End of training

README.md

@@ -1,13 +1,40 @@
 ---
-license: apache-2.0
-base_model: bert-base-uncased
+license: mit
+base_model: roberta-large
 tags:
 - generated_from_trainer
 datasets:
 - generator
+metrics:
+- precision
+- recall
+- f1
+- accuracy
 model-index:
 - name: model
-  results: []
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: generator
+      type: generator
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.5931758530183727
+    - name: Recall
+      type: recall
+      value: 0.7371167645140247
+    - name: F1
+      type: f1
+      value: 0.6573589296102385
+    - name: Accuracy
+      type: accuracy
+      value: 0.896675559203776
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,18 +42,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # model
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the generator dataset.
+This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the generator dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.6236
-- eval_precision: 0.4599
-- eval_recall: 0.7381
-- eval_f1: 0.5667
-- eval_accuracy: 0.8546
-- eval_runtime: 31.2775
-- eval_samples_per_second: 21.038
-- eval_steps_per_second: 1.343
-- epoch: 2.23
-- step: 699
+- Loss: 0.5350
+- Precision: 0.5932
+- Recall: 0.7371
+- F1: 0.6574
+- Accuracy: 0.8967
 
 ## Model description
 
@@ -46,16 +68,25 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - training_steps: 1000
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 0.47  | 466  | 0.5513          | 0.5389    | 0.7358 | 0.6222 | 0.8787   |
+| 0.4041        | 1.47  | 932  | 0.5179          | 0.5398    | 0.7613 | 0.6317 | 0.8797   |
+| 0.3968        | 2.07  | 1000 | 0.5350          | 0.5932    | 0.7371 | 0.6574 | 0.8967   |
+
+
 ### Framework versions
 
 - Transformers 4.33.2
-- Pytorch 2.0.1+cu117
+- Pytorch 2.0.1+cu118
 - Datasets 2.14.5
 - Tokenizers 0.13.3