kennethge123
commited on
Commit
•
84d0bb4
1
Parent(s):
1fd3aea
Model save
Browse files
README.md
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: bert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- sst
|
8 |
+
model-index:
|
9 |
+
- name: sst-bert-base-uncased
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# sst-bert-base-uncased
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the sst dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.0201
|
21 |
+
- Mse: 0.0201
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 5e-05
|
41 |
+
- train_batch_size: 16
|
42 |
+
- eval_batch_size: 32
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 20
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Mse |
|
51 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
52 |
+
| 0.0428 | 1.0 | 534 | 0.0218 | 0.0218 |
|
53 |
+
| 0.0169 | 2.0 | 1068 | 0.0216 | 0.0216 |
|
54 |
+
| 0.0096 | 3.0 | 1602 | 0.0231 | 0.0232 |
|
55 |
+
| 0.0066 | 4.0 | 2136 | 0.0222 | 0.0223 |
|
56 |
+
| 0.0046 | 5.0 | 2670 | 0.0220 | 0.0220 |
|
57 |
+
| 0.0035 | 6.0 | 3204 | 0.0209 | 0.0210 |
|
58 |
+
| 0.0029 | 7.0 | 3738 | 0.0226 | 0.0227 |
|
59 |
+
| 0.0025 | 8.0 | 4272 | 0.0211 | 0.0211 |
|
60 |
+
| 0.0023 | 9.0 | 4806 | 0.0207 | 0.0208 |
|
61 |
+
| 0.002 | 10.0 | 5340 | 0.0218 | 0.0218 |
|
62 |
+
| 0.0017 | 11.0 | 5874 | 0.0201 | 0.0202 |
|
63 |
+
| 0.0015 | 12.0 | 6408 | 0.0212 | 0.0212 |
|
64 |
+
| 0.0014 | 13.0 | 6942 | 0.0202 | 0.0202 |
|
65 |
+
| 0.0012 | 14.0 | 7476 | 0.0205 | 0.0206 |
|
66 |
+
| 0.0009 | 15.0 | 8010 | 0.0203 | 0.0203 |
|
67 |
+
| 0.0008 | 16.0 | 8544 | 0.0202 | 0.0202 |
|
68 |
+
| 0.0007 | 17.0 | 9078 | 0.0206 | 0.0207 |
|
69 |
+
| 0.0006 | 18.0 | 9612 | 0.0200 | 0.0200 |
|
70 |
+
| 0.0005 | 19.0 | 10146 | 0.0201 | 0.0201 |
|
71 |
+
| 0.0005 | 20.0 | 10680 | 0.0201 | 0.0201 |
|
72 |
+
|
73 |
+
|
74 |
+
### Framework versions
|
75 |
+
|
76 |
+
- Transformers 4.37.0
|
77 |
+
- Pytorch 1.13.1+cu117
|
78 |
+
- Datasets 2.15.0
|
79 |
+
- Tokenizers 0.15.2
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 437955572
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:babcc3e9d42b269289fd0edeef516041d9a920f43e1dea132f0f2bee6983fa8b
|
3 |
size 437955572
|
runs/Mar29_07-34-39_dsail2/events.out.tfevents.1711712081.dsail2.11956.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:570e96eba2eb86d2341a5ba91cff0e67a33aea466f119951f934fd5c094973c6
|
3 |
+
size 14448
|