End of training
Browse files- README.md +78 -0
- generation_config.json +7 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: luqh/ClinicalT5-base
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: medical_jargons_simplifierT5
|
| 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 |
+
# medical_jargons_simplifierT5
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [luqh/ClinicalT5-base](https://huggingface.co/luqh/ClinicalT5-base) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.4734
|
| 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: 2e-05
|
| 37 |
+
- train_batch_size: 4
|
| 38 |
+
- eval_batch_size: 4
|
| 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: 50
|
| 43 |
+
- num_epochs: 5
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
| 49 |
+
| 3.3369 | 0.2198 | 500 | 0.5700 |
|
| 50 |
+
| 0.601 | 0.4396 | 1000 | 0.5279 |
|
| 51 |
+
| 0.572 | 0.6593 | 1500 | 0.5137 |
|
| 52 |
+
| 0.5556 | 0.8791 | 2000 | 0.5051 |
|
| 53 |
+
| 0.5132 | 1.0989 | 2500 | 0.4991 |
|
| 54 |
+
| 0.5406 | 1.3187 | 3000 | 0.4941 |
|
| 55 |
+
| 0.513 | 1.5385 | 3500 | 0.4909 |
|
| 56 |
+
| 0.5328 | 1.7582 | 4000 | 0.4880 |
|
| 57 |
+
| 0.5304 | 1.9780 | 4500 | 0.4846 |
|
| 58 |
+
| 0.5215 | 2.1978 | 5000 | 0.4825 |
|
| 59 |
+
| 0.5296 | 2.4176 | 5500 | 0.4811 |
|
| 60 |
+
| 0.5143 | 2.6374 | 6000 | 0.4799 |
|
| 61 |
+
| 0.4768 | 2.8571 | 6500 | 0.4780 |
|
| 62 |
+
| 0.513 | 3.0769 | 7000 | 0.4775 |
|
| 63 |
+
| 0.4933 | 3.2967 | 7500 | 0.4761 |
|
| 64 |
+
| 0.4891 | 3.5165 | 8000 | 0.4761 |
|
| 65 |
+
| 0.5022 | 3.7363 | 8500 | 0.4749 |
|
| 66 |
+
| 0.523 | 3.9560 | 9000 | 0.4743 |
|
| 67 |
+
| 0.5233 | 4.1758 | 9500 | 0.4742 |
|
| 68 |
+
| 0.5004 | 4.3956 | 10000 | 0.4738 |
|
| 69 |
+
| 0.4817 | 4.6154 | 10500 | 0.4733 |
|
| 70 |
+
| 0.4848 | 4.8352 | 11000 | 0.4734 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.41.2
|
| 76 |
+
- Pytorch 2.1.2
|
| 77 |
+
- Datasets 2.19.2
|
| 78 |
+
- Tokenizers 0.19.1
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.41.2"
|
| 7 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 891644712
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:459a0633a02deee44277f3b7d215816196f129df5d8b6c894e0ec5f77e8e52fb
|
| 3 |
size 891644712
|