learning_rate: 5e-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
num_epochs: 20
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Accuracy	Precision	Recall	F1	Validation Loss
No log	1.0	13	0.5457	0.5231	0.5457	0.4294	1.0285
No log	2.0	26	0.4100	0.1876	0.4100	0.2461	1.0252
No log	3.0	39	0.5023	0.6704	0.5023	0.4244	0.8830
No log	4.0	52	0.4991	0.7051	0.4991	0.4072	1.2035
No log	5.0	65	0.4291	0.7156	0.4291	0.2829	1.3921
No log	6.0	78	0.5491	0.7090	0.5491	0.4926	0.9938
No log	7.0	91	0.5763	0.7044	0.5763	0.5365	1.0815
No log	8.0	104	0.6624	0.6520	0.6624	0.6503	0.7027
No log	9.0	117	0.6374	0.6696	0.6374	0.6308	0.9327
No log	10.0	130	0.6549	0.6680	0.6549	0.6484	0.7493
No log	11.0	143	0.6552	0.6597	0.6552	0.6499	0.7772
No log	12.0	156	0.6604	0.6500	0.6604	0.6536	0.7496
No log	13.0	169	0.6556	0.6643	0.6556	0.6502	0.8145
No log	14.0	182	0.6588	0.6591	0.6588	0.6536	0.7831
No log	15.0	195	0.6622	0.6604	0.6622	0.6572	0.7797
No log	16.0	208	0.6588	0.6661	0.6588	0.6532	0.8084
No log	17.0	221	0.6624	0.6672	0.6624	0.6578	0.8129
No log	18.0	234	0.6597	0.6617	0.6597	0.6550	0.8171
No log	18.48	240	0.6570	0.6586	0.6570	0.6525	0.8216

yemen2016/danskbert_indirect_speech

danskbert_indirect_speech