atigilef commited on
Commit
d812840
1 Parent(s): b20e421

Training in progress epoch 0

Browse files
Files changed (3) hide show
  1. README.md +6 -8
  2. config.json +4 -12
  3. tf_model.h5 +2 -2
README.md CHANGED
@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 0.0995
19
- - Validation Loss: 0.1463
20
- - Train Accuracy: 0.93
21
- - Epoch: 2
22
 
23
  ## Model description
24
 
@@ -37,16 +37,14 @@ More information needed
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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 5000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
41
  - training_precision: float32
42
 
43
  ### Training results
44
 
45
  | Train Loss | Validation Loss | Train Accuracy | Epoch |
46
  |:----------:|:---------------:|:--------------:|:-----:|
47
- | 0.4766 | 0.1981 | 0.922 | 0 |
48
- | 0.1461 | 0.1705 | 0.9285 | 1 |
49
- | 0.0995 | 0.1463 | 0.93 | 2 |
50
 
51
 
52
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 0.2233
19
+ - Validation Loss: 0.1877
20
+ - Train Accuracy: 0.9274
21
+ - Epoch: 0
22
 
23
  ## Model description
24
 
 
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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 7810, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
41
  - training_precision: float32
42
 
43
  ### Training results
44
 
45
  | Train Loss | Validation Loss | Train Accuracy | Epoch |
46
  |:----------:|:---------------:|:--------------:|:-----:|
47
+ | 0.2233 | 0.1877 | 0.9274 | 0 |
 
 
48
 
49
 
50
  ### Framework versions
config.json CHANGED
@@ -9,21 +9,13 @@
9
  "dropout": 0.1,
10
  "hidden_dim": 3072,
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
  "label2id": {
21
- "ANGER": 3,
22
- "FEAR ": 4,
23
- "JOY": 1,
24
- "LOVE": 2,
25
- "SADNESS": 0,
26
- "SURPRISE ": 5
27
  },
28
  "max_position_embeddings": 512,
29
  "model_type": "distilbert",
 
9
  "dropout": 0.1,
10
  "hidden_dim": 3072,
11
  "id2label": {
12
+ "0": "NEGATIVE",
13
+ "1": "POSITIVE"
 
 
 
 
14
  },
15
  "initializer_range": 0.02,
16
  "label2id": {
17
+ "NEGATIVE": 0,
18
+ "POSITIVE": 1
 
 
 
 
19
  },
20
  "max_position_embeddings": 512,
21
  "model_type": "distilbert",
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e0349a591901782b710694bfe3b34c43706e64a75bd7bdec26f72e68299f319
3
- size 267964096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:843b921ec48fa734684144289ef491853792170acacc29faa638ebbd8fb46172
3
+ size 267951808