haibotamiu commited on
Commit
5d6ac48
1 Parent(s): 6401273

End of training

Browse files
README.md CHANGED
@@ -2,7 +2,10 @@
2
  license: apache-2.0
3
  base_model: albert-base-v2
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 [albert-base-v2](https://huggingface.co/albert-base-v2) on the None dataset.
17
 
18
  ## Model description
19
 
 
2
  license: apache-2.0
3
  base_model: albert-base-v2
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 [albert-base-v2](https://huggingface.co/albert-base-v2) on the squad dataset.
20
 
21
  ## Model description
22
 
all_results.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "epoch": 100.0,
3
  "eval_samples": 3000,
4
- "exact_match": 69.0,
5
- "f1": 78.89666079356367,
6
- "train_loss": 0.08420621717969577,
7
- "train_runtime": 1629.8221,
8
  "train_samples": 3000,
9
- "train_samples_per_second": 184.069,
10
- "train_steps_per_second": 0.736
11
  }
 
1
  {
2
+ "epoch": 3.0,
3
  "eval_samples": 3000,
4
+ "exact_match": 68.56666666666666,
5
+ "f1": 78.31093544823585,
6
+ "train_loss": 1.5496142705281575,
7
+ "train_runtime": 55.38,
8
  "train_samples": 3000,
9
+ "train_samples_per_second": 162.513,
10
+ "train_steps_per_second": 1.3
11
  }
args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4623367a901eddc57d675a066a6f9ad4d0713b876fdaba747336b4e82e84dbb3
3
  size 5652
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27e96aa596383a62b53fd4c3ceeb13e8f24294281671bceac6b94fc330804d03
3
  size 5652
eval_nbest_predictions.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:faf66bf79f75e61369aa6297120c187c19df5dd5a9c8f553d34cbd37d7d679be
3
- size 13453266
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b806aa658647d9bf8f5b76bb7f27e6f1a6fd65b396c9fd2187599b49a899dbe1
3
+ size 13531727
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": 100.0,
3
  "eval_samples": 3000,
4
- "exact_match": 69.0,
5
- "f1": 78.89666079356367
6
  }
 
1
  {
2
+ "epoch": 3.0,
3
  "eval_samples": 3000,
4
+ "exact_match": 68.56666666666666,
5
+ "f1": 78.31093544823585
6
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 100.0,
3
- "train_loss": 0.08420621717969577,
4
- "train_runtime": 1629.8221,
5
  "train_samples": 3000,
6
- "train_samples_per_second": 184.069,
7
- "train_steps_per_second": 0.736
8
  }
 
1
  {
2
+ "epoch": 3.0,
3
+ "train_loss": 1.5496142705281575,
4
+ "train_runtime": 55.38,
5
  "train_samples": 3000,
6
+ "train_samples_per_second": 162.513,
7
+ "train_steps_per_second": 1.3
8
  }
trainer_state.json CHANGED
@@ -1,40 +1,28 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 100.0,
5
  "eval_steps": 500,
6
- "global_step": 1200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 41.67,
13
- "learning_rate": 2.916666666666667e-05,
14
- "loss": 0.1992,
15
- "step": 500
16
- },
17
- {
18
- "epoch": 83.33,
19
- "learning_rate": 8.333333333333334e-06,
20
- "loss": 0.0023,
21
- "step": 1000
22
- },
23
- {
24
- "epoch": 100.0,
25
- "step": 1200,
26
- "total_flos": 4968855705600000.0,
27
- "train_loss": 0.08420621717969577,
28
- "train_runtime": 1629.8221,
29
- "train_samples_per_second": 184.069,
30
- "train_steps_per_second": 0.736
31
  }
32
  ],
33
  "logging_steps": 500,
34
- "max_steps": 1200,
35
- "num_train_epochs": 100,
36
  "save_steps": 500,
37
- "total_flos": 4968855705600000.0,
38
  "trial_name": null,
39
  "trial_params": null
40
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
  "eval_steps": 500,
6
+ "global_step": 72,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 3.0,
13
+ "step": 72,
14
+ "total_flos": 149065671168000.0,
15
+ "train_loss": 1.5496142705281575,
16
+ "train_runtime": 55.38,
17
+ "train_samples_per_second": 162.513,
18
+ "train_steps_per_second": 1.3
 
 
 
 
 
 
 
 
 
 
 
 
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 72,
23
+ "num_train_epochs": 3,
24
  "save_steps": 500,
25
+ "total_flos": 149065671168000.0,
26
  "trial_name": null,
27
  "trial_params": null
28
  }