gokulsrinivasagan commited on
Commit
f7c7917
1 Parent(s): 5cf3428

End of training

Browse files
README.md CHANGED
@@ -1,13 +1,28 @@
1
  ---
2
  library_name: transformers
 
 
3
  base_model: gokulsrinivasagan/bert_tiny_lda_100_v1
4
  tags:
5
  - generated_from_trainer
 
 
6
  metrics:
7
  - accuracy
8
  model-index:
9
  - name: bert_tiny_lda_100_v1_wnli
10
- results: []
 
 
 
 
 
 
 
 
 
 
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # bert_tiny_lda_100_v1_wnli
17
 
18
- This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.7216
21
- - Accuracy: 0.2958
22
 
23
  ## Model description
24
 
 
1
  ---
2
  library_name: transformers
3
+ language:
4
+ - en
5
  base_model: gokulsrinivasagan/bert_tiny_lda_100_v1
6
  tags:
7
  - generated_from_trainer
8
+ datasets:
9
+ - glue
10
  metrics:
11
  - accuracy
12
  model-index:
13
  - name: bert_tiny_lda_100_v1_wnli
14
+ results:
15
+ - task:
16
+ name: Text Classification
17
+ type: text-classification
18
+ dataset:
19
+ name: GLUE WNLI
20
+ type: glue
21
+ args: wnli
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.5633802816901409
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
30
 
31
  # bert_tiny_lda_100_v1_wnli
32
 
33
+ This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1) on the GLUE WNLI dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.7026
36
+ - Accuracy: 0.5634
37
 
38
  ## Model description
39
 
all_results.json CHANGED
@@ -1,15 +1,15 @@
1
  {
2
- "epoch": 11.0,
3
  "eval_accuracy": 0.5633802816901409,
4
- "eval_loss": 0.6844189763069153,
5
- "eval_runtime": 0.0309,
6
  "eval_samples": 71,
7
- "eval_samples_per_second": 2297.504,
8
- "eval_steps_per_second": 32.359,
9
- "total_flos": 183171693112320.0,
10
- "train_loss": 0.7242465091474128,
11
- "train_runtime": 11.5122,
12
  "train_samples": 635,
13
- "train_samples_per_second": 2757.938,
14
- "train_steps_per_second": 13.03
15
  }
 
1
  {
2
+ "epoch": 7.0,
3
  "eval_accuracy": 0.5633802816901409,
4
+ "eval_loss": 0.7025748491287231,
5
+ "eval_runtime": 0.0316,
6
  "eval_samples": 71,
7
+ "eval_samples_per_second": 2249.993,
8
+ "eval_steps_per_second": 31.69,
9
+ "total_flos": 116563804707840.0,
10
+ "train_loss": 0.6973756040845599,
11
+ "train_runtime": 8.699,
12
  "train_samples": 635,
13
+ "train_samples_per_second": 3649.84,
14
+ "train_steps_per_second": 17.243
15
  }
eval_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 11.0,
3
  "eval_accuracy": 0.5633802816901409,
4
- "eval_loss": 0.6844189763069153,
5
- "eval_runtime": 0.0309,
6
  "eval_samples": 71,
7
- "eval_samples_per_second": 2297.504,
8
- "eval_steps_per_second": 32.359
9
  }
 
1
  {
2
+ "epoch": 7.0,
3
  "eval_accuracy": 0.5633802816901409,
4
+ "eval_loss": 0.7025748491287231,
5
+ "eval_runtime": 0.0316,
6
  "eval_samples": 71,
7
+ "eval_samples_per_second": 2249.993,
8
+ "eval_steps_per_second": 31.69
9
  }
logs/events.out.tfevents.1733327421.ki-g0008.1208741.33 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fb7cb88eb3810f724eff99b07b2fa31cfafeaf16453190a802458829bacdf15
3
+ size 405
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 11.0,
3
- "total_flos": 183171693112320.0,
4
- "train_loss": 0.7242465091474128,
5
- "train_runtime": 11.5122,
6
  "train_samples": 635,
7
- "train_samples_per_second": 2757.938,
8
- "train_steps_per_second": 13.03
9
  }
 
