JuliusAlphonso
commited on
Commit
•
2d8bb5f
1
Parent(s):
ebc8910
add model
Browse files- README.md +61 -0
- config.json +45 -0
- pytorch_model.bin +3 -0
README.md
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- null
|
5 |
+
model_index:
|
6 |
+
- name: dear-jarvis-v5
|
7 |
+
results:
|
8 |
+
- task:
|
9 |
+
name: Text Classification
|
10 |
+
type: text-classification
|
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 |
+
# dear-jarvis-v5
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.3148
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 5e-05
|
40 |
+
- train_batch_size: 32
|
41 |
+
- eval_batch_size: 8
|
42 |
+
- seed: 42
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 3
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| No log | 1.0 | 470 | 0.3106 |
|
52 |
+
| 0.3452 | 2.0 | 940 | 0.3064 |
|
53 |
+
| 0.2692 | 3.0 | 1410 | 0.3148 |
|
54 |
+
|
55 |
+
|
56 |
+
### Framework versions
|
57 |
+
|
58 |
+
- Transformers 4.7.0
|
59 |
+
- Pytorch 1.9.0+cu102
|
60 |
+
- Datasets 1.8.0
|
61 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "neutral",
|
13 |
+
"1": "anger",
|
14 |
+
"2": "anticipation",
|
15 |
+
"3": "disgust",
|
16 |
+
"4": "fear",
|
17 |
+
"5": "joy",
|
18 |
+
"6": "sadness",
|
19 |
+
"7": "surprise",
|
20 |
+
"8": "trust"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"label2id": {
|
24 |
+
"anger": "1",
|
25 |
+
"anticipation": "2",
|
26 |
+
"disgust": "3",
|
27 |
+
"fear": "4",
|
28 |
+
"joy": "5",
|
29 |
+
"neutral": "0",
|
30 |
+
"sadness": "6",
|
31 |
+
"surprise": "7",
|
32 |
+
"trust": "8"
|
33 |
+
},
|
34 |
+
"max_position_embeddings": 512,
|
35 |
+
"model_type": "distilbert",
|
36 |
+
"n_heads": 12,
|
37 |
+
"n_layers": 6,
|
38 |
+
"pad_token_id": 0,
|
39 |
+
"problem_type": "multi_label_classification",
|
40 |
+
"qa_dropout": 0.1,
|
41 |
+
"seq_classif_dropout": 0.2,
|
42 |
+
"sinusoidal_pos_embds": false,
|
43 |
+
"transformers_version": "4.7.0",
|
44 |
+
"vocab_size": 28996
|
45 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:413930be117b33ca344bc3ec89facb9f8313b90533ed970a9f1066e53de5de42
|
3 |
+
size 263193713
|