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-e4l58-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-e4l58-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: 0.7743
|
| 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: 1.2009578191195431e-08
|
| 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 |
+
| 0.4588 | 0.0921 | 500 | 1.4195 |
|
| 50 |
+
| 0.4255 | 0.1842 | 1000 | 1.3417 |
|
| 51 |
+
| 0.3724 | 0.2763 | 1500 | 1.2873 |
|
| 52 |
+
| 0.3251 | 0.3684 | 2000 | 1.2349 |
|
| 53 |
+
| 0.3308 | 0.4605 | 2500 | 1.1945 |
|
| 54 |
+
| 0.3017 | 0.5526 | 3000 | 1.1593 |
|
| 55 |
+
| 0.2962 | 0.6447 | 3500 | 1.1259 |
|
| 56 |
+
| 0.2919 | 0.7368 | 4000 | 1.0954 |
|
| 57 |
+
| 0.307 | 0.8289 | 4500 | 1.0729 |
|
| 58 |
+
| 0.2764 | 0.9210 | 5000 | 1.0524 |
|
| 59 |
+
| 0.2456 | 1.0131 | 5500 | 1.0375 |
|
| 60 |
+
| 0.2642 | 1.1052 | 6000 | 1.0233 |
|
| 61 |
+
| 0.2066 | 1.1973 | 6500 | 1.0104 |
|
| 62 |
+
| 0.2376 | 1.2894 | 7000 | 0.9984 |
|
| 63 |
+
| 0.1931 | 1.3815 | 7500 | 0.9887 |
|
| 64 |
+
| 0.2163 | 1.4736 | 8000 | 0.9767 |
|
| 65 |
+
| 0.1903 | 1.5657 | 8500 | 0.9665 |
|
| 66 |
+
| 0.2069 | 1.6578 | 9000 | 0.9572 |
|
| 67 |
+
| 0.2093 | 1.7499 | 9500 | 0.9497 |
|
| 68 |
+
| 0.2523 | 1.8420 | 10000 | 0.9420 |
|
| 69 |
+
| 0.2127 | 1.9341 | 10500 | 0.9329 |
|
| 70 |
+
| 0.1968 | 2.0262 | 11000 | 0.9270 |
|
| 71 |
+
| 0.1879 | 2.1183 | 11500 | 0.9231 |
|
| 72 |
+
| 0.1981 | 2.2104 | 12000 | 0.9184 |
|
| 73 |
+
| 0.1964 | 2.3024 | 12500 | 0.9135 |
|
| 74 |
+
| 0.1697 | 2.3945 | 13000 | 0.9100 |
|
| 75 |
+
| 0.2015 | 2.4866 | 13500 | 0.9052 |
|
| 76 |
+
| 0.1827 | 2.5787 | 14000 | 0.9026 |
|
| 77 |
+
| 0.1435 | 2.6708 | 14500 | 0.8998 |
|
| 78 |
+
| 0.1541 | 2.7629 | 15000 | 0.8963 |
|
| 79 |
+
| 0.1716 | 2.8550 | 15500 | 0.8935 |
|
| 80 |
+
| 0.2056 | 2.9471 | 16000 | 0.8905 |
|
| 81 |
+
| 0.1843 | 3.0392 | 16500 | 0.8875 |
|
| 82 |
+
| 0.1611 | 3.1313 | 17000 | 0.8858 |
|
| 83 |
+
| 0.1568 | 3.2240 | 17500 | 0.7821 |
|
| 84 |
+
| 0.1395 | 3.3161 | 18000 | 0.7794 |
|
| 85 |
+
| 0.1804 | 3.4083 | 18500 | 0.7778 |
|
| 86 |
+
| 0.1728 | 3.5004 | 19000 | 0.7769 |
|
| 87 |
+
| 0.179 | 3.5925 | 19500 | 0.7758 |
|
| 88 |
+
| 0.179 | 3.6846 | 20000 | 0.7752 |
|
| 89 |
+
| 0.1454 | 3.7767 | 20500 | 0.7747 |
|
| 90 |
+
| 0.1568 | 3.8688 | 21000 | 0.7744 |
|
| 91 |
+
| 0.1663 | 3.9609 | 21500 | 0.7743 |
|
| 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
|
runs/Aug21_23-55-57_wolf-creek/events.out.tfevents.1724306210.wolf-creek.101957.0
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 sha256:85487a8881b7700bd4ca7f193ee0a98bd60a4d9a5fba31df29387b70f2885f5e
|
| 3 |
+
size 9834
|