haibotamiu commited on
Commit
ed13d45
1 Parent(s): aadcb14

End of training

Browse files
README.md CHANGED
@@ -2,7 +2,10 @@
2
  license: apache-2.0
3
  base_model: bert-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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
17
 
18
  ## Model description
19
 
 
2
  license: apache-2.0
3
  base_model: bert-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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the squad dataset.
20
 
21
  ## Model description
22
 
all_results.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "epoch": 50.0,
3
  "eval_samples": 3000,
4
- "exact_match": 55.833333333333336,
5
- "f1": 65.67795577455873,
6
- "train_loss": 0.1556171702324076,
7
- "train_runtime": 1356.8935,
8
  "train_samples": 3000,
9
- "train_samples_per_second": 110.547,
10
- "train_steps_per_second": 3.464
11
  }
 
1
  {
2
+ "epoch": 100.0,
3
  "eval_samples": 3000,
4
+ "exact_match": 48.3,
5
+ "f1": 59.76387313784877,
6
+ "train_loss": 0.1459447158651149,
7
+ "train_runtime": 2721.3121,
8
  "train_samples": 3000,
9
+ "train_samples_per_second": 110.241,
10
+ "train_steps_per_second": 3.454
11
  }
args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6483b4338266a431a726740f9d0603e8af5b5ea355462122d055eb126bb9e1e
3
  size 5652
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f140c580ce20b0c341613069c779fdc1ae1caec64fbe449d785823651e822ba
3
  size 5652
eval_nbest_predictions.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:630b581cec250940167a383435d09347c398cba0c12a4e660ef2760f5d1b9877
3
- size 14106174
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e93beefb2d2ba12031615060145a1efb9f0ba9b4e4b3b542feda79321cf90b3
3
+ size 14014825
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": 50.0,
3
  "eval_samples": 3000,
4
- "exact_match": 55.833333333333336,
5
- "f1": 65.67795577455873
6
  }
 
1
  {
2
+ "epoch": 100.0,
3
  "eval_samples": 3000,
4
+ "exact_match": 48.3,
5
+ "f1": 59.76387313784877
6
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 50.0,
3
- "train_loss": 0.1556171702324076,
4
- "train_runtime": 1356.8935,
5
  "train_samples": 3000,
6
- "train_samples_per_second": 110.547,
7
- "train_steps_per_second": 3.464
8
  }
 
