aish31 commited on
Commit
a4ff5c4
1 Parent(s): b0f8d9e

Upload TFBartForConditionalGeneration

Browse files
Files changed (4) hide show
  1. README.md +10 -13
  2. config.json +1 -1
  3. generation_config.json +1 -1
  4. 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 [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 0.3501
19
- - Validation Loss: 0.6153
20
- - Epoch: 7
21
 
22
  ## Model description
23
 
@@ -36,26 +36,23 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 1e-05}
40
  - training_precision: float32
41
 
42
  ### Training results
43
 
44
  | Train Loss | Validation Loss | Epoch |
45
  |:----------:|:---------------:|:-----:|
46
- | 1.3410 | 0.9278 | 0 |
47
- | 0.8642 | 0.8051 | 1 |
48
- | 0.7179 | 0.6812 | 2 |
49
- | 0.6052 | 0.7129 | 3 |
50
- | 0.5071 | 0.6385 | 4 |
51
- | 0.4461 | 0.6174 | 5 |
52
- | 0.3939 | 0.6276 | 6 |
53
- | 0.3501 | 0.6153 | 7 |
54
 
55
 
56
  ### Framework versions
57
 
58
- - Transformers 4.33.1
59
  - TensorFlow 2.13.0
60
  - Datasets 2.14.5
61
  - Tokenizers 0.13.3
 
15
 
16
  This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 0.5063
19
+ - Validation Loss: 0.6842
20
+ - Epoch: 4
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.001}
40
  - training_precision: float32
41
 
42
  ### Training results
43
 
44
  | Train Loss | Validation Loss | Epoch |
45
  |:----------:|:---------------:|:-----:|
46
+ | 1.4675 | 0.9956 | 0 |
47
+ | 0.9108 | 0.8082 | 1 |
48
+ | 0.7168 | 0.7359 | 2 |
49
+ | 0.5947 | 1.1556 | 3 |
50
+ | 0.5063 | 0.6842 | 4 |
 
 
 
51
 
52
 
53
  ### Framework versions
54
 
55
+ - Transformers 4.33.2
56
  - TensorFlow 2.13.0
57
  - Datasets 2.14.5
58
  - Tokenizers 0.13.3
config.json CHANGED
@@ -67,7 +67,7 @@
67
  "num_beams": 6
68
  }
69
  },
70
- "transformers_version": "4.33.1",
71
  "use_cache": true,
72
  "vocab_size": 50265
73
  }
 
67
  "num_beams": 6
68
  }
69
  },
70
+ "transformers_version": "4.33.2",
71
  "use_cache": true,
72
  "vocab_size": 50265
73
  }
generation_config.json CHANGED
@@ -9,5 +9,5 @@
9
  "no_repeat_ngram_size": 3,
10
  "num_beams": 4,
11
  "pad_token_id": 1,
12
- "transformers_version": "4.33.1"
13
  }
 
9
  "no_repeat_ngram_size": 3,
10
  "num_beams": 4,
11
  "pad_token_id": 1,
12
+ "transformers_version": "4.33.2"
13
  }
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f3379c1b5233daa4d9a43d1682edd3c9dbf1e96cf5c6bd6644a171d9b93b1d0
3
  size 1625925412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e5f71818b4531faf0a1c52c9e4ad71b6c8f82e53c0f13654af2fca59b980212
3
  size 1625925412