update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: ec-biogpt-masked-pubmed
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# ec-biogpt-masked-pubmed
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [microsoft/biogpt](https://huggingface.co/microsoft/biogpt) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.7418
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 5e-05
|
| 37 |
+
- train_batch_size: 16
|
| 38 |
+
- eval_batch_size: 16
|
| 39 |
+
- seed: 42
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- lr_scheduler_warmup_steps: 10
|
| 43 |
+
- num_epochs: 5
|
| 44 |
+
- mixed_precision_training: Native AMP
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 50 |
+
| 0.3707 | 0.07 | 500 | 0.8468 |
|
| 51 |
+
| 0.5388 | 0.14 | 1000 | 0.7643 |
|
| 52 |
+
| 0.5857 | 0.21 | 1500 | 0.7669 |
|
| 53 |
+
| 0.5441 | 0.28 | 2000 | 0.7576 |
|
| 54 |
+
| 0.5294 | 0.36 | 2500 | 0.7570 |
|
| 55 |
+
| 0.7544 | 0.43 | 3000 | 0.7227 |
|
| 56 |
+
| 0.7075 | 0.5 | 3500 | 0.7153 |
|
| 57 |
+
| 0.7513 | 0.57 | 4000 | 0.7105 |
|
| 58 |
+
| 0.7101 | 0.64 | 4500 | 0.7059 |
|
| 59 |
+
| 0.7369 | 0.71 | 5000 | 0.7031 |
|
| 60 |
+
| 0.7477 | 0.78 | 5500 | 0.6991 |
|
| 61 |
+
| 0.6831 | 0.85 | 6000 | 0.6978 |
|
| 62 |
+
| 0.6458 | 0.93 | 6500 | 0.6940 |
|
| 63 |
+
| 0.6998 | 1.0 | 7000 | 0.6907 |
|
| 64 |
+
| 0.5901 | 1.07 | 7500 | 0.7036 |
|
| 65 |
+
| 0.633 | 1.14 | 8000 | 0.7016 |
|
| 66 |
+
| 0.6375 | 1.21 | 8500 | 0.7020 |
|
| 67 |
+
| 0.6378 | 1.28 | 9000 | 0.6988 |
|
| 68 |
+
| 0.5952 | 1.35 | 9500 | 0.6965 |
|
| 69 |
+
| 0.5714 | 1.42 | 10000 | 0.6960 |
|
| 70 |
+
| 0.5874 | 1.5 | 10500 | 0.6957 |
|
| 71 |
+
| 0.5828 | 1.57 | 11000 | 0.6917 |
|
| 72 |
+
| 0.5921 | 1.64 | 11500 | 0.6920 |
|
| 73 |
+
| 0.6086 | 1.71 | 12000 | 0.6905 |
|
| 74 |
+
| 0.5872 | 1.78 | 12500 | 0.6878 |
|
| 75 |
+
| 0.5895 | 1.85 | 13000 | 0.6883 |
|
| 76 |
+
| 0.5953 | 1.92 | 13500 | 0.6860 |
|
| 77 |
+
| 0.598 | 1.99 | 14000 | 0.6852 |
|
| 78 |
+
| 0.4805 | 2.07 | 14500 | 0.7077 |
|
| 79 |
+
| 0.4885 | 2.14 | 15000 | 0.7107 |
|
| 80 |
+
| 0.5048 | 2.21 | 15500 | 0.7083 |
|
| 81 |
+
| 0.4665 | 2.28 | 16000 | 0.7098 |
|
| 82 |
+
| 0.5057 | 2.35 | 16500 | 0.7088 |
|
| 83 |
+
| 0.4706 | 2.42 | 17000 | 0.7081 |
|
| 84 |
+
| 0.5056 | 2.49 | 17500 | 0.7076 |
|
| 85 |
+
| 0.4884 | 2.56 | 18000 | 0.7068 |
|
| 86 |
+
| 0.487 | 2.64 | 18500 | 0.7051 |
|
| 87 |
+
| 0.5327 | 2.71 | 19000 | 0.7062 |
|
| 88 |
+
| 0.4902 | 2.78 | 19500 | 0.7042 |
|
| 89 |
+
| 0.5277 | 2.85 | 20000 | 0.7021 |
|
| 90 |
+
| 0.499 | 2.92 | 20500 | 0.7024 |
|
| 91 |
+
| 0.4981 | 2.99 | 21000 | 0.7002 |
|
| 92 |
+
| 0.4174 | 3.06 | 21500 | 0.7237 |
|
| 93 |
+
| 0.4233 | 3.13 | 22000 | 0.7244 |
|
| 94 |
+
| 0.4331 | 3.21 | 22500 | 0.7265 |
|
| 95 |
+
| 0.4203 | 3.28 | 23000 | 0.7275 |
|
| 96 |
+
| 0.4265 | 3.35 | 23500 | 0.7252 |
|
| 97 |
+
| 0.4302 | 3.42 | 24000 | 0.7271 |
|
| 98 |
+
| 0.4343 | 3.49 | 24500 | 0.7244 |
|
| 99 |
+
| 0.4264 | 3.56 | 25000 | 0.7265 |
|
| 100 |
+
| 0.4565 | 3.63 | 25500 | 0.7247 |
|
| 101 |
+
| 0.4258 | 3.7 | 26000 | 0.7245 |
|
| 102 |
+
| 0.4191 | 3.78 | 26500 | 0.7246 |
|
| 103 |
+
| 0.4412 | 3.85 | 27000 | 0.7234 |
|
| 104 |
+
| 0.4604 | 3.92 | 27500 | 0.7249 |
|
| 105 |
+
| 0.4197 | 3.99 | 28000 | 0.7238 |
|
| 106 |
+
| 0.3666 | 4.06 | 28500 | 0.7413 |
|
| 107 |
+
| 0.3772 | 4.13 | 29000 | 0.7414 |
|
| 108 |
+
| 0.3628 | 4.2 | 29500 | 0.7410 |
|
| 109 |
+
| 0.3611 | 4.27 | 30000 | 0.7431 |
|
| 110 |
+
| 0.3736 | 4.35 | 30500 | 0.7414 |
|
| 111 |
+
| 0.3741 | 4.42 | 31000 | 0.7420 |
|
| 112 |
+
| 0.3661 | 4.49 | 31500 | 0.7424 |
|
| 113 |
+
| 0.3966 | 4.56 | 32000 | 0.7423 |
|
| 114 |
+
| 0.4058 | 4.63 | 32500 | 0.7423 |
|
| 115 |
+
| 0.4028 | 4.7 | 33000 | 0.7423 |
|
| 116 |
+
| 0.4028 | 4.77 | 33500 | 0.7420 |
|
| 117 |
+
| 0.3802 | 4.84 | 34000 | 0.7421 |
|
| 118 |
+
| 0.3612 | 4.92 | 34500 | 0.7418 |
|
| 119 |
+
| 0.3804 | 4.99 | 35000 | 0.7418 |
|
| 120 |
+
|
| 121 |
+
|
| 122 |
+
### Framework versions
|
| 123 |
+
|
| 124 |
+
- Transformers 4.27.3
|
| 125 |
+
- Pytorch 1.13.1+cu116
|
| 126 |
+
- Datasets 2.10.1
|
| 127 |
+
- Tokenizers 0.13.2
|