gokulsrinivasagan commited on
Commit
d9f6e50
1 Parent(s): bbb0351

End of training

Browse files
README.md CHANGED
@@ -1,13 +1,28 @@
1
  ---
2
  library_name: transformers
 
 
3
  base_model: gokulsrinivasagan/bert_base_lda_50_v1
4
  tags:
5
  - generated_from_trainer
 
 
6
  metrics:
7
  - accuracy
8
  model-index:
9
  - name: bert_base_lda_50_v1_qnli
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_base_lda_50_v1_qnli
17
 
18
- This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_50_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_50_v1) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.0230
21
- - Accuracy: 0.7276
22
 
23
  ## Model description
24
 
 
1
  ---
2
  library_name: transformers
3
+ language:
4
+ - en
5
  base_model: gokulsrinivasagan/bert_base_lda_50_v1
6
  tags:
7
  - generated_from_trainer
8
+ datasets:
9
+ - glue
10
  metrics:
11
  - accuracy
12
  model-index:
13
  - name: bert_base_lda_50_v1_qnli
14
+ results:
15
+ - task:
16
+ name: Text Classification
17
+ type: text-classification
18
+ dataset:
19
+ name: GLUE QNLI
20
+ type: glue
21
+ args: qnli
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.7367746659344683
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
30
 
31
  # bert_base_lda_50_v1_qnli
32
 
33
+ This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_50_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_50_v1) on the GLUE QNLI dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.5458
36
+ - Accuracy: 0.7368
37
 
38
  ## Model description
39
 
all_results.json CHANGED
@@ -1,15 +1,15 @@
1
  {
2
- "epoch": 6.0,
3
- "eval_accuracy": 0.5053999633900788,
4
- "eval_loss": 0.69140625,
5
- "eval_runtime": 3.4852,
6
  "eval_samples": 5463,
7
- "eval_samples_per_second": 1567.487,
8
- "eval_steps_per_second": 6.312,
9
- "total_flos": 8.267712381471744e+16,
10
- "train_loss": 0.700571944073933,
11
- "train_runtime": 1041.1142,
12
  "train_samples": 104743,
13
- "train_samples_per_second": 5030.332,
14
- "train_steps_per_second": 19.69
15
  }
 
1
  {
2
+ "epoch": 8.0,
3
+ "eval_accuracy": 0.7367746659344683,
4
+ "eval_loss": 0.5458308458328247,
5
+ "eval_runtime": 3.5103,
6
  "eval_samples": 5463,
7
+ "eval_samples_per_second": 1556.293,
8
+ "eval_steps_per_second": 6.267,
9
+ "total_flos": 1.1023616508628992e+17,
10
+ "train_loss": 0.33002244205009645,
11
+ "train_runtime": 1412.0901,
12
  "train_samples": 104743,
13
+ "train_samples_per_second": 3708.793,
14
+ "train_steps_per_second": 14.517
15
  }
eval_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 6.0,
3
- "eval_accuracy": 0.5053999633900788,
4
- "eval_loss": 0.69140625,
5
- "eval_runtime": 3.4852,
6
  "eval_samples": 5463,
7
- "eval_samples_per_second": 1567.487,
8
- "eval_steps_per_second": 6.312
9
  }
 
1
  {
2
+ "epoch": 8.0,
3
+ "eval_accuracy": 0.7367746659344683,
4
+ "eval_loss": 0.5458308458328247,
5
+ "eval_runtime": 3.5103,
6
  "eval_samples": 5463,
7
+ "eval_samples_per_second": 1556.293,
8
+ "eval_steps_per_second": 6.267
9
  }
logs/events.out.tfevents.1733311267.ki-g0008.1207984.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a0e9e7ba719ab830cd9eec59146b596644a4a5b376b3069eb2da4ae5a45067
3
+ size 411
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 6.0,
3
- "total_flos": 8.267712381471744e+16,
4
- "train_loss": 0.700571944073933,
5
- "train_runtime": 1041.1142,
6
  "train_samples": 104743,
7
- "train_samples_per_second": 5030.332,
8
- "train_steps_per_second": 19.69
9
  }
 
