dimasichsanul
commited on
Commit
•
f334762
1
Parent(s):
7274439
End of training
Browse files- README.md +100 -0
- config.json +29 -0
- model.safetensors +3 -0
- runs/May02_06-03-06_095e505998c8/events.out.tfevents.1714629786.095e505998c8.963.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: indolem/indobert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- f1
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
model-index:
|
12 |
+
- name: IndoBERT_top5_bm25_rr5_10_epoch
|
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 |
+
# IndoBERT_top5_bm25_rr5_10_epoch
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.0484
|
24 |
+
- Accuracy: 0.8476
|
25 |
+
- F1: 0.7027
|
26 |
+
- Precision: 0.7143
|
27 |
+
- Recall: 0.6915
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 5e-05
|
47 |
+
- train_batch_size: 16
|
48 |
+
- eval_batch_size: 16
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- lr_scheduler_warmup_steps: 100
|
53 |
+
- num_epochs: 10
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
58 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
59 |
+
| No log | 0.2857 | 16 | 0.5745 | 0.7396 | 0.0 | 0.0 | 0.0 |
|
60 |
+
| No log | 0.5714 | 32 | 0.5547 | 0.7396 | 0.0 | 0.0 | 0.0 |
|
61 |
+
| No log | 0.8571 | 48 | 0.5288 | 0.7396 | 0.0 | 0.0 | 0.0 |
|
62 |
+
| No log | 1.1429 | 64 | 0.4822 | 0.8006 | 0.4462 | 0.8056 | 0.3085 |
|
63 |
+
| No log | 1.4286 | 80 | 0.4105 | 0.8310 | 0.6013 | 0.7797 | 0.4894 |
|
64 |
+
| No log | 1.7143 | 96 | 0.3975 | 0.8172 | 0.6633 | 0.6373 | 0.6915 |
|
65 |
+
| No log | 2.0 | 112 | 0.3980 | 0.8172 | 0.5541 | 0.7593 | 0.4362 |
|
66 |
+
| No log | 2.2857 | 128 | 0.4243 | 0.8144 | 0.6794 | 0.6174 | 0.7553 |
|
67 |
+
| No log | 2.5714 | 144 | 0.4404 | 0.8033 | 0.4580 | 0.8108 | 0.3191 |
|
68 |
+
| No log | 2.8571 | 160 | 0.3763 | 0.8504 | 0.6824 | 0.7632 | 0.6170 |
|
69 |
+
| No log | 3.1429 | 176 | 0.6084 | 0.7701 | 0.6527 | 0.5379 | 0.8298 |
|
70 |
+
| No log | 3.4286 | 192 | 0.4822 | 0.8587 | 0.7052 | 0.7722 | 0.6489 |
|
71 |
+
| No log | 3.7143 | 208 | 0.4620 | 0.8449 | 0.6164 | 0.8654 | 0.4787 |
|
72 |
+
| No log | 4.0 | 224 | 0.6729 | 0.7922 | 0.6809 | 0.5674 | 0.8511 |
|
73 |
+
| No log | 4.2857 | 240 | 0.7337 | 0.8449 | 0.7143 | 0.6863 | 0.7447 |
|
74 |
+
| No log | 4.5714 | 256 | 1.0946 | 0.7812 | 0.6580 | 0.5547 | 0.8085 |
|
75 |
+
| No log | 4.8571 | 272 | 1.0382 | 0.7535 | 0.6397 | 0.5163 | 0.8404 |
|
76 |
+
| No log | 5.1429 | 288 | 0.5228 | 0.8532 | 0.6971 | 0.7531 | 0.6489 |
|
77 |
+
| No log | 5.4286 | 304 | 0.8456 | 0.8255 | 0.6897 | 0.6422 | 0.7447 |
|
78 |
+
| No log | 5.7143 | 320 | 0.8758 | 0.8504 | 0.6860 | 0.7564 | 0.6277 |
|
79 |
+
| No log | 6.0 | 336 | 0.9307 | 0.8116 | 0.6699 | 0.6161 | 0.7340 |
|
80 |
+
| No log | 6.2857 | 352 | 0.7016 | 0.8421 | 0.6743 | 0.7284 | 0.6277 |
|
81 |
+
| No log | 6.5714 | 368 | 0.6991 | 0.8560 | 0.6941 | 0.7763 | 0.6277 |
|
82 |
+
| No log | 6.8571 | 384 | 0.7400 | 0.8504 | 0.7188 | 0.7041 | 0.7340 |
|
83 |
+
| No log | 7.1429 | 400 | 0.8463 | 0.8532 | 0.7166 | 0.7204 | 0.7128 |
|
84 |
+
| No log | 7.4286 | 416 | 0.8996 | 0.8560 | 0.7234 | 0.7234 | 0.7234 |
|
85 |
+
| No log | 7.7143 | 432 | 0.9267 | 0.8504 | 0.7158 | 0.7083 | 0.7234 |
|
86 |
+
| No log | 8.0 | 448 | 0.9227 | 0.8587 | 0.7182 | 0.7471 | 0.6915 |
|
87 |
+
| No log | 8.2857 | 464 | 0.9840 | 0.8476 | 0.7027 | 0.7143 | 0.6915 |
|
88 |
+
| No log | 8.5714 | 480 | 1.0115 | 0.8449 | 0.6923 | 0.7159 | 0.6702 |
|
89 |
+
| No log | 8.8571 | 496 | 1.0437 | 0.8449 | 0.6957 | 0.7111 | 0.6809 |
|
90 |
+
| 0.2421 | 9.1429 | 512 | 1.0514 | 0.8449 | 0.6957 | 0.7111 | 0.6809 |
|
91 |
+
| 0.2421 | 9.4286 | 528 | 1.0470 | 0.8476 | 0.7027 | 0.7143 | 0.6915 |
|
92 |
+
| 0.2421 | 9.7143 | 544 | 1.0438 | 0.8476 | 0.7027 | 0.7143 | 0.6915 |
|
93 |
+
| 0.2421 | 10.0 | 560 | 1.0484 | 0.8476 | 0.7027 | 0.7143 | 0.6915 |
|
94 |
+
|
95 |
+
|
96 |
+
### Framework versions
|
97 |
+
|
98 |
+
- Transformers 4.40.1
|
99 |
+
- Pytorch 2.2.1+cu121
|
100 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "indolem/indobert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_ids": 0,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "bert",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"problem_type": "single_label_classification",
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.40.1",
|
26 |
+
"type_vocab_size": 2,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 31923
|
29 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f3fedd28e8f45023742ccb02ac3e8b2988487dde65b7425719c73576f3f486c
|
3 |
+
size 442262520
|
runs/May02_06-03-06_095e505998c8/events.out.tfevents.1714629786.095e505998c8.963.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39c8c08a1ad2f82813c3ebfa8ee7825f00ade729900d00b74eeaa10a3e10db12
|
3 |
+
size 21796
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdb61402d47332b7bc080de3ce9cc68e93bcb690d70a42bcfb7fdf171b10dc70
|
3 |
+
size 4984
|