learning_rate: 5e-05
train_batch_size: 128
eval_batch_size: 128
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 256
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 20
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision Macro	Recall Macro	F1 Macro	F1 Weighted
1.0641	1.0	72	0.6313	0.7565	0.7672	0.7575	0.7562	0.7561
0.64	2.0	144	0.5313	0.8044	0.8077	0.8042	0.8039	0.8040
0.3679	3.0	216	0.5117	0.8062	0.8078	0.8067	0.8060	0.8059
0.2855	4.0	288	0.5816	0.8098	0.8150	0.8101	0.8087	0.8087
0.1571	5.0	360	0.6372	0.8058	0.8060	0.8058	0.8058	0.8059
0.1165	6.0	432	0.6929	0.8177	0.8186	0.8177	0.8178	0.8178
0.0855	7.0	504	0.7374	0.8084	0.8090	0.8087	0.8084	0.8084
0.0704	8.0	576	0.8241	0.8075	0.8107	0.8071	0.8075	0.8075
0.0593	9.0	648	0.9712	0.8098	0.8108	0.8094	0.8095	0.8096
0.0415	10.0	720	0.8643	0.8155	0.8165	0.8153	0.8155	0.8155
0.034	11.0	792	0.9662	0.8124	0.8149	0.8120	0.8123	0.8123
0.0273	12.0	864	1.0114	0.8182	0.8188	0.8181	0.8182	0.8182
0.0189	13.0	936	1.2237	0.8155	0.8195	0.8159	0.8156	0.8155
0.0068	14.0	1008	1.2312	0.8244	0.8265	0.8247	0.8244	0.8244
0.011	15.0	1080	1.2062	0.8315	0.8316	0.8316	0.8314	0.8314
0.003	16.0	1152	1.2550	0.8279	0.8280	0.8280	0.8280	0.8279
0.0024	17.0	1224	1.2774	0.8302	0.8303	0.8303	0.8302	0.8302
0.003	18.0	1296	1.2946	0.8293	0.8295	0.8295	0.8292	0.8292
0.0023	19.0	1368	1.2969	0.8306	0.8307	0.8308	0.8306	0.8306
0.0012	20.0	1440	1.2989	0.8306	0.8307	0.8308	0.8306	0.8306

aiface/CafeBERT_nli

CafeBERT_nli