BasharAlZamel
commited on
Commit
•
4335bb6
1
Parent(s):
7cd12f5
Training in progress epoch 0
Browse files- README.md +6 -10
- config.json +5 -5
- tf_model.h5 +2 -2
README.md
CHANGED
@@ -15,9 +15,9 @@ 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.
|
19 |
-
- Validation Loss: 0.
|
20 |
-
- Epoch:
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -36,23 +36,19 @@ More information needed
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
-
- 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': False, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps':
|
40 |
- training_precision: float32
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
-
| 0.
|
47 |
-
| 0.0221 | 0.0245 | 1 |
|
48 |
-
| 0.0122 | 0.0168 | 2 |
|
49 |
-
| 0.0053 | 0.0166 | 3 |
|
50 |
-
| 0.0027 | 0.0167 | 4 |
|
51 |
|
52 |
|
53 |
### Framework versions
|
54 |
|
55 |
-
- Transformers 4.
|
56 |
- TensorFlow 2.16.2
|
57 |
- Datasets 2.20.0
|
58 |
- Tokenizers 0.19.1
|
|
|
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: 0.2034
|
19 |
+
- Validation Loss: 0.0864
|
20 |
+
- Epoch: 0
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
+
- 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': False, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1410, '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}
|
40 |
- training_precision: float32
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
+
| 0.2034 | 0.0864 | 0 |
|
|
|
|
|
|
|
|
|
47 |
|
48 |
|
49 |
### Framework versions
|
50 |
|
51 |
+
- Transformers 4.44.0
|
52 |
- TensorFlow 2.16.2
|
53 |
- Datasets 2.20.0
|
54 |
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -9,13 +9,13 @@
|
|
9 |
"dropout": 0.1,
|
10 |
"hidden_dim": 3072,
|
11 |
"id2label": {
|
12 |
-
"0": "
|
13 |
-
"1": "
|
14 |
},
|
15 |
"initializer_range": 0.02,
|
16 |
"label2id": {
|
17 |
-
"NEGATIVE":
|
18 |
-
"POSITIVE":
|
19 |
},
|
20 |
"max_position_embeddings": 512,
|
21 |
"model_type": "distilbert",
|
@@ -26,6 +26,6 @@
|
|
26 |
"seq_classif_dropout": 0.2,
|
27 |
"sinusoidal_pos_embds": false,
|
28 |
"tie_weights_": true,
|
29 |
-
"transformers_version": "4.
|
30 |
"vocab_size": 30522
|
31 |
}
|
|
|
9 |
"dropout": 0.1,
|
10 |
"hidden_dim": 3072,
|
11 |
"id2label": {
|
12 |
+
"0": "POSITIVE",
|
13 |
+
"1": "NEGATIVE"
|
14 |
},
|
15 |
"initializer_range": 0.02,
|
16 |
"label2id": {
|
17 |
+
"NEGATIVE": 1,
|
18 |
+
"POSITIVE": 0
|
19 |
},
|
20 |
"max_position_embeddings": 512,
|
21 |
"model_type": "distilbert",
|
|
|
26 |
"seq_classif_dropout": 0.2,
|
27 |
"sinusoidal_pos_embds": false,
|
28 |
"tie_weights_": true,
|
29 |
+
"transformers_version": "4.44.0",
|
30 |
"vocab_size": 30522
|
31 |
}
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ca9d2f5d87bed2f9ea6517ae6eddbbd4424c4f8c7734d0bf8f8c76e761a9b50
|
3 |
+
size 267951808
|