sharren
/

vit-epsilon-5e-9

+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: vit-epsilon-5e-9
+  results: []
+---
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+# vit-epsilon-5e-9
+This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6199
+- Accuracy: 0.8582
+- Precision: 0.8561
+- Recall: 0.8582
+- F1: 0.8541
+## Model description
+More information needed
+## Intended uses & limitations
+More information needed
+## Training and evaluation data
+More information needed
+## Training procedure
+### Training hyperparameters
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.99) and epsilon=5e-09
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 1733
+- num_epochs: 100
+- mixed_precision_training: Native AMP
+### Training results
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 1.7673        | 1.0   | 321  | 0.9546          | 0.6890   | 0.6435    | 0.6890 | 0.6302 |
+| 1.1951        | 2.0   | 642  | 0.7244          | 0.7438   | 0.7325    | 0.7438 | 0.7199 |
+| 1.0711        | 3.0   | 963  | 0.6499          | 0.7552   | 0.7394    | 0.7552 | 0.7224 |
+| 0.9944        | 4.0   | 1284 | 0.5907          | 0.7590   | 0.7962    | 0.7590 | 0.7683 |
+| 0.9231        | 5.0   | 1605 | 0.6988          | 0.7084   | 0.8054    | 0.7084 | 0.7306 |
+| 0.9889        | 6.0   | 1926 | 0.5912          | 0.7746   | 0.7919    | 0.7746 | 0.7808 |
+| 0.8818        | 7.0   | 2247 | 0.6374          | 0.7569   | 0.8001    | 0.7569 | 0.7697 |
+| 0.7973        | 8.0   | 2568 | 0.6658          | 0.7580   | 0.7925    | 0.7580 | 0.7684 |
+| 0.7525        | 9.0   | 2889 | 0.5220          | 0.8044   | 0.8124    | 0.8044 | 0.8068 |
+| 0.6938        | 10.0  | 3210 | 0.5634          | 0.7899   | 0.8335    | 0.7899 | 0.7980 |
+| 0.6354        | 11.0  | 3531 | 0.4961          | 0.8252   | 0.8358    | 0.8252 | 0.8286 |
+| 0.5602        | 12.0  | 3852 | 0.5486          | 0.8141   | 0.8276    | 0.8141 | 0.8185 |
+| 0.44          | 13.0  | 4173 | 0.6554          | 0.8141   | 0.8442    | 0.8141 | 0.8155 |
+| 0.4704        | 14.0  | 4494 | 0.5704          | 0.8235   | 0.8431    | 0.8235 | 0.8287 |
+| 0.4275        | 15.0  | 4815 | 0.5563          | 0.8141   | 0.8459    | 0.8141 | 0.8230 |
+| 0.3511        | 16.0  | 5136 | 0.5933          | 0.8072   | 0.8402    | 0.8072 | 0.8166 |
+| 0.2853        | 17.0  | 5457 | 0.5246          | 0.8436   | 0.8542    | 0.8436 | 0.8470 |
+| 0.2691        | 18.0  | 5778 | 0.5257          | 0.8509   | 0.8551    | 0.8509 | 0.8519 |
+| 0.2134        | 19.0  | 6099 | 0.6391          | 0.8332   | 0.8553    | 0.8332 | 0.8404 |
+| 0.224         | 20.0  | 6420 | 0.6297          | 0.8488   | 0.8537    | 0.8488 | 0.8497 |
+| 0.1843        | 21.0  | 6741 | 0.6199          | 0.8582   | 0.8561    | 0.8582 | 0.8541 |
+### Framework versions
+- Transformers 4.40.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0403181e2c6a51e10231f826c63366eb3b73a930770c7c0a20423b893def7b24
 size 343239356

 version https://git-lfs.github.com/spec/v1
+oid sha256:732c8a91ce8550bcec325778a8a7bc808742053acd8dc56970e64dc84e904145
 size 343239356