vinh120203
commited on
Commit
•
529a3b4
1
Parent(s):
1cccdeb
rwBK-sentiment-analysis-heBert
Browse files- README.md +101 -0
- config.json +38 -0
- events.out.tfevents.1722224799.6585b62f5721.175.0 +3 -0
- events.out.tfevents.1722228638.6585b62f5721.175.1 +3 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: avichr/heBERT_sentiment_analysis
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
- f1
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
model-index:
|
11 |
+
- name: heBERT_sentiment_analysis
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# heBERT_sentiment_analysis
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [avichr/heBERT_sentiment_analysis](https://huggingface.co/avichr/heBERT_sentiment_analysis) on an unknown dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.4046
|
23 |
+
- Accuracy: 0.8563
|
24 |
+
- F1: 0.8554
|
25 |
+
- Precision: 0.8551
|
26 |
+
- Recall: 0.8567
|
27 |
+
|
28 |
+
## Model description
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Intended uses & limitations
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training and evaluation data
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training procedure
|
41 |
+
|
42 |
+
### Training hyperparameters
|
43 |
+
|
44 |
+
The following hyperparameters were used during training:
|
45 |
+
- learning_rate: 5e-05
|
46 |
+
- train_batch_size: 32
|
47 |
+
- eval_batch_size: 32
|
48 |
+
- seed: 42
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- lr_scheduler_warmup_steps: 100
|
52 |
+
- num_epochs: 3
|
53 |
+
- mixed_precision_training: Native AMP
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
58 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
59 |
+
| 2.5497 | 0.0820 | 50 | 0.7625 | 0.7076 | 0.6676 | 0.7357 | 0.7090 |
|
60 |
+
| 0.6821 | 0.1639 | 100 | 0.5465 | 0.7898 | 0.7818 | 0.7916 | 0.7905 |
|
61 |
+
| 0.5475 | 0.2459 | 150 | 0.4972 | 0.8155 | 0.8074 | 0.8198 | 0.8161 |
|
62 |
+
| 0.5397 | 0.3279 | 200 | 0.4992 | 0.8213 | 0.8168 | 0.8210 | 0.8217 |
|
63 |
+
| 0.5328 | 0.4098 | 250 | 0.4999 | 0.8101 | 0.7988 | 0.8213 | 0.8109 |
|
64 |
+
| 0.5052 | 0.4918 | 300 | 0.4983 | 0.8108 | 0.8131 | 0.8191 | 0.8107 |
|
65 |
+
| 0.4627 | 0.5738 | 350 | 0.4597 | 0.8291 | 0.8290 | 0.8317 | 0.8291 |
|
66 |
+
| 0.4565 | 0.6557 | 400 | 0.4328 | 0.8362 | 0.8332 | 0.8356 | 0.8366 |
|
67 |
+
| 0.4187 | 0.7377 | 450 | 0.4416 | 0.8402 | 0.8361 | 0.8413 | 0.8406 |
|
68 |
+
| 0.4611 | 0.8197 | 500 | 0.4655 | 0.8308 | 0.8306 | 0.8304 | 0.8311 |
|
69 |
+
| 0.436 | 0.9016 | 550 | 0.4246 | 0.8335 | 0.8343 | 0.8350 | 0.8338 |
|
70 |
+
| 0.4118 | 0.9836 | 600 | 0.4179 | 0.8429 | 0.8418 | 0.8425 | 0.8431 |
|
71 |
+
| 0.4019 | 1.0656 | 650 | 0.4041 | 0.8436 | 0.8426 | 0.8426 | 0.8438 |
|
72 |
+
| 0.419 | 1.1475 | 700 | 0.4238 | 0.8418 | 0.8405 | 0.8403 | 0.8422 |
|
73 |
+
| 0.3656 | 1.2295 | 750 | 0.4046 | 0.8485 | 0.8486 | 0.8486 | 0.8487 |
|
74 |
+
| 0.3559 | 1.3115 | 800 | 0.4032 | 0.8414 | 0.8415 | 0.8414 | 0.8417 |
|
75 |
+
| 0.3529 | 1.3934 | 850 | 0.4229 | 0.8489 | 0.8452 | 0.8498 | 0.8494 |
|
76 |
+
| 0.3247 | 1.4754 | 900 | 0.4198 | 0.8491 | 0.8463 | 0.8491 | 0.8494 |
