Hugging Face's logo

kamalkraj
/
bert-base-uncased-squad-v2.0-finetuned

Question Answering
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
kamalkraj commited on
Commit
df254ec
•
1 Parent(s): d6119e4

End of training

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. all_results.json +22 -0
  3. eval_nbest_predictions.json +3 -0
  4. eval_null_odds.json +0 -0
  5. eval_predictions.json +0 -0
  6. eval_results.json +17 -0
  7. runs/May31_03-47-55_SUCADTA369/events.out.tfevents.1653997485.SUCADTA369.15014.2 +3 -0
  8. train_results.json +8 -0
  9. trainer_state.json +85 -0
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text
all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_HasAns_exact": 70.25978407557355,
4
+ "eval_HasAns_f1": 76.64904270889281,
5
+ "eval_HasAns_total": 5928,
6
+ "eval_NoAns_exact": 71.42136248948697,
7
+ "eval_NoAns_f1": 71.42136248948697,
8
+ "eval_NoAns_total": 5945,
9
+ "eval_best_exact": 70.84140486818832,
10
+ "eval_best_exact_thresh": 0.0,
11
+ "eval_best_f1": 74.03146005039315,
12
+ "eval_best_f1_thresh": 0.0,
13
+ "eval_exact": 70.84140486818832,
14
+ "eval_f1": 74.03146005039315,
15
+ "eval_samples": 12134,
16
+ "eval_total": 11873,
17
+ "train_loss": 0.9859708636619137,
18
+ "train_runtime": 2796.8161,
19
+ "train_samples": 131754,
20
+ "train_samples_per_second": 94.217,
21
+ "train_steps_per_second": 1.963
22
+ }
eval_nbest_predictions.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46af5dfe6464a0ae65605546dd324d1a1ffa1e7ee0438fad7cdf45c563e1b818
3
+ size 52239158
eval_null_odds.json ADDED
The diff for this file is too large to render. See raw diff
 
eval_predictions.json ADDED
The diff for this file is too large to render. See raw diff
 
eval_results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_HasAns_exact": 70.25978407557355,
4
+ "eval_HasAns_f1": 76.64904270889281,
5
+ "eval_HasAns_total": 5928,
6
+ "eval_NoAns_exact": 71.42136248948697,
7
+ "eval_NoAns_f1": 71.42136248948697,
8
+ "eval_NoAns_total": 5945,
9
+ "eval_best_exact": 70.84140486818832,
10
+ "eval_best_exact_thresh": 0.0,
11
+ "eval_best_f1": 74.03146005039315,
12
+ "eval_best_f1_thresh": 0.0,
13
+ "eval_exact": 70.84140486818832,
14
+ "eval_f1": 74.03146005039315,
15
+ "eval_samples": 12134,
16
+ "eval_total": 11873
17
+ }
runs/May31_03-47-55_SUCADTA369/events.out.tfevents.1653997485.SUCADTA369.15014.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8378c0914df1d97c5c08cd6db95216ab4c711adc57a39e6e7d9be1e81f06d7d3
3
+ size 785
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "train_loss": 0.9859708636619137,
4
+ "train_runtime": 2796.8161,
5
+ "train_samples": 131754,
6
+ "train_samples_per_second": 94.217,
7
+ "train_steps_per_second": 1.963
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 5490,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.18,
12
+ "learning_rate": 0.00010911475409836066,
13
+ "loss": 1.7923,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.36,
18
+ "learning_rate": 9.820765027322405e-05,
19
+ "loss": 1.3442,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.55,
24
+ "learning_rate": 8.727868852459017e-05,
25
+ "loss": 1.218,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.73,
30
+ "learning_rate": 7.63497267759563e-05,
31
+ "loss": 1.1314,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.91,
36
+ "learning_rate": 6.54207650273224e-05,
37
+ "loss": 1.0894,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 1.09,
42
+ "learning_rate": 5.4513661202185795e-05,
43
+ "loss": 0.881,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.28,
48
+ "learning_rate": 4.3584699453551917e-05,
49
+ "loss": 0.7084,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 1.46,
54
+ "learning_rate": 3.265573770491803e-05,
55
+ "loss": 0.6909,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 1.64,
60
+ "learning_rate": 2.1726775956284153e-05,
61
+ "loss": 0.682,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 1.82,
66
+ "learning_rate": 1.0797814207650273e-05,
67
+ "loss": 0.6723,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 2.0,
72
+ "step": 5490,
73
+ "total_flos": 5.164033933049242e+16,
74
+ "train_loss": 0.9859708636619137,
75
+ "train_runtime": 2796.8161,
76
+ "train_samples_per_second": 94.217,
77
+ "train_steps_per_second": 1.963
78
+ }
79
+ ],
80
+ "max_steps": 5490,
81
+ "num_train_epochs": 2,
82
+ "total_flos": 5.164033933049242e+16,
83
+ "trial_name": null,
84
+ "trial_params": null
85
+ }