1
  {
2
+ "epoch": 8.0,
3
+ "total_flos": 1.1023616508628992e+17,
4
+ "train_loss": 0.33002244205009645,
5
+ "train_runtime": 1412.0901,
6
  "train_samples": 104743,
7
+ "train_samples_per_second": 3708.793,
8
+ "train_steps_per_second": 14.517
9
  }
trainer_state.json CHANGED
@@ -1,117 +1,149 @@
1
  {
2
- "best_metric": 0.69140625,
3
- "best_model_checkpoint": "bert_base_lda_50_v1_qnli/checkpoint-410",
4
- "epoch": 6.0,
5
  "eval_steps": 500,
6
- "global_step": 2460,
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": 0.1446128487586975,
14
- "learning_rate": 0.00098,
15
- "loss": 0.7377,
16
  "step": 410
17
  },
18
  {
19
  "epoch": 1.0,
20
- "eval_accuracy": 0.5053999633900788,
21
- "eval_loss": 0.69140625,
22
- "eval_runtime": 3.4916,
23
- "eval_samples_per_second": 1564.617,
24
- "eval_steps_per_second": 6.301,
25
  "step": 410
26
  },
27
  {
28
  "epoch": 2.0,
29
- "grad_norm": 0.09045995026826859,
30
- "learning_rate": 0.00096,
31
- "loss": 0.6931,
32
  "step": 820
33
  },
34
  {
35
  "epoch": 2.0,
36
- "eval_accuracy": 0.5053999633900788,
37
- "eval_loss": 0.6933382749557495,
38
- "eval_runtime": 3.4757,
39
- "eval_samples_per_second": 1571.764,
40
- "eval_steps_per_second": 6.33,
41
  "step": 820
42
  },
43
  {
44
  "epoch": 3.0,
45
- "grad_norm": 0.1270582526922226,
46
- "learning_rate": 0.00094,
47
- "loss": 0.6931,
48
  "step": 1230
49
  },
50
  {
51
  "epoch": 3.0,
52
- "eval_accuracy": 0.5053999633900788,
53
- "eval_loss": 0.6933382749557495,
54
- "eval_runtime": 3.4762,
55
- "eval_samples_per_second": 1571.546,
56
- "eval_steps_per_second": 6.329,
57
  "step": 1230
58
  },
59
  {
60
  "epoch": 4.0,
61
- "grad_norm": 0.01812651753425598,
62
- "learning_rate": 0.00092,
63
- "loss": 0.6931,
64
  "step": 1640
65
  },
66
  {
67
  "epoch": 4.0,
68
- "eval_accuracy": 0.5053999633900788,
69
- "eval_loss": 0.6933382749557495,
70
- "eval_runtime": 3.4854,
71
- "eval_samples_per_second": 1567.408,
72
- "eval_steps_per_second": 6.312,
73
  "step": 1640
74
  },
75
  {
76
  "epoch": 5.0,
77
- "grad_norm": 0.047646842896938324,
78
- "learning_rate": 0.0009000000000000001,
79
- "loss": 0.6931,
80
  "step": 2050
81
  },
82
  {
83
  "epoch": 5.0,
84
- "eval_accuracy": 0.4946000366099213,
85
- "eval_loss": 0.6934648156166077,
86
- "eval_runtime": 3.4742,
87
- "eval_samples_per_second": 1572.454,
88
- "eval_steps_per_second": 6.332,
89
  "step": 2050
90
  },
91
  {
92
  "epoch": 6.0,
93
- "grad_norm": 0.05455218255519867,
94
- "learning_rate": 0.00088,
95
- "loss": 0.6932,
96
  "step": 2460
97
  },
98
  {
99
  "epoch": 6.0,
100
- "eval_accuracy": 0.5053999633900788,
101
- "eval_loss": 0.6933382749557495,
102
- "eval_runtime": 3.4771,
103
- "eval_samples_per_second": 1571.138,
104
- "eval_steps_per_second": 6.327,
105
  "step": 2460
106
  },
107
  {
108
- "epoch": 6.0,
109
- "step": 2460,
110
- "total_flos": 8.267712381471744e+16,
111
- "train_loss": 0.700571944073933,
112
- "train_runtime": 1041.1142,
113
- "train_samples_per_second": 5030.332,
114
- "train_steps_per_second": 19.69
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
115
  }
116
  ],
117
  "logging_steps": 1,
@@ -140,7 +172,7 @@
140
  "attributes": {}
141
  }
142
  },
143
- "total_flos": 8.267712381471744e+16,
144
  "train_batch_size": 256,
145
  "trial_name": null,
146
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5458308458328247,
3
+ "best_model_checkpoint": "bert_base_lda_50_v1_qnli/checkpoint-1230",
4
+ "epoch": 8.0,
5
  "eval_steps": 500,
6
+ "global_step": 3280,
