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: 10

Training Loss	Epoch	Step	Validation Loss	Macro F1	Literal F1	Idiom F1	Metaphor F1	Simile F1
0.3636	1.0	664	4.6354	0.3972	0.6867	0.28	0.1220	0.5
0.1915	2.0	1328	3.9581	0.4750	0.7029	0.2462	0.0938	0.8571
0.1923	3.0	1992	4.6809	0.4816	0.8373	0.0889	0.0	1.0
0.0204	4.0	2656	5.2775	0.5317	0.8401	0.1754	0.1111	1.0
0.0056	5.0	3320	6.5724	0.4901	0.8653	0.0952	0.0	1.0
0.0201	6.0	3984	8.8089	0.4797	0.8689	0.05	0.0	1.0
0.0284	7.0	4648	8.3943	0.5089	0.8734	0.0513	0.1111	1.0

KonradBRG/xlm-mlm-plains-cree-en-silver-sft-no-tlm

xlm-mlm-plains-cree-en-silver-sft-no-tlm