Electro98 commited on
Commit
b4a6193
1 Parent(s): f113b00

Training in progress epoch 0

Browse files
Files changed (7) hide show
  1. README.md +54 -0
  2. config.json +84 -0
  3. special_tokens_map.json +7 -0
  4. tf_model.h5 +3 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +13 -0
  7. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_keras_callback
5
+ model-index:
6
+ - name: Electro98/my_awesome_model
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
11
+ probably proofread and complete it, then remove this comment. -->
12
+
13
+ # Electro98/my_awesome_model
14
+
15
+ This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Train Loss: 1.7195
18
+ - Validation Loss: 1.4305
19
+ - Train Accuracy: 0.5707
20
+ - Epoch: 0
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
+ - optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 13565, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
40
+ - training_precision: float32
41
+
42
+ ### Training results
43
+
44
+ | Train Loss | Validation Loss | Train Accuracy | Epoch |
45
+ |:----------:|:---------------:|:--------------:|:-----:|
46
+ | 1.7195 | 1.4305 | 0.5707 | 0 |
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.27.4
52
+ - TensorFlow 2.10.0
53
+ - Datasets 2.18.0
54
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/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": "admiration",
13
+ "1": "amusement",
14
+ "2": "anger",
15
+ "3": "annoyance",
16
+ "4": "approval",
17
+ "5": "caring",
18
+ "6": "confusion",
19
+ "7": "curiosity",
20
+ "8": "desire",
21
+ "9": "disappointment",
22
+ "10": "disapproval",
23
+ "11": "disgust",
24
+ "12": "embarrassment",
25
+ "13": "excitement",
26
+ "14": "fear",
27
+ "15": "gratitude",
28
+ "16": "grief",
29
+ "17": "joy",
30
+ "18": "love",
31
+ "19": "nervousness",
32
+ "20": "optimism",
33
+ "21": "pride",
34
+ "22": "realization",
35
+ "23": "relief",
36
+ "24": "remorse",
37
+ "25": "sadness",
38
+ "26": "surprise",
39
+ "27": "neutral"
40
+ },
41
+ "initializer_range": 0.02,
42
+ "label2id": {
43
+ "admiration": 0,
44
+ "amusement": 1,
45
+ "anger": 2,
46
+ "annoyance": 3,
47
+ "approval": 4,
48
+ "caring": 5,
49
+ "confusion": 6,
50
+ "curiosity": 7,
51
+ "desire": 8,
52
+ "disappointment": 9,
53
+ "disapproval": 10,
54
+ "disgust": 11,
55
+ "embarrassment": 12,
56
+ "excitement": 13,
57
+ "fear": 14,
58
+ "gratitude": 15,
59
+ "grief": 16,
60
+ "joy": 17,
61
+ "love": 18,
62
+ "nervousness": 19,
63
+ "neutral": 27,
64
+ "optimism": 20,
65
+ "pride": 21,
66
+ "realization": 22,
67
+ "relief": 23,
68
+ "remorse": 24,
69
+ "sadness": 25,
70
+ "surprise": 26
71
+ },
72
+ "max_position_embeddings": 512,
73
+ "model_type": "distilbert",
74
+ "n_heads": 12,
75
+ "n_layers": 6,
76
+ "pad_token_id": 0,
77
+ "problem_type": "multi_label_classification",
78
+ "qa_dropout": 0.1,
79
+ "seq_classif_dropout": 0.2,
80
+ "sinusoidal_pos_embds": false,
81
+ "tie_weights_": true,
82
+ "transformers_version": "4.27.4",
83
+ "vocab_size": 30522
84
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3748e31ef9b0c2003558db3d3a5ed729fb4ad87b2a2304fb7f9cb103b1e9356a
3
+ size 268035016
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": true,
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "special_tokens_map_file": null,
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "DistilBertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff