Hugging Face's logo

gokuls
/
hbertv1-massive-logit_KD-tiny_ffn_0.5

Text Classification
Transformers
TensorBoard
Safetensors
hybridbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
gokuls commited on
Commit
84f9fb0
·
1 Parent(s): d708299

End of training

Browse files
Files changed (4) hide show
  1. README.md +122 -0
  2. logs/events.out.tfevents.1700961956.serv-3318.864794.6 +2 -2
  3. logs/events.out.tfevents.1700962197.serv-3318.864794.7 +3 -0
  4. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: gokuls/model_v1_complete_training_wt_init_48_tiny_freeze_new_ffn_0.5
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - massive
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: hbertv1-massive-logit_KD-tiny_ffn_0.5
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ dataset:
16
+ name: massive
17
+ type: massive
18
+ config: en-US
19
+ split: validation
20
+ args: en-US
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.8307919331037875
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # hbertv1-massive-logit_KD-tiny_ffn_0.5
31
+
32
+ This model is a fine-tuned version of [gokuls/model_v1_complete_training_wt_init_48_tiny_freeze_new_ffn_0.5](https://huggingface.co/gokuls/model_v1_complete_training_wt_init_48_tiny_freeze_new_ffn_0.5) on the massive dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.6585
35
+ - Accuracy: 0.8308
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 5e-05
55
+ - train_batch_size: 64
56
+ - eval_batch_size: 64
57
+ - seed: 33
58
+ - distributed_type: multi-GPU
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - num_epochs: 50
62
+
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | 4.3023 | 1.0 | 180 | 3.8354 | 0.1766 |
68
+ | 3.7037 | 2.0 | 360 | 3.2686 | 0.2027 |
69
+ | 3.2011 | 3.0 | 540 | 2.8012 | 0.2966 |
70
+ | 2.774 | 4.0 | 720 | 2.4055 | 0.3802 |
71
+ | 2.4069 | 5.0 | 900 | 2.0833 | 0.4747 |
72
+ | 2.1164 | 6.0 | 1080 | 1.8300 | 0.5588 |
73
+ | 1.8907 | 7.0 | 1260 | 1.6351 | 0.6252 |
74
+ | 1.71 | 8.0 | 1440 | 1.4792 | 0.6621 |
75
+ | 1.5648 | 9.0 | 1620 | 1.3605 | 0.6936 |
76
+ | 1.4399 | 10.0 | 1800 | 1.2607 | 0.7103 |
77
+ | 1.3436 | 11.0 | 1980 | 1.1872 | 0.7201 |
78
+ | 1.266 | 12.0 | 2160 | 1.1295 | 0.7285 |
79
+ | 1.1934 | 13.0 | 2340 | 1.0829 | 0.7359 |
80
+ | 1.1413 | 14.0 | 2520 | 1.0428 | 0.7472 |
81
+ | 1.0807 | 15.0 | 2700 | 0.9984 | 0.7585 |
82
+ | 1.0382 | 16.0 | 2880 | 0.9693 | 0.7600 |
83
+ | 0.9982 | 17.0 | 3060 | 0.9439 | 0.7673 |
84
+ | 0.9626 | 18.0 | 3240 | 0.9207 | 0.7723 |
85
+ | 0.9299 | 19.0 | 3420 | 0.8887 | 0.7796 |
86
+ | 0.8828 | 20.0 | 3600 | 0.8686 | 0.7796 |
87
+ | 0.8593 | 21.0 | 3780 | 0.8537 | 0.7905 |
88
+ | 0.8329 | 22.0 | 3960 | 0.8250 | 0.7934 |
89
+ | 0.8043 | 23.0 | 4140 | 0.8098 | 0.7959 |
90
+ | 0.7764 | 24.0 | 4320 | 0.7990 | 0.8008 |
91
+ | 0.7569 | 25.0 | 4500 | 0.7823 | 0.8067 |
92
+ | 0.7372 | 26.0 | 4680 | 0.7749 | 0.8023 |
93
+ | 0.7182 | 27.0 | 4860 | 0.7640 | 0.8101 |
94
+ | 0.6987 | 28.0 | 5040 | 0.7509 | 0.8106 |
95
+ | 0.6842 | 29.0 | 5220 | 0.7386 | 0.8146 |
96
+ | 0.6673 | 30.0 | 5400 | 0.7305 | 0.8146 |
97
+ | 0.6509 | 31.0 | 5580 | 0.7196 | 0.8214 |
98
+ | 0.6382 | 32.0 | 5760 | 0.7120 | 0.8170 |
99
+ | 0.6301 | 33.0 | 5940 | 0.7134 | 0.8190 |
100
+ | 0.6139 | 34.0 | 6120 | 0.7062 | 0.8200 |
101
+ | 0.6076 | 35.0 | 6300 | 0.6928 | 0.8205 |
102
+ | 0.5919 | 36.0 | 6480 | 0.6838 | 0.8244 |
103
+ | 0.5792 | 37.0 | 6660 | 0.6819 | 0.8264 |
104
+ | 0.5739 | 38.0 | 6840 | 0.6780 | 0.8210 |
105
+ | 0.5698 | 39.0 | 7020 | 0.6684 | 0.8283 |
106
+ | 0.5602 | 40.0 | 7200 | 0.6692 | 0.8249 |
107
+ | 0.5534 | 41.0 | 7380 | 0.6644 | 0.8298 |
108
+ | 0.5429 | 42.0 | 7560 | 0.6599 | 0.8278 |
109
+ | 0.5423 | 43.0 | 7740 | 0.6585 | 0.8308 |
110
+ | 0.5356 | 44.0 | 7920 | 0.6569 | 0.8293 |
111
+ | 0.5374 | 45.0 | 8100 | 0.6565 | 0.8293 |
112
+ | 0.5327 | 46.0 | 8280 | 0.6540 | 0.8273 |
113
+ | 0.5324 | 47.0 | 8460 | 0.6523 | 0.8273 |
114
+ | 0.5281 | 48.0 | 8640 | 0.6519 | 0.8283 |
115
+
116
+
117
+ ### Framework versions
118
+
119
+ - Transformers 4.35.2
120
+ - Pytorch 1.14.0a0+410ce96
121
+ - Datasets 2.15.0
122
+ - Tokenizers 0.15.0
logs/events.out.tfevents.1700961956.serv-3318.864794.6 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01fcbe1ce7476f9f62064ad5d7ffeb76ae5cd19224dc8caf541a8cff675b8460
3
- size 30074
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f921b44a090f0af77e3220119edc215afa3d68d31e8da21f8bb9e868281e2eb
3
+ size 30908
logs/events.out.tfevents.1700962197.serv-3318.864794.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e817bd675fdd322ee2f6be6071b0482df30405c5ac524789e671698f8d75e8d
3
+ size 363
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c196ada482e57bc10d38bb534a7b5494724bc2420550820e0b0491241f8978b
3
  size 16858128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf483b46d06beab68d8b65fb62ac1f0d5b90ae744eeac9d84333895bc2db1735
3
  size 16858128