Model save

README.md

@@ -0,0 +1,101 @@
+---
+base_model: openai/clip-vit-base-patch32
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: document-crop
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: validation
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9120879120879121
+---
+
+<!-- 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. -->
+
+# document-crop
+
+This model is a fine-tuned version of [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2842
+- Accuracy: 0.9121
+
+## 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: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 25
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Accuracy |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|
+| No log        | 0.9655  | 7    | 0.7309          | 0.5495   |
+| No log        | 1.9310  | 14   | 0.6289          | 0.5934   |
+| 0.6408        | 2.8966  | 21   | 0.5930          | 0.6923   |
+| 0.6408        | 4.0     | 29   | 0.8962          | 0.6154   |
+| 0.4193        | 4.9655  | 36   | 0.4717          | 0.8022   |
+| 0.4193        | 5.9310  | 43   | 0.4143          | 0.8242   |
+| 0.3622        | 6.8966  | 50   | 0.4415          | 0.8242   |
+| 0.3622        | 8.0     | 58   | 0.3617          | 0.8462   |
+| 0.2049        | 8.9655  | 65   | 0.4250          | 0.8352   |
+| 0.2049        | 9.9310  | 72   | 0.4062          | 0.8462   |
+| 0.1712        | 10.8966 | 79   | 0.4120          | 0.8242   |
+| 0.1712        | 12.0    | 87   | 0.5777          | 0.8132   |
+| 0.1291        | 12.9655 | 94   | 0.3530          | 0.8571   |
+| 0.1291        | 13.9310 | 101  | 0.3432          | 0.8571   |
+| 0.0836        | 14.8966 | 108  | 0.2558          | 0.8901   |
+| 0.0836        | 16.0    | 116  | 0.4536          | 0.8352   |
+| 0.1053        | 16.9655 | 123  | 0.4638          | 0.8462   |
+| 0.1053        | 17.9310 | 130  | 0.5922          | 0.8352   |
+| 0.0734        | 18.8966 | 137  | 0.3474          | 0.8681   |
+| 0.0734        | 20.0    | 145  | 0.5511          | 0.8462   |
+| 0.046         | 20.9655 | 152  | 0.5115          | 0.8462   |
+| 0.046         | 21.9310 | 159  | 0.3097          | 0.9011   |
+| 0.0139        | 22.8966 | 166  | 0.2511          | 0.9121   |
+| 0.0139        | 24.0    | 174  | 0.2863          | 0.9121   |
+| 0.0139        | 24.1379 | 175  | 0.2842          | 0.9121   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

runs/Jul24_10-55-21_gurame007/events.out.tfevents.1721793322.gurame007.72841.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:087ef1cea700e850936207aa0745112c323ed802bc1de29a3d4bf279a8041ece
-size 14339
+oid sha256:52ee63ee056d5e77b34485f32eaa412e440a874a50158b53984fc4e227996ad0
+size 15339