Alireza1044 commited on
Commit
69a2540
1 Parent(s): 0c34984
README.md CHANGED
@@ -21,7 +21,7 @@ model_index:
21
  metric:
22
  name: Accuracy
23
  type: accuracy
24
- value: 0.642504118616145
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the GLUE QNLI dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.6284
35
- - Accuracy: 0.6425
36
 
37
  ## Model description
38
 
@@ -57,7 +57,7 @@ The following hyperparameters were used during training:
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
60
- - num_epochs: 0.001
61
 
62
  ### Training results
63
 
 
21
  metric:
22
  name: Accuracy
23
  type: accuracy
24
+ value: 0.9137836353651839
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the GLUE QNLI dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.3608
35
+ - Accuracy: 0.9138
36
 
37
  ## Model description
38
 
 
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
60
+ - num_epochs: 4.0
61
 
62
  ### Training results
63
 
all_results.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
- "epoch": 0.0,
3
- "eval_accuracy": 0.642504118616145,
4
- "eval_loss": 0.6284383535385132,
5
- "eval_runtime": 27.9064,
6
  "eval_samples": 5463,
7
- "eval_samples_per_second": 195.761,
8
- "eval_steps_per_second": 24.475,
9
- "train_loss": 0.6153523921966553,
10
- "train_runtime": 1.5743,
11
  "train_samples": 104743,
12
- "train_samples_per_second": 66.532,
13
- "train_steps_per_second": 2.541
14
  }
 
1
  {
2
+ "epoch": 4.0,
3
+ "eval_accuracy": 0.9137836353651839,
4
+ "eval_loss": 0.36082589626312256,
5
+ "eval_runtime": 28.0959,
6
  "eval_samples": 5463,
7
+ "eval_samples_per_second": 194.441,
8
+ "eval_steps_per_second": 24.31,
9
+ "train_loss": 0.1811416630491514,
10
+ "train_runtime": 5121.9571,
11
  "train_samples": 104743,
12
+ "train_samples_per_second": 81.799,
13
+ "train_steps_per_second": 2.557
14
  }
eval_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 0.0,
3
- "eval_accuracy": 0.642504118616145,
4
- "eval_loss": 0.6284383535385132,
5
- "eval_runtime": 27.9064,
6
  "eval_samples": 5463,
7
- "eval_samples_per_second": 195.761,
8
- "eval_steps_per_second": 24.475
9
  }
 
1
  {
2
+ "epoch": 4.0,
3
+ "eval_accuracy": 0.9137836353651839,
4
+ "eval_loss": 0.36082589626312256,
5
+ "eval_runtime": 28.0959,
6
  "eval_samples": 5463,
7
+ "eval_samples_per_second": 194.441,
8
+ "eval_steps_per_second": 24.31
9
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae50e44ae6c4889694abbe34789e6aabd80d3015327c765d912c85905c45a160
3
  size 46755537
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36ffc9d15038cc4564cd3d06d2fa169b5f87327701ba99cde04b03852a7b6aaf
3
  size 46755537
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 0.0,
3
- "train_loss": 0.6153523921966553,
4
- "train_runtime": 1.5743,
5
  "train_samples": 104743,
6
- "train_samples_per_second": 66.532,
7
- "train_steps_per_second": 2.541
8
  }
 
