Hugging Face's logo

gokuls
/
HBERTv1_emb_compress_48_L12_H64_A2

Fill-Mask
Transformers
PyTorch
hybridbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
gokuls commited on
Commit
164efe6
•
1 Parent(s): be5a051

Model save

Browse files
Files changed (2) hide show
  1. README.md +89 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ metrics:
5
+ - accuracy
6
+ model-index:
7
+ - name: HBERTv1_emb_compress_48_L12_H64_A2
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # HBERTv1_emb_compress_48_L12_H64_A2
15
+
16
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 6.4070
19
+ - Accuracy: 0.1285
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 1e-05
39
+ - train_batch_size: 96
40
+ - eval_batch_size: 96
41
+ - seed: 10
42
+ - distributed_type: multi-GPU
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 10000
46
+ - num_epochs: 5
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:------:|:---------------:|:--------:|
52
+ | 8.6554 | 0.16 | 10000 | 8.5846 | 0.0483 |
53
+ | 7.2331 | 0.33 | 20000 | 7.2280 | 0.0542 |
54
+ | 7.0014 | 0.49 | 30000 | 6.9927 | 0.0677 |
55
+ | 6.8699 | 0.66 | 40000 | 6.8637 | 0.0856 |
56
+ | 6.7777 | 0.82 | 50000 | 6.7726 | 0.0922 |
57
+ | 6.7091 | 0.98 | 60000 | 6.7101 | 0.0974 |
58
+ | 6.6626 | 1.15 | 70000 | 6.6620 | 0.1015 |
59
+ | 6.6279 | 1.31 | 80000 | 6.6255 | 0.1040 |
60
+ | 6.5917 | 1.47 | 90000 | 6.5948 | 0.1068 |
61
+ | 6.5691 | 1.64 | 100000 | 6.5695 | 0.1094 |
62
+ | 6.5486 | 1.8 | 110000 | 6.5460 | 0.1122 |
63
+ | 6.5246 | 1.97 | 120000 | 6.5275 | 0.1144 |
64
+ | 6.5069 | 2.13 | 130000 | 6.5115 | 0.1162 |
65
+ | 6.5001 | 2.29 | 140000 | 6.4962 | 0.1180 |
66
+ | 6.4785 | 2.46 | 150000 | 6.4822 | 0.1197 |
67
+ | 6.4706 | 2.62 | 160000 | 6.4714 | 0.1212 |
68
+ | 6.4612 | 2.79 | 170000 | 6.4610 | 0.1225 |
69
+ | 6.4485 | 2.95 | 180000 | 6.4530 | 0.1233 |
70
+ | 6.4477 | 3.11 | 190000 | 6.4441 | 0.1243 |
71
+ | 6.4373 | 3.28 | 200000 | 6.4395 | 0.1251 |
72
+ | 6.4351 | 3.44 | 210000 | 6.4322 | 0.1259 |
73
+ | 6.4273 | 3.6 | 220000 | 6.4264 | 0.1262 |
74
+ | 6.4153 | 3.77 | 230000 | 6.4219 | 0.1269 |
75
+ | 6.4188 | 3.93 | 240000 | 6.4182 | 0.1274 |
76
+ | 6.4128 | 4.1 | 250000 | 6.4150 | 0.1278 |
77
+ | 6.4189 | 4.26 | 260000 | 6.4121 | 0.1280 |
78
+ | 6.4102 | 4.42 | 270000 | 6.4112 | 0.1282 |
79
+ | 6.4105 | 4.59 | 280000 | 6.4087 | 0.1285 |
80
+ | 6.4065 | 4.75 | 290000 | 6.4067 | 0.1287 |
81
+ | 6.4082 | 4.92 | 300000 | 6.4070 | 0.1285 |
82
+
83
+
84
+ ### Framework versions
85
+
86
+ - Transformers 4.33.2
87
+ - Pytorch 1.14.0a0+410ce96
88
+ - Datasets 2.14.5
89
+ - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad4de385b3ad1caf6d11b39835622034d110284e0a25d531d025c3b907ae695e
3
  size 10824365
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3300684772216ce58bd818ea5a96e5761edb6ff6fc2971a533325714c1f3c3d5
3
  size 10824365