Hugging Face's logo

haibotamiu
/
out

Question Answering
Transformers
PyTorch
albert
Generated from Trainer
Inference Endpoints
Model card Files Community
haibotamiu commited on
Commit
e332b42
•
1 Parent(s): 660135b

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 +36 -18
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": 10.0,
3
  "eval_samples": 5000,
4
- "exact_match": 57.08,
5
- "f1": 66.97081276161907,
6
- "train_loss": 0.6390924392991765,
7
- "train_runtime": 369.0669,
8
  "train_samples": 5000,
9
- "train_samples_per_second": 135.477,
10
- "train_steps_per_second": 4.254
11
  }
 
1
  {
2
+ "epoch": 20.0,
3
  "eval_samples": 5000,
4
+ "exact_match": 54.98,
5
+ "f1": 64.8393012609491,
6
+ "train_loss": 0.33844285147964576,
7
+ "train_runtime": 834.8611,
8
  "train_samples": 5000,
9
+ "train_samples_per_second": 119.78,
10
+ "train_steps_per_second": 3.761
11
  }
args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20547050d211a1ecb3f507bde8c60ae690d2e27e036cdf37d181d44c016fcc0b
3
  size 5652
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f946d98a9617f980361984cacbf785267525745c05202665c5c91ae7eabc6eab
3
  size 5652
eval_nbest_predictions.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c69717155be3c4a43779b680faa2754e117c6879233c9caff804f2698e095200
3
- size 22971523
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2aeb60ee75a6e8451f3bb8c3aad80140b4c60baf9690d122cf17a6e37000fa8
3
+ size 23031302
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": 10.0,
3
  "eval_samples": 5000,
4
- "exact_match": 57.08,
5
- "f1": 66.97081276161907
6
  }
 
1
  {
2
+ "epoch": 20.0,
3
  "eval_samples": 5000,
4
+ "exact_match": 54.98,
5
+ "f1": 64.8393012609491
6
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 10.0,
3
- "train_loss": 0.6390924392991765,
4
- "train_runtime": 369.0669,
5
  "train_samples": 5000,
6
- "train_samples_per_second": 135.477,
7
- "train_steps_per_second": 4.254
8
  }
 
1
  {
2
+ "epoch": 20.0,
3
+ "train_loss": 0.33844285147964576,
4
+ "train_runtime": 834.8611,
5
  "train_samples": 5000,
6
+ "train_samples_per_second": 119.78,
7
+ "train_steps_per_second": 3.761
8
  }
trainer_state.json CHANGED
@@ -1,46 +1,64 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 10.0,
5
  "eval_steps": 500,
6
- "global_step": 1570,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 3.18,
13
- "learning_rate": 3.407643312101911e-05,
14
- "loss": 1.5984,
15
  "step": 500
16
  },
17
  {
18
  "epoch": 6.37,
19
- "learning_rate": 1.8152866242038215e-05,
20
- "loss": 0.2991,
21
  "step": 1000
22
  },
23
  {
24
  "epoch": 9.55,
25
- "learning_rate": 2.229299363057325e-06,
26
- "loss": 0.1001,
27
  "step": 1500
28
  },
29
  {
30
- "epoch": 10.0,
31
- "step": 1570,
32
- "total_flos": 4899491251200000.0,
33
- "train_loss": 0.6390924392991765,
34
- "train_runtime": 369.0669,
35
- "train_samples_per_second": 135.477,
36
- "train_steps_per_second": 4.254
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37
  }
38
  ],
39
  "logging_steps": 500,
40
- "max_steps": 1570,
41
- "num_train_epochs": 10,
42
  "save_steps": 500,
43
- "total_flos": 4899491251200000.0,
44
  "trial_name": null,
45
  "trial_params": null
46
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 20.0,
5
  "eval_steps": 500,
6
+ "global_step": 3140,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 3.18,
13
+ "learning_rate": 4.2038216560509556e-05,
14
+ "loss": 1.5882,
15
  "step": 500
16
  },
17
  {
18
  "epoch": 6.37,
19
+ "learning_rate": 3.407643312101911e-05,
20
+ "loss": 0.2947,
21
  "step": 1000
22
  },
23
  {
24
  "epoch": 9.55,
25
+ "learning_rate": 2.6114649681528662e-05,
26
+ "loss": 0.112,
27
  "step": 1500
28
  },
29
  {
30
+ "epoch": 12.74,
31
+ "learning_rate": 1.8152866242038215e-05,
32
+ "loss": 0.0544,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 15.92,
37
+ "learning_rate": 1.0191082802547772e-05,
38
+ "loss": 0.033,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 19.11,
43
+ "learning_rate": 2.229299363057325e-06,
44
+ "loss": 0.0291,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 20.0,
49
+ "step": 3140,
50
+ "total_flos": 9798982502400000.0,
51
+ "train_loss": 0.33844285147964576,
52
+ "train_runtime": 834.8611,
53
+ "train_samples_per_second": 119.78,
54
+ "train_steps_per_second": 3.761
55
  }
56
  ],
57
  "logging_steps": 500,
58
+ "max_steps": 3140,
59
+ "num_train_epochs": 20,
60
  "save_steps": 500,
61
+ "total_flos": 9798982502400000.0,
62
  "trial_name": null,
63
  "trial_params": null
64
  }