|
77 |
+
| 0.3435 | 1.5574 | 950 | 0.4254 | 0.8395 | 0.8413 | 0.8468 | 0.8394 |
|
78 |
+
| 0.3519 | 1.6393 | 1000 | 0.4414 | 0.8447 | 0.8427 | 0.8472 | 0.8448 |
|
79 |
+
| 0.3763 | 1.7213 | 1050 | 0.4097 | 0.8534 | 0.8521 | 0.8534 | 0.8536 |
|
80 |
+
| 0.3739 | 1.8033 | 1100 | 0.3926 | 0.8523 | 0.8487 | 0.8540 | 0.8527 |
|
81 |
+
| 0.3807 | 1.8852 | 1150 | 0.3896 | 0.8528 | 0.8515 | 0.8514 | 0.8531 |
|
82 |
+
| 0.3655 | 1.9672 | 1200 | 0.3897 | 0.8526 | 0.8504 | 0.8535 | 0.8528 |
|
83 |
+
| 0.3125 | 2.0492 | 1250 | 0.4199 | 0.8539 | 0.8540 | 0.8545 | 0.8540 |
|
84 |
+
| 0.2851 | 2.1311 | 1300 | 0.4107 | 0.8550 | 0.8541 | 0.8554 | 0.8551 |
|
85 |
+
| 0.2907 | 2.2131 | 1350 | 0.4093 | 0.8527 | 0.8532 | 0.8539 | 0.8528 |
|
86 |
+
| 0.2619 | 2.2951 | 1400 | 0.4085 | 0.8585 | 0.8572 | 0.8573 | 0.8588 |
|
87 |
+
| 0.2619 | 2.3770 | 1450 | 0.4166 | 0.8490 | 0.8501 | 0.8523 | 0.8491 |
|
88 |
+
| 0.2863 | 2.4590 | 1500 | 0.4046 | 0.8548 | 0.8538 | 0.8536 | 0.8550 |
|
89 |
+
| 0.2604 | 2.5410 | 1550 | 0.4143 | 0.8550 | 0.8544 | 0.8541 | 0.8552 |
|
90 |
+
| 0.2778 | 2.6230 | 1600 | 0.4021 | 0.8532 | 0.8540 | 0.8551 | 0.8533 |
|
91 |
+
| 0.2579 | 2.7049 | 1650 | 0.4071 | 0.8505 | 0.8518 | 0.8542 | 0.8505 |
|
92 |
+
| 0.2734 | 2.7869 | 1700 | 0.4069 | 0.8565 | 0.8566 | 0.8567 | 0.8567 |
|
93 |
+
| 0.2873 | 2.8689 | 1750 | 0.4006 | 0.8567 | 0.8563 | 0.8563 | 0.8569 |
|
94 |
+
| 0.2568 | 2.9508 | 1800 | 0.3998 | 0.8567 | 0.8568 | 0.8570 | 0.8569 |
|
95 |
+
|
96 |
+
|
97 |
+
### Framework versions
|
98 |
+
|
99 |
+
- Transformers 4.42.4
|
100 |
+
- Pytorch 2.3.1+cu121
|
101 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "avichr/heBERT_sentiment_analysis",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "Positive",
|
14 |
+
"1": "Neutral",
|
15 |
+
"2": "Negative"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"Negative": 2,
|
21 |
+
"Neutral": 1,
|
22 |
+
"Positive": 0
|
23 |
+
},
|
24 |
+
"layer_norm_eps": 1e-12,
|
25 |
+
"max_position_embeddings": 512,
|
26 |
+
"model_type": "bert",
|
27 |
+
"num_attention_heads": 12,
|
28 |
+
"num_hidden_layers": 12,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"position_embedding_type": "absolute",
|
31 |
+
"problem_type": "single_label_classification",
|
32 |
+
"torch_dtype": "float32",
|
33 |
+
"total_flos": 6997313242916978688,
|
34 |
+
"transformers_version": "4.42.4",
|
35 |
+
"type_vocab_size": 2,
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 30522
|
38 |
+
}
|
events.out.tfevents.1722224799.6585b62f5721.175.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd6bd3292f1c8e2984662fa5f5d9947fd469bd2c8aaec3f0790c82dc9416e4dc
|
3 |
+
size 29961
|
events.out.tfevents.1722228638.6585b62f5721.175.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb50728eaa9a759d96dc463c240c21b488d5a6af0ec6999f5260314d4e32db09
|
3 |
+
size 1504
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c05ec8e673e9bd5485117d8a2469b6d15f896b128d7147a0b7ce3888ef760f60
|
3 |
+
size 437961724
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aaeb20cc6f53740239effdf841ca72664de73a271ea774e8d07adf1c53a86813
|
3 |
+
size 5048
|