learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 32
seed: 42
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: 0.1
num_epochs: 6
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	F1 Contradictory	F1 Overriding Suspicion	F1 Nefarious Intent	F1 Persecuted Victim	F1 Immune To Evidence	F1 Reinterpreting Randomness	Macro F1	Micro F1
0.2721	1.0	100	0.3105	0.0	0.6	0.5649	0.2092	0.28	0.3920	0.3410	0.4886
0.2332	2.0	200	0.3372	0.0177	0.6601	0.6708	0.3167	0.3344	0.3814	0.3968	0.5335
0.1490	3.0	300	0.3975	0.0	0.7035	0.6841	0.2857	0.3396	0.4010	0.4023	0.5893
0.1420	4.0	400	0.4999	0.0	0.7089	0.6701	0.2532	0.3314	0.3830	0.3911	0.5987
0.1038	5.0	500	0.5314	0.0	0.6874	0.6601	0.2532	0.3541	0.4070	0.3936	0.5871
0.0963	6.0	600	0.5686	0.0	0.6617	0.6628	0.2133	0.3263	0.3878	0.3753	0.5741

MarcoCharon/iw-conspir-v3

iw-conspir-v3