haibotamiu commited on
Commit
1c8a2e5
1 Parent(s): fa56135

End of training

Browse files
README.md CHANGED
@@ -2,7 +2,10 @@
2
  license: apache-2.0
3
  base_model: distilbert-base-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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
17
 
18
  ## Model description
19
 
 
2
  license: apache-2.0
3
  base_model: distilbert-base-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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset.
20
 
21
  ## Model description
22
 
all_results.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "epoch": 5.0,
3
  "eval_samples": 3000,
4
- "exact_match": 53.53333333333333,
5
- "f1": 63.283542684518345,
6
- "train_loss": 1.5697038366439495,
7
- "train_runtime": 80.4186,
8
  "train_samples": 3000,
9
- "train_samples_per_second": 186.524,
10
- "train_steps_per_second": 5.844
11
  }
 
1
  {
2
+ "epoch": 10.0,
3
  "eval_samples": 3000,
4
+ "exact_match": 54.166666666666664,
5
+ "f1": 64.12697846015462,
6
+ "train_loss": 0.8370751482375125,
7
+ "train_runtime": 155.0335,
8
  "train_samples": 3000,
9
+ "train_samples_per_second": 193.507,
10
+ "train_steps_per_second": 6.063
11
  }
args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5ad6d9f72bf7e4a3096700a478257bc8d4a8dfed20cfb091ba8f83890913187
3
  size 5652
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08d22ca21f3ec4ea0c247b375abd931a41d7082140b5289acb92b656bb1418d8
3
  size 5652
eval_nbest_predictions.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db9382aefdac2f83b40fe23a6f8222f14e77d5617edfeab7dd0a2b642b7de742
3
- size 14051098
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5ed5e61243535ff4955375d06ea43a2e05949b5ca7358091b7242a30a8570e2
3
+ size 14110407
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": 5.0,
3
  "eval_samples": 3000,
4
- "exact_match": 53.53333333333333,
5
- "f1": 63.283542684518345
6
  }
 
1
  {
2
+ "epoch": 10.0,
3
  "eval_samples": 3000,
4
+ "exact_match": 54.166666666666664,
5
+ "f1": 64.12697846015462
6
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 5.0,
3
- "train_loss": 1.5697038366439495,
4
- "train_runtime": 80.4186,
5
  "train_samples": 3000,
6
- "train_samples_per_second": 186.524,
7
- "train_steps_per_second": 5.844
8
  }
 
1
  {
2
+ "epoch": 10.0,
3
+ "train_loss": 0.8370751482375125,
4
+ "train_runtime": 155.0335,
5
  "train_samples": 3000,
6
+ "train_samples_per_second": 193.507,
7
+ "train_steps_per_second": 6.063
8
  }
trainer_state.json CHANGED
@@ -1,28 +1,34 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 5.0,
5
  "eval_steps": 500,
6
- "global_step": 470,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 5.0,
13
- "step": 470,
14
- "total_flos": 1469847375360000.0,
15
- "train_loss": 1.5697038366439495,
16
- "train_runtime": 80.4186,
17
- "train_samples_per_second": 186.524,
18
- "train_steps_per_second": 5.844
 
 
 
 
 
 
19
  }
20
  ],
21
  "logging_steps": 500,
22
- "max_steps": 470,
23
- "num_train_epochs": 5,
24
  "save_steps": 500,
25
- "total_flos": 1469847375360000.0,
26
  "trial_name": null,
27
  "trial_params": null
28
  }
 
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": 1.4252,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 10.0,
19
+ "step": 940,
20
+ "total_flos": 2939694750720000.0,
21
+ "train_loss": 0.8370751482375125,
22
+ "train_runtime": 155.0335,
23
+ "train_samples_per_second": 193.507,
24
+ "train_steps_per_second": 6.063
25
  }
26
  ],
27
  "logging_steps": 500,
28
+ "max_steps": 940,
29
+ "num_train_epochs": 10,
30
  "save_steps": 500,
31
+ "total_flos": 2939694750720000.0,
32
  "trial_name": null,
33
  "trial_params": null
34
  }