s-man2099 commited on
Commit
5c927ec
1 Parent(s): b8d19f4

Training in progress epoch 7

Browse files
Files changed (2) hide show
  1. README.md +4 -3
  2. tf_model.h5 +1 -1
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 [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 16.2823
19
  - Validation Loss: 11.7026
20
- - Epoch: 6
21
 
22
  ## Model description
23
 
@@ -36,7 +36,7 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - optimizer: {'name': 'Adafactor', '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': 5.999999e-12, 'beta_2_decay': -0.8, 'epsilon_1': 1e-30, 'epsilon_2': 0.001, 'clip_threshold': 1.0, 'relative_step': True}
40
  - training_precision: mixed_float16
41
 
42
  ### Training results
@@ -50,6 +50,7 @@ The following hyperparameters were used during training:
50
  | 15.9325 | 11.7026 | 4 |
51
  | 16.2546 | 11.7026 | 5 |
52
  | 16.2823 | 11.7026 | 6 |
 
53
 
54
 
55
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 16.1010
19
  - Validation Loss: 11.7026
20
+ - Epoch: 7
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - optimizer: {'name': 'Adafactor', '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': 5.999999e-13, 'beta_2_decay': -0.8, 'epsilon_1': 1e-30, 'epsilon_2': 0.001, 'clip_threshold': 1.0, 'relative_step': True}
40
  - training_precision: mixed_float16
41
 
42
  ### Training results
 
50
  | 15.9325 | 11.7026 | 4 |
51
  | 16.2546 | 11.7026 | 5 |
52
  | 16.2823 | 11.7026 | 6 |
53
+ | 16.1010 | 11.7026 | 7 |
54
 
55
 
56
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bee73f696187fafc8cb2ba8839f4a52a27d9c074b242a60ae87cb3e552c45916
3
  size 2225560376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c25edb1adf2a2cf7216e800c90ccf07d156a339bbadeca4aa86663d42354179c
3
  size 2225560376