Upload TFT5ForConditionalGeneration
Browse files- README.md +8 -8
- config.json +1 -1
- generation_config.json +13 -0
- tf_model.h5 +2 -2
README.md
CHANGED
@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Train Loss: 3.
|
18 |
-
- Validation Loss: 3.
|
19 |
-
- Train Rougel: tf.Tensor(0.
|
20 |
- Epoch: 0
|
21 |
|
22 |
## Model description
|
@@ -36,19 +36,19 @@ More information needed
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
-
- optimizer: {'name': 'Adam', '
|
40 |
- training_precision: float32
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
| Train Loss | Validation Loss | Train Rougel | Epoch |
|
45 |
|:----------:|:---------------:|:----------------------------------------------:|:-----:|
|
46 |
-
| 3.
|
47 |
|
48 |
|
49 |
### Framework versions
|
50 |
|
51 |
-
- Transformers 4.
|
52 |
-
- TensorFlow 2.
|
53 |
-
- Datasets 2.
|
54 |
- Tokenizers 0.12.1
|
|
|
14 |
|
15 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 3.8679
|
18 |
+
- Validation Loss: 3.5523
|
19 |
+
- Train Rougel: tf.Tensor(0.11994212, shape=(), dtype=float32)
|
20 |
- Epoch: 0
|
21 |
|
22 |
## Model description
|
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
+
- optimizer: {'name': 'Adam', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
|
40 |
- training_precision: float32
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
| Train Loss | Validation Loss | Train Rougel | Epoch |
|
45 |
|:----------:|:---------------:|:----------------------------------------------:|:-----:|
|
46 |
+
| 3.8679 | 3.5523 | tf.Tensor(0.11994212, shape=(), dtype=float32) | 0 |
|
47 |
|
48 |
|
49 |
### Framework versions
|
50 |
|
51 |
+
- Transformers 4.26.1
|
52 |
+
- TensorFlow 2.10.1
|
53 |
+
- Datasets 2.13.1
|
54 |
- Tokenizers 0.12.1
|
config.json
CHANGED
@@ -60,7 +60,7 @@
|
|
60 |
"prefix": "translate English to Romanian: "
|
61 |
}
|
62 |
},
|
63 |
-
"transformers_version": "4.
|
64 |
"use_cache": true,
|
65 |
"vocab_size": 32128
|
66 |
}
|
|
|
60 |
"prefix": "translate English to Romanian: "
|
61 |
}
|
62 |
},
|
63 |
+
"transformers_version": "4.26.1",
|
64 |
"use_cache": true,
|
65 |
"vocab_size": 32128
|
66 |
}
|
generation_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"early_stopping": true,
|
5 |
+
"eos_token_id": 1,
|
6 |
+
"length_penalty": 2.0,
|
7 |
+
"max_length": 200,
|
8 |
+
"min_length": 30,
|
9 |
+
"no_repeat_ngram_size": 3,
|
10 |
+
"num_beams": 4,
|
11 |
+
"pad_token_id": 0,
|
12 |
+
"transformers_version": "4.26.1"
|
13 |
+
}
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e5c73b02d0ffc722ade34ff3f9abd341d9856bbc11caecb4c99d1ea9c5be19c
|
3 |
+
size 373902664
|