gokulsrinivasagan commited on
Commit
fbff369
1 Parent(s): 4b01e24

End of training

Browse files
README.md CHANGED
@@ -1,13 +1,28 @@
1
  ---
2
  library_name: transformers
 
 
3
  base_model: gokulsrinivasagan/bert_tiny_lda_20_v1
4
  tags:
5
  - generated_from_trainer
 
 
6
  metrics:
7
  - accuracy
8
  model-index:
9
  - name: bert_tiny_lda_20_v1_rte
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_20_v1_rte
17
 
18
- This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_20_v1) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.7016
21
- - Accuracy: 0.4729
22
 
23
  ## Model description
24
 
 
1
  ---
2
  library_name: transformers
3
+ language:
4
+ - en
5
  base_model: gokulsrinivasagan/bert_tiny_lda_20_v1
6
  tags:
7
  - generated_from_trainer
8
+ datasets:
9
+ - glue
10
  metrics:
11
  - accuracy
12
  model-index:
13
  - name: bert_tiny_lda_20_v1_rte
14
+ results:
15
+ - task:
16
+ name: Text Classification
17
+ type: text-classification
18
+ dataset:
19
+ name: GLUE RTE
20
+ type: glue
21
+ args: rte
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.5270758122743683
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_20_v1_rte
32
 
33
+ This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_20_v1) on the GLUE RTE dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.6920
36
+ - Accuracy: 0.5271
37
 
38
  ## Model description
39
 
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.0,
3
+ "eval_accuracy": 0.5270758122743683,
4
+ "eval_loss": 0.6919703483581543,
5
+ "eval_runtime": 0.0907,
6
+ "eval_samples": 277,
7
+ "eval_samples_per_second": 3054.758,
8
+ "eval_steps_per_second": 22.056,
9
+ "total_flos": 391780256993280.0,
10
+ "train_loss": 0.7266074577967326,
11
+ "train_runtime": 12.795,
12
+ "train_samples": 2490,
13
+ "train_samples_per_second": 9730.346,
14
+ "train_steps_per_second": 39.078
15
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.0,
3
+ "eval_accuracy": 0.5270758122743683,
4
+ "eval_loss": 0.6919703483581543,
5
+ "eval_runtime": 0.0907,
6
+ "eval_samples": 277,
7
+ "eval_samples_per_second": 3054.758,
8
+ "eval_steps_per_second": 22.056
9
+ }
logs/events.out.tfevents.1732658236.ki-g0008.2136969.27 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb7dddc0e028a7941639fb2bf9c73aaff37af6a1cc0cc2055e687046f8effe86
3
+ size 405
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.0,
3
+ "total_flos": 391780256993280.0,
4
+ "train_loss": 0.7266074577967326,
5
+ "train_runtime": 12.795,
6
+ "train_samples": 2490,
7
+ "train_samples_per_second": 9730.346,
8
+ "train_steps_per_second": 39.078
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6919703483581543,
3
+ "best_model_checkpoint": "bert_tiny_lda_20_v1_rte/checkpoint-10",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 60,
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": 0.6528123617172241,
14
+ "learning_rate": 0.00098,
15
+ "loss": 0.7827,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5270758122743683,
21
+ "eval_loss": 0.6919703483581543,
22
+ "eval_runtime": 0.0925,
23
+ "eval_samples_per_second": 2994.349,
24
+ "eval_steps_per_second": 21.62,
25
+ "step": 10
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": 61.58826446533203,
30
+ "learning_rate": 0.00096,
31
+ "loss": 0.7523,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.4729241877256318,
37
+ "eval_loss": 0.9407504796981812,
38
+ "eval_runtime": 0.0956,
39
+ "eval_samples_per_second": 2897.052,
40
+ "eval_steps_per_second": 20.917,
41
+ "step": 20
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 0.22817732393741608,
46
+ "learning_rate": 0.00094,
47
+ "loss": 0.7355,
48
+ "step": 30
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.5270758122743683,
53
+ "eval_loss": 0.6925626397132874,
54
+ "eval_runtime": 0.0957,
55
+ "eval_samples_per_second": 2895.327,
56
+ "eval_steps_per_second": 20.905,
57
+ "step": 30
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 0.17734946310520172,
62
+ "learning_rate": 0.00092,
63
+ "loss": 0.6946,
64
+ "step": 40
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.5270758122743683,
69
+ "eval_loss": 0.6931407451629639,
70
+ "eval_runtime": 0.0931,
71
+ "eval_samples_per_second": 2975.598,
72
+ "eval_steps_per_second": 21.484,
73
+ "step": 40
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "grad_norm": 0.5333439111709595,
78
+ "learning_rate": 0.0009000000000000001,
79
+ "loss": 0.6954,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_accuracy": 0.5270758122743683,
85
+ "eval_loss": 0.6965110898017883,
86
+ "eval_runtime": 0.0932,
87
+ "eval_samples_per_second": 2970.774,
88
+ "eval_steps_per_second": 21.45,
89
+ "step": 50
90
+ },
91
+ {
92
+ "epoch": 6.0,
93
+ "grad_norm": 0.4501447379589081,
94
+ "learning_rate": 0.00088,
95
+ "loss": 0.699,
96
+ "step": 60
97
+ },
98
+ {
99
+ "epoch": 6.0,
100
+ "eval_accuracy": 0.4729241877256318,
101
+ "eval_loss": 0.7016019821166992,
102
+ "eval_runtime": 0.0946,
103
+ "eval_samples_per_second": 2926.696,
104
+ "eval_steps_per_second": 21.131,
105
+ "step": 60
106
+ },
107
+ {
108
+ "epoch": 6.0,
109
+ "step": 60,
110
+ "total_flos": 391780256993280.0,
111
+ "train_loss": 0.7266074577967326,
112
+ "train_runtime": 12.795,
113
+ "train_samples_per_second": 9730.346,
114
+ "train_steps_per_second": 39.078
115
+ }
116
+ ],
117
+ "logging_steps": 1,
118
+ "max_steps": 500,
119
+ "num_input_tokens_seen": 0,
120
+ "num_train_epochs": 50,
121
+ "save_steps": 500,
122
+ "stateful_callbacks": {
123
+ "EarlyStoppingCallback": {
124
+ "args": {
125
+ "early_stopping_patience": 5,
126
+ "early_stopping_threshold": 0.0
127
+ },
128
+ "attributes": {
129
+ "early_stopping_patience_counter": 5
130
+ }
131
+ },
132
+ "TrainerControl": {
133
+ "args": {
134
+ "should_epoch_stop": false,
135
+ "should_evaluate": false,
136
+ "should_log": false,
137
+ "should_save": true,
138
+ "should_training_stop": true
139
+ },
140
+ "attributes": {}
141
+ }
142
+ },
143
+ "total_flos": 391780256993280.0,
144
+ "train_batch_size": 256,
145
+ "trial_name": null,
146
+ "trial_params": null
147
+ }