ShaunThayil
commited on
Commit
•
e2d1bc0
1
Parent(s):
8b162c3
End of training
Browse files- README.md +84 -0
- config.json +27 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: bert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
model-index:
|
12 |
+
- name: training-5
|
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 |
+
# training-5
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.0341
|
24 |
+
- Accuracy: 0.9952
|
25 |
+
- Precision: 0.9982
|
26 |
+
- Recall: 0.9841
|
27 |
+
- F1: 0.9911
|
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: 2e-05
|
47 |
+
- train_batch_size: 8
|
48 |
+
- eval_batch_size: 8
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 5
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
58 |
+
| No log | 0.25 | 151 | 0.0468 | 0.9923 | 1.0 | 0.9717 | 0.9856 |
|
59 |
+
| No log | 0.5 | 302 | 0.0497 | 0.9908 | 0.9840 | 0.9823 | 0.9832 |
|
60 |
+
| No log | 0.75 | 453 | 0.0571 | 0.9918 | 1.0 | 0.9699 | 0.9847 |
|
61 |
+
| No log | 1.0 | 604 | 0.0319 | 0.9961 | 1.0 | 0.9858 | 0.9929 |
|
62 |
+
| 0.0471 | 1.25 | 755 | 0.0353 | 0.9952 | 0.9982 | 0.9841 | 0.9911 |
|
63 |
+
| 0.0471 | 1.5 | 906 | 0.0346 | 0.9942 | 0.9929 | 0.9858 | 0.9893 |
|
64 |
+
| 0.0471 | 1.75 | 1057 | 0.0678 | 0.9899 | 0.9772 | 0.9858 | 0.9815 |
|
65 |
+
| 0.0471 | 2.0 | 1208 | 0.0380 | 0.9952 | 1.0 | 0.9823 | 0.9911 |
|
66 |
+
| 0.0156 | 2.25 | 1359 | 0.0362 | 0.9952 | 1.0 | 0.9823 | 0.9911 |
|
67 |
+
| 0.0156 | 2.5 | 1510 | 0.0388 | 0.9942 | 0.9946 | 0.9841 | 0.9893 |
|
68 |
+
| 0.0156 | 2.75 | 1661 | 0.0418 | 0.9952 | 1.0 | 0.9823 | 0.9911 |
|
69 |
+
| 0.0156 | 3.0 | 1812 | 0.0333 | 0.9952 | 0.9982 | 0.9841 | 0.9911 |
|
70 |
+
| 0.0121 | 3.24 | 1963 | 0.0326 | 0.9952 | 0.9982 | 0.9841 | 0.9911 |
|
71 |
+
| 0.0121 | 3.49 | 2114 | 0.0309 | 0.9957 | 0.9982 | 0.9858 | 0.9920 |
|
72 |
+
| 0.0121 | 3.74 | 2265 | 0.0311 | 0.9952 | 0.9982 | 0.9841 | 0.9911 |
|
73 |
+
| 0.0121 | 3.99 | 2416 | 0.0344 | 0.9952 | 0.9982 | 0.9841 | 0.9911 |
|
74 |
+
| 0.0084 | 4.24 | 2567 | 0.0334 | 0.9952 | 0.9982 | 0.9841 | 0.9911 |
|
75 |
+
| 0.0084 | 4.49 | 2718 | 0.0327 | 0.9952 | 0.9982 | 0.9841 | 0.9911 |
|
76 |
+
| 0.0084 | 4.74 | 2869 | 0.0336 | 0.9952 | 0.9982 | 0.9841 | 0.9911 |
|
77 |
+
| 0.0084 | 4.99 | 3020 | 0.0341 | 0.9952 | 0.9982 | 0.9841 | 0.9911 |
|
78 |
+
|
79 |
+
|
80 |
+
### Framework versions
|
81 |
+
|
82 |
+
- Transformers 4.33.1
|
83 |
+
- Pytorch 2.2.0.dev20230913+cu121
|
84 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
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 |
+
"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 |
+
"position_embedding_type": "absolute",
|
21 |
+
"problem_type": "single_label_classification",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.33.1",
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 30522
|
27 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7471141c23621529798afc2e9b74f73b611e2632862a7e6cf43d9601613db1a
|
3 |
+
size 438003950
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9035ff1380872a13468a6ad5d396c18d8b3f2fc6ccc477b51a400bc64b64ccf8
|
3 |
+
size 4472
|