Upload model
Browse files- README.md +8 -9
- config.json +1 -11
- generation_config.json +1 -1
- 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 [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Train Loss:
|
18 |
-
- Validation Loss:
|
19 |
-
- Epoch:
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -35,20 +35,19 @@ More information needed
|
|
35 |
### Training hyperparameters
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
-
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-
|
39 |
- training_precision: float32
|
40 |
|
41 |
### Training results
|
42 |
|
43 |
| Train Loss | Validation Loss | Epoch |
|
44 |
|:----------:|:---------------:|:-----:|
|
45 |
-
|
|
46 |
-
| 8.2488 | 8.1350 | 1 |
|
47 |
|
48 |
|
49 |
### Framework versions
|
50 |
|
51 |
-
- Transformers 4.
|
52 |
-
- TensorFlow 2.
|
53 |
-
- Datasets 2.
|
54 |
- Tokenizers 0.13.3
|
|
|
14 |
|
15 |
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 7.3780
|
18 |
+
- Validation Loss: 6.6626
|
19 |
+
- Epoch: 0
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
35 |
### Training hyperparameters
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
39 |
- training_precision: float32
|
40 |
|
41 |
### Training results
|
42 |
|
43 |
| Train Loss | Validation Loss | Epoch |
|
44 |
|:----------:|:---------------:|:-----:|
|
45 |
+
| 7.3780 | 6.6626 | 0 |
|
|
|
46 |
|
47 |
|
48 |
### Framework versions
|
49 |
|
50 |
+
- Transformers 4.28.1
|
51 |
+
- TensorFlow 2.11.0
|
52 |
+
- Datasets 2.1.0
|
53 |
- Tokenizers 0.13.3
|
config.json
CHANGED
@@ -8,17 +8,7 @@
|
|
8 |
"bos_token_id": 1,
|
9 |
"embd_pdrop": 0.1,
|
10 |
"eos_token_id": 2,
|
11 |
-
"id2label": {
|
12 |
-
"0": "NEUTRAL",
|
13 |
-
"1": "POSITIVE",
|
14 |
-
"2": "NEGATIVE"
|
15 |
-
},
|
16 |
"initializer_range": 0.02,
|
17 |
-
"label2id": {
|
18 |
-
"NEGATIVE": 2,
|
19 |
-
"NEUTRAL": 0,
|
20 |
-
"POSITIVE": 1
|
21 |
-
},
|
22 |
"layer_norm_epsilon": 1e-05,
|
23 |
"model_type": "gpt2",
|
24 |
"n_ctx": 1024,
|
@@ -43,7 +33,7 @@
|
|
43 |
"max_length": 50
|
44 |
}
|
45 |
},
|
46 |
-
"transformers_version": "4.
|
47 |
"use_cache": true,
|
48 |
"vocab_size": 50000
|
49 |
}
|
|
|
8 |
"bos_token_id": 1,
|
9 |
"embd_pdrop": 0.1,
|
10 |
"eos_token_id": 2,
|
|
|
|
|
|
|
|
|
|
|
11 |
"initializer_range": 0.02,
|
|
|
|
|
|
|
|
|
|
|
12 |
"layer_norm_epsilon": 1e-05,
|
13 |
"model_type": "gpt2",
|
14 |
"n_ctx": 1024,
|
|
|
33 |
"max_length": 50
|
34 |
}
|
35 |
},
|
36 |
+
"transformers_version": "4.28.1",
|
37 |
"use_cache": true,
|
38 |
"vocab_size": 50000
|
39 |
}
|
generation_config.json
CHANGED
@@ -3,5 +3,5 @@
|
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
"pad_token_id": 3,
|
6 |
-
"transformers_version": "4.
|
7 |
}
|
|
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
"pad_token_id": 3,
|
6 |
+
"transformers_version": "4.28.1"
|
7 |
}
|
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 sha256:96802e0cd6207b4c929d2d1832dbf7d52d700bb60230aa29bc0a44c3949f4e72
|
3 |
+
size 650749592
|