borough-oblast commited on
Commit
142752d
·
1 Parent(s): cb4f192

Training in progress epoch 0

Browse files
Files changed (2) hide show
  1. README.md +4 -4
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -13,8 +13,8 @@ probably proofread and complete it, then remove this comment. -->
13
 
14
  This model was trained from scratch on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
- - Train Loss: nan
17
- - Validation Loss: nan
18
  - Epoch: 0
19
 
20
  ## Model description
@@ -34,14 +34,14 @@ More information needed
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
- - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 204512, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
38
  - training_precision: float32
39
 
40
  ### Training results
41
 
42
  | Train Loss | Validation Loss | Epoch |
43
  |:----------:|:---------------:|:-----:|
44
- | nan | nan | 0 |
45
 
46
 
47
  ### Framework versions
 
13
 
14
  This model was trained from scratch on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Train Loss: 1.6754
17
+ - Validation Loss: 2.6110
18
  - Epoch: 0
19
 
20
  ## Model description
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 248327, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
38
  - training_precision: float32
39
 
40
  ### Training results
41
 
42
  | Train Loss | Validation Loss | Epoch |
43
  |:----------:|:---------------:|:-----:|
44
+ | 1.6754 | 2.6110 | 0 |
45
 
46
 
47
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae739bdee0f635510b5b6639fb75159a3f932a2f7f4a7fed002644b92993a0b7
3
  size 910749348
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88d7d635f17205338afe0c31fc1ebab540d8e9c45726ead21690eabfcf826d00
3
  size 910749348