temporary0-0name
commited on
Commit
•
6e4a371
1
Parent(s):
97dd670
Training in progress, step 100
Browse files- README.md +27 -8
- config.json +1 -1
- generation_config.json +1 -1
- pytorch_model.bin +1 -1
- special_tokens_map.json +1 -7
- tokenizer_config.json +0 -42
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
@@ -15,7 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# run_opt
|
17 |
|
18 |
-
This model is a fine-tuned version of [
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -43,18 +45,35 @@ The following hyperparameters were used during training:
|
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: cosine
|
45 |
- lr_scheduler_warmup_steps: 100
|
46 |
-
- num_epochs:
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
53 |
|
54 |
|
55 |
### Framework versions
|
56 |
|
57 |
-
- Transformers 4.
|
58 |
-
- Pytorch
|
59 |
-
- Datasets 2.
|
60 |
-
- Tokenizers 0.
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: bert-base-uncased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
|
|
15 |
|
16 |
# run_opt
|
17 |
|
18 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the wikitext dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.0107
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: cosine
|
47 |
- lr_scheduler_warmup_steps: 100
|
48 |
+
- num_epochs: 10
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
+
| 7.6252 | 0.55 | 100 | 6.4113 |
|
55 |
+
| 4.839 | 1.1 | 200 | 2.0385 |
|
56 |
+
| 0.9137 | 1.65 | 300 | 0.3108 |
|
57 |
+
| 0.171 | 2.2 | 400 | 0.0877 |
|
58 |
+
| 0.0542 | 2.75 | 500 | 0.0396 |
|
59 |
+
| 0.025 | 3.29 | 600 | 0.0242 |
|
60 |
+
| 0.0148 | 3.84 | 700 | 0.0180 |
|
61 |
+
| 0.0098 | 4.39 | 800 | 0.0148 |
|
62 |
+
| 0.0077 | 4.94 | 900 | 0.0130 |
|
63 |
+
| 0.006 | 5.49 | 1000 | 0.0121 |
|
64 |
+
| 0.0053 | 6.04 | 1100 | 0.0115 |
|
65 |
+
| 0.0045 | 6.59 | 1200 | 0.0112 |
|
66 |
+
| 0.0042 | 7.14 | 1300 | 0.0110 |
|
67 |
+
| 0.0039 | 7.69 | 1400 | 0.0109 |
|
68 |
+
| 0.0038 | 8.24 | 1500 | 0.0108 |
|
69 |
+
| 0.0037 | 8.79 | 1600 | 0.0107 |
|
70 |
+
| 0.0037 | 9.33 | 1700 | 0.0107 |
|
71 |
+
| 0.0036 | 9.88 | 1800 | 0.0107 |
|
72 |
|
73 |
|
74 |
### Framework versions
|
75 |
|
76 |
+
- Transformers 4.33.1
|
77 |
+
- Pytorch 1.12.1
|
78 |
+
- Datasets 2.14.6
|
79 |
+
- Tokenizers 0.13.3
|
config.json
CHANGED
@@ -19,7 +19,7 @@
|
|
19 |
"pad_token_id": 0,
|
20 |
"position_embedding_type": "absolute",
|
21 |
"torch_dtype": "float32",
|
22 |
-
"transformers_version": "4.
|
23 |
"type_vocab_size": 2,
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 30522
|
|
|
19 |
"pad_token_id": 0,
|
20 |
"position_embedding_type": "absolute",
|
21 |
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.33.1",
|
23 |
"type_vocab_size": 2,
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 30522
|
generation_config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"pad_token_id": 0,
|
4 |
-
"transformers_version": "4.
|
5 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"pad_token_id": 0,
|
4 |
+
"transformers_version": "4.33.1"
|
5 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 438124333
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdd8f113d389f61fde19184ebf65e6dd85c933e950529fa92f416eb7355be49d
|
3 |
size 438124333
|
special_tokens_map.json
CHANGED
@@ -1,13 +1,7 @@
|
|
1 |
{
|
2 |
"cls_token": "[CLS]",
|
3 |
"mask_token": "[MASK]",
|
4 |
-
"pad_token":
|
5 |
-
"content": "[PAD]",
|
6 |
-
"lstrip": false,
|
7 |
-
"normalized": false,
|
8 |
-
"rstrip": false,
|
9 |
-
"single_word": false
|
10 |
-
},
|
11 |
"sep_token": "[SEP]",
|
12 |
"unk_token": "[UNK]"
|
13 |
}
|
|
|
1 |
{
|
2 |
"cls_token": "[CLS]",
|
3 |
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"sep_token": "[SEP]",
|
6 |
"unk_token": "[UNK]"
|
7 |
}
|
tokenizer_config.json
CHANGED
@@ -1,46 +1,4 @@
|
|
1 |
{
|
2 |
-
"added_tokens_decoder": {
|
3 |
-
"0": {
|
4 |
-
"content": "[PAD]",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false,
|
9 |
-
"special": true
|
10 |
-
},
|
11 |
-
"100": {
|
12 |
-
"content": "[UNK]",
|
13 |
-
"lstrip": false,
|
14 |
-
"normalized": false,
|
15 |
-
"rstrip": false,
|
16 |
-
"single_word": false,
|
17 |
-
"special": true
|
18 |
-
},
|
19 |
-
"101": {
|
20 |
-
"content": "[CLS]",
|
21 |
-
"lstrip": false,
|
22 |
-
"normalized": false,
|
23 |
-
"rstrip": false,
|
24 |
-
"single_word": false,
|
25 |
-
"special": true
|
26 |
-
},
|
27 |
-
"102": {
|
28 |
-
"content": "[SEP]",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": false,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"103": {
|
36 |
-
"content": "[MASK]",
|
37 |
-
"lstrip": false,
|
38 |
-
"normalized": false,
|
39 |
-
"rstrip": false,
|
40 |
-
"single_word": false,
|
41 |
-
"special": true
|
42 |
-
}
|
43 |
-
},
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_lower_case": true,
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
"cls_token": "[CLS]",
|
4 |
"do_lower_case": true,
|
training_args.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 sha256:8e0d0bb29f293a55e44e7583d04f2a3e382a5ea8209ae54677a2375f081f16a2
|
3 |
+
size 3951
|