Commit
•
aeb6ca9
1
Parent(s):
360bea0
MohamedAhmedAE/Chest-X-Ray-Roco-Clip
Browse files- README.md +70 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: clip_roberta
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- imagefolder
|
| 7 |
+
model-index:
|
| 8 |
+
- name: Chest-X-Ray-Roco-Clip
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# Chest-X-Ray-Roco-Clip
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [clip_roberta](https://huggingface.co/clip_roberta) on the imagefolder dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.3863
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-05
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 4
|
| 41 |
+
- seed: 2
|
| 42 |
+
- gradient_accumulation_steps: 2
|
| 43 |
+
- total_train_batch_size: 8
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_steps: 5
|
| 47 |
+
- num_epochs: 5
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
+
| 1.3868 | 0.4619 | 100 | 1.3863 |
|
| 54 |
+
| 1.3867 | 0.9238 | 200 | 1.3863 |
|
| 55 |
+
| 1.3862 | 1.3857 | 300 | 1.3863 |
|
| 56 |
+
| 1.3872 | 1.8476 | 400 | 1.3863 |
|
| 57 |
+
| 1.3869 | 2.3095 | 500 | 1.3863 |
|
| 58 |
+
| 1.3861 | 2.7714 | 600 | 1.3863 |
|
| 59 |
+
| 1.3862 | 3.2333 | 700 | 1.3863 |
|
| 60 |
+
| 1.3863 | 3.6952 | 800 | 1.3863 |
|
| 61 |
+
| 1.3865 | 4.1570 | 900 | 1.3863 |
|
| 62 |
+
| 1.3864 | 4.6189 | 1000 | 1.3863 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 4.41.2
|
| 68 |
+
- Pytorch 2.1.2
|
| 69 |
+
- Datasets 2.19.2
|
| 70 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1716360444
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:019098aa7f1b866038f581bfe0b63e57484e982097ef89dd5830f661a4eb71f8
|
| 3 |
size 1716360444
|