Model save

README.md

@@ -0,0 +1,72 @@
+---
+library_name: transformers
+base_model: syssec-utd/py314-pylingual-v3-mlm
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: py314-pylingual-v3-segmenter
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# py314-pylingual-v3-segmenter
+
+This model is a fine-tuned version of [syssec-utd/py314-pylingual-v3-mlm](https://huggingface.co/syssec-utd/py314-pylingual-v3-mlm) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0069
+- Precision: 0.9918
+- Recall: 0.9848
+- F1: 0.9883
+- Accuracy: 0.9968
+
+## 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: 2e-05
+- train_batch_size: 48
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 3
+- total_train_batch_size: 144
+- total_eval_batch_size: 24
+- 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
+- num_epochs: 2
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0068        | 1.0   | 44197 | 0.0076          | 0.9903    | 0.9772 | 0.9837 | 0.9959   |
+| 0.0039        | 2.0   | 88394 | 0.0069          | 0.9918    | 0.9848 | 0.9883 | 0.9968   |
+
+
+### Framework versions
+
+- Transformers 4.57.3
+- Pytorch 2.9.1+cu128
+- Datasets 4.4.1
+- Tokenizers 0.22.1