gokuls commited on
Commit
e7a721c
1 Parent(s): 4c16074

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: qnli
18
  split: validation
@@ -20,7 +22,7 @@ model-index:
20
  metrics:
21
  - name: Accuracy
22
  type: accuracy
23
- value: 0.7752150832875709
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_qnli
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: 0.7668
34
- - Accuracy: 0.7752
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 QNLI
18
  type: glue
19
  config: qnli
20
  split: validation
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8112758557569101
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
30
 
31
  # hBERTv1_qnli
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 QNLI dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.4198
36
+ - Accuracy: 0.8113
37
 
38
  ## Model description
39
 
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 8.0,
3
+ "eval_accuracy": 0.8112758557569101,
4
+ "eval_loss": 0.4198276698589325,
5
+ "eval_runtime": 6.7804,
6
+ "eval_samples": 5463,
7
+ "eval_samples_per_second": 805.699,
8
+ "eval_steps_per_second": 3.245,
9
+ "train_loss": 0.3110694268854653,
10
+ "train_runtime": 3241.717,
11
+ "train_samples": 104743,
12
+ "train_samples_per_second": 1615.548,
13
+ "train_steps_per_second": 6.324
14
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 8.0,
3
+ "eval_accuracy": 0.8112758557569101,
4
+ "eval_loss": 0.4198276698589325,
5
+ "eval_runtime": 6.7804,
6
+ "eval_samples": 5463,
7
+ "eval_samples_per_second": 805.699,
8
+ "eval_steps_per_second": 3.245
9
+ }
logs/events.out.tfevents.1677684770.serv-9220.1178704.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2033be8d7a3e737be96839feb22048425d6600f71fb1d91b12037029d4c737f9
3
+ size 363
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 8.0,
3
+ "train_loss": 0.3110694268854653,
4
+ "train_runtime": 3241.717,
5
+ "train_samples": 104743,
6
+ "train_samples_per_second": 1615.548,
7
+ "train_steps_per_second": 6.324
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4198276698589325,
3
+ "best_model_checkpoint": "hBERTv1_qnli/checkpoint-1230",
4
+ "epoch": 8.0,
5
+ "global_step": 3280,
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": 0.6667,
14
+ "step": 410
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.6873512721947648,
19
+ "eval_loss": 0.5954663157463074,
20
+ "eval_runtime": 6.817,
21
+ "eval_samples_per_second": 801.373,
22
+ "eval_steps_per_second": 3.227,
23
+ "step": 410
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 4.8e-05,
28
+ "loss": 0.4998,
29
+ "step": 820
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.794801391177009,
34
+ "eval_loss": 0.44860708713531494,
35
+ "eval_runtime": 6.81,
36
+ "eval_samples_per_second": 802.199,
37
+ "eval_steps_per_second": 3.231,
38
+ "step": 820
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 4.7e-05,
43
+ "loss": 0.3985,
44
+ "step": 1230
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.8112758557569101,
49
+ "eval_loss": 0.4198276698589325,
50
+ "eval_runtime": 6.8165,
51
+ "eval_samples_per_second": 801.434,
52
+ "eval_steps_per_second": 3.227,
53
+ "step": 1230
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "learning_rate": 4.600000000000001e-05,
58
+ "loss": 0.3106,
59
+ "step": 1640
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "eval_accuracy": 0.7865641588870584,
64
+ "eval_loss": 0.48407182097435,
65
+ "eval_runtime": 6.8451,
66
+ "eval_samples_per_second": 798.094,
67
+ "eval_steps_per_second": 3.214,
68
+ "step": 1640
69
+ },
70
+ {
71
+ "epoch": 5.0,
72
+ "learning_rate": 4.5e-05,
73
+ "loss": 0.2286,
74
+ "step": 2050
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "eval_accuracy": 0.790591250228812,
79
+ "eval_loss": 0.5340340733528137,
80
+ "eval_runtime": 6.828,
81
+ "eval_samples_per_second": 800.093,
82
+ "eval_steps_per_second": 3.222,
83
+ "step": 2050
84
+ },
85
+ {
86
+ "epoch": 6.0,
87
+ "learning_rate": 4.4000000000000006e-05,
88
+ "loss": 0.1662,
89
+ "step": 2460
90
+ },
91
+ {
92
+ "epoch": 6.0,
93
+ "eval_accuracy": 0.7728354384038074,
94
+ "eval_loss": 0.6281628608703613,
95
+ "eval_runtime": 6.835,
96
+ "eval_samples_per_second": 799.265,
97
+ "eval_steps_per_second": 3.219,
98
+ "step": 2460
99
+ },
100
+ {
101
+ "epoch": 7.0,
102
+ "learning_rate": 4.3e-05,
103
+ "loss": 0.1237,
104
+ "step": 2870
105
+ },
106
+ {
107
+ "epoch": 7.0,
108
+ "eval_accuracy": 0.7752150832875709,
109
+ "eval_loss": 0.6678447723388672,
110
+ "eval_runtime": 6.8476,
111
+ "eval_samples_per_second": 797.793,
112
+ "eval_steps_per_second": 3.213,
113
+ "step": 2870
114
+ },
115
+ {
116
+ "epoch": 8.0,
117
+ "learning_rate": 4.2e-05,
118
+ "loss": 0.0945,
119
+ "step": 3280
120
+ },
121
+ {
122
+ "epoch": 8.0,
123
+ "eval_accuracy": 0.7752150832875709,
124
+ "eval_loss": 0.7668098211288452,
125
+ "eval_runtime": 6.8357,
126
+ "eval_samples_per_second": 799.183,
127
+ "eval_steps_per_second": 3.218,
128
+ "step": 3280
129
+ },
130
+ {
131
+ "epoch": 8.0,
132
+ "step": 3280,
133
+ "total_flos": 1.0584157486002995e+17,
134
+ "train_loss": 0.3110694268854653,
135
+ "train_runtime": 3241.717,
136
+ "train_samples_per_second": 1615.548,
137
+ "train_steps_per_second": 6.324
138
+ }
139
+ ],
140
+ "max_steps": 20500,
141
+ "num_train_epochs": 50,
142
+ "total_flos": 1.0584157486002995e+17,
143
+ "trial_name": null,
144
+ "trial_params": null
145
+ }