Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: openai/clip-vit-large-patch14-336
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: clip-finetuned-csu-p14-336-e4l57-l
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# clip-finetuned-csu-p14-336-e4l57-l
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [openai/clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.4956
|
| 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 |
+
- learning_rate: 5e-07
|
| 38 |
+
- train_batch_size: 128
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 4.0
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
| 49 |
+
| 0.271 | 0.0921 | 500 | 1.0693 |
|
| 50 |
+
| 0.2493 | 0.1842 | 1000 | 0.9427 |
|
| 51 |
+
| 0.2348 | 0.2763 | 1500 | 0.8727 |
|
| 52 |
+
| 0.1552 | 0.3685 | 2000 | 0.8326 |
|
| 53 |
+
| 0.1753 | 0.4606 | 2500 | 0.7550 |
|
| 54 |
+
| 0.1659 | 0.5527 | 3000 | 0.7192 |
|
| 55 |
+
| 0.105 | 0.6448 | 3500 | 0.7118 |
|
| 56 |
+
| 0.1336 | 0.7369 | 4000 | 0.6953 |
|
| 57 |
+
| 0.1154 | 0.8290 | 4500 | 0.6745 |
|
| 58 |
+
| 0.108 | 0.9211 | 5000 | 0.6560 |
|
| 59 |
+
| 0.1106 | 1.0133 | 5500 | 0.6367 |
|
| 60 |
+
| 0.0591 | 1.1054 | 6000 | 0.6259 |
|
| 61 |
+
| 0.0745 | 1.1975 | 6500 | 0.6210 |
|
| 62 |
+
| 0.0502 | 1.2896 | 7000 | 0.6133 |
|
| 63 |
+
| 0.079 | 1.3817 | 7500 | 0.6007 |
|
| 64 |
+
| 0.0776 | 1.4738 | 8000 | 0.5866 |
|
| 65 |
+
| 0.0492 | 1.5660 | 8500 | 0.5679 |
|
| 66 |
+
| 0.0794 | 1.6581 | 9000 | 0.5762 |
|
| 67 |
+
| 0.0677 | 1.7502 | 9500 | 0.5566 |
|
| 68 |
+
| 0.0566 | 1.8423 | 10000 | 0.5482 |
|
| 69 |
+
| 0.0828 | 1.9344 | 10500 | 0.5500 |
|
| 70 |
+
| 0.0573 | 2.0265 | 11000 | 0.5342 |
|
| 71 |
+
| 0.0401 | 2.1186 | 11500 | 0.5351 |
|
| 72 |
+
| 0.0152 | 2.2108 | 12000 | 0.5349 |
|
| 73 |
+
| 0.0638 | 2.3029 | 12500 | 0.5318 |
|
| 74 |
+
| 0.0488 | 2.3950 | 13000 | 0.5306 |
|
| 75 |
+
| 0.0456 | 2.4871 | 13500 | 0.5211 |
|
| 76 |
+
| 0.0264 | 2.5792 | 14000 | 0.5194 |
|
| 77 |
+
| 0.0381 | 2.6713 | 14500 | 0.5206 |
|
| 78 |
+
| 0.0413 | 2.7634 | 15000 | 0.5168 |
|
| 79 |
+
| 0.0392 | 2.8556 | 15500 | 0.5149 |
|
| 80 |
+
| 0.0352 | 2.9477 | 16000 | 0.5112 |
|
| 81 |
+
| 0.0467 | 3.0398 | 16500 | 0.5098 |
|
| 82 |
+
| 0.0366 | 3.1319 | 17000 | 0.5089 |
|
| 83 |
+
| 0.0454 | 3.2240 | 17500 | 0.5104 |
|
| 84 |
+
| 0.0209 | 3.3161 | 18000 | 0.5071 |
|
| 85 |
+
| 0.0636 | 3.4083 | 18500 | 0.5045 |
|
| 86 |
+
| 0.0159 | 3.5004 | 19000 | 0.5019 |
|
| 87 |
+
| 0.0303 | 3.5925 | 19500 | 0.4985 |
|
| 88 |
+
| 0.0353 | 3.6846 | 20000 | 0.4975 |
|
| 89 |
+
| 0.0261 | 3.7767 | 20500 | 0.4962 |
|
| 90 |
+
| 0.0291 | 3.8688 | 21000 | 0.4956 |
|
| 91 |
+
| 0.0338 | 3.9609 | 21500 | 0.4956 |
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
### Framework versions
|
| 95 |
+
|
| 96 |
+
- Transformers 4.45.0.dev0
|
| 97 |
+
- Pytorch 1.12.1
|
| 98 |
+
- Datasets 2.21.0
|
| 99 |
+
- 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 1711848436
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea50fac774db3c9cb31abb6664787287909cb07e28db1e469d90f49d2c7441b6
|
| 3 |
size 1711848436
|
runs/Aug23_05-29-26_winter-park/events.out.tfevents.1724412588.winter-park.827525.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f7fc86e672e5138a7b4dd14438e58e034f0eecebacabf8e8e904d947e7fec6f
|
| 3 |
+
size 56218
|