sgugger commited on
Commit
b1c863e
1 Parent(s): 3b5cd83

End of training

Browse files
README.md CHANGED
@@ -1,13 +1,34 @@
1
  ---
 
 
2
  license: apache-2.0
3
  base_model: bert-base-cased
4
  tags:
5
  - generated_from_trainer
6
  datasets:
7
  - glue
 
 
 
8
  model-index:
9
  - name: push-to-hub-test-2
10
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,7 +36,12 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # push-to-hub-test-2
17
 
18
- This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the glue dataset.
 
 
 
 
 
19
 
20
  ## Model description
21
 
 
1
  ---
2
+ language:
3
+ - en
4
  license: apache-2.0
5
  base_model: bert-base-cased
6
  tags:
7
  - generated_from_trainer
8
  datasets:
9
  - glue
10
+ metrics:
11
+ - accuracy
12
+ - f1
13
  model-index:
14
  - name: push-to-hub-test-2
15
+ results:
16
+ - task:
17
+ name: Text Classification
18
+ type: text-classification
19
+ dataset:
20
+ name: GLUE MRPC
21
+ type: glue
22
+ config: mrpc
23
+ split: validation
24
+ args: mrpc
25
+ metrics:
26
+ - name: Accuracy
27
+ type: accuracy
28
+ value: 0.8676470588235294
29
+ - name: F1
30
+ type: f1
31
+ value: 0.9078498293515359
32
  ---
33
 
34
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
36
 
37
  # push-to-hub-test-2
38
 
39
+ This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the GLUE MRPC dataset.
40
+ It achieves the following results on the evaluation set:
41
+ - Loss: 0.6255
42
+ - Accuracy: 0.8676
43
+ - F1: 0.9078
44
+ - Combined Score: 0.8877
45
 
46
  ## Model description
47
 
all_results.json CHANGED
@@ -4,13 +4,13 @@
4
  "eval_combined_score": 0.8877484440875327,
5
  "eval_f1": 0.9078498293515359,
6
  "eval_loss": 0.6254646182060242,
7
- "eval_runtime": 0.9668,
8
  "eval_samples": 408,
9
- "eval_samples_per_second": 422.028,
10
- "eval_steps_per_second": 26.894,
11
  "train_loss": 0.29736072982566947,
12
- "train_runtime": 72.3445,
13
  "train_samples": 3668,
14
- "train_samples_per_second": 152.106,
15
- "train_steps_per_second": 9.538
16
  }
 
4
  "eval_combined_score": 0.8877484440875327,
5
  "eval_f1": 0.9078498293515359,
6
  "eval_loss": 0.6254646182060242,
7
+ "eval_runtime": 0.9827,
8
  "eval_samples": 408,
9
+ "eval_samples_per_second": 415.192,
10
+ "eval_steps_per_second": 26.458,
11
  "train_loss": 0.29736072982566947,
12
+ "train_runtime": 69.9797,
13
  "train_samples": 3668,
14
+ "train_samples_per_second": 157.246,
15
+ "train_steps_per_second": 9.86
16
  }
eval_results.json CHANGED
@@ -4,8 +4,8 @@
4
  "eval_combined_score": 0.8877484440875327,
5
  "eval_f1": 0.9078498293515359,
6
  "eval_loss": 0.6254646182060242,
7
- "eval_runtime": 0.9668,
8
  "eval_samples": 408,
9
- "eval_samples_per_second": 422.028,
10
- "eval_steps_per_second": 26.894
11
  }
 
4
  "eval_combined_score": 0.8877484440875327,
5
  "eval_f1": 0.9078498293515359,
6
  "eval_loss": 0.6254646182060242,
7
+ "eval_runtime": 0.9827,
8
  "eval_samples": 408,
9
+ "eval_samples_per_second": 415.192,
10
+ "eval_steps_per_second": 26.458
11
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.0,
3
  "train_loss": 0.29736072982566947,
4
- "train_runtime": 72.3445,
5
  "train_samples": 3668,
6
- "train_samples_per_second": 152.106,
7
- "train_steps_per_second": 9.538
8
  }
 
1
  {
2
  "epoch": 3.0,
3
  "train_loss": 0.29736072982566947,
4
+ "train_runtime": 69.9797,
5
  "train_samples": 3668,
6
+ "train_samples_per_second": 157.246,
7
+ "train_steps_per_second": 9.86
8
  }
trainer_state.json CHANGED
@@ -18,9 +18,9 @@
18
  "step": 690,
19
  "total_flos": 723818513295360.0,
20
  "train_loss": 0.29736072982566947,
21
- "train_runtime": 72.3445,
22
- "train_samples_per_second": 152.106,
23
- "train_steps_per_second": 9.538
24
  }
25
  ],
26
  "max_steps": 690,
 
18
  "step": 690,
19
  "total_flos": 723818513295360.0,
20
  "train_loss": 0.29736072982566947,
21
+ "train_runtime": 69.9797,
22
+ "train_samples_per_second": 157.246,
23
+ "train_steps_per_second": 9.86
24
  }
25
  ],
26
  "max_steps": 690,