Commit
•
cc33197
1
Parent(s):
be20873
Training in progress epoch 0
Browse files- README.md +8 -10
- checkpoint/extra_data.pickle +1 -1
- checkpoint/weights.h5 +1 -1
- config.json +1 -1
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -14,10 +14,8 @@ 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 |
-
-
|
19 |
-
- Validation Loss: 6.3627
|
20 |
-
- Validation Accuracy: 0.0277
|
21 |
- Epoch: 0
|
22 |
|
23 |
## Model description
|
@@ -37,19 +35,19 @@ More information needed
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
-
- optimizer: {'name': '
|
41 |
- training_precision: mixed_float16
|
42 |
|
43 |
### Training results
|
44 |
|
45 |
-
| Train Loss |
|
46 |
-
|
47 |
-
|
|
48 |
|
49 |
|
50 |
### Framework versions
|
51 |
|
52 |
-
- Transformers 4.
|
53 |
-
- TensorFlow 2.
|
54 |
- Datasets 2.8.0
|
55 |
- Tokenizers 0.13.2
|
|
|
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: 4.8667
|
18 |
+
- Validation Loss: 4.5766
|
|
|
|
|
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': 'WarmUp', 'config': {'initial_learning_rate': 5e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 3892, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 1000, 'power': 1.0, '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: mixed_float16
|
40 |
|
41 |
### Training results
|
42 |
|
43 |
+
| Train Loss | Validation Loss | Epoch |
|
44 |
+
|:----------:|:---------------:|:-----:|
|
45 |
+
| 4.8667 | 4.5766 | 0 |
|
46 |
|
47 |
|
48 |
### Framework versions
|
49 |
|
50 |
+
- Transformers 4.25.1
|
51 |
+
- TensorFlow 2.9.0
|
52 |
- Datasets 2.8.0
|
53 |
- Tokenizers 0.13.2
|
checkpoint/extra_data.pickle
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 995530137
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bed9e2a4f2ed868e7517c109610526f3e345ac59d12de62b8037d8631d068a7e
|
3 |
size 995530137
|
checkpoint/weights.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 497935440
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c8888721188c45722117ef0d47917c03a4f94e2b8672ffc36c0c9bf9dd19b00
|
3 |
size 497935440
|
config.json
CHANGED
@@ -32,7 +32,7 @@
|
|
32 |
"max_length": 50
|
33 |
}
|
34 |
},
|
35 |
-
"transformers_version": "4.
|
36 |
"use_cache": true,
|
37 |
"vocab_size": 50257
|
38 |
}
|
|
|
32 |
"max_length": 50
|
33 |
}
|
34 |
},
|
35 |
+
"transformers_version": "4.25.1",
|
36 |
"use_cache": true,
|
37 |
"vocab_size": 50257
|
38 |
}
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 497935440
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c8888721188c45722117ef0d47917c03a4f94e2b8672ffc36c0c9bf9dd19b00
|
3 |
size 497935440
|