1
  {
2
+ "epoch": 100.0,
3
+ "train_loss": 0.1459447158651149,
4
+ "train_runtime": 2721.3121,
5
  "train_samples": 3000,
6
+ "train_samples_per_second": 110.241,
7
+ "train_steps_per_second": 3.454
8
  }
trainer_state.json CHANGED
@@ -1,82 +1,136 @@
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": 1.1017,
15
  "step": 500
16
  },
17
  {
18
  "epoch": 10.64,
19
- "learning_rate": 3.936170212765958e-05,
20
- "loss": 0.1281,
21
  "step": 1000
22
  },
23
  {
24
  "epoch": 15.96,
25
- "learning_rate": 3.4042553191489365e-05,
26
- "loss": 0.0555,
27
  "step": 1500
28
  },
29
  {
30
  "epoch": 21.28,
31
- "learning_rate": 2.8723404255319154e-05,
32
- "loss": 0.027,
33
  "step": 2000
34
  },
35
  {
36
  "epoch": 26.6,
37
- "learning_rate": 2.340425531914894e-05,
38
- "loss": 0.0195,
39
  "step": 2500
40
  },
41
  {
42
  "epoch": 31.91,
43
- "learning_rate": 1.8085106382978724e-05,
44
- "loss": 0.0135,
45
  "step": 3000
46
  },
47
  {
48
  "epoch": 37.23,
49
- "learning_rate": 1.2765957446808511e-05,
50
- "loss": 0.0103,
51
  "step": 3500
52
  },
53
  {
54
  "epoch": 42.55,
55
- "learning_rate": 7.446808510638298e-06,
56
- "loss": 0.0173,
57
  "step": 4000
58
  },
59
  {
60
  "epoch": 47.87,
61
- "learning_rate": 2.1276595744680853e-06,
62
- "loss": 0.0432,
63
  "step": 4500
64
  },
65
  {
66
- "epoch": 50.0,
67
- "step": 4700,
68
- "total_flos": 2.93958851328e+16,
69
- "train_loss": 0.1556171702324076,
70
- "train_runtime": 1356.8935,
71
- "train_samples_per_second": 110.547,
72
- "train_steps_per_second": 3.464
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
73
  }
74
  ],
75
  "logging_steps": 500,
76
- "max_steps": 4700,
77
- "num_train_epochs": 50,
78
  "save_steps": 500,
79
- "total_flos": 2.93958851328e+16,
80
  "trial_name": null,
81
  "trial_params": null
82
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 100.0,
5
  "eval_steps": 500,
6
+ "global_step": 9400,
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": 4.734042553191489e-05,
14
+ "loss": 1.0988,
15
  "step": 500
16
  },
17
  {
18
  "epoch": 10.64,
19
+ "learning_rate": 4.468085106382979e-05,
20
+ "loss": 0.1377,
21
  "step": 1000
22
  },
23
  {
24
  "epoch": 15.96,
25
+ "learning_rate": 4.2021276595744684e-05,
26
+ "loss": 0.0645,
27
  "step": 1500
28
  },
29
  {
30
  "epoch": 21.28,
31
+ "learning_rate": 3.936170212765958e-05,
32
+ "loss": 0.0425,
33
  "step": 2000
34
  },
35
  {
36
  "epoch": 26.6,
37
+ "learning_rate": 3.670212765957447e-05,
38
+ "loss": 0.0245,
39
  "step": 2500
40
  },
41
  {
42
  "epoch": 31.91,
43
+ "learning_rate": 3.4042553191489365e-05,
44
+ "loss": 0.0228,
45
  "step": 3000
46
  },
47
  {
48
  "epoch": 37.23,
49
+ "learning_rate": 3.1382978723404254e-05,
50
+ "loss": 0.0251,
51
  "step": 3500
52
  },
53
  {
54
  "epoch": 42.55,
55
+ "learning_rate": 2.8723404255319154e-05,
56
+ "loss": 0.0384,
57
  "step": 4000
58
  },
59
  {
60
  "epoch": 47.87,
61
+ "learning_rate": 2.6063829787234046e-05,
62
+ "loss": 0.0429,
63
  "step": 4500
64
  },
65
  {
66
+ "epoch": 53.19,
67
+ "learning_rate": 2.340425531914894e-05,
68
+ "loss": 0.055,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 58.51,
73
+ "learning_rate": 2.074468085106383e-05,
74
+ "loss": 0.0883,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 63.83,
79
+ "learning_rate": 1.8085106382978724e-05,
80
+ "loss": 0.1385,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 69.15,
85
+ "learning_rate": 1.5425531914893617e-05,
86
+ "loss": 0.2111,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 74.47,
91
+ "learning_rate": 1.2765957446808511e-05,
92
+ "loss": 0.2821,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 79.79,
97
+ "learning_rate": 1.0106382978723404e-05,
98
+ "loss": 0.1479,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 85.11,
103
+ "learning_rate": 7.446808510638298e-06,
104
+ "loss": 0.1729,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 90.43,
109
+ "learning_rate": 4.787234042553191e-06,
110
+ "loss": 0.0951,
111
+ "step": 8500
112
+ },
113
+ {
114
+ "epoch": 95.74,
115
+ "learning_rate": 2.1276595744680853e-06,
116
+ "loss": 0.0391,
117
+ "step": 9000
118
+ },
119
+ {
120
+ "epoch": 100.0,
121
+ "step": 9400,
122
+ "total_flos": 5.87917702656e+16,
123
+ "train_loss": 0.1459447158651149,
124
+ "train_runtime": 2721.3121,
125
+ "train_samples_per_second": 110.241,
126
+ "train_steps_per_second": 3.454
127
  }
128
  ],
129
  "logging_steps": 500,
130
+ "max_steps": 9400,
131
+ "num_train_epochs": 100,
132
  "save_steps": 500,
133
+ "total_flos": 5.87917702656e+16,
134
  "trial_name": null,
135
  "trial_params": null
136
  }