gokuls commited on
Commit
adf4e70
1 Parent(s): 547a8f0

End of training

Browse files
README.md CHANGED
@@ -1,4 +1,6 @@
1
  ---
 
 
2
  license: apache-2.0
3
  tags:
4
  - generated_from_trainer
@@ -13,7 +15,7 @@ model-index:
13
  name: Text Classification
14
  type: text-classification
15
  dataset:
16
- name: glue
17
  type: glue
18
  config: sst2
19
  split: validation
@@ -21,7 +23,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.5871559633027523
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
29
 
30
  # mobilebert_add_GLUE_Experiment_sst2_256
31
 
32
- This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the glue dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.6983
35
- - Accuracy: 0.5872
36
 
37
  ## Model description
38
 
 
1
  ---
2
+ language:
3
+ - en
4
  license: apache-2.0
5
  tags:
6
  - generated_from_trainer
 
15
  name: Text Classification
16
  type: text-classification
17
  dataset:
18
+ name: GLUE SST2
19
  type: glue
20
  config: sst2
21
  split: validation
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.5561926605504587
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  # mobilebert_add_GLUE_Experiment_sst2_256
33
 
34
+ This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the GLUE SST2 dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.6814
37
+ - Accuracy: 0.5562
38
 
39
  ## Model description
40
 
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.0,
3
+ "eval_accuracy": 0.5561926605504587,
4
+ "eval_loss": 0.6813856959342957,
5
+ "eval_runtime": 1.6098,
6
+ "eval_samples": 872,
7
+ "eval_samples_per_second": 541.676,
8
+ "eval_steps_per_second": 4.348,
9
+ "train_loss": 0.5790761504876017,
10
+ "train_runtime": 2176.4824,
11
+ "train_samples": 67349,
12
+ "train_samples_per_second": 1547.198,
13
+ "train_steps_per_second": 12.107
14
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.0,
3
+ "eval_accuracy": 0.5561926605504587,
4
+ "eval_loss": 0.6813856959342957,
5
+ "eval_runtime": 1.6098,
6
+ "eval_samples": 872,
7
+ "eval_samples_per_second": 541.676,
8
+ "eval_steps_per_second": 4.348
9
+ }
logs/events.out.tfevents.1674762349.gera.2823283.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49024cfdb265d67081f21ba7a56e1624da02c421eb7a539ac745c1036ae7d035
3
+ size 363
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.0,
3
+ "train_loss": 0.5790761504876017,
4
+ "train_runtime": 2176.4824,
5
+ "train_samples": 67349,
6
+ "train_samples_per_second": 1547.198,
7
+ "train_steps_per_second": 12.107
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6813856959342957,
3
+ "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_sst2_256/checkpoint-527",
4
+ "epoch": 6.0,
5
+ "global_step": 3162,
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": 0.6662,
14
+ "step": 527
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.5561926605504587,
19
+ "eval_loss": 0.6813856959342957,
20
+ "eval_runtime": 1.5529,
21
+ "eval_samples_per_second": 561.531,
22
+ "eval_steps_per_second": 4.508,
23
+ "step": 527
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 4.8e-05,
28
+ "loss": 0.5954,
29
+ "step": 1054
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.5493119266055045,
34
+ "eval_loss": 0.7089729905128479,
35
+ "eval_runtime": 1.5587,
36
+ "eval_samples_per_second": 559.425,
37
+ "eval_steps_per_second": 4.491,
38
+ "step": 1054
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 4.7e-05,
43
+ "loss": 0.5689,
44
+ "step": 1581
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.5596330275229358,
49
+ "eval_loss": 0.715036153793335,
50
+ "eval_runtime": 1.6372,
51
+ "eval_samples_per_second": 532.618,
52
+ "eval_steps_per_second": 4.276,
53
+ "step": 1581
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "learning_rate": 4.600000000000001e-05,
58
+ "loss": 0.5546,
59
+ "step": 2108
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "eval_accuracy": 0.5538990825688074,
64
+ "eval_loss": 0.6892502307891846,
65
+ "eval_runtime": 1.5477,
66
+ "eval_samples_per_second": 563.399,
67
+ "eval_steps_per_second": 4.523,
68
+ "step": 2108
69
+ },
70
+ {
71
+ "epoch": 5.0,
72
+ "learning_rate": 4.5e-05,
73
+ "loss": 0.5473,
74
+ "step": 2635
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "eval_accuracy": 0.5871559633027523,
79
+ "eval_loss": 0.7050522565841675,
80
+ "eval_runtime": 1.5988,
81
+ "eval_samples_per_second": 545.394,
82
+ "eval_steps_per_second": 4.378,
83
+ "step": 2635
84
+ },
85
+ {
86
+ "epoch": 6.0,
87
+ "learning_rate": 4.4000000000000006e-05,
88
+ "loss": 0.5421,
89
+ "step": 3162
90
+ },
91
+ {
92
+ "epoch": 6.0,
93
+ "eval_accuracy": 0.5871559633027523,
94
+ "eval_loss": 0.69826340675354,
95
+ "eval_runtime": 1.5749,
96
+ "eval_samples_per_second": 553.7,
97
+ "eval_steps_per_second": 4.445,
98
+ "step": 3162
99
+ },
100
+ {
101
+ "epoch": 6.0,
102
+ "step": 3162,
103
+ "total_flos": 1.0415609493848064e+16,
104
+ "train_loss": 0.5790761504876017,
105
+ "train_runtime": 2176.4824,
106
+ "train_samples_per_second": 1547.198,
107
+ "train_steps_per_second": 12.107
108
+ }
109
+ ],
110
+ "max_steps": 26350,
111
+ "num_train_epochs": 50,
112
+ "total_flos": 1.0415609493848064e+16,
113
+ "trial_name": null,
114
+ "trial_params": null
115
+ }