LexFerrinson commited on
Commit
f99bef1
·
1 Parent(s): 30e30c6

Training in progress epoch 0

Browse files
Files changed (3) hide show
  1. README.md +11 -13
  2. config.json +1 -1
  3. tf_model.h5 +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: FirulAI/FirstModel
4
  tags:
5
  - generated_from_keras_callback
6
  model-index:
@@ -13,15 +13,15 @@ probably proofread and complete it, then remove this comment. -->
13
 
14
  # LexFerrinson/FirulaiModel
15
 
16
- This model is a fine-tuned version of [FirulAI/FirstModel](https://huggingface.co/FirulAI/FirstModel) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 0.7569
19
- - Validation Loss: 0.7565
20
- - Train Precision: 0.0
21
- - Train Recall: 0.0
22
- - Train F1: 0.0
23
- - Train Accuracy: 0.9082
24
- - Epoch: 2
25
 
26
  ## Model description
27
 
@@ -40,16 +40,14 @@ More information needed
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
- - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 3, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
44
  - training_precision: float32
45
 
46
  ### Training results
47
 
48
  | Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
49
  |:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
50
- | 0.7652 | 0.7565 | 0.0 | 0.0 | 0.0 | 0.9082 | 0 |
51
- | 0.7588 | 0.7565 | 0.0 | 0.0 | 0.0 | 0.9082 | 1 |
52
- | 0.7569 | 0.7565 | 0.0 | 0.0 | 0.0 | 0.9082 | 2 |
53
 
54
 
55
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: distilbert-base-uncased
4
  tags:
5
  - generated_from_keras_callback
6
  model-index:
 
13
 
14
  # LexFerrinson/FirulaiModel
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: 0.9805
19
+ - Validation Loss: 0.8370
20
+ - Train Precision: 0.2727
21
+ - Train Recall: 0.1034
22
+ - Train F1: 0.15
23
+ - Train Accuracy: 0.8924
24
+ - Epoch: 0
25
 
26
  ## Model description
27
 
 
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 6, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
44
  - training_precision: float32
45
 
46
  ### Training results
47
 
48
  | Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
49
  |:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
50
+ | 0.9805 | 0.8370 | 0.2727 | 0.1034 | 0.15 | 0.8924 | 0 |
 
 
51
 
52
 
53
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "FirulAI/FirstModel",
3
  "activation": "gelu",
4
  "architectures": [
5
  "DistilBertForTokenClassification"
 
1
  {
2
+ "_name_or_path": "distilbert-base-uncased",
3
  "activation": "gelu",
4
  "architectures": [
5
  "DistilBertForTokenClassification"
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5151199966e83f1458779685692032be6228f2705956afefbedc294b2971f4c
3
  size 265587984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75e9143704850f0ea4cd609bb8a54346365b9ee6d8aa80846b53987bcfabcb03
3
  size 265587984