learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 0.06
num_epochs: 40
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	F1 Micro	F1 Macro
0.3106	1.0	140	0.2986	0.0	0.0
0.2294	2.0	280	0.2075	0.5667	0.2151
0.1731	3.0	420	0.1717	0.7017	0.4464
0.1240	4.0	560	0.1316	0.7654	0.5373
0.0812	5.0	700	0.1237	0.7710	0.5790
0.0737	6.0	840	0.1214	0.7860	0.6067
0.0599	7.0	980	0.1111	0.8108	0.6502
0.0446	8.0	1120	0.1067	0.8161	0.6664
0.0359	9.0	1260	0.1090	0.8164	0.6773
0.0277	10.0	1400	0.1099	0.8209	0.6826
0.0206	11.0	1540	0.1133	0.8114	0.6649
0.0193	12.0	1680	0.1109	0.8214	0.6812
0.0175	13.0	1820	0.1182	0.8178	0.6996
0.0130	14.0	1960	0.1137	0.8262	0.7195
0.0107	15.0	2100	0.1129	0.8287	0.7033
0.0084	16.0	2240	0.1142	0.8355	0.7179
0.0073	17.0	2380	0.1153	0.8314	0.7213
0.0086	18.0	2520	0.1124	0.8381	0.7254
0.0064	19.0	2660	0.1142	0.8388	0.7269
0.0065	20.0	2800	0.1150	0.8400	0.7367
0.0046	21.0	2940	0.1171	0.8346	0.7174
0.0055	22.0	3080	0.1168	0.8421	0.7333
0.0048	23.0	3220	0.1184	0.8375	0.7252
0.0057	24.0	3360	0.1191	0.8389	0.7425
0.0046	25.0	3500	0.1195	0.8380	0.7264
0.0051	26.0	3640	0.1192	0.8383	0.7407
0.0042	27.0	3780	0.1205	0.8355	0.7315
0.0040	28.0	3920	0.1229	0.8331	0.7263
0.0035	29.0	4060	0.1231	0.8344	0.7326

silke-delcart/NLP-final-project

NLP-final-project