1
  {
2
+ "epoch": 4.0,
3
+ "train_loss": 0.1811416630491514,
4
+ "train_runtime": 5121.9571,
5
  "train_samples": 104743,
6
+ "train_samples_per_second": 81.799,
7
+ "train_steps_per_second": 2.557
8
  }
trainer_state.json CHANGED
@@ -1,25 +1,181 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.0012217470983506415,
5
- "global_step": 4,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
- "epoch": 0.0,
12
- "step": 4,
13
- "total_flos": 764739256320.0,
14
- "train_loss": 0.6153523921966553,
15
- "train_runtime": 1.5743,
16
- "train_samples_per_second": 66.532,
17
- "train_steps_per_second": 2.541
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18
  }
19
  ],
20
- "max_steps": 4,
21
- "num_train_epochs": 1,
22
- "total_flos": 764739256320.0,
23
  "trial_name": null,
24
  "trial_params": null
25
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 4.0,
5
+ "global_step": 13096,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
+ "epoch": 0.15,
12
+ "learning_rate": 9.618204031765426e-06,
13
+ "loss": 0.3591,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.31,
18
+ "learning_rate": 9.23640806353085e-06,
19
+ "loss": 0.3059,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.46,
24
+ "learning_rate": 8.854612095296275e-06,
25
+ "loss": 0.2878,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.61,
30
+ "learning_rate": 8.4728161270617e-06,
31
+ "loss": 0.2803,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.76,
36
+ "learning_rate": 8.091020158827123e-06,
37
+ "loss": 0.2734,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.92,
42
+ "learning_rate": 7.709224190592548e-06,
43
+ "loss": 0.2593,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.07,
48
+ "learning_rate": 7.327428222357973e-06,
49
+ "loss": 0.2356,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 1.22,
54
+ "learning_rate": 6.945632254123397e-06,
55
+ "loss": 0.1979,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 1.37,
60
+ "learning_rate": 6.563836285888821e-06,
61
+ "loss": 0.1948,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 1.53,
66
+ "learning_rate": 6.1820403176542464e-06,
67
+ "loss": 0.1996,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.68,
72
+ "learning_rate": 5.80024434941967e-06,
73
+ "loss": 0.1996,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.83,
78
+ "learning_rate": 5.418448381185095e-06,
79
+ "loss": 0.1905,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 1.99,
84
+ "learning_rate": 5.03665241295052e-06,
85
+ "loss": 0.1908,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 2.14,
90
+ "learning_rate": 4.6548564447159445e-06,
91
+ "loss": 0.1417,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 2.29,
96
+ "learning_rate": 4.273060476481369e-06,
97
+ "loss": 0.1369,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 2.44,
102
+ "learning_rate": 3.891264508246793e-06,
103
+ "loss": 0.1378,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 2.6,
108
+ "learning_rate": 3.5094685400122174e-06,
109
+ "loss": 0.1355,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 2.75,
114
+ "learning_rate": 3.1276725717776426e-06,
115
+ "loss": 0.145,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 2.9,
120
+ "learning_rate": 2.745876603543067e-06,
121
+ "loss": 0.1411,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 3.05,
126
+ "learning_rate": 2.364080635308491e-06,
127
+ "loss": 0.1127,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 3.21,
132
+ "learning_rate": 1.982284667073916e-06,
133
+ "loss": 0.0956,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 3.36,
138
+ "learning_rate": 1.6004886988393402e-06,
139
+ "loss": 0.0963,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 3.51,
144
+ "learning_rate": 1.218692730604765e-06,
145
+ "loss": 0.1004,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 3.67,
150
+ "learning_rate": 8.368967623701894e-07,
151
+ "loss": 0.1026,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 3.82,
156
+ "learning_rate": 4.55100794135614e-07,
157
+ "loss": 0.1097,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 3.97,
162
+ "learning_rate": 7.330482590103849e-08,
163
+ "loss": 0.0936,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 4.0,
168
+ "step": 13096,
169
+ "total_flos": 2503158872647680.0,
170
+ "train_loss": 0.1811416630491514,
171
+ "train_runtime": 5121.9571,
172
+ "train_samples_per_second": 81.799,
173
+ "train_steps_per_second": 2.557
174
  }
175
  ],
176
+ "max_steps": 13096,
177
+ "num_train_epochs": 4,
178
+ "total_flos": 2503158872647680.0,
179
  "trial_name": null,
180
  "trial_params": null
181
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ae27f71105e7743e6d9c42fd3887cf54f03f8d711b08b7fe00d90710bc91811
3
  size 2607
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d06131cb3582905e5d815d5003443b54e994c9e6d74601fcb7d532e20569611
3
  size 2607