Model save
Browse files- README.md +11 -12
- config.json +2 -2
- generation_config.json +1 -1
- model.safetensors +1 -1
- runs/Jan31_16-06-34_e1d82b87f05d/events.out.tfevents.1706717256.e1d82b87f05d.1707.0 +3 -0
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,13 +1,10 @@
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
model-index:
|
5 |
- name: indonesia-distilgpt2
|
6 |
results: []
|
7 |
-
datasets:
|
8 |
-
- esteler-ai/idn-news-az
|
9 |
-
language:
|
10 |
-
- id
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -15,7 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# indonesia-distilgpt2
|
17 |
|
18 |
-
This model
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -35,18 +32,20 @@ More information needed
|
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 5e-05
|
38 |
-
- train_batch_size:
|
39 |
-
- eval_batch_size:
|
40 |
- seed: 42
|
41 |
-
- gradient_accumulation_steps: 4
|
42 |
-
- total_train_batch_size: 8
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
- num_epochs: 2.0
|
46 |
|
|
|
|
|
|
|
|
|
47 |
### Framework versions
|
48 |
|
49 |
-
- Transformers 4.37.
|
50 |
-
- Pytorch 2.1.
|
51 |
- Datasets 2.16.1
|
52 |
-
- Tokenizers 0.15.1
|
|
|
1 |
---
|
2 |
+
base_model: zaenalium/indonesia-distilgpt2
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
model-index:
|
6 |
- name: indonesia-distilgpt2
|
7 |
results: []
|
|
|
|
|
|
|
|
|
8 |
---
|
9 |
|
10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
12 |
|
13 |
# indonesia-distilgpt2
|
14 |
|
15 |
+
This model is a fine-tuned version of [zaenalium/indonesia-distilgpt2](https://huggingface.co/zaenalium/indonesia-distilgpt2) on an unknown dataset.
|
16 |
|
17 |
## Model description
|
18 |
|
|
|
32 |
|
33 |
The following hyperparameters were used during training:
|
34 |
- learning_rate: 5e-05
|
35 |
+
- train_batch_size: 4
|
36 |
+
- eval_batch_size: 4
|
37 |
- seed: 42
|
|
|
|
|
38 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
39 |
- lr_scheduler_type: linear
|
40 |
- num_epochs: 2.0
|
41 |
|
42 |
+
### Training results
|
43 |
+
|
44 |
+
|
45 |
+
|
46 |
### Framework versions
|
47 |
|
48 |
+
- Transformers 4.37.2
|
49 |
+
- Pytorch 2.1.0+cu121
|
50 |
- Datasets 2.16.1
|
51 |
+
- Tokenizers 0.15.1
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "indonesia-distilgpt2",
|
3 |
"_num_labels": 1,
|
4 |
"activation_function": "gelu_new",
|
5 |
"architectures": [
|
@@ -40,7 +40,7 @@
|
|
40 |
}
|
41 |
},
|
42 |
"torch_dtype": "float32",
|
43 |
-
"transformers_version": "4.37.
|
44 |
"use_cache": true,
|
45 |
"vocab_size": 52000
|
46 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "zaenalium/indonesia-distilgpt2",
|
3 |
"_num_labels": 1,
|
4 |
"activation_function": "gelu_new",
|
5 |
"architectures": [
|
|
|
40 |
}
|
41 |
},
|
42 |
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.37.2",
|
44 |
"use_cache": true,
|
45 |
"vocab_size": 52000
|
46 |
}
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 50256,
|
4 |
"eos_token_id": 50256,
|
5 |
-
"transformers_version": "4.37.
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 50256,
|
4 |
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.37.2"
|
6 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 333012424
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f2bf7a4d441badb64d222411561532884909f6588b9854e1ce7993ce159c064
|
3 |
size 333012424
|
runs/Jan31_16-06-34_e1d82b87f05d/events.out.tfevents.1706717256.e1d82b87f05d.1707.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b57653626ef851f2fed85e31a44c92176fb069b5e3b6f958b648b2280c229206
|
3 |
+
size 5409
|
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 sha256:95279236f9fe33c6e1302a90373fb7d68e2b0c0a82edc3f014edfb423770c105
|
3 |
+
size 4728
|