Vasanthengineer4949
commited on
Commit
•
48ae0f6
1
Parent(s):
a521aa4
add model
Browse files- .gitignore +1 -0
- README.md +74 -0
- config.json +40 -0
- pytorch_model.bin +3 -0
- runs/Aug23_06-28-04_514fc84c5b16/1629700088.1643567/events.out.tfevents.1629700088.514fc84c5b16.1599.1 +3 -0
- runs/Aug23_06-28-04_514fc84c5b16/events.out.tfevents.1629700088.514fc84c5b16.1599.0 +3 -0
- runs/Aug23_06-28-04_514fc84c5b16/events.out.tfevents.1629700776.514fc84c5b16.1599.2 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- tamilmixsentiment
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
model_index:
|
10 |
+
- name: tamil-sentiment-distilbert
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Text Classification
|
14 |
+
type: text-classification
|
15 |
+
dataset:
|
16 |
+
name: tamilmixsentiment
|
17 |
+
type: tamilmixsentiment
|
18 |
+
args: default
|
19 |
+
metric:
|
20 |
+
name: Accuracy
|
21 |
+
type: accuracy
|
22 |
+
value: 0.653
|
23 |
+
---
|
24 |
+
|
25 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
26 |
+
should probably proofread and complete it, then remove this comment. -->
|
27 |
+
|
28 |
+
# tamil-sentiment-distilbert
|
29 |
+
|
30 |
+
This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the tamilmixsentiment dataset.
|
31 |
+
It achieves the following results on the evaluation set:
|
32 |
+
- Loss: 1.0230
|
33 |
+
- Accuracy: 0.653
|
34 |
+
|
35 |
+
## Model description
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Intended uses & limitations
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Training and evaluation data
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Training procedure
|
48 |
+
|
49 |
+
### Training hyperparameters
|
50 |
+
|
51 |
+
The following hyperparameters were used during training:
|
52 |
+
- learning_rate: 5e-05
|
53 |
+
- train_batch_size: 8
|
54 |
+
- eval_batch_size: 8
|
55 |
+
- seed: 42
|
56 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
57 |
+
- lr_scheduler_type: linear
|
58 |
+
- num_epochs: 3.0
|
59 |
+
|
60 |
+
### Training results
|
61 |
+
|
62 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
63 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
64 |
+
| 1.0442 | 1.0 | 250 | 0.9883 | 0.674 |
|
65 |
+
| 0.9227 | 2.0 | 500 | 0.9782 | 0.673 |
|
66 |
+
| 0.7591 | 3.0 | 750 | 1.0230 | 0.653 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.9.2
|
72 |
+
- Pytorch 1.9.0+cu102
|
73 |
+
- Datasets 1.11.0
|
74 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-cased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2",
|
15 |
+
"3": "LABEL_3",
|
16 |
+
"4": "LABEL_4"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"label2id": {
|
20 |
+
"LABEL_0": 0,
|
21 |
+
"LABEL_1": 1,
|
22 |
+
"LABEL_2": 2,
|
23 |
+
"LABEL_3": 3,
|
24 |
+
"LABEL_4": 4
|
25 |
+
},
|
26 |
+
"max_position_embeddings": 512,
|
27 |
+
"model_type": "distilbert",
|
28 |
+
"n_heads": 12,
|
29 |
+
"n_layers": 6,
|
30 |
+
"output_past": true,
|
31 |
+
"pad_token_id": 0,
|
32 |
+
"problem_type": "single_label_classification",
|
33 |
+
"qa_dropout": 0.1,
|
34 |
+
"seq_classif_dropout": 0.2,
|
35 |
+
"sinusoidal_pos_embds": false,
|
36 |
+
"tie_weights_": true,
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.9.2",
|
39 |
+
"vocab_size": 28996
|
40 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebfdbb6e28cfd3782bdbfd25bb6db62900544dfbcca9bba7ddeb9b6df2ac218c
|
3 |
+
size 263181425
|
runs/Aug23_06-28-04_514fc84c5b16/1629700088.1643567/events.out.tfevents.1629700088.514fc84c5b16.1599.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e051dd4321ff2c5cf52a4f1f58ba9349ac1734ce0dee6626b61eaa38d272dc4
|
3 |
+
size 4250
|
runs/Aug23_06-28-04_514fc84c5b16/events.out.tfevents.1629700088.514fc84c5b16.1599.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba55db019b3239cb1c14ce24998b234de1c3050aa3c8445194351e8998788d14
|
3 |
+
size 4891
|
runs/Aug23_06-28-04_514fc84c5b16/events.out.tfevents.1629700776.514fc84c5b16.1599.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52f00567038c78444f49d32231d057ebca794ce923216312886c78777ea6676f
|
3 |
+
size 363
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-cased", "tokenizer_class": "DistilBertTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:495a039cf02ebfd7143e74b105961a10df8cbd2041e895362d0961b7670733c7
|
3 |
+
size 2671
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|