Model save

README.md

@@ -0,0 +1,73 @@
+---
+license: apache-2.0
+base_model: google-bert/bert-base-cased
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- recall
+model-index:
+- name: bert-base-cased_K3
+  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. -->
+
+# bert-base-cased_K3
+
+This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0108
+- F1 Macro: 0.9945
+- F1: 0.9962
+- F1 Neg: 0.9928
+- Acc: 0.995
+- Prec: 0.9981
+- Recall: 0.9943
+- Mcc: 0.9890
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1     | F1 Neg | Acc    | Prec   | Recall | Mcc    |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|
+| No log        | 1.0   | 400  | 0.0460          | 0.9861   | 0.9905 | 0.9818 | 0.9875 | 0.9867 | 0.9943 | 0.9723 |
+| 0.112         | 2.0   | 800  | 0.0108          | 0.9945   | 0.9962 | 0.9928 | 0.995  | 0.9981 | 0.9943 | 0.9890 |
+| 0.0513        | 3.0   | 1200 | 0.0271          | 0.9931   | 0.9952 | 0.9910 | 0.9938 | 0.9962 | 0.9943 | 0.9862 |
+| 0.0162        | 4.0   | 1600 | 0.0217          | 0.9945   | 0.9962 | 0.9928 | 0.995  | 0.9962 | 0.9962 | 0.9889 |
+| 0.0142        | 5.0   | 2000 | 0.0369          | 0.9889   | 0.9924 | 0.9854 | 0.99   | 0.9886 | 0.9962 | 0.9779 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09c3861ee0753819d3af7fb83e119e2079db3c2c5cb931f94363b64924eb77e1
+oid sha256:19e25298bcb3ae74c7cfe72467e88fdc087c462f43d45b96ea8fa5f3708ad14d
 size 433270768