Kirkos27/ModelFor_yelp_review_full
Browse files- README.md +85 -0
- config.json +41 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google-bert/bert-base-cased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: results
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# results
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.0462
|
21 |
+
- Accuracy: 0.565
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 5e-05
|
41 |
+
- train_batch_size: 4
|
42 |
+
- eval_batch_size: 2
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- lr_scheduler_warmup_steps: 15
|
47 |
+
- num_epochs: 3
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
53 |
+
| 1.6966 | 0.12 | 30 | 1.6482 | 0.205 |
|
54 |
+
| 1.6111 | 0.24 | 60 | 1.5500 | 0.312 |
|
55 |
+
| 1.5634 | 0.36 | 90 | 1.4253 | 0.391 |
|
56 |
+
| 1.4389 | 0.48 | 120 | 1.2866 | 0.429 |
|
57 |
+
| 1.3507 | 0.6 | 150 | 1.2292 | 0.466 |
|
58 |
+
| 1.3072 | 0.72 | 180 | 1.2251 | 0.435 |
|
59 |
+
| 1.2346 | 0.84 | 210 | 1.3498 | 0.412 |
|
60 |
+
| 1.3884 | 0.96 | 240 | 1.1693 | 0.515 |
|
61 |
+
| 1.0748 | 1.08 | 270 | 1.2255 | 0.474 |
|
62 |
+
| 1.02 | 1.2 | 300 | 1.2691 | 0.475 |
|
63 |
+
| 1.0354 | 1.32 | 330 | 1.1937 | 0.48 |
|
64 |
+
| 1.0622 | 1.44 | 360 | 1.1304 | 0.512 |
|
65 |
+
| 1.0289 | 1.56 | 390 | 1.2823 | 0.465 |
|
66 |
+
| 1.1433 | 1.6800 | 420 | 1.0603 | 0.527 |
|
67 |
+
| 1.0125 | 1.8 | 450 | 1.0753 | 0.522 |
|
68 |
+
| 0.8716 | 1.92 | 480 | 1.0901 | 0.532 |
|
69 |
+
| 0.8761 | 2.04 | 510 | 1.0462 | 0.565 |
|
70 |
+
| 0.6857 | 2.16 | 540 | 1.0626 | 0.555 |
|
71 |
+
| 0.7674 | 2.2800 | 570 | 1.0799 | 0.545 |
|
72 |
+
| 0.6676 | 2.4 | 600 | 1.0843 | 0.546 |
|
73 |
+
| 0.6254 | 2.52 | 630 | 1.1148 | 0.551 |
|
74 |
+
| 0.6813 | 2.64 | 660 | 1.1227 | 0.553 |
|
75 |
+
| 0.7043 | 2.76 | 690 | 1.1267 | 0.558 |
|
76 |
+
| 0.4643 | 2.88 | 720 | 1.1227 | 0.551 |
|
77 |
+
| 0.6665 | 3.0 | 750 | 1.1222 | 0.557 |
|
78 |
+
|
79 |
+
|
80 |
+
### Framework versions
|
81 |
+
|
82 |
+
- Transformers 4.42.3
|
83 |
+
- Pytorch 2.3.0+cu121
|
84 |
+
- Datasets 2.20.0
|
85 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-cased",
|
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": "LABEL_0",
|
14 |
+
"1": "LABEL_1",
|
15 |
+
"2": "LABEL_2",
|
16 |
+
"3": "LABEL_3",
|
17 |
+
"4": "LABEL_4"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"LABEL_0": 0,
|
23 |
+
"LABEL_1": 1,
|
24 |
+
"LABEL_2": 2,
|
25 |
+
"LABEL_3": 3,
|
26 |
+
"LABEL_4": 4
|
27 |
+
},
|
28 |
+
"layer_norm_eps": 1e-12,
|
29 |
+
"max_position_embeddings": 512,
|
30 |
+
"model_type": "bert",
|
31 |
+
"num_attention_heads": 12,
|
32 |
+
"num_hidden_layers": 12,
|
33 |
+
"pad_token_id": 0,
|
34 |
+
"position_embedding_type": "absolute",
|
35 |
+
"problem_type": "single_label_classification",
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.42.3",
|
38 |
+
"type_vocab_size": 2,
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 28996
|
41 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:809f5973df6f3ada0305672b6f8985a63ee51f9603880a359843ef1f8cb3e8b4
|
3 |
+
size 433279996
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e159087fa074b84f9e73295d041495135e3f4dcb9c6737ae412d3f87f1bdf1bf
|
3 |
+
size 5048
|