hamzasidat
commited on
Commit
•
3819b3e
1
Parent(s):
182a17b
Hamzas_assignment1_Distil2
Browse files
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- emotion
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: DistilBertResults2
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Text Classification
|
15 |
+
type: text-classification
|
16 |
+
dataset:
|
17 |
+
name: emotion
|
18 |
+
type: emotion
|
19 |
+
config: split
|
20 |
+
split: validation
|
21 |
+
args: split
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.94
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# DistilBertResults2
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.1381
|
36 |
+
- Accuracy: 0.94
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 3e-05
|
56 |
+
- train_batch_size: 32
|
57 |
+
- eval_batch_size: 32
|
58 |
+
- seed: 42
|
59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
+
- lr_scheduler_type: linear
|
61 |
+
- num_epochs: 2
|
62 |
+
|
63 |
+
### Training results
|
64 |
+
|
65 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
66 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
67 |
+
| 0.5165 | 1.0 | 500 | 0.1820 | 0.9325 |
|
68 |
+
| 0.1463 | 2.0 | 1000 | 0.1381 | 0.94 |
|
69 |
+
|
70 |
+
|
71 |
+
### Framework versions
|
72 |
+
|
73 |
+
- Transformers 4.38.2
|
74 |
+
- Pytorch 2.1.0+cu121
|
75 |
+
- Datasets 2.18.0
|
76 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
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 |
+
"5": "LABEL_5"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"label2id": {
|
21 |
+
"LABEL_0": 0,
|
22 |
+
"LABEL_1": 1,
|
23 |
+
"LABEL_2": 2,
|
24 |
+
"LABEL_3": 3,
|
25 |
+
"LABEL_4": 4,
|
26 |
+
"LABEL_5": 5
|
27 |
+
},
|
28 |
+
"max_position_embeddings": 512,
|
29 |
+
"model_type": "distilbert",
|
30 |
+
"n_heads": 12,
|
31 |
+
"n_layers": 6,
|
32 |
+
"pad_token_id": 0,
|
33 |
+
"problem_type": "single_label_classification",
|
34 |
+
"qa_dropout": 0.1,
|
35 |
+
"seq_classif_dropout": 0.2,
|
36 |
+
"sinusoidal_pos_embds": false,
|
37 |
+
"tie_weights_": true,
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.38.2",
|
40 |
+
"vocab_size": 30522
|
41 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d358d2357e8078505a20931c02d0dbb069dfb53bc149d5eae193192083adf3b2
|
3 |
+
size 267844872
|
runs/Mar10_17-34-33_b4d9bf49ff45/events.out.tfevents.1710092109.b4d9bf49ff45.285.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:120f8e742b1f0d7d26f4b559d02f15cd8fcf0c8fa1afc725533dec54e777ad01
|
3 |
+
size 6971
|
runs/Mar10_17-34-33_b4d9bf49ff45/events.out.tfevents.1710094086.b4d9bf49ff45.285.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d6bb1eaf3ccf3d806aafad2024dcdfd7d7f6b4260f420b1892b7aaa5bdebda3
|
3 |
+
size 1057
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b90e741aad5ff170f18ae0b2df8b0bed3e58ffb8b087c5a438c1de39174f423
|
3 |
+
size 4920
|