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": 2.3502628803253174,
14
+ "learning_rate": 4.9e-05,
15
+ "loss": 0.6503,
16
  "step": 410
17
  },
18
  {
19
  "epoch": 1.0,
20
+ "eval_accuracy": 0.6505583012996522,
21
+ "eval_loss": 0.6147003173828125,
22
+ "eval_runtime": 3.5547,
23
+ "eval_samples_per_second": 1536.826,
24
+ "eval_steps_per_second": 6.189,
25
  "step": 410
26
  },
27
  {
28
  "epoch": 2.0,
29
+ "grad_norm": 3.2205982208251953,
30
+ "learning_rate": 4.8e-05,
31
+ "loss": 0.5535,
32
  "step": 820
33
  },
34
  {
35
  "epoch": 2.0,
36
+ "eval_accuracy": 0.7155409115870401,
37
+ "eval_loss": 0.5496997237205505,
38
+ "eval_runtime": 3.5498,
39
+ "eval_samples_per_second": 1538.962,
40
+ "eval_steps_per_second": 6.198,
41
  "step": 820
42
  },
43
  {
44
  "epoch": 3.0,
45
+ "grad_norm": 3.7460732460021973,
46
+ "learning_rate": 4.7e-05,
47
+ "loss": 0.4425,
48
  "step": 1230
49
  },
50
  {
51
  "epoch": 3.0,
52
+ "eval_accuracy": 0.7367746659344683,
53
+ "eval_loss": 0.5458308458328247,
54
+ "eval_runtime": 3.5648,
55
+ "eval_samples_per_second": 1532.48,
56
+ "eval_steps_per_second": 6.171,
57
  "step": 1230
58
  },
59
  {
60
  "epoch": 4.0,
61
+ "grad_norm": 6.930105209350586,
62
+ "learning_rate": 4.600000000000001e-05,
63
+ "loss": 0.3413,
64
  "step": 1640
65
  },
66
  {
67
  "epoch": 4.0,
68
+ "eval_accuracy": 0.733479773018488,
69
+ "eval_loss": 0.6162947416305542,
70
+ "eval_runtime": 3.5841,
71
+ "eval_samples_per_second": 1524.219,
72
+ "eval_steps_per_second": 6.138,
73
  "step": 1640
74
  },
75
  {
76
  "epoch": 5.0,
77
+ "grad_norm": 7.669921398162842,
78
+ "learning_rate": 4.5e-05,
79
+ "loss": 0.2508,
80
  "step": 2050
81
  },
82
  {
83
  "epoch": 5.0,
84
+ "eval_accuracy": 0.7384221123924584,
85
+ "eval_loss": 0.6988028883934021,
86
+ "eval_runtime": 3.562,
87
+ "eval_samples_per_second": 1533.698,
88
+ "eval_steps_per_second": 6.176,
89
  "step": 2050
90
  },
91
  {
92
  "epoch": 6.0,
93
+ "grad_norm": 8.73188304901123,
94
+ "learning_rate": 4.4000000000000006e-05,
95
+ "loss": 0.1792,
96
  "step": 2460
97
  },
98
  {
99
  "epoch": 6.0,
100
+ "eval_accuracy": 0.7338458722313747,
101
+ "eval_loss": 0.8530865907669067,
102
+ "eval_runtime": 3.5879,
103
+ "eval_samples_per_second": 1522.601,
104
+ "eval_steps_per_second": 6.132,
105
  "step": 2460
106
  },
107
  {
108
+ "epoch": 7.0,
109
+ "grad_norm": 6.224167346954346,
110
+ "learning_rate": 4.3e-05,
111
+ "loss": 0.1282,
112
+ "step": 2870
113
+ },
114
+ {
115
+ "epoch": 7.0,
116
+ "eval_accuracy": 0.7285374336445176,
117
+ "eval_loss": 0.9750887155532837,
118
+ "eval_runtime": 3.585,
119
+ "eval_samples_per_second": 1523.83,
120
+ "eval_steps_per_second": 6.137,
121
+ "step": 2870
122
+ },
123
+ {
124
+ "epoch": 8.0,
125
+ "grad_norm": 6.511787414550781,
126
+ "learning_rate": 4.2e-05,
127
+ "loss": 0.0942,
128
+ "step": 3280
129
+ },
130
+ {
131
+ "epoch": 8.0,
132
+ "eval_accuracy": 0.727622185612301,
133
+ "eval_loss": 1.022977352142334,
134
+ "eval_runtime": 3.522,
135
+ "eval_samples_per_second": 1551.101,
136
+ "eval_steps_per_second": 6.246,
137
+ "step": 3280
138
+ },
139
+ {
140
+ "epoch": 8.0,
141
+ "step": 3280,
142
+ "total_flos": 1.1023616508628992e+17,
143
+ "train_loss": 0.33002244205009645,
144
+ "train_runtime": 1412.0901,
145
+ "train_samples_per_second": 3708.793,
146
+ "train_steps_per_second": 14.517
147
  }
148
  ],
149
  "logging_steps": 1,
 
172
  "attributes": {}
173
  }
174
  },
175
+ "total_flos": 1.1023616508628992e+17,
176
  "train_batch_size": 256,
177
  "trial_name": null,
178
  "trial_params": null