Model save

README.md

@@ -0,0 +1,84 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: vit-lr-cosine-restarts
+  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-lr-cosine-restarts
+
+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: 0.8289
+- Accuracy: 0.8405
+- Precision: 0.8428
+- Recall: 0.8405
+- F1: 0.8367
+
+## 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=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine_with_restarts
+- num_epochs: 100
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.5734        | 0.31  | 100  | 0.6008          | 0.7885   | 0.7631    | 0.7885 | 0.7655 |
+| 0.5602        | 0.62  | 200  | 0.7843          | 0.7542   | 0.7425    | 0.7542 | 0.7004 |
+| 0.7117        | 0.93  | 300  | 0.6222          | 0.7660   | 0.8158    | 0.7660 | 0.7754 |
+| 0.4445        | 1.25  | 400  | 0.5481          | 0.7923   | 0.8181    | 0.7923 | 0.7999 |
+| 0.3471        | 1.56  | 500  | 0.5285          | 0.8218   | 0.8158    | 0.8218 | 0.8048 |
+| 0.3144        | 1.87  | 600  | 0.5565          | 0.7961   | 0.8312    | 0.7961 | 0.8023 |
+| 0.1702        | 2.18  | 700  | 0.5404          | 0.8256   | 0.8320    | 0.8256 | 0.8240 |
+| 0.2557        | 2.49  | 800  | 0.5153          | 0.8402   | 0.8327    | 0.8402 | 0.8301 |
+| 0.1579        | 2.8   | 900  | 0.5867          | 0.8218   | 0.8420    | 0.8218 | 0.8250 |
+| 0.0815        | 3.12  | 1000 | 0.6218          | 0.8402   | 0.8476    | 0.8402 | 0.8351 |
+| 0.1075        | 3.43  | 1100 | 0.6123          | 0.8429   | 0.8456    | 0.8429 | 0.8342 |
+| 0.161         | 3.74  | 1200 | 0.6439          | 0.8509   | 0.8478    | 0.8509 | 0.8419 |
+| 0.0446        | 4.05  | 1300 | 0.6347          | 0.8561   | 0.8515    | 0.8561 | 0.8516 |
+| 0.1209        | 4.36  | 1400 | 0.6838          | 0.8454   | 0.8482    | 0.8454 | 0.8454 |
+| 0.006         | 4.67  | 1500 | 0.7756          | 0.8395   | 0.8375    | 0.8395 | 0.8363 |
+| 0.0219        | 4.98  | 1600 | 0.8815          | 0.8280   | 0.8368    | 0.8280 | 0.8271 |
+| 0.0616        | 5.3   | 1700 | 1.0825          | 0.8155   | 0.8128    | 0.8155 | 0.7864 |
+| 0.0305        | 5.61  | 1800 | 0.8289          | 0.8405   | 0.8428    | 0.8405 | 0.8367 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72acec732c47966b68d2faa14d9105206e4d5aa92ce96624703d728c012b6fce
+oid sha256:b63414d64d58868f9f12778c6f4f12d4cc8636a13e329ba9be76845535c66c90
 size 343239356

runs/Mar18_15-27-23_9c311a5b3773/events.out.tfevents.1710775645.9c311a5b3773.3314.20

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac14bb7fb877136223ec3877943bc85dcc71c156a49992d5b826d9e9a2417ad7
-size 51119
+oid sha256:289d22891a8b2006aba63d4021afc9c002ffc80289f8e009b7e9faa632abc207
+size 51473