dimasichsanul
commited on
Commit
•
487f343
1
Parent(s):
a6fcef2
End of training
Browse files- README.md +84 -0
- config.json +32 -0
- model.safetensors +3 -0
- runs/Jun09_04-19-26_ebb31ef29bd8/events.out.tfevents.1717906767.ebb31ef29bd8.606.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google-bert/bert-base-multilingual-cased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- f1
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
model-index:
|
12 |
+
- name: results
|
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 |
+
# results
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.4003
|
24 |
+
- Accuracy: 0.8589
|
25 |
+
- F1: 0.7308
|
26 |
+
- Precision: 0.7238
|
27 |
+
- Recall: 0.7379
|
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: 5
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
58 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
59 |
+
| No log | 0.2623 | 16 | 0.6597 | 0.7406 | 0.0 | 0.0 | 0.0 |
|
60 |
+
| No log | 0.5246 | 32 | 0.5547 | 0.7406 | 0.0 | 0.0 | 0.0 |
|
61 |
+
| No log | 0.7869 | 48 | 0.5144 | 0.7406 | 0.0 | 0.0 | 0.0 |
|
62 |
+
| No log | 1.0492 | 64 | 0.4658 | 0.8237 | 0.5205 | 0.8837 | 0.3689 |
|
63 |
+
| No log | 1.3115 | 80 | 0.4164 | 0.8338 | 0.7 | 0.6581 | 0.7476 |
|
64 |
+
| No log | 1.5738 | 96 | 0.3812 | 0.8212 | 0.6872 | 0.6290 | 0.7573 |
|
65 |
+
| No log | 1.8361 | 112 | 0.3799 | 0.8564 | 0.6705 | 0.8286 | 0.5631 |
|
66 |
+
| No log | 2.0984 | 128 | 0.3736 | 0.8111 | 0.6725 | 0.6111 | 0.7476 |
|
67 |
+
| No log | 2.3607 | 144 | 0.3726 | 0.8564 | 0.7047 | 0.7556 | 0.6602 |
|
68 |
+
| No log | 2.6230 | 160 | 0.4651 | 0.7456 | 0.6456 | 0.5055 | 0.8932 |
|
69 |
+
| No log | 2.8852 | 176 | 0.3592 | 0.8413 | 0.7070 | 0.6786 | 0.7379 |
|
70 |
+
| No log | 3.1475 | 192 | 0.3633 | 0.8514 | 0.7035 | 0.7292 | 0.6796 |
|
71 |
+
| No log | 3.4098 | 208 | 0.4381 | 0.8086 | 0.6984 | 0.5906 | 0.8544 |
|
72 |
+
| No log | 3.6721 | 224 | 0.4114 | 0.8338 | 0.7080 | 0.6504 | 0.7767 |
|
73 |
+
| No log | 3.9344 | 240 | 0.4588 | 0.8186 | 0.7025 | 0.6115 | 0.8252 |
|
74 |
+
| No log | 4.1967 | 256 | 0.3795 | 0.8615 | 0.7291 | 0.74 | 0.7184 |
|
75 |
+
| No log | 4.4590 | 272 | 0.4418 | 0.8262 | 0.7113 | 0.625 | 0.8252 |
|
76 |
+
| No log | 4.7213 | 288 | 0.3962 | 0.8489 | 0.7170 | 0.6972 | 0.7379 |
|
77 |
+
| No log | 4.9836 | 304 | 0.4003 | 0.8589 | 0.7308 | 0.7238 | 0.7379 |
|
78 |
+
|
79 |
+
|
80 |
+
### Framework versions
|
81 |
+
|
82 |
+
- Transformers 4.41.2
|
83 |
+
- Pytorch 2.3.0+cu121
|
84 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-multilingual-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pooler_fc_size": 768,
|
21 |
+
"pooler_num_attention_heads": 12,
|
22 |
+
"pooler_num_fc_layers": 3,
|
23 |
+
"pooler_size_per_head": 128,
|
24 |
+
"pooler_type": "first_token_transform",
|
25 |
+
"position_embedding_type": "absolute",
|
26 |
+
"problem_type": "single_label_classification",
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.41.2",
|
29 |
+
"type_vocab_size": 2,
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 119547
|
32 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ca4668d4a9eed08e652f739b601eab2bb44be197163d3f1d6113fc530dce6c4
|
3 |
+
size 711443456
|
runs/Jun09_04-19-26_ebb31ef29bd8/events.out.tfevents.1717906767.ebb31ef29bd8.606.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72cf9ba1928c0e814037dd76facfe98138a77b10a7ee75a108244c8c4cbe69ed
|
3 |
+
size 14256
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65e70e519d7d286adfff885e5cd8b24494c84c517403fd1b6d75d22d1186bd3f
|
3 |
+
size 5112
|