Commit
•
8ff6249
1
Parent(s):
0fe748a
End of training
Browse files- README.md +7 -12
- config.json +2 -2
- generation_config.json +1 -1
- model.safetensors +3 -0
- special_tokens_map.json +7 -1
- tokenizer_config.json +42 -0
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,6 +1,5 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
base_model: temporary0-0name/run_opt1
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
@@ -15,9 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# run_opt1
|
17 |
|
18 |
-
This model is a fine-tuned version of [temporary0-0name/
|
19 |
-
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.0540
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -45,18 +42,16 @@ The following hyperparameters were used during training:
|
|
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:
|
|
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
-
| 0.0126 | 0.55 | 100 | 0.0540 |
|
55 |
|
56 |
|
57 |
### Framework versions
|
58 |
|
59 |
-
- Transformers 4.
|
60 |
-
- Pytorch
|
61 |
- Datasets 2.14.6
|
62 |
-
- Tokenizers 0.
|
|
|
1 |
---
|
2 |
+
base_model: temporary0-0name/rand_model
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
|
|
14 |
|
15 |
# run_opt1
|
16 |
|
17 |
+
This model is a fine-tuned version of [temporary0-0name/rand_model](https://huggingface.co/temporary0-0name/rand_model) on the wikitext dataset.
|
|
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: cosine
|
44 |
- lr_scheduler_warmup_steps: 100
|
45 |
+
- num_epochs: 3
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
|
48 |
### Training results
|
49 |
|
|
|
|
|
|
|
50 |
|
51 |
|
52 |
### Framework versions
|
53 |
|
54 |
+
- Transformers 4.35.0
|
55 |
+
- Pytorch 2.0.1+cu118
|
56 |
- Datasets 2.14.6
|
57 |
+
- Tokenizers 0.14.1
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "temporary0-0name/
|
3 |
"architectures": [
|
4 |
"BertLMHeadModel"
|
5 |
],
|
@@ -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
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "temporary0-0name/rand_model",
|
3 |
"architectures": [
|
4 |
"BertLMHeadModel"
|
5 |
],
|
|
|
19 |
"pad_token_id": 0,
|
20 |
"position_embedding_type": "absolute",
|
21 |
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.35.0",
|
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": "4.35.0"
|
5 |
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c32343c48106fcbf4a07ef352cc6efa7421a6a613dd6e76a4e570a66c90f54ac
|
3 |
+
size 438080896
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,13 @@
|
|
1 |
{
|
2 |
"cls_token": "[CLS]",
|
3 |
"mask_token": "[MASK]",
|
4 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"sep_token": "[SEP]",
|
6 |
"unk_token": "[UNK]"
|
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 |
}
|
tokenizer_config.json
CHANGED
@@ -1,4 +1,46 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
"cls_token": "[CLS]",
|
4 |
"do_lower_case": true,
|
|
|
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,
|
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:e3c35310a37ecf2fc81c922a1e33d5ce9798882501cc8dfe7a456af7650fe663
|
3 |
+
size 4091
|