haibotamiu commited on
Commit
692ae4e
1 Parent(s): 7d6a82e

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": 20.0,
3
  "eval_samples": 3000,
4
- "exact_match": 56.36666666666667,
5
- "f1": 65.6870988663549,
6
- "train_loss": 0.4278867336029702,
7
- "train_runtime": 303.7628,
8
  "train_samples": 3000,
9
- "train_samples_per_second": 197.523,
10
- "train_steps_per_second": 6.189
11
  }
 
1
  {
2
+ "epoch": 50.0,
3
  "eval_samples": 3000,
4
+ "exact_match": 47.233333333333334,
5
+ "f1": 57.723557986903565,
6
+ "train_loss": 0.1978351655919501,
7
+ "train_runtime": 783.094,
8
  "train_samples": 3000,
9
+ "train_samples_per_second": 191.548,
10
+ "train_steps_per_second": 6.002
11
  }
args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:595225b3aa7c124c5f885a052fc420cdeab0cde9c0f9c0f591a4d5c26d64c460
3
  size 5652
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbd2d598f9b28d49a56ad7856529421c5ad5920bc930c02adeb9ff43faaf2126
3
  size 5652
eval_nbest_predictions.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e8750c3930348fa2231008fbd0cd44e4a8f1b07f3ca07a864dbe897357f9d11
3
- size 14240855
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd33d0496ad36f95724c9f4b0cad861fbdfd34b4d7adc0c5afb9254e6f92b45
3
+ size 14129439
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": 20.0,
3
  "eval_samples": 3000,
4
- "exact_match": 56.36666666666667,
5
- "f1": 65.6870988663549
6
  }
 
1
  {
2
+ "epoch": 50.0,
3
  "eval_samples": 3000,
4
+ "exact_match": 47.233333333333334,
5
+ "f1": 57.723557986903565
6
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 20.0,
3
- "train_loss": 0.4278867336029702,
4
- "train_runtime": 303.7628,
5
  "train_samples": 3000,
6
- "train_samples_per_second": 197.523,
7
- "train_steps_per_second": 6.189
8
  }
 
1
  {
2
+ "epoch": 50.0,
3
+ "train_loss": 0.1978351655919501,
4
+ "train_runtime": 783.094,
5
  "train_samples": 3000,
6
+ "train_samples_per_second": 191.548,
7
+ "train_steps_per_second": 6.002
8
  }
trainer_state.json CHANGED
@@ -1,46 +1,82 @@
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": 1.4055,
15
  "step": 500
16
  },
17
  {
18
  "epoch": 10.64,
19
- "learning_rate": 2.340425531914894e-05,
20
- "loss": 0.1477,
21
  "step": 1000
22
  },
23
  {
24
  "epoch": 15.96,
25
- "learning_rate": 1.0106382978723404e-05,
26
- "loss": 0.0432,
27
  "step": 1500
28
  },
29
  {
30
- "epoch": 20.0,
31
- "step": 1880,
32
- "total_flos": 5879389501440000.0,
33
- "train_loss": 0.4278867336029702,
34
- "train_runtime": 303.7628,
35
- "train_samples_per_second": 197.523,
36
- "train_steps_per_second": 6.189
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37
  }
38
  ],
39
  "logging_steps": 500,
40
- "max_steps": 1880,
41
- "num_train_epochs": 20,
42
  "save_steps": 500,
43
- "total_flos": 5879389501440000.0,
44
  "trial_name": null,
45
  "trial_params": null
46
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 50.0,
5
  "eval_steps": 500,
6
+ "global_step": 4700,
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": 4.468085106382979e-05,
14
+ "loss": 1.3964,
15
  "step": 500
16
  },
17
  {
18
  "epoch": 10.64,
19
+ "learning_rate": 3.936170212765958e-05,
20
+ "loss": 0.1539,
21
  "step": 1000
22
  },
23
  {
24
  "epoch": 15.96,
25
+ "learning_rate": 3.4042553191489365e-05,
26
+ "loss": 0.0614,
27
  "step": 1500
28
  },
29
  {
30
+ "epoch": 21.28,
31
+ "learning_rate": 2.8723404255319154e-05,
32
+ "loss": 0.0292,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 26.6,
37
+ "learning_rate": 2.340425531914894e-05,
38
+ "loss": 0.0187,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 31.91,
43
+ "learning_rate": 1.8085106382978724e-05,
44
+ "loss": 0.0171,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 37.23,
49
+ "learning_rate": 1.2765957446808511e-05,
50
+ "loss": 0.0174,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 42.55,
55
+ "learning_rate": 7.446808510638298e-06,
56
+ "loss": 0.0293,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 47.87,
61
+ "learning_rate": 2.1276595744680853e-06,
62
+ "loss": 0.0693,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 50.0,
67
+ "step": 4700,
68
+ "total_flos": 1.46984737536e+16,
69
+ "train_loss": 0.1978351655919501,
70
+ "train_runtime": 783.094,
71
+ "train_samples_per_second": 191.548,
72
+ "train_steps_per_second": 6.002
73
  }
74
  ],
75
  "logging_steps": 500,
76
+ "max_steps": 4700,
77
+ "num_train_epochs": 50,
78
  "save_steps": 500,
79
+ "total_flos": 1.46984737536e+16,
80
  "trial_name": null,
81
  "trial_params": null
82
  }