vietnhatthai
commited on
Commit
•
15265e1
1
Parent(s):
859e680
End of training
Browse files- README.md +57 -0
- added_tokens.json +3 -0
- config.json +34 -0
- generation_config.json +4 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +4 -0
- tokenizer.json +0 -0
- tokenizer_config.json +6 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: openai-gpt
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: viet_news_pretrain_pipeline
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# viet_news_pretrain_pipeline
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [openai-gpt](https://huggingface.co/openai-gpt) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 1.3521
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 0.0003
|
38 |
+
- train_batch_size: 8
|
39 |
+
- eval_batch_size: 8
|
40 |
+
- seed: 42
|
41 |
+
- gradient_accumulation_steps: 8
|
42 |
+
- total_train_batch_size: 64
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- lr_scheduler_warmup_ratio: 0.18
|
46 |
+
- num_epochs: 3.0
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
|
51 |
+
|
52 |
+
### Framework versions
|
53 |
+
|
54 |
+
- Transformers 4.32.0.dev0
|
55 |
+
- Pytorch 2.0.1+cu118
|
56 |
+
- Datasets 2.14.4
|
57 |
+
- Tokenizers 0.13.3
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 40478
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openai-gpt",
|
3 |
+
"afn": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"OpenAIGPTLMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"embd_pdrop": 0.1,
|
9 |
+
"initializer_range": 0.02,
|
10 |
+
"layer_norm_epsilon": 1e-05,
|
11 |
+
"model_type": "openai-gpt",
|
12 |
+
"n_ctx": 512,
|
13 |
+
"n_embd": 768,
|
14 |
+
"n_head": 12,
|
15 |
+
"n_layer": 12,
|
16 |
+
"n_positions": 512,
|
17 |
+
"n_special": 0,
|
18 |
+
"predict_special_tokens": true,
|
19 |
+
"resid_pdrop": 0.1,
|
20 |
+
"summary_activation": null,
|
21 |
+
"summary_first_dropout": 0.1,
|
22 |
+
"summary_proj_to_labels": true,
|
23 |
+
"summary_type": "cls_index",
|
24 |
+
"summary_use_proj": true,
|
25 |
+
"task_specific_params": {
|
26 |
+
"text-generation": {
|
27 |
+
"do_sample": true,
|
28 |
+
"max_length": 50
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.32.0.dev0",
|
33 |
+
"vocab_size": 40478
|
34 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"transformers_version": "4.32.0.dev0"
|
4 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ace0892d12c2baf5bc804ae2015d2c1c1099dc1034c0d704388fa6ff7f89a18e
|
3 |
+
size 466186517
|
special_tokens_map.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"pad_token": "[PAD]",
|
3 |
+
"unk_token": "<unk>"
|
4 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"model_max_length": 512,
|
4 |
+
"tokenizer_class": "OpenAIGPTTokenizer",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79dde609f80143d553d8ca4c169b70b683bed130edb2851c3c29728e42174cac
|
3 |
+
size 4091
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|