update model
Browse files- README.md +64 -0
- compressed_graph.dot +0 -0
- mobilebert-base-qat-vs.json +29 -0
- openvino_model.bin +2 -2
- openvino_model.xml +0 -0
- pytorch_model.bin +1 -1
- trainer_state.json +0 -0
- trainer_states.json +0 -0
README.md
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- squad
|
7 |
+
model-index:
|
8 |
+
- name: 0314_i6dh_mobilebert_int8vs_lr7e-05
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# 0314_i6dh_mobilebert_int8vs_lr7e-05
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [csarron/mobilebert-uncased-squad-v1](https://huggingface.co/csarron/mobilebert-uncased-squad-v1) on the squad dataset.
|
18 |
+
|
19 |
+
The model has 12 blocks, and is quantized. The embeddings are also quantized.
|
20 |
+
|
21 |
+
```json
|
22 |
+
{
|
23 |
+
"epoch": 15.0,
|
24 |
+
"eval_exact_match": 83.68968779564806,
|
25 |
+
"eval_f1": 90.37926101768134,
|
26 |
+
"step": 41500
|
27 |
+
}
|
28 |
+
```
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 7e-05
|
47 |
+
- train_batch_size: 32
|
48 |
+
- eval_batch_size: 64
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: cosine_with_restarts
|
52 |
+
- num_epochs: 15.0
|
53 |
+
- mixed_precision_training: Native AMP
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
|
58 |
+
|
59 |
+
### Framework versions
|
60 |
+
|
61 |
+
- Transformers 4.26.0
|
62 |
+
- Pytorch 1.13.1+cu116
|
63 |
+
- Datasets 2.8.0
|
64 |
+
- Tokenizers 0.13.2
|
compressed_graph.dot
ADDED
The diff for this file is too large to render.
See raw diff
|
|
mobilebert-base-qat-vs.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"algorithm": "quantization",
|
3 |
+
"preset": "mixed",
|
4 |
+
"overflow_fix": "disable",
|
5 |
+
"initializer": {
|
6 |
+
"range": {
|
7 |
+
"num_init_samples": 128,
|
8 |
+
"type": "percentile",
|
9 |
+
"params": {
|
10 |
+
"min_percentile": 0.01,
|
11 |
+
"max_percentile": 99.99
|
12 |
+
}
|
13 |
+
},
|
14 |
+
"batchnorm_adaptation": {
|
15 |
+
"num_bn_adaptation_samples": 16
|
16 |
+
}
|
17 |
+
},
|
18 |
+
"scope_overrides": {
|
19 |
+
"activations": {
|
20 |
+
"{re}.*matmul_0": {
|
21 |
+
"mode": "symmetric"
|
22 |
+
}
|
23 |
+
}
|
24 |
+
},
|
25 |
+
"ignored_scopes": [
|
26 |
+
"{re}.*__add___[0-1]",
|
27 |
+
"{re}.*__truediv__*",
|
28 |
+
],
|
29 |
+
}
|
openvino_model.bin
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 sha256:6672e949ad1cdcf3e17f101ed252e6f47197b2ecb1b9f642c3e7ce5d17f9a792
|
3 |
+
size 14913204
|
openvino_model.xml
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 59190159
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9437ce84764871c8d1474484ecd1583954f64a38986ce3f35336e3790ffbd885
|
3 |
size 59190159
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
trainer_states.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|