Hugging Face's logo

haibotamiu
/
out

Question Answering
Transformers
PyTorch
albert
Generated from Trainer
Inference Endpoints
Model card Files Community
haibotamiu commited on
Commit
a98ff2a
•
1 Parent(s): 3a5e877

End of training

Browse files
Files changed (8) hide show
  1. README.md +4 -1
  2. all_results.json +7 -7
  3. args.bin +1 -1
  4. eval_nbest_predictions.json +2 -2
  5. eval_predictions.json +0 -0
  6. eval_results.json +3 -3
  7. train_results.json +5 -5
  8. trainer_state.json +12 -60
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": 5000,
4
- "exact_match": 58.36,
5
- "f1": 67.63478561868162,
6
- "train_loss": 0.12255857245624066,
7
- "train_runtime": 2635.091,
8
  "train_samples": 5000,
9
- "train_samples_per_second": 189.747,
10
- "train_steps_per_second": 1.518
11
  }
 
1
  {
2
+ "epoch": 3.0,
3
  "eval_samples": 5000,
4
+ "exact_match": 52.04,
5
+ "f1": 62.61864766642532,
6
+ "train_loss": 2.208091510499077,
7
+ "train_runtime": 92.7531,
8
  "train_samples": 5000,
9
+ "train_samples_per_second": 161.72,
10
+ "train_steps_per_second": 2.555
11
  }
args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bd04ab629d9115ddb3c5fb00216165f5ed1049866e5870faf646b7b757f5a85
3
  size 5588
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1ab1b00a5a03ccf832b544d870dd31669776e4867051d4f905923f7ee9d1b04
3
  size 5588
eval_nbest_predictions.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcc2b3dc394ff1ea957b66d8672e17eca66dd6f87a6fe6c047ce62debbe5cdeb
3
- size 23010977
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66e3820923f65a4c437d3fac23193b7fc97334a3e79c01f0fd5dc6d9cc85b66f
3
+ size 22888741
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": 5000,
4
- "exact_match": 58.36,
5
- "f1": 67.63478561868162
6
  }
 
1
  {
2
+ "epoch": 3.0,
3
  "eval_samples": 5000,
4
+ "exact_match": 52.04,
5
+ "f1": 62.61864766642532
6
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 100.0,
3
- "train_loss": 0.12255857245624066,
4
- "train_runtime": 2635.091,
5
  "train_samples": 5000,
6
- "train_samples_per_second": 189.747,
7
- "train_steps_per_second": 1.518
8
  }
 
1
  {
2
+ "epoch": 3.0,
3
+ "train_loss": 2.208091510499077,
4
+ "train_runtime": 92.7531,
5
  "train_samples": 5000,
6
+ "train_samples_per_second": 161.72,
7
+ "train_steps_per_second": 2.555
8
  }
trainer_state.json CHANGED
@@ -1,76 +1,28 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 100.0,
5
  "eval_steps": 500,
6
- "global_step": 4000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 12.5,
13
- "learning_rate": 4.375e-05,
14
- "loss": 0.8815,
15
- "step": 500
16
- },
17
- {
18
- "epoch": 25.0,
19
- "learning_rate": 3.7500000000000003e-05,
20
- "loss": 0.0559,
21
- "step": 1000
22
- },
23
- {
24
- "epoch": 37.5,
25
- "learning_rate": 3.125e-05,
26
- "loss": 0.0193,
27
- "step": 1500
28
- },
29
- {
30
- "epoch": 50.0,
31
- "learning_rate": 2.5e-05,
32
- "loss": 0.009,
33
- "step": 2000
34
- },
35
- {
36
- "epoch": 62.5,
37
- "learning_rate": 1.8750000000000002e-05,
38
- "loss": 0.0058,
39
- "step": 2500
40
- },
41
- {
42
- "epoch": 75.0,
43
- "learning_rate": 1.25e-05,
44
- "loss": 0.0042,
45
- "step": 3000
46
- },
47
- {
48
- "epoch": 87.5,
49
- "learning_rate": 6.25e-06,
50
- "loss": 0.0027,
51
- "step": 3500
52
- },
53
- {
54
- "epoch": 100.0,
55
- "learning_rate": 0.0,
56
- "loss": 0.002,
57
- "step": 4000
58
- },
59
- {
60
- "epoch": 100.0,
61
- "step": 4000,
62
- "total_flos": 4.8994912512e+16,
63
- "train_loss": 0.12255857245624066,
64
- "train_runtime": 2635.091,
65
- "train_samples_per_second": 189.747,
66
- "train_steps_per_second": 1.518
67
  }
68
  ],
69
  "logging_steps": 500,
70
- "max_steps": 4000,
71
- "num_train_epochs": 100,
72
  "save_steps": 500,
73
- "total_flos": 4.8994912512e+16,
74
  "trial_name": null,
75
  "trial_params": null
76
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
  "eval_steps": 500,
6
+ "global_step": 237,
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": 237,
14
+ "total_flos": 1469847375360000.0,
15
+ "train_loss": 2.208091510499077,
16
+ "train_runtime": 92.7531,
17
+ "train_samples_per_second": 161.72,
18
+ "train_steps_per_second": 2.555
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 237,
23
+ "num_train_epochs": 3,
24
  "save_steps": 500,
25
+ "total_flos": 1469847375360000.0,
26
  "trial_name": null,
27
  "trial_params": null
28
  }