-mdd-arab-grad-project

wav2vec2-mdd-arab-grad-project