run_muril_raw

This model is a fine-tuned version of google/muril-base-cased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.8973
• Macro F1: 0.8200
• Accuracy: 0.8125

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Macro F1	Accuracy
No log	1.0	97	1.7769	0.2355	0.3281
No log	2.0	194	1.4481	0.3167	0.4271
No log	3.0	291	1.2057	0.4595	0.5625
No log	4.0	388	0.9584	0.6679	0.6979
No log	5.0	485	0.7727	0.8177	0.8177
1.2290	6.0	582	0.6978	0.8170	0.8177
1.2290	7.0	679	0.6900	0.8202	0.8177
1.2290	8.0	776	0.6740	0.8313	0.8229
1.2290	9.0	873	0.6215	0.8560	0.8542
1.2290	10.0	970	0.7259	0.8320	0.8281
0.2276	11.0	1067	0.8884	0.8074	0.8021
0.2276	12.0	1164	0.8973	0.8200	0.8125

Framework versions

• Transformers 5.16.1
• Pytorch 2.11.0+cu128
• Datasets 4.8.5
• Tokenizers 0.23.1