Commit
•
ff35ec6
1
Parent(s):
41ee493
Model save
Browse files- README.md +71 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: distilbert-base-uncased
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
metrics:
|
| 6 |
+
- f1
|
| 7 |
+
tags:
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: distilbert-base-uncased-ICU-Readmission-classification_test1_DistilBERT
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# distilbert-base-uncased-ICU-Readmission-classification_test1_DistilBERT
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.2541
|
| 22 |
+
- F1: 0.6140
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.001
|
| 42 |
+
- train_batch_size: 8
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- num_epochs: 10
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 53 |
+
| 0.6211 | 1.0 | 125 | 0.6684 | 0.7654 |
|
| 54 |
+
| 0.6914 | 2.0 | 250 | 0.6944 | 0.4948 |
|
| 55 |
+
| 0.5586 | 3.0 | 375 | 0.6777 | 0.6774 |
|
| 56 |
+
| 0.4336 | 4.0 | 500 | 0.8128 | 0.5983 |
|
| 57 |
+
| 0.1934 | 5.0 | 625 | 0.9031 | 0.6508 |
|
| 58 |
+
| 0.4551 | 6.0 | 750 | 1.0683 | 0.6 |
|
| 59 |
+
| 0.2402 | 7.0 | 875 | 1.0870 | 0.6615 |
|
| 60 |
+
| 0.3594 | 8.0 | 1000 | 1.2305 | 0.6055 |
|
| 61 |
+
| 0.127 | 9.0 | 1125 | 1.2516 | 0.6372 |
|
| 62 |
+
| 0.0884 | 10.0 | 1250 | 1.2541 | 0.6140 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- PEFT 0.12.0
|
| 68 |
+
- Transformers 4.44.0
|
| 69 |
+
- Pytorch 2.4.0
|
| 70 |
+
- Datasets 2.21.0
|
| 71 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1481324
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24278647c8feeaca5beb072134c65c9b25ee399ec342e6bb283fd6363981cc05
|
| 3 |
size 1481324
|