Upload README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,151 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_keras_callback
|
| 5 |
+
model-index:
|
| 6 |
+
- name: hsohn3/mayo-timebert-visit-uncased-wordlevel-block512-batch4-ep100
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
| 11 |
+
probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# hsohn3/mayo-timebert-visit-uncased-wordlevel-block512-batch4-ep100
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Train Loss: 0.8536
|
| 18 |
+
- Epoch: 99
|
| 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 | Epoch |
|
| 43 |
+
|:----------:|:-----:|
|
| 44 |
+
| 3.9508 | 0 |
|
| 45 |
+
| 3.4063 | 1 |
|
| 46 |
+
| 3.3682 | 2 |
|
| 47 |
+
| 3.3468 | 3 |
|
| 48 |
+
| 3.3330 | 4 |
|
| 49 |
+
| 3.3308 | 5 |
|
| 50 |
+
| 3.3225 | 6 |
|
| 51 |
+
| 3.3106 | 7 |
|
| 52 |
+
| 3.2518 | 8 |
|
| 53 |
+
| 3.1859 | 9 |
|
| 54 |
+
| 3.1373 | 10 |
|
| 55 |
+
| 3.0923 | 11 |
|
| 56 |
+
| 3.0390 | 12 |
|
| 57 |
+
| 2.9560 | 13 |
|
| 58 |
+
| 2.8605 | 14 |
|
| 59 |
+
| 2.7564 | 15 |
|
| 60 |
+
| 2.4969 | 16 |
|
| 61 |
+
| 2.2044 | 17 |
|
| 62 |
+
| 1.9566 | 18 |
|
| 63 |
+
| 1.7686 | 19 |
|
| 64 |
+
| 1.5995 | 20 |
|
| 65 |
+
| 1.4932 | 21 |
|
| 66 |
+
| 1.4100 | 22 |
|
| 67 |
+
| 1.3538 | 23 |
|
| 68 |
+
| 1.2973 | 24 |
|
| 69 |
+
| 1.2610 | 25 |
|
| 70 |
+
| 1.2160 | 26 |
|
| 71 |
+
| 1.1916 | 27 |
|
| 72 |
+
| 1.1607 | 28 |
|
| 73 |
+
| 1.1468 | 29 |
|
| 74 |
+
| 1.1262 | 30 |
|
| 75 |
+
| 1.1123 | 31 |
|
| 76 |
+
| 1.0942 | 32 |
|
| 77 |
+
| 1.0816 | 33 |
|
| 78 |
+
| 1.0717 | 34 |
|
| 79 |
+
| 1.0575 | 35 |
|
| 80 |
+
| 1.0503 | 36 |
|
| 81 |
+
| 1.0411 | 37 |
|
| 82 |
+
| 1.0293 | 38 |
|
| 83 |
+
| 1.0229 | 39 |
|
| 84 |
+
| 1.0139 | 40 |
|
| 85 |
+
| 1.0081 | 41 |
|
| 86 |
+
| 1.0028 | 42 |
|
| 87 |
+
| 0.9967 | 43 |
|
| 88 |
+
| 0.9906 | 44 |
|
| 89 |
+
| 0.9834 | 45 |
|
| 90 |
+
| 0.9782 | 46 |
|
| 91 |
+
| 0.9766 | 47 |
|
| 92 |
+
| 0.9676 | 48 |
|
| 93 |
+
| 0.9618 | 49 |
|
| 94 |
+
| 0.9611 | 50 |
|
| 95 |
+
| 0.9553 | 51 |
|
| 96 |
+
| 0.9504 | 52 |
|
| 97 |
+
| 0.9483 | 53 |
|
| 98 |
+
| 0.9404 | 54 |
|
| 99 |
+
| 0.9423 | 55 |
|
| 100 |
+
| 0.9361 | 56 |
|
| 101 |
+
| 0.9327 | 57 |
|
| 102 |
+
| 0.9327 | 58 |
|
| 103 |
+
| 0.9263 | 59 |
|
| 104 |
+
| 0.9275 | 60 |
|
| 105 |
+
| 0.9218 | 61 |
|
| 106 |
+
| 0.9202 | 62 |
|
| 107 |
+
| 0.9158 | 63 |
|
| 108 |
+
| 0.9152 | 64 |
|
| 109 |
+
| 0.9091 | 65 |
|
| 110 |
+
| 0.9104 | 66 |
|
| 111 |
+
| 0.9094 | 67 |
|
| 112 |
+
| 0.9087 | 68 |
|
| 113 |
+
| 0.9034 | 69 |
|
| 114 |
+
| 0.9063 | 70 |
|
| 115 |
+
| 0.8984 | 71 |
|
| 116 |
+
| 0.8966 | 72 |
|
| 117 |
+
| 0.8953 | 73 |
|
| 118 |
+
| 0.8910 | 74 |
|
| 119 |
+
| 0.8913 | 75 |
|
| 120 |
+
| 0.8887 | 76 |
|
| 121 |
+
| 0.8868 | 77 |
|
| 122 |
+
| 0.8868 | 78 |
|
| 123 |
+
| 0.8815 | 79 |
|
| 124 |
+
| 0.8821 | 80 |
|
| 125 |
+
| 0.8791 | 81 |
|
| 126 |
+
| 0.8752 | 82 |
|
| 127 |
+
| 0.8731 | 83 |
|
| 128 |
+
| 0.8779 | 84 |
|
| 129 |
+
| 0.8727 | 85 |
|
| 130 |
+
| 0.8702 | 86 |
|
| 131 |
+
| 0.8712 | 87 |
|
| 132 |
+
| 0.8689 | 88 |
|
| 133 |
+
| 0.8646 | 89 |
|
| 134 |
+
| 0.8644 | 90 |
|
| 135 |
+
| 0.8608 | 91 |
|
| 136 |
+
| 0.8643 | 92 |
|
| 137 |
+
| 0.8602 | 93 |
|
| 138 |
+
| 0.8605 | 94 |
|
| 139 |
+
| 0.8568 | 95 |
|
| 140 |
+
| 0.8567 | 96 |
|
| 141 |
+
| 0.8557 | 97 |
|
| 142 |
+
| 0.8543 | 98 |
|
| 143 |
+
| 0.8536 | 99 |
|
| 144 |
+
|
| 145 |
+
|
| 146 |
+
### Framework versions
|
| 147 |
+
|
| 148 |
+
- Transformers 4.20.1
|
| 149 |
+
- TensorFlow 2.8.2
|
| 150 |
+
- Datasets 2.3.2
|
| 151 |
+
- Tokenizers 0.12.1
|