1
  {
2
+ "epoch": 7.0,
3
+ "total_flos": 116563804707840.0,
4
+ "train_loss": 0.6973756040845599,
5
+ "train_runtime": 8.699,
6
  "train_samples": 635,
7
+ "train_samples_per_second": 3649.84,
8
+ "train_steps_per_second": 17.243
9
  }
trainer_state.json CHANGED
@@ -1,197 +1,133 @@
1
  {
2
- "best_metric": 0.6844189763069153,
3
- "best_model_checkpoint": "bert_tiny_lda_100_v1_wnli/checkpoint-18",
4
- "epoch": 11.0,
5
  "eval_steps": 500,
6
- "global_step": 33,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "grad_norm": 8.367554664611816,
14
- "learning_rate": 0.00098,
15
- "loss": 0.988,
16
  "step": 3
17
  },
18
  {
19
  "epoch": 1.0,
20
- "eval_accuracy": 0.5633802816901409,
21
- "eval_loss": 0.6867297291755676,
22
- "eval_runtime": 0.0295,
23
- "eval_samples_per_second": 2410.246,
24
- "eval_steps_per_second": 33.947,
25
  "step": 3
26
  },
27
  {
28
  "epoch": 2.0,
29
- "grad_norm": 0.5282027125358582,
30
- "learning_rate": 0.00096,
31
- "loss": 0.694,
32
  "step": 6
33
  },
34
  {
35
  "epoch": 2.0,
36
  "eval_accuracy": 0.5633802816901409,
37
- "eval_loss": 0.6856295466423035,
38
- "eval_runtime": 0.0289,
39
- "eval_samples_per_second": 2460.978,
40
- "eval_steps_per_second": 34.662,
41
  "step": 6
42
  },
43
  {
44
  "epoch": 3.0,
45
- "grad_norm": 0.9888330101966858,
46
- "learning_rate": 0.00094,
47
- "loss": 0.7144,
48
  "step": 9
49
  },
50
  {
51
  "epoch": 3.0,
52
- "eval_accuracy": 0.5633802816901409,
53
- "eval_loss": 0.6856295466423035,
54
- "eval_runtime": 0.0284,
55
- "eval_samples_per_second": 2497.971,
56
- "eval_steps_per_second": 35.183,
57
  "step": 9
58
  },
59
  {
60
  "epoch": 4.0,
61
- "grad_norm": 1.2957957983016968,
62
- "learning_rate": 0.00092,
63
- "loss": 0.7011,
64
  "step": 12
65
  },
66
  {
67
  "epoch": 4.0,
68
- "eval_accuracy": 0.43661971830985913,
69
- "eval_loss": 0.6941022872924805,
70
- "eval_runtime": 0.0294,
71
- "eval_samples_per_second": 2412.218,
72
- "eval_steps_per_second": 33.975,
73
  "step": 12
74
  },
75
  {
76
  "epoch": 5.0,
77
- "grad_norm": 0.28737398982048035,
78
- "learning_rate": 0.0009000000000000001,
79
- "loss": 0.6932,
80
  "step": 15
81
  },
82
  {
83
  "epoch": 5.0,
84
- "eval_accuracy": 0.43661971830985913,
85
- "eval_loss": 0.7037302851676941,
86
- "eval_runtime": 0.0277,
87
- "eval_samples_per_second": 2565.434,
88
- "eval_steps_per_second": 36.133,
89
  "step": 15
90
  },
91
  {
92
  "epoch": 6.0,
93
- "grad_norm": 0.4876857399940491,
94
- "learning_rate": 0.00088,
95
- "loss": 0.6964,
96
  "step": 18
97
  },
98
  {
99
  "epoch": 6.0,
100
- "eval_accuracy": 0.5633802816901409,
101
- "eval_loss": 0.6844189763069153,
102
- "eval_runtime": 0.0275,
103
- "eval_samples_per_second": 2579.769,
104
- "eval_steps_per_second": 36.335,
105
  "step": 18
106
  },
107
  {
108
  "epoch": 7.0,
109
- "grad_norm": 0.35543572902679443,
110
- "learning_rate": 0.00086,
