haibotamiu commited on
Commit
bd14e74
1 Parent(s): 2d083fc

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": 46.46666666666667,
5
- "f1": 57.048156525818875,
6
- "train_loss": 0.1373301104281811,
7
- "train_runtime": 1170.2721,
8
  "train_samples": 3000,
9
- "train_samples_per_second": 256.351,
10
- "train_steps_per_second": 4.016
11
  }
 
1
  {
2
+ "epoch": 3.0,
3
  "eval_samples": 3000,
4
+ "exact_match": 49.86666666666667,
5
+ "f1": 59.61058102716164,
6
+ "train_loss": 2.3143946870844414,
7
+ "train_runtime": 49.5839,
8
  "train_samples": 3000,
9
+ "train_samples_per_second": 181.511,
10
+ "train_steps_per_second": 5.687
11
  }
args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:674b658cb5de3b2d73ab687b0015e16b01f592ed2c2a5e165578fb83c5f8c6fa
3
  size 5652
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec2e39b08df8c2a081fb8e5631f0856a540b5d572c8c142195a55a84002cc4e1
3
  size 5652
eval_nbest_predictions.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31492035a229852f166abd6073c14daf95cfb304676e60079cee35e0ac6d87b9
3
- size 14143928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1485367969b2d45f98fb1dd10711eaa35f90669a6025ce9d5baaa1cdba2cfb2
3
+ size 14050357
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": 46.46666666666667,
5
- "f1": 57.048156525818875
6
  }
 
1
  {
2
+ "epoch": 3.0,
3
  "eval_samples": 3000,
4
+ "exact_match": 49.86666666666667,
5
+ "f1": 59.61058102716164
6
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 100.0,
3
- "train_loss": 0.1373301104281811,
4
- "train_runtime": 1170.2721,
5
  "train_samples": 3000,
6
- "train_samples_per_second": 256.351,
7
- "train_steps_per_second": 4.016
8
  }
 
1
  {
2
+ "epoch": 3.0,
3
+ "train_loss": 2.3143946870844414,
4
+ "train_runtime": 49.5839,
5
  "train_samples": 3000,
6
+ "train_samples_per_second": 181.511,
7
+ "train_steps_per_second": 5.687
8
  }
trainer_state.json CHANGED
@@ -1,82 +1,28 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 100.0,
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": 10.64,
13
- "learning_rate": 4.468085106382979e-05,
14
- "loss": 1.0426,
15
- "step": 500
16
- },
17
- {
18
- "epoch": 21.28,
19
- "learning_rate": 3.936170212765958e-05,
20
- "loss": 0.0678,
21
- "step": 1000
22
- },
23
- {
24
- "epoch": 31.91,
25
- "learning_rate": 3.4042553191489365e-05,
26
- "loss": 0.0241,
27
- "step": 1500
28
- },
29
- {
30
- "epoch": 42.55,
31
- "learning_rate": 2.8723404255319154e-05,
32
- "loss": 0.0124,
33
- "step": 2000
34
- },
35
- {
36
- "epoch": 53.19,
37
- "learning_rate": 2.340425531914894e-05,
38
- "loss": 0.0083,
39
- "step": 2500
40
- },
41
- {
42
- "epoch": 63.83,
43
- "learning_rate": 1.8085106382978724e-05,
44
- "loss": 0.0099,
45
- "step": 3000
46
- },
47
- {
48
- "epoch": 74.47,
49
- "learning_rate": 1.2765957446808511e-05,
50
- "loss": 0.0117,
51
- "step": 3500
52
- },
53
- {
54
- "epoch": 85.11,
55
- "learning_rate": 7.446808510638298e-06,
56
- "loss": 0.0168,
57
- "step": 4000
58
- },
59
- {
60
- "epoch": 95.74,
61
- "learning_rate": 2.1276595744680853e-06,
62
- "loss": 0.0463,
63
- "step": 4500
64
- },
65
- {
66
- "epoch": 100.0,
67
- "step": 4700,
68
- "total_flos": 2.93969475072e+16,
69
- "train_loss": 0.1373301104281811,
70
- "train_runtime": 1170.2721,
71
- "train_samples_per_second": 256.351,
72
- "train_steps_per_second": 4.016
73
  }
74
  ],
75
  "logging_steps": 500,
76
- "max_steps": 4700,
77
- "num_train_epochs": 100,
78
  "save_steps": 500,
79
- "total_flos": 2.93969475072e+16,
80
  "trial_name": null,
81
  "trial_params": null
82
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
  "eval_steps": 500,
6
+ "global_step": 282,
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": 282,
14
+ "total_flos": 881908425216000.0,
15
+ "train_loss": 2.3143946870844414,
16
+ "train_runtime": 49.5839,
17
+ "train_samples_per_second": 181.511,
18
+ "train_steps_per_second": 5.687
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 282,
23
+ "num_train_epochs": 3,
24
  "save_steps": 500,
25
+ "total_flos": 881908425216000.0,
26
  "trial_name": null,
27
  "trial_params": null
28
  }