Gracoy commited on
Commit
27db98f
1 Parent(s): 949d4df

Upload model

Browse files
Files changed (2) hide show
  1. README.md +9 -9
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -1,4 +1,5 @@
1
  ---
 
2
  tags:
3
  - generated_from_keras_callback
4
  model-index:
@@ -11,11 +12,11 @@ probably proofread and complete it, then remove this comment. -->
11
 
12
  # ingredients_compatibility_GPT2_S
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: 0.9775
17
- - Validation Loss: 1.0329
18
- - Epoch: 2
19
 
20
  ## Model description
21
 
@@ -34,21 +35,20 @@ More information needed
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
- - optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': 0.0003, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.99, 'epsilon': 1e-07, 'amsgrad': True, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
38
  - training_precision: mixed_float16
39
 
40
  ### Training results
41
 
42
  | Train Loss | Validation Loss | Epoch |
43
  |:----------:|:---------------:|:-----:|
44
- | 1.0466 | 1.0321 | 0 |
45
- | 1.0046 | 1.0296 | 1 |
46
- | 0.9775 | 1.0329 | 2 |
47
 
48
 
49
  ### Framework versions
50
 
51
  - Transformers 4.31.0
52
  - TensorFlow 2.12.0
53
- - Datasets 2.14.2
54
  - Tokenizers 0.13.3
 
1
  ---
2
+ base_model: Gracoy/ingredients_compatibility_GPT2_S
3
  tags:
4
  - generated_from_keras_callback
5
  model-index:
 
12
 
13
  # ingredients_compatibility_GPT2_S
14
 
15
+ This model is a fine-tuned version of [Gracoy/ingredients_compatibility_GPT2_S](https://huggingface.co/Gracoy/ingredients_compatibility_GPT2_S) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.9872
18
+ - Validation Loss: 1.0135
19
+ - Epoch: 1
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 0.0003, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.99, 'epsilon': 1e-07, 'amsgrad': True, 'weight_decay_rate': 0.01}
39
  - training_precision: mixed_float16
40
 
41
  ### Training results
42
 
43
  | Train Loss | Validation Loss | Epoch |
44
  |:----------:|:---------------:|:-----:|
45
+ | 1.0214 | 1.0158 | 0 |
46
+ | 0.9872 | 1.0135 | 1 |
 
47
 
48
 
49
  ### Framework versions
50
 
51
  - Transformers 4.31.0
52
  - TensorFlow 2.12.0
53
+ - Datasets 2.14.3
54
  - Tokenizers 0.13.3
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef9cf87ded1469cb70ea860f0e2a3028d5b2f1cf7f428758e0a6f436e92aa773
3
  size 370269264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d913412712da2470b6b828fcf17c04865aedfdecb0fd4db4950c5f2005403a45
3
  size 370269264