111
- "loss": 0.6965,
112
  "step": 21
113
  },
114
  {
115
  "epoch": 7.0,
116
- "eval_accuracy": 0.5633802816901409,
117
- "eval_loss": 0.6926164627075195,
118
- "eval_runtime": 0.0276,
119
- "eval_samples_per_second": 2574.861,
120
- "eval_steps_per_second": 36.266,
121
  "step": 21
122
  },
123
  {
124
- "epoch": 8.0,
125
- "grad_norm": 0.9181599617004395,
126
- "learning_rate": 0.00084,
127
- "loss": 0.6957,
128
- "step": 24
129
- },
130
- {
131
- "epoch": 8.0,
132
- "eval_accuracy": 0.43661971830985913,
133
- "eval_loss": 0.7037302851676941,
134
- "eval_runtime": 0.0276,
135
- "eval_samples_per_second": 2572.304,
136
- "eval_steps_per_second": 36.23,
137
- "step": 24
138
- },
139
- {
140
- "epoch": 9.0,
141
- "grad_norm": 0.4169580638408661,
142
- "learning_rate": 0.00082,
143
- "loss": 0.699,
144
- "step": 27
145
- },
146
- {
147
- "epoch": 9.0,
148
- "eval_accuracy": 0.43661971830985913,
149
- "eval_loss": 0.694597065448761,
150
- "eval_runtime": 0.0273,
151
- "eval_samples_per_second": 2599.813,
152
- "eval_steps_per_second": 36.617,
153
- "step": 27
154
- },
155
- {
156
- "epoch": 10.0,
157
- "grad_norm": 0.704374372959137,
158
- "learning_rate": 0.0008,
159
- "loss": 0.6936,
160
- "step": 30
161
- },
162
- {
163
- "epoch": 10.0,
164
- "eval_accuracy": 0.5633802816901409,
165
- "eval_loss": 0.6876101493835449,
166
- "eval_runtime": 0.0276,
167
- "eval_samples_per_second": 2573.526,
168
- "eval_steps_per_second": 36.247,
169
- "step": 30
170
- },
171
- {
172
- "epoch": 11.0,
173
- "grad_norm": 0.26875758171081543,
174
- "learning_rate": 0.0007800000000000001,
175
- "loss": 0.6948,
176
- "step": 33
177
- },
178
- {
179
- "epoch": 11.0,
180
- "eval_accuracy": 0.43661971830985913,
181
- "eval_loss": 0.6944872736930847,
182
- "eval_runtime": 0.028,
183
- "eval_samples_per_second": 2538.427,
184
- "eval_steps_per_second": 35.752,
185
- "step": 33
186
- },
187
- {
188
- "epoch": 11.0,
189
- "step": 33,
190
- "total_flos": 183171693112320.0,
191
- "train_loss": 0.7242465091474128,
192
- "train_runtime": 11.5122,
193
- "train_samples_per_second": 2757.938,
194
- "train_steps_per_second": 13.03
195
  }
196
  ],
197
  "logging_steps": 1,
@@ -220,7 +156,7 @@
220
  "attributes": {}
221
  }
222
  },
223
- "total_flos": 183171693112320.0,
224
  "train_batch_size": 256,
225
  "trial_name": null,
226
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7025748491287231,
3
+ "best_model_checkpoint": "bert_tiny_lda_100_v1_wnli/checkpoint-6",
4
+ "epoch": 7.0,
5
  "eval_steps": 500,
6
+ "global_step": 21,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "grad_norm": 1.800396203994751,
14
+ "learning_rate": 4.9e-05,
15
+ "loss": 0.7082,
16
  "step": 3
17
  },
18
  {
19
  "epoch": 1.0,
20
+ "eval_accuracy": 0.352112676056338,
21
+ "eval_loss": 0.7107725739479065,
22
+ "eval_runtime": 0.0282,
23
+ "eval_samples_per_second": 2516.037,
