shirsh10mall commited on
Commit
5b9a600
1 Parent(s): 7d76223

Training in progress epoch 0

Browse files
Files changed (4) hide show
  1. README.md +5 -5
  2. config.json +1 -1
  3. generation_config.json +1 -1
  4. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,8 +14,8 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-hi](https://huggingface.co/Helsinki-NLP/opus-mt-en-hi) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 4.5330
18
- - Validation Loss: 4.7299
19
  - Epoch: 0
20
 
21
  ## Model description
@@ -35,19 +35,19 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 2, '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, 'weight_decay_rate': 0.01}
39
  - training_precision: float32
40
 
41
  ### Training results
42
 
43
  | Train Loss | Validation Loss | Epoch |
44
  |:----------:|:---------------:|:-----:|
45
- | 4.5330 | 4.7299 | 0 |
46
 
47
 
48
  ### Framework versions
49
 
50
- - Transformers 4.30.1
51
  - TensorFlow 2.12.0
52
  - Datasets 2.1.0
53
  - Tokenizers 0.13.3
 
14
 
15
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-hi](https://huggingface.co/Helsinki-NLP/opus-mt-en-hi) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 4.5587
18
+ - Validation Loss: 3.9141
19
  - Epoch: 0
20
 
21
  ## Model description
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 1, '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, 'weight_decay_rate': 0.01}
39
  - training_precision: float32
40
 
41
  ### Training results
42
 
43
  | Train Loss | Validation Loss | Epoch |
44
  |:----------:|:---------------:|:-----:|
45
+ | 4.5587 | 3.9141 | 0 |
46
 
47
 
48
  ### Framework versions
49
 
50
+ - Transformers 4.30.2
51
  - TensorFlow 2.12.0
52
  - Datasets 2.1.0
53
  - Tokenizers 0.13.3
config.json CHANGED
@@ -54,7 +54,7 @@
54
  "scale_embedding": true,
55
  "share_encoder_decoder_embeddings": true,
56
  "static_position_embeddings": true,
57
- "transformers_version": "4.30.1",
58
  "use_cache": true,
59
  "vocab_size": 61950
60
  }
 
54
  "scale_embedding": true,
55
  "share_encoder_decoder_embeddings": true,
56
  "static_position_embeddings": true,
57
+ "transformers_version": "4.30.2",
58
  "use_cache": true,
59
  "vocab_size": 61950
60
  }
generation_config.json CHANGED
@@ -12,5 +12,5 @@
12
  "max_length": 512,
13
  "num_beams": 4,
14
  "pad_token_id": 61949,
15
- "transformers_version": "4.30.1"
16
  }
 
12
  "max_length": 512,
13
  "num_beams": 4,
14
  "pad_token_id": 61949,
15
+ "transformers_version": "4.30.2"
16
  }
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4139ba24ee6c76e9b4c8045c8aa6dfd4b2503da88c84e0199a52335555ceb36a
3
  size 306059944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db61872933ca2f93a285aa14a874d9ceec464d9e883f03ddb71dd7485e97164c
3
  size 306059944