Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: openai/clip-vit-large-patch14
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: sail-clip
|
| 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 |
+
# sail-clip
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [openai/clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 2.0815
|
| 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-05
|
| 38 |
+
- train_batch_size: 64
|
| 39 |
+
- eval_batch_size: 64
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 1
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 49 |
+
| 4.8985 | 0.0552 | 10 | 4.0903 |
|
| 50 |
+
| 4.1607 | 0.1105 | 20 | 3.9977 |
|
| 51 |
+
| 3.9999 | 0.1657 | 30 | 3.8481 |
|
| 52 |
+
| 3.7439 | 0.2210 | 40 | 3.6745 |
|
| 53 |
+
| 3.6873 | 0.2762 | 50 | 3.5240 |
|
| 54 |
+
| 3.4241 | 0.3315 | 60 | 3.2912 |
|
| 55 |
+
| 3.2521 | 0.3867 | 70 | 3.1707 |
|
| 56 |
+
| 3.0498 | 0.4420 | 80 | 2.9794 |
|
| 57 |
+
| 2.9275 | 0.4972 | 90 | 2.8728 |
|
| 58 |
+
| 2.8409 | 0.5525 | 100 | 2.6969 |
|
| 59 |
+
| 2.6954 | 0.6077 | 110 | 2.6175 |
|
| 60 |
+
| 2.5344 | 0.6630 | 120 | 2.5060 |
|
| 61 |
+
| 2.5042 | 0.7182 | 130 | 2.4477 |
|
| 62 |
+
| 2.2965 | 0.7735 | 140 | 2.3057 |
|
| 63 |
+
| 2.3179 | 0.8287 | 150 | 2.2107 |
|
| 64 |
+
| 2.2797 | 0.8840 | 160 | 2.1689 |
|
| 65 |
+
| 2.0838 | 0.9392 | 170 | 2.1016 |
|
| 66 |
+
| 1.9926 | 0.9945 | 180 | 2.0815 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- Transformers 4.49.0
|
| 72 |
+
- Pytorch 2.5.1+cu118
|
| 73 |
+
- Datasets 3.2.0
|
| 74 |
+
- Tokenizers 0.21.0
|