Electro98 commited on
Commit
bb4d857
1 Parent(s): b4a6193

Training in progress epoch 0

Browse files
Files changed (3) hide show
  1. README.md +7 -7
  2. config.json +0 -1
  3. tf_model.h5 +2 -2
README.md CHANGED
@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
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
@@ -36,14 +36,14 @@ More information needed
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
 
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: 1.7072
18
+ - Validation Loss: 1.4686
19
+ - Train F1: 0.5398
20
  - Epoch: 0
21
 
22
  ## Model description
 
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': 27130, '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 F1 | Epoch |
45
+ |:----------:|:---------------:|:--------:|:-----:|
46
+ | 1.7072 | 1.4686 | 0.5398 | 0 |
47
 
48
 
49
  ### Framework versions
config.json CHANGED
@@ -74,7 +74,6 @@
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,
 
74
  "n_heads": 12,
75
  "n_layers": 6,
76
  "pad_token_id": 0,
 
77
  "qa_dropout": 0.1,
78
  "seq_classif_dropout": 0.2,
79
  "sinusoidal_pos_embds": false,
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3748e31ef9b0c2003558db3d3a5ed729fb4ad87b2a2304fb7f9cb103b1e9356a
3
- size 268035016
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:140d4e43e43f0618927a2527d0fc21314a4b0dfc417ca1e3614ec8994a747101
3
+ size 268031680