mujerry
commited on
Commit
•
4680faa
1
Parent(s):
0402cf6
add model
Browse files- .gitignore +1 -0
- README.md +70 -0
- config.json +25 -0
- pytorch_model.bin +3 -0
- runs/Jul27_13-17-21_cd07f0ba5ee6/1627391953.2391515/events.out.tfevents.1627391953.cd07f0ba5ee6.62.1 +3 -0
- runs/Jul27_13-17-21_cd07f0ba5ee6/events.out.tfevents.1627391953.cd07f0ba5ee6.62.0 +3 -0
- runs/Jul27_13-26-00_cd07f0ba5ee6/1627392445.8834243/events.out.tfevents.1627392445.cd07f0ba5ee6.62.3 +3 -0
- runs/Jul27_13-26-00_cd07f0ba5ee6/events.out.tfevents.1627392445.cd07f0ba5ee6.62.2 +3 -0
- runs/Jul27_13-26-00_cd07f0ba5ee6/events.out.tfevents.1627392569.cd07f0ba5ee6.62.4 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- null
|
7 |
+
model_index:
|
8 |
+
- name: bert-base-uncased-finetuned-QnA
|
9 |
+
results:
|
10 |
+
- task:
|
11 |
+
name: Masked Language Modeling
|
12 |
+
type: fill-mask
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# bert-base-uncased-finetuned-QnA
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 3.0604
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 2e-05
|
42 |
+
- train_batch_size: 8
|
43 |
+
- eval_batch_size: 8
|
44 |
+
- seed: 42
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 10
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
+
| No log | 1.0 | 20 | 3.4894 |
|
54 |
+
| No log | 2.0 | 40 | 3.5654 |
|
55 |
+
| No log | 3.0 | 60 | 3.3185 |
|
56 |
+
| No log | 4.0 | 80 | 3.2859 |
|
57 |
+
| No log | 5.0 | 100 | 3.2947 |
|
58 |
+
| No log | 6.0 | 120 | 3.3998 |
|
59 |
+
| No log | 7.0 | 140 | 3.1642 |
|
60 |
+
| No log | 8.0 | 160 | 3.2653 |
|
61 |
+
| No log | 9.0 | 180 | 3.3427 |
|
62 |
+
| No log | 10.0 | 200 | 3.3549 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- Transformers 4.9.1
|
68 |
+
- Pytorch 1.9.0+cu102
|
69 |
+
- Datasets 1.10.2
|
70 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"gradient_checkpointing": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 3072,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
+
"torch_dtype": "float32",
|
21 |
+
"transformers_version": "4.9.1",
|
22 |
+
"type_vocab_size": 2,
|
23 |
+
"use_cache": true,
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b79bc1a722cc7ce88fd5342436b52c65c18046ac63e17a485a2dbbcbd71b6150
|
3 |
+
size 438141995
|
runs/Jul27_13-17-21_cd07f0ba5ee6/1627391953.2391515/events.out.tfevents.1627391953.cd07f0ba5ee6.62.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:845f2e2e6e0eda8974b810bca3b906f4bb7589f66194857d2c8b2ded97825643
|
3 |
+
size 4192
|
runs/Jul27_13-17-21_cd07f0ba5ee6/events.out.tfevents.1627391953.cd07f0ba5ee6.62.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e510a84f9d8a711dae756ec4f4f07af9fa5b6f456f86c9291fe32d8f1ed72da6
|
3 |
+
size 4068
|
runs/Jul27_13-26-00_cd07f0ba5ee6/1627392445.8834243/events.out.tfevents.1627392445.cd07f0ba5ee6.62.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:806ee76e911cc6a16b4043ac0351b9d40534e77832cfed22d3131f49736df0e8
|
3 |
+
size 4192
|
runs/Jul27_13-26-00_cd07f0ba5ee6/events.out.tfevents.1627392445.cd07f0ba5ee6.62.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbdc954e4f37772cfa1f9928fcda5ccace9f6aa7d020e943973736c2b0257631
|
3 |
+
size 5955
|
runs/Jul27_13-26-00_cd07f0ba5ee6/events.out.tfevents.1627392569.cd07f0ba5ee6.62.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7d58227da1e75244f83c1060a82dce4aa92ea13c98d0354182ad39a47fe0f30
|
3 |
+
size 582
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4d46abba81489639ff3ce12444048bc96428e251d83d3eef3411012261864fc
|
3 |
+
size 2671
|