End of training
Browse files- README.md +71 -0
- config.json +62 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: indobenchmark/indogpt
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
model-index:
|
12 |
+
- name: bdc2024-indogpt-chatgpt-1
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# bdc2024-indogpt-chatgpt-1
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [indobenchmark/indogpt](https://huggingface.co/indobenchmark/indogpt) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.4125
|
24 |
+
- Accuracy: 0.9120
|
25 |
+
- Balanced Accuracy: 0.7419
|
26 |
+
- Precision: 0.9074
|
27 |
+
- Recall: 0.9120
|
28 |
+
- F1: 0.9000
|
29 |
+
|
30 |
+
## Model description
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Intended uses & limitations
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training and evaluation data
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training procedure
|
43 |
+
|
44 |
+
### Training hyperparameters
|
45 |
+
|
46 |
+
The following hyperparameters were used during training:
|
47 |
+
- learning_rate: 1e-05
|
48 |
+
- train_batch_size: 16
|
49 |
+
- eval_batch_size: 16
|
50 |
+
- seed: 42
|
51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
+
- lr_scheduler_type: linear
|
53 |
+
- num_epochs: 5
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Balanced Accuracy | Precision | Recall | F1 |
|
58 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------------:|:---------:|:------:|:------:|
|
59 |
+
| No log | 1.0 | 483 | 0.7389 | 0.7859 | 0.5178 | 0.8025 | 0.7859 | 0.7522 |
|
60 |
+
| 0.9144 | 2.0 | 966 | 0.5773 | 0.8337 | 0.6070 | 0.8360 | 0.8337 | 0.8036 |
|
61 |
+
| 0.5745 | 3.0 | 1449 | 0.4493 | 0.8910 | 0.7056 | 0.8885 | 0.8910 | 0.8747 |
|
62 |
+
| 0.3836 | 4.0 | 1932 | 0.4228 | 0.9025 | 0.7261 | 0.8978 | 0.9025 | 0.8878 |
|
63 |
+
| 0.2392 | 5.0 | 2415 | 0.4125 | 0.9120 | 0.7419 | 0.9074 | 0.9120 | 0.9000 |
|
64 |
+
|
65 |
+
|
66 |
+
### Framework versions
|
67 |
+
|
68 |
+
- Transformers 4.33.1
|
69 |
+
- Pytorch 2.3.0+cu121
|
70 |
+
- Datasets 2.19.2
|
71 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "indobenchmark/indogpt",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2ForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2",
|
15 |
+
"3": "LABEL_3",
|
16 |
+
"4": "LABEL_4",
|
17 |
+
"5": "LABEL_5",
|
18 |
+
"6": "LABEL_6",
|
19 |
+
"7": "LABEL_7"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"label2id": {
|
23 |
+
"LABEL_0": 0,
|
24 |
+
"LABEL_1": 1,
|
25 |
+
"LABEL_2": 2,
|
26 |
+
"LABEL_3": 3,
|
27 |
+
"LABEL_4": 4,
|
28 |
+
"LABEL_5": 5,
|
29 |
+
"LABEL_6": 6,
|
30 |
+
"LABEL_7": 7
|
31 |
+
},
|
32 |
+
"layer_norm_epsilon": 1e-05,
|
33 |
+
"model_type": "gpt2",
|
34 |
+
"n_ctx": 1024,
|
35 |
+
"n_embd": 768,
|
36 |
+
"n_head": 12,
|
37 |
+
"n_inner": null,
|
38 |
+
"n_layer": 12,
|
39 |
+
"n_positions": 1024,
|
40 |
+
"pad_token_id": 1,
|
41 |
+
"problem_type": "single_label_classification",
|
42 |
+
"reorder_and_upcast_attn": false,
|
43 |
+
"resid_pdrop": 0.1,
|
44 |
+
"scale_attn_by_inverse_layer_idx": false,
|
45 |
+
"scale_attn_weights": true,
|
46 |
+
"summary_activation": null,
|
47 |
+
"summary_first_dropout": 0.1,
|
48 |
+
"summary_proj_to_labels": true,
|
49 |
+
"summary_type": "cls_index",
|
50 |
+
"summary_use_proj": true,
|
51 |
+
"task_specific_params": {
|
52 |
+
"text-generation": {
|
53 |
+
"do_sample": true,
|
54 |
+
"max_length": 50
|
55 |
+
}
|
56 |
+
},
|
57 |
+
"tokenizer_class": "IndoNLGTokenizer",
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.33.1",
|
60 |
+
"use_cache": true,
|
61 |
+
"vocab_size": 40005
|
62 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfa248339de874035d0dafde70e468c7abef5c027523d31f4b28ac05d5ac7cd7
|
3 |
+
size 466338334
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:700abc7093344ddacf77e44afb9d946d1c4b26babeb025c5d32b0933ff48511b
|
3 |
+
size 4536
|