cwchang commited on
Commit
4fbe588
1 Parent(s): 21a384f

End of training

Browse files
README.md CHANGED
@@ -5,9 +5,36 @@ tags:
5
  - generated_from_trainer
6
  datasets:
7
  - wnut_17
 
 
 
 
 
8
  model-index:
9
  - name: ner_model
10
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,6 +43,12 @@ should probably proofread and complete it, then remove this comment. -->
16
  # ner_model
17
 
18
  This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on the wnut_17 dataset.
 
 
 
 
 
 
19
 
20
  ## Model description
21
 
 
5
  - generated_from_trainer
6
  datasets:
7
  - wnut_17
8
+ metrics:
9
+ - precision
10
+ - recall
11
+ - f1
12
+ - accuracy
13
  model-index:
14
  - name: ner_model
15
+ results:
16
+ - task:
17
+ name: Token Classification
18
+ type: token-classification
19
+ dataset:
20
+ name: wnut_17
21
+ type: wnut_17
22
+ config: wnut_17
23
+ split: validation
24
+ args: wnut_17
25
+ metrics:
26
+ - name: Precision
27
+ type: precision
28
+ value: 0.6122448979591837
29
+ - name: Recall
30
+ type: recall
31
+ value: 0.430622009569378
32
+ - name: F1
33
+ type: f1
34
+ value: 0.5056179775280899
35
+ - name: Accuracy
36
+ type: accuracy
37
+ value: 0.9499141930973114
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
43
  # ner_model
44
 
45
  This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on the wnut_17 dataset.
46
+ It achieves the following results on the evaluation set:
47
+ - Loss: 0.2729
48
+ - Precision: 0.6122
49
+ - Recall: 0.4306
50
+ - F1: 0.5056
51
+ - Accuracy: 0.9499
52
 
53
  ## Model description
54
 
all_results.json CHANGED
@@ -1,17 +1,17 @@
1
  {
2
  "epoch": 3.0,
3
- "eval_accuracy": 0.9553054866806535,
4
- "eval_f1": 0.590027700831025,
5
- "eval_loss": 0.2586243450641632,
6
- "eval_precision": 0.7006578947368421,
7
- "eval_recall": 0.5095693779904307,
8
- "eval_runtime": 1.8637,
9
  "eval_samples": 1009,
10
- "eval_samples_per_second": 541.382,
11
- "eval_steps_per_second": 68.142,
12
- "train_loss": 0.10290272581811044,
13
- "train_runtime": 78.6134,
14
  "train_samples": 3394,
15
- "train_samples_per_second": 129.52,
16
- "train_steps_per_second": 16.219
17
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "eval_accuracy": 0.9499141930973114,
4
+ "eval_f1": 0.5056179775280899,
5
+ "eval_loss": 0.2729117274284363,
6
+ "eval_precision": 0.6122448979591837,
7
+ "eval_recall": 0.430622009569378,
8
+ "eval_runtime": 1.9245,
9
  "eval_samples": 1009,
10
+ "eval_samples_per_second": 524.305,
11
+ "eval_steps_per_second": 65.993,
12
+ "train_loss": 0.09562072828704235,
13
+ "train_runtime": 125.9576,
14
  "train_samples": 3394,
15
+ "train_samples_per_second": 80.837,
16
+ "train_steps_per_second": 10.122
17
  }
eval_results.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
  "epoch": 3.0,
3
- "eval_accuracy": 0.9553054866806535,
4
- "eval_f1": 0.590027700831025,
5
- "eval_loss": 0.2586243450641632,
6
- "eval_precision": 0.7006578947368421,
7
- "eval_recall": 0.5095693779904307,
8
- "eval_runtime": 1.8637,
9
  "eval_samples": 1009,
10
- "eval_samples_per_second": 541.382,
11
- "eval_steps_per_second": 68.142
12
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "eval_accuracy": 0.9499141930973114,
4
+ "eval_f1": 0.5056179775280899,
5
+ "eval_loss": 0.2729117274284363,
6
+ "eval_precision": 0.6122448979591837,
7
+ "eval_recall": 0.430622009569378,
8
+ "eval_runtime": 1.9245,
9
  "eval_samples": 1009,
10
+ "eval_samples_per_second": 524.305,
11
+ "eval_steps_per_second": 65.993
12
  }
runs/Dec05_06-40-48_ddba0bfe6b5f/events.out.tfevents.1701758685.ddba0bfe6b5f.848.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6c50f93de690ca19f3468f7b801752ef8db1a70257073c549cae838bcdcd5ad
3
+ size 560
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.0,
3
- "train_loss": 0.10290272581811044,
4
- "train_runtime": 78.6134,
5
  "train_samples": 3394,
6
- "train_samples_per_second": 129.52,
7
- "train_steps_per_second": 16.219
8
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "train_loss": 0.09562072828704235,
4
+ "train_runtime": 125.9576,
5
  "train_samples": 3394,
6
+ "train_samples_per_second": 80.837,
7
+ "train_steps_per_second": 10.122
8
  }
trainer_state.json CHANGED
@@ -11,23 +11,23 @@
11
  {
12
  "epoch": 1.18,
13
  "learning_rate": 3.0392156862745097e-05,
14
- "loss": 0.1847,
15
  "step": 500
16
  },
17
  {
18
  "epoch": 2.35,
19
  "learning_rate": 1.0784313725490197e-05,
20
- "loss": 0.0585,
21
  "step": 1000
22
  },
23
  {
24
  "epoch": 3.0,
25
  "step": 1275,
26
- "total_flos": 127179336805920.0,
27
- "train_loss": 0.10290272581811044,
28
- "train_runtime": 78.6134,
29
- "train_samples_per_second": 129.52,
30
- "train_steps_per_second": 16.219
31
  }
32
  ],
33
  "logging_steps": 500,
@@ -35,7 +35,7 @@
35
  "num_input_tokens_seen": 0,
36
  "num_train_epochs": 3,
37
  "save_steps": 500,
38
- "total_flos": 127179336805920.0,
39
  "trial_name": null,
40
  "trial_params": null
41
  }
 
11
  {
12
  "epoch": 1.18,
13
  "learning_rate": 3.0392156862745097e-05,
14
+ "loss": 0.1665,
15
  "step": 500
16
  },
17
  {
18
  "epoch": 2.35,
19
  "learning_rate": 1.0784313725490197e-05,
20
+ "loss": 0.0587,
21
  "step": 1000
22
  },
23
  {
24
  "epoch": 3.0,
25
  "step": 1275,
26
+ "total_flos": 140113503536760.0,
27
+ "train_loss": 0.09562072828704235,
28
+ "train_runtime": 125.9576,
29
+ "train_samples_per_second": 80.837,
30
+ "train_steps_per_second": 10.122
31
  }
32
  ],
33
  "logging_steps": 500,
 
35
  "num_input_tokens_seen": 0,
36
  "num_train_epochs": 3,
37
  "save_steps": 500,
38
+ "total_flos": 140113503536760.0,
39
  "trial_name": null,
40
  "trial_params": null
41
  }