gokuls commited on
Commit
320bb2b
1 Parent(s): e5c9698

End of training

Browse files
README.md CHANGED
@@ -1,4 +1,6 @@
1
  ---
 
 
2
  tags:
3
  - generated_from_trainer
4
  datasets:
@@ -12,7 +14,7 @@ model-index:
12
  name: Text Classification
13
  type: text-classification
14
  dataset:
15
- name: glue
16
  type: glue
17
  config: rte
18
  split: validation
@@ -20,7 +22,7 @@ model-index:
20
  metrics:
21
  - name: Accuracy
22
  type: accuracy
23
- value: 0.49097472924187724
24
  ---
25
 
26
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
28
 
29
  # hBERTv1_rte
30
 
31
- This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1](https://huggingface.co/gokuls/bert_12_layer_model_v1) on the glue dataset.
32
  It achieves the following results on the evaluation set:
33
- - Loss: 0.8230
34
- - Accuracy: 0.4910
35
 
36
  ## Model description
37
 
 
1
  ---
2
+ language:
3
+ - en
4
  tags:
5
  - generated_from_trainer
6
  datasets:
 
14
  name: Text Classification
15
  type: text-classification
16
  dataset:
17
+ name: GLUE RTE
18
  type: glue
19
  config: rte
20
  split: validation
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.5451263537906137
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
30
 
31
  # hBERTv1_rte
32
 
33
+ This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1](https://huggingface.co/gokuls/bert_12_layer_model_v1) on the GLUE RTE dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.6896
36
+ - Accuracy: 0.5451
37
 
38
  ## Model description
39
 
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.0,
3
+ "eval_accuracy": 0.5451263537906137,
4
+ "eval_loss": 0.6895958781242371,
5
+ "eval_runtime": 0.3771,
6
+ "eval_samples": 277,
7
+ "eval_samples_per_second": 734.458,
8
+ "eval_steps_per_second": 5.303,
9
+ "train_loss": 0.6846395254135131,
10
+ "train_runtime": 78.7517,
11
+ "train_samples": 2490,
12
+ "train_samples_per_second": 1580.919,
13
+ "train_steps_per_second": 6.349
14
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.0,
3
+ "eval_accuracy": 0.5451263537906137,
4
+ "eval_loss": 0.6895958781242371,
5
+ "eval_runtime": 0.3771,
6
+ "eval_samples": 277,
7
+ "eval_samples_per_second": 734.458,
8
+ "eval_steps_per_second": 5.303
9
+ }
logs/events.out.tfevents.1677696537.serv-9220.1178704.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d00c598c707d584c5dcf41d83b0b39b67f1c87464913e3d61fe0994d452c3b0
3
+ size 357
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.0,
3
+ "train_loss": 0.6846395254135131,
4
+ "train_runtime": 78.7517,
5
+ "train_samples": 2490,
6
+ "train_samples_per_second": 1580.919,
7
+ "train_steps_per_second": 6.349
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6895958781242371,
3
+ "best_model_checkpoint": "hBERTv1_rte/checkpoint-10",
4
+ "epoch": 6.0,
5
+ "global_step": 60,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 4.9e-05,
13
+ "loss": 0.7247,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.5451263537906137,
19
+ "eval_loss": 0.6895958781242371,
20
+ "eval_runtime": 0.3609,
21
+ "eval_samples_per_second": 767.565,
22
+ "eval_steps_per_second": 5.542,
23
+ "step": 10
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 4.8e-05,
28
+ "loss": 0.7046,
29
+ "step": 20
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.4729241877256318,
34
+ "eval_loss": 0.7013799548149109,
35
+ "eval_runtime": 0.3547,
36
+ "eval_samples_per_second": 780.85,
37
+ "eval_steps_per_second": 5.638,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 4.7e-05,
43
+ "loss": 0.6934,
44
+ "step": 30
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.4729241877256318,
49
+ "eval_loss": 0.6982845067977905,
50
+ "eval_runtime": 0.3536,
51
+ "eval_samples_per_second": 783.333,
52
+ "eval_steps_per_second": 5.656,
53
+ "step": 30
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "learning_rate": 4.600000000000001e-05,
58
+ "loss": 0.6846,
59
+ "step": 40
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "eval_accuracy": 0.5126353790613718,
64
+ "eval_loss": 0.7091580033302307,
65
+ "eval_runtime": 0.3613,
66
+ "eval_samples_per_second": 766.716,
67
+ "eval_steps_per_second": 5.536,
68
+ "step": 40
69
+ },
70
+ {
71
+ "epoch": 5.0,
72
+ "learning_rate": 4.5e-05,
73
+ "loss": 0.6853,
74
+ "step": 50
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "eval_accuracy": 0.5126353790613718,
79
+ "eval_loss": 0.713951826095581,
80
+ "eval_runtime": 0.3543,
81
+ "eval_samples_per_second": 781.867,
82
+ "eval_steps_per_second": 5.645,
83
+ "step": 50
84
+ },
85
+ {
86
+ "epoch": 6.0,
87
+ "learning_rate": 4.4000000000000006e-05,
88
+ "loss": 0.6152,
89
+ "step": 60
90
+ },
91
+ {
92
+ "epoch": 6.0,
93
+ "eval_accuracy": 0.49097472924187724,
94
+ "eval_loss": 0.8229976892471313,
95
+ "eval_runtime": 0.3532,
96
+ "eval_samples_per_second": 784.179,
97
+ "eval_steps_per_second": 5.662,
98
+ "step": 60
99
+ },
100
+ {
101
+ "epoch": 6.0,
102
+ "step": 60,
103
+ "total_flos": 1887086894383104.0,
104
+ "train_loss": 0.6846395254135131,
105
+ "train_runtime": 78.7517,
106
+ "train_samples_per_second": 1580.919,
107
+ "train_steps_per_second": 6.349
108
+ }
109
+ ],
110
+ "max_steps": 500,
111
+ "num_train_epochs": 50,
112
+ "total_flos": 1887086894383104.0,
113
+ "trial_name": null,
114
+ "trial_params": null
115
+ }