24
+ "eval_steps_per_second": 35.437,
25
  "step": 3
26
  },
27
  {
28
  "epoch": 2.0,
29
+ "grad_norm": 1.2788060903549194,
30
+ "learning_rate": 4.8e-05,
31
+ "loss": 0.7024,
32
  "step": 6
33
  },
34
  {
35
  "epoch": 2.0,
36
  "eval_accuracy": 0.5633802816901409,
37
+ "eval_loss": 0.7025748491287231,
38
+ "eval_runtime": 0.0293,
39
+ "eval_samples_per_second": 2424.71,
40
+ "eval_steps_per_second": 34.151,
41
  "step": 6
42
  },
43
  {
44
  "epoch": 3.0,
45
+ "grad_norm": 0.7909756302833557,
46
+ "learning_rate": 4.7e-05,
47
+ "loss": 0.7001,
48
  "step": 9
49
  },
50
  {
51
  "epoch": 3.0,
52
+ "eval_accuracy": 0.352112676056338,
53
+ "eval_loss": 0.723371684551239,
54
+ "eval_runtime": 0.0314,
55
+ "eval_samples_per_second": 2260.411,
56
+ "eval_steps_per_second": 31.837,
57
  "step": 9
58
  },
59
  {
60
  "epoch": 4.0,
61
+ "grad_norm": 0.8608013987541199,
62
+ "learning_rate": 4.600000000000001e-05,
63
+ "loss": 0.6938,
64
  "step": 12
65
  },
66
  {
67
  "epoch": 4.0,
68
+ "eval_accuracy": 0.5070422535211268,
69
+ "eval_loss": 0.7065912485122681,
70
+ "eval_runtime": 0.0296,
71
+ "eval_samples_per_second": 2398.618,
72
+ "eval_steps_per_second": 33.783,
73
  "step": 12
74
  },
75
  {
76
  "epoch": 5.0,
77
+ "grad_norm": 1.210613489151001,
78
+ "learning_rate": 4.5e-05,
79
+ "loss": 0.6922,
80
  "step": 15
81
  },
82
  {
83
  "epoch": 5.0,
84
+ "eval_accuracy": 0.4225352112676056,
85
+ "eval_loss": 0.7106072902679443,
86
+ "eval_runtime": 0.0321,
87
+ "eval_samples_per_second": 2208.56,
88
+ "eval_steps_per_second": 31.106,
89
  "step": 15
90
  },
91
  {
92
  "epoch": 6.0,
93
+ "grad_norm": 1.0442590713500977,
94
+ "learning_rate": 4.4000000000000006e-05,
95
+ "loss": 0.6958,
96
  "step": 18
97
  },
98
  {
99
  "epoch": 6.0,
100
+ "eval_accuracy": 0.36619718309859156,
101
+ "eval_loss": 0.7257372736930847,
102
+ "eval_runtime": 0.0321,
103
+ "eval_samples_per_second": 2214.884,
104
+ "eval_steps_per_second": 31.196,
105
  "step": 18
106
  },
107
  {
108
  "epoch": 7.0,
109
+ "grad_norm": 0.6264722943305969,
110
+ "learning_rate": 4.3e-05,
111
+ "loss": 0.6891,
112
  "step": 21
113
  },
114
  {
115
  "epoch": 7.0,
116
+ "eval_accuracy": 0.29577464788732394,
117
+ "eval_loss": 0.721610963344574,
118
+ "eval_runtime": 0.0298,
119
+ "eval_samples_per_second": 2382.593,
120
+ "eval_steps_per_second": 33.558,
121
  "step": 21
122
  },
123
  {
124
+ "epoch": 7.0,
125
+ "step": 21,
126
+ "total_flos": 116563804707840.0,
127
+ "train_loss": 0.6973756040845599,
128
+ "train_runtime": 8.699,
129
+ "train_samples_per_second": 3649.84,
130
+ "train_steps_per_second": 17.243
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
131
  }
132
  ],
133
  "logging_steps": 1,
 
156
  "attributes": {}
157
  }
158
  },
159
+ "total_flos": 116563804707840.0,
160
  "train_batch_size": 256,
161
  "trial_name": null,
162
  "trial_params": null