Upload TFBartForConditionalGeneration
Browse files- README.md +10 -13
- config.json +1 -1
- generation_config.json +1 -1
- 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.
|
19 |
-
- Validation Loss: 0.
|
20 |
-
- Epoch:
|
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-
|
40 |
- training_precision: float32
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
-
| 1.
|
47 |
-
| 0.
|
48 |
-
| 0.
|
49 |
-
| 0.
|
50 |
-
| 0.
|
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.
|
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.
|
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.
|
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:
|
3 |
size 1625925412
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e5f71818b4531faf0a1c52c9e4ad71b6c8f82e53c0f13654af2fca59b980212
|
3 |
size 1625925412
|