laxsvips commited on
Commit
c05de60
1 Parent(s): 18ffd71

Training in progress epoch 0

Browse files
Files changed (7) hide show
  1. README.md +55 -0
  2. config.json +40 -0
  3. special_tokens_map.json +7 -0
  4. tf_model.h5 +3 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +17 -0
  7. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_keras_callback
5
+ model-index:
6
+ - name: laxsvips/minilm-finetuned-emotion
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
+ # laxsvips/minilm-finetuned-emotion
14
+
15
+ This model is a fine-tuned version of [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.7443
18
+ - Train Accuracy: 0.6832
19
+ - Validation Loss: 0.9091
20
+ - Validation Accuracy: 0.6820
21
+ - Epoch: 0
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 250, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
41
+ - training_precision: float32
42
+
43
+ ### Training results
44
+
45
+ | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
46
+ |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
47
+ | 0.7443 | 0.6832 | 0.9091 | 0.6820 | 0 |
48
+
49
+
50
+ ### Framework versions
51
+
52
+ - Transformers 4.26.1
53
+ - TensorFlow 2.11.0
54
+ - Datasets 2.9.0
55
+ - Tokenizers 0.13.2
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/MiniLM-L12-H384-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 384,
11
+ "id2label": {
12
+ "0": "sadness",
13
+ "1": "joy",
14
+ "2": "love",
15
+ "3": "anger",
16
+ "4": "fear",
17
+ "5": "surprise"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 1536,
21
+ "label2id": {
22
+ "anger": 3,
23
+ "fear": 4,
24
+ "joy": 1,
25
+ "love": 2,
26
+ "sadness": 0,
27
+ "surprise": 5
28
+ },
29
+ "layer_norm_eps": 1e-12,
30
+ "max_position_embeddings": 512,
31
+ "model_type": "bert",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "pad_token_id": 0,
35
+ "position_embedding_type": "absolute",
36
+ "transformers_version": "4.26.1",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 30522
40
+ }
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 sha256:12e4d16197c8c81c27c9e8bfcfc87f72eaf1bfa072fbcdff2b9ae370858084ee
3
+ size 133754512
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "name_or_path": "microsoft/MiniLM-L12-H384-uncased",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "return_tensors": "tf",
11
+ "sep_token": "[SEP]",
12
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--microsoft--MiniLM-L12-H384-uncased/snapshots/44acabbec0ef496f6dbc93adadea57f376b7c0ec/special_tokens_map.json",
13
+ "strip_accents": null,
14
+ "tokenize_chinese_chars": true,
15
+ "tokenizer_class": "BertTokenizer",
16
+ "unk_token": "[UNK]"
17
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff