haibotamiu commited on
Commit
3c760b1
1 Parent(s): ee5ddf3

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": 100.0,
3
  "eval_samples": 3000,
4
- "exact_match": 36.53333333333333,
5
- "f1": 48.441986654053316,
6
- "train_loss": 0.4032590159964054,
7
- "train_runtime": 6707.7517,
8
  "train_samples": 3000,
9
- "train_samples_per_second": 44.724,
10
- "train_steps_per_second": 1.401
11
  }
 
1
  {
2
+ "epoch": 3.0,
3
  "eval_samples": 3000,
4
+ "exact_match": 9.333333333333334,
5
+ "f1": 14.467623210820486,
6
+ "train_loss": 4.351121690538195,
7
+ "train_runtime": 29.5562,
8
  "train_samples": 3000,
9
+ "train_samples_per_second": 304.504,
10
+ "train_steps_per_second": 1.218
11
  }
args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4400e0723d955f89d2c29d11637b0e906726ed7e53cff9034c6d35f718150e0
3
  size 5652
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94d3340ea92839db6cd8c2883d58b0997147a20c31a76b1b9b4fc38097640b62
3
  size 5652
eval_nbest_predictions.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e9c9c0c43a722680701799a80e2c8b9bcb73e155f99d4c95e4fbf112c6f48a2
3
- size 13915047
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:712e1b60dc69e369d446b9cab4e9b3a4d8e1674aee0ebe8bbfde1fc436e15c52
3
+ size 14416993
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": 36.53333333333333,
5
- "f1": 48.441986654053316
6
  }
 
1
  {
2
+ "epoch": 3.0,
3
  "eval_samples": 3000,
4
+ "exact_match": 9.333333333333334,
5
+ "f1": 14.467623210820486
6
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 100.0,
3
- "train_loss": 0.4032590159964054,
4
- "train_runtime": 6707.7517,
5
  "train_samples": 3000,
6
- "train_samples_per_second": 44.724,
7
- "train_steps_per_second": 1.401
8
  }
 
1
  {
2
+ "epoch": 3.0,
3
+ "train_loss": 4.351121690538195,
4
+ "train_runtime": 29.5562,
5
  "train_samples": 3000,
6
+ "train_samples_per_second": 304.504,
7
+ "train_steps_per_second": 1.218
8
  }
trainer_state.json CHANGED
@@ -1,136 +1,28 @@
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": 0.9695,
15
- "step": 500
16
- },
17
- {
18
- "epoch": 10.64,
19
- "learning_rate": 4.468085106382979e-05,
20
- "loss": 0.145,
21
- "step": 1000
22
- },
23
- {
24
- "epoch": 15.96,
25
- "learning_rate": 4.2021276595744684e-05,
26
- "loss": 0.083,
27
- "step": 1500
28
- },
29
- {
30
- "epoch": 21.28,
31
- "learning_rate": 3.936170212765958e-05,
32
- "loss": 0.0518,
33
- "step": 2000
34
- },
35
- {
36
- "epoch": 26.6,
37
- "learning_rate": 3.670212765957447e-05,
38
- "loss": 0.0495,
39
- "step": 2500
40
- },
41
- {
42
- "epoch": 31.91,
43
- "learning_rate": 3.4042553191489365e-05,
44
- "loss": 0.042,
45
- "step": 3000
46
- },
47
- {
48
- "epoch": 37.23,
49
- "learning_rate": 3.1382978723404254e-05,
50
- "loss": 0.0514,
51
- "step": 3500
52
- },
53
- {
54
- "epoch": 42.55,
55
- "learning_rate": 2.8723404255319154e-05,
56
- "loss": 0.053,
57
- "step": 4000
58
- },
59
- {
60
- "epoch": 47.87,
61
- "learning_rate": 2.6063829787234046e-05,
62
- "loss": 0.074,
63
- "step": 4500
64
- },
65
- {
66
- "epoch": 53.19,
67
- "learning_rate": 2.340425531914894e-05,
68
- "loss": 0.1369,
69
- "step": 5000
70
- },
71
- {
72
- "epoch": 58.51,
73
- "learning_rate": 2.074468085106383e-05,
74
- "loss": 0.2306,
75
- "step": 5500
76
- },
77
- {
78
- "epoch": 63.83,
79
- "learning_rate": 1.8085106382978724e-05,
80
- "loss": 0.49,
81
- "step": 6000
82
- },
83
- {
84
- "epoch": 69.15,
85
- "learning_rate": 1.5425531914893617e-05,
86
- "loss": 0.5549,
87
- "step": 6500
88
- },
89
- {
90
- "epoch": 74.47,
91
- "learning_rate": 1.2765957446808511e-05,
92
- "loss": 0.715,
93
- "step": 7000
94
- },
95
- {
96
- "epoch": 79.79,
97
- "learning_rate": 1.0106382978723404e-05,
98
- "loss": 0.9123,
99
- "step": 7500
100
- },
101
- {
102
- "epoch": 85.11,
103
- "learning_rate": 7.446808510638298e-06,
104
- "loss": 0.9641,
105
- "step": 8000
106
- },
107
- {
108
- "epoch": 90.43,
109
- "learning_rate": 4.787234042553191e-06,
110
- "loss": 1.027,
111
- "step": 8500
112
- },
113
- {
114
- "epoch": 95.74,
115
- "learning_rate": 2.1276595744680853e-06,
116
- "loss": 0.7927,
117
- "step": 9000
118
- },
119
- {
120
- "epoch": 100.0,
121
- "step": 9400,
122
- "total_flos": 2.089590732288e+17,
123
- "train_loss": 0.4032590159964054,
124
- "train_runtime": 6707.7517,
125
- "train_samples_per_second": 44.724,
126
- "train_steps_per_second": 1.401
127
  }
128
  ],
129
  "logging_steps": 500,
130
- "max_steps": 9400,
131
- "num_train_epochs": 100,
132
  "save_steps": 500,
133
- "total_flos": 2.089590732288e+17,
134
  "trial_name": null,
135
  "trial_params": null
136
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
  "eval_steps": 500,
6
+ "global_step": 36,
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": 36,
14
+ "total_flos": 881908425216000.0,
15
+ "train_loss": 4.351121690538195,
16
+ "train_runtime": 29.5562,
17
+ "train_samples_per_second": 304.504,
18
+ "train_steps_per_second": 1.218
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 36,
23
+ "num_train_epochs": 3,
24
  "save_steps": 500,
25
+ "total_flos": 881908425216000.0,
26
  "trial_name": null,
27
  "trial_params": null
28
  }