learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
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_steps: 2580
num_epochs: 15

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
12.4308	1.0	1032	3.0083	0.8616	0.8616
5.9766	2.0	2064	2.4421	0.8892	0.8891
4.296	3.0	3096	1.8710	0.8791	0.8791
3.0918	4.0	4128	1.5497	0.8855	0.8855
2.3284	5.0	5160	1.1863	0.8990	0.8990
1.8019	6.0	6192	1.0596	0.9016	0.9016
1.4113	7.0	7224	0.8676	0.8944	0.8943
1.1585	8.0	8256	0.7534	0.9079	0.9080
0.9332	9.0	9288	0.6953	0.9001	0.9002
0.8079	10.0	10320	0.7428	0.8973	0.8973
0.7033	11.0	11352	0.7131	0.9076	0.9077

ttqdunggg/hybrid_lexical_hosting_64_15

hybrid_lexical_hosting_64_15