learning_rate: 3e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
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_ratio: 0.1
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	Precision Macro	Recall Macro
1.2114	1.0	4931	1.2224	0.6245	0.5249	0.5555	0.5501
1.0885	2.0	9862	1.1036	0.6427	0.5596	0.6009	0.5591
0.9781	3.0	14793	1.0828	0.6491	0.5760	0.6188	0.5811
0.8621	4.0	19724	1.0956	0.6569	0.5979	0.6363	0.6014
0.7267	5.0	24655	1.0899	0.6626	0.5970	0.6088	0.5941
0.6066	6.0	29586	1.2078	0.6517	0.5928	0.6177	0.5848
0.4627	7.0	34517	1.3349	0.6504	0.6037	0.6113	0.6008
0.3238	8.0	39448	1.5315	0.6398	0.5951	0.6064	0.5891
0.224	9.0	44379	1.8234	0.6438	0.5936	0.5994	0.5897
0.149	9.9981	49300	2.0762	0.6442	0.6011	0.6024	0.6007

c-ho/xlm_roberta_large_test_linsearch_apr2025

xlm_roberta_large_test_linsearch_only_abstract