Commit
•
b645e2e
1
Parent(s):
cd7f6b7
add model
Browse files- README.md +111 -0
- config.json +23 -0
- tf_model.h5 +3 -0
README.md
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_keras_callback
|
| 4 |
+
model-index:
|
| 5 |
+
- name: distilgpt_new_0060
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
| 10 |
+
probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# distilgpt_new_0060
|
| 13 |
+
|
| 14 |
+
This model was trained from scratch on an unknown dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Train Loss: 1.1173
|
| 17 |
+
- Validation Loss: 1.0714
|
| 18 |
+
- Epoch: 59
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
| 38 |
+
- training_precision: float32
|
| 39 |
+
|
| 40 |
+
### Training results
|
| 41 |
+
|
| 42 |
+
| Train Loss | Validation Loss | Epoch |
|
| 43 |
+
|:----------:|:---------------:|:-----:|
|
| 44 |
+
| 3.5889 | 2.6197 | 0 |
|
| 45 |
+
| 2.4784 | 2.2040 | 1 |
|
| 46 |
+
| 2.1855 | 1.9980 | 2 |
|
| 47 |
+
| 2.0181 | 1.8643 | 3 |
|
| 48 |
+
| 1.9031 | 1.7652 | 4 |
|
| 49 |
+
| 1.8166 | 1.6924 | 5 |
|
| 50 |
+
| 1.7467 | 1.6360 | 6 |
|
| 51 |
+
| 1.6904 | 1.5843 | 7 |
|
| 52 |
+
| 1.6430 | 1.5421 | 8 |
|
| 53 |
+
| 1.6021 | 1.5059 | 9 |
|
| 54 |
+
| 1.5668 | 1.4761 | 10 |
|
| 55 |
+
| 1.5359 | 1.4481 | 11 |
|
| 56 |
+
| 1.5071 | 1.4220 | 12 |
|
| 57 |
+
| 1.4841 | 1.4020 | 13 |
|
| 58 |
+
| 1.4608 | 1.3797 | 14 |
|
| 59 |
+
| 1.4399 | 1.3595 | 15 |
|
| 60 |
+
| 1.4213 | 1.3426 | 16 |
|
| 61 |
+
| 1.4031 | 1.3266 | 17 |
|
| 62 |
+
| 1.3875 | 1.3113 | 18 |
|
| 63 |
+
| 1.3735 | 1.3024 | 19 |
|
| 64 |
+
| 1.3600 | 1.2871 | 20 |
|
| 65 |
+
| 1.3456 | 1.2753 | 21 |
|
| 66 |
+
| 1.3336 | 1.2648 | 22 |
|
| 67 |
+
| 1.3214 | 1.2539 | 23 |
|
| 68 |
+
| 1.3103 | 1.2451 | 24 |
|
| 69 |
+
| 1.3005 | 1.2335 | 25 |
|
| 70 |
+
| 1.2905 | 1.2258 | 26 |
|
| 71 |
+
| 1.2815 | 1.2179 | 27 |
|
| 72 |
+
| 1.2728 | 1.2123 | 28 |
|
| 73 |
+
| 1.2643 | 1.2029 | 29 |
|
| 74 |
+
| 1.2564 | 1.1980 | 30 |
|
| 75 |
+
| 1.2494 | 1.1877 | 31 |
|
| 76 |
+
| 1.2414 | 1.1806 | 32 |
|
| 77 |
+
| 1.2348 | 1.1788 | 33 |
|
| 78 |
+
| 1.2290 | 1.1699 | 34 |
|
| 79 |
+
| 1.2209 | 1.1654 | 35 |
|
| 80 |
+
| 1.2156 | 1.1575 | 36 |
|
| 81 |
+
| 1.2110 | 1.1537 | 37 |
|
| 82 |
+
| 1.2046 | 1.1499 | 38 |
|
| 83 |
+
| 1.1986 | 1.1436 | 39 |
|
| 84 |
+
| 1.1940 | 1.1408 | 40 |
|
| 85 |
+
| 1.1877 | 1.1356 | 41 |
|
| 86 |
+
| 1.1830 | 1.1314 | 42 |
|
| 87 |
+
| 1.1779 | 1.1278 | 43 |
|
| 88 |
+
| 1.1737 | 1.1211 | 44 |
|
| 89 |
+
| 1.1692 | 1.1192 | 45 |
|
| 90 |
+
| 1.1647 | 1.1163 | 46 |
|
| 91 |
+
| 1.1611 | 1.1107 | 47 |
|
| 92 |
+
| 1.1560 | 1.1066 | 48 |
|
| 93 |
+
| 1.1521 | 1.1060 | 49 |
|
| 94 |
+
| 1.1489 | 1.1002 | 50 |
|
| 95 |
+
| 1.1440 | 1.0960 | 51 |
|
| 96 |
+
| 1.1406 | 1.0931 | 52 |
|
| 97 |
+
| 1.1373 | 1.0897 | 53 |
|
| 98 |
+
| 1.1329 | 1.0855 | 54 |
|
| 99 |
+
| 1.1302 | 1.0842 | 55 |
|
| 100 |
+
| 1.1265 | 1.0818 | 56 |
|
| 101 |
+
| 1.1237 | 1.0784 | 57 |
|
| 102 |
+
| 1.1204 | 1.0737 | 58 |
|
| 103 |
+
| 1.1173 | 1.0714 | 59 |
|
| 104 |
+
|
| 105 |
+
|
| 106 |
+
### Framework versions
|
| 107 |
+
|
| 108 |
+
- Transformers 4.20.1
|
| 109 |
+
- TensorFlow 2.8.2
|
| 110 |
+
- Datasets 2.3.2
|
| 111 |
+
- Tokenizers 0.12.1
|
config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/content/drive/MyDrive/Colab Notebooks/oscar/trybackup_distilbert/backup_0115115",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForMaskedLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"max_position_embeddings": 512,
|
| 13 |
+
"model_type": "distilbert",
|
| 14 |
+
"n_heads": 12,
|
| 15 |
+
"n_layers": 6,
|
| 16 |
+
"pad_token_id": 0,
|
| 17 |
+
"qa_dropout": 0.1,
|
| 18 |
+
"seq_classif_dropout": 0.2,
|
| 19 |
+
"sinusoidal_pos_embds": false,
|
| 20 |
+
"tie_weights_": true,
|
| 21 |
+
"transformers_version": "4.20.1",
|
| 22 |
+
"vocab_size": 27672
|
| 23 |
+
}
|
tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5efe2d6ccebd2af4d837ff42ee4edc23904df5218a6389ac36f2e34b9e6c818b
|
| 3 |
+
size 345901880
|