Model save
Browse files- README.md +89 -0
- 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:
|
3 |
size 10824365
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3300684772216ce58bd818ea5a96e5761edb6ff6fc2971a533325714c1f3c3d5
|
3 |
size 10824365
|