haibotamiu commited on
Commit
551d009
1 Parent(s): c3da2c0

End of training

Browse files
README.md CHANGED
@@ -2,7 +2,10 @@
2
  license: apache-2.0
3
  base_model: bert-large-uncased
4
  tags:
 
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: out
8
  results: []
@@ -13,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # out
15
 
16
- This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the None dataset.
17
 
18
  ## Model description
19
 
 
2
  license: apache-2.0
3
  base_model: bert-large-uncased
4
  tags:
5
+ - question-answering
6
  - generated_from_trainer
7
+ datasets:
8
+ - squad
9
  model-index:
10
  - name: out
11
  results: []
 
16
 
17
  # out
18
 
19
+ This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the squad dataset.
20
 
21
  ## Model description
22
 
all_results.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "epoch": 10.0,
3
  "eval_samples": 3000,
4
- "exact_match": 68.73333333333333,
5
- "f1": 78.36309301342095,
6
- "train_loss": 0.48002195561185795,
7
- "train_runtime": 662.3397,
8
  "train_samples": 3000,
9
- "train_samples_per_second": 45.294,
10
- "train_steps_per_second": 1.419
11
  }
 
1
  {
2
+ "epoch": 20.0,
3
  "eval_samples": 3000,
4
+ "exact_match": 69.46666666666667,
5
+ "f1": 78.52201610798303,
6
+ "train_loss": 0.25617312586053886,
7
+ "train_runtime": 1340.3293,
8
  "train_samples": 3000,
9
+ "train_samples_per_second": 44.765,
10
+ "train_steps_per_second": 1.403
11
  }
args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ce873faf62e9b8c73335816ed6f8395382c212b964f79aaa247c3e125bbb3a8
3
  size 5652
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:473444ca6843cc35f2602bf4bdc716a47558896ba324db65063deeee2fde600a
3
  size 5652
eval_nbest_predictions.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f523387d37ce6d7a45723c9adc184a901b07da45282cb4e461a24a8c77645f3
3
- size 13889786
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:818de6cb2d9868992829d844fbe6f92ace0352dabfd1435c1b504332d1d8cc84
3
+ size 13787846
eval_predictions.json CHANGED
The diff for this file is too large to render. See raw diff
 
eval_results.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "epoch": 10.0,
3
  "eval_samples": 3000,
4
- "exact_match": 68.73333333333333,
5
- "f1": 78.36309301342095
6
  }
 
1
  {
2
+ "epoch": 20.0,
3
  "eval_samples": 3000,
4
+ "exact_match": 69.46666666666667,
5
+ "f1": 78.52201610798303
6
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 10.0,
3
- "train_loss": 0.48002195561185795,
4
- "train_runtime": 662.3397,
5
  "train_samples": 3000,
6
- "train_samples_per_second": 45.294,
7
- "train_steps_per_second": 1.419
8
  }
 
1
  {
2
+ "epoch": 20.0,
3
+ "train_loss": 0.25617312586053886,
4
+ "train_runtime": 1340.3293,
5
  "train_samples": 3000,
6
+ "train_samples_per_second": 44.765,
7
+ "train_steps_per_second": 1.403
8
  }
trainer_state.json CHANGED
@@ -1,34 +1,46 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 10.0,
5
  "eval_steps": 500,
6
- "global_step": 940,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 5.32,
13
- "learning_rate": 2.340425531914894e-05,
14
- "loss": 0.8504,
15
  "step": 500
16
  },
17
  {
18
- "epoch": 10.0,
19
- "step": 940,
20
- "total_flos": 2.089590732288e+16,
21
- "train_loss": 0.48002195561185795,
22
- "train_runtime": 662.3397,
23
- "train_samples_per_second": 45.294,
24
- "train_steps_per_second": 1.419
 
 
 
 
 
 
 
 
 
 
 
 
25
  }
26
  ],
27
  "logging_steps": 500,
28
- "max_steps": 940,
29
- "num_train_epochs": 10,
30
  "save_steps": 500,
31
- "total_flos": 2.089590732288e+16,
32
  "trial_name": null,
33
  "trial_params": null
34
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 20.0,
5
  "eval_steps": 500,
6
+ "global_step": 1880,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 5.32,
13
+ "learning_rate": 3.670212765957447e-05,
14
+ "loss": 0.8422,
15
  "step": 500
16
  },
17
  {
18
+ "epoch": 10.64,
19
+ "learning_rate": 2.340425531914894e-05,
20
+ "loss": 0.0931,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 15.96,
25
+ "learning_rate": 1.0106382978723404e-05,
26
+ "loss": 0.0236,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 20.0,
31
+ "step": 1880,
32
+ "total_flos": 4.179181464576e+16,
33
+ "train_loss": 0.25617312586053886,
34
+ "train_runtime": 1340.3293,
35
+ "train_samples_per_second": 44.765,
36
+ "train_steps_per_second": 1.403
37
  }
38
  ],
39
  "logging_steps": 500,
40
+ "max_steps": 1880,
41
+ "num_train_epochs": 20,
42
  "save_steps": 500,
43
+ "total_flos": 4.179181464576e+16,
44
  "trial_name": null,
45
  "trial_params": null
46
  }