Hugging Face's logo

gokuls
/
mobilebert_add_GLUE_Experiment_logit_kd_pretrain_stsb

Text Classification
Transformers
PyTorch
TensorBoard
English
mobilebert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
gokuls commited on
Commit
23e8490
•
1 Parent(s): 4475573

End of training

Browse files
Files changed (6) hide show
  1. README.md +3 -1
  2. all_results.json +14 -0
  3. eval_results.json +9 -0
  4. logs/events.out.tfevents.1675106773.serv-3329.2971728.2 +3 -0
  5. train_results.json +8 -0
  6. trainer_state.json +115 -0
README.md CHANGED
@@ -1,4 +1,6 @@
1
  ---
 
 
2
  license: apache-2.0
3
  tags:
4
  - generated_from_trainer
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # mobilebert_add_GLUE_Experiment_logit_kd_pretrain_stsb
16
 
17
- This model is a fine-tuned version of [gokuls/mobilebert_add_pre-training-complete](https://huggingface.co/gokuls/mobilebert_add_pre-training-complete) on the glue dataset.
18
  It achieves the following results on the evaluation set:
19
  - Loss: nan
20
  - Mse: nan
 
1
  ---
2
+ language:
3
+ - en
4
  license: apache-2.0
5
  tags:
6
  - generated_from_trainer
 
16
 
17
  # mobilebert_add_GLUE_Experiment_logit_kd_pretrain_stsb
18
 
19
+ This model is a fine-tuned version of [gokuls/mobilebert_add_pre-training-complete](https://huggingface.co/gokuls/mobilebert_add_pre-training-complete) on the GLUE STSB dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: nan
22
  - Mse: nan
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.0,
3
+ "eval_loss": NaN,
4
+ "eval_mse": NaN,
5
+ "eval_runtime": 3.2786,
6
+ "eval_samples": 1500,
7
+ "eval_samples_per_second": 457.51,
8
+ "eval_steps_per_second": 3.66,
9
+ "train_loss": 0.0,
10
+ "train_runtime": 274.6362,
11
+ "train_samples": 5749,
12
+ "train_samples_per_second": 1046.657,
13
+ "train_steps_per_second": 8.193
14
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.0,
3
+ "eval_loss": NaN,
4
+ "eval_mse": NaN,
5
+ "eval_runtime": 3.2786,
6
+ "eval_samples": 1500,
7
+ "eval_samples_per_second": 457.51,
8
+ "eval_steps_per_second": 3.66
9
+ }
logs/events.out.tfevents.1675106773.serv-3329.2971728.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b34367cc54ed0f8f30f65380dc9a399a1ccc5f2c238a2d6477215f9f130d410
3
+ size 358
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.0,
3
+ "train_loss": 0.0,
4
+ "train_runtime": 274.6362,
5
+ "train_samples": 5749,
6
+ "train_samples_per_second": 1046.657,
7
+ "train_steps_per_second": 8.193
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": NaN,
3
+ "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_logit_kd_pretrain_stsb/checkpoint-45",
4
+ "epoch": 6.0,
5
+ "global_step": 270,
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": 0.0,
14
+ "step": 45
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": NaN,
19
+ "eval_mse": NaN,
20
+ "eval_runtime": 3.2792,
21
+ "eval_samples_per_second": 457.422,
22
+ "eval_steps_per_second": 3.659,
23
+ "step": 45
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 4.8e-05,
28
+ "loss": 0.0,
29
+ "step": 90
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_loss": NaN,
34
+ "eval_mse": NaN,
35
+ "eval_runtime": 4.2807,
36
+ "eval_samples_per_second": 350.411,
37
+ "eval_steps_per_second": 2.803,
38
+ "step": 90
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 4.7e-05,
43
+ "loss": 0.0,
44
+ "step": 135
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_loss": NaN,
49
+ "eval_mse": NaN,
50
+ "eval_runtime": 3.2608,
51
+ "eval_samples_per_second": 460.015,
52
+ "eval_steps_per_second": 3.68,
53
+ "step": 135
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "learning_rate": 4.600000000000001e-05,
58
+ "loss": 0.0,
59
+ "step": 180
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "eval_loss": NaN,
64
+ "eval_mse": NaN,
65
+ "eval_runtime": 4.301,
66
+ "eval_samples_per_second": 348.759,
67
+ "eval_steps_per_second": 2.79,
68
+ "step": 180
69
+ },
70
+ {
71
+ "epoch": 5.0,
72
+ "learning_rate": 4.5e-05,
73
+ "loss": 0.0,
74
+ "step": 225
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "eval_loss": NaN,
79
+ "eval_mse": NaN,
80
+ "eval_runtime": 3.2605,
81
+ "eval_samples_per_second": 460.047,
82
+ "eval_steps_per_second": 3.68,
83
+ "step": 225
84
+ },
85
+ {
86
+ "epoch": 6.0,
87
+ "learning_rate": 4.4000000000000006e-05,
88
+ "loss": 0.0,
89
+ "step": 270
90
+ },
91
+ {
92
+ "epoch": 6.0,
93
+ "eval_loss": NaN,
94
+ "eval_mse": NaN,
95
+ "eval_runtime": 4.2804,
96
+ "eval_samples_per_second": 350.434,
97
+ "eval_steps_per_second": 2.803,
98
+ "step": 270
99
+ },
100
+ {
101
+ "epoch": 6.0,
102
+ "step": 270,
103
+ "total_flos": 1034234131120128.0,
104
+ "train_loss": 0.0,
105
+ "train_runtime": 274.6362,
106
+ "train_samples_per_second": 1046.657,
107
+ "train_steps_per_second": 8.193
108
+ }
109
+ ],
110
+ "max_steps": 2250,
111
+ "num_train_epochs": 50,
112
+ "total_flos": 1034234131120128.0,
113
+ "trial_name": null,
114
+ "trial_params": null
115
+ }