Modelo para clasificar hojas de frejol

README.md

@@ -0,0 +1,62 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- image-classification
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: vit-model-upeu_sistemas_v2
+  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-model-upeu_sistemas_v2
+
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the AI-Lab-Makerere/beans dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0550
+- Accuracy: 0.9850
+
+## 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: 0.0002
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.1264        | 3.8462 | 500  | 0.0550          | 0.9850   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.5.0+cu121
+- Datasets 3.0.2
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9849624060150376,
+    "eval_loss": 0.054959025233983994,
+    "eval_runtime": 2.4426,
+    "eval_samples_per_second": 54.449,
+    "eval_steps_per_second": 6.96,
+    "total_flos": 3.205097416476426e+17,
+    "train_loss": 0.12177124903179132,
+    "train_runtime": 205.4405,
+    "train_samples_per_second": 20.132,
+    "train_steps_per_second": 2.531
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9849624060150376,
+    "eval_loss": 0.054959025233983994,
+    "eval_runtime": 2.4426,
+    "eval_samples_per_second": 54.449,
+    "eval_steps_per_second": 6.96
+}

runs/Oct28_17-46-40_7df710cc28e4/events.out.tfevents.1730137641.7df710cc28e4.6103.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e154b0e3d919e9973bb388c2bb06da7993a80d3665d2dc87005e27f18fb2d4de
-size 5549
+oid sha256:dbdbf7d5012fd93f61332e728b0601ec74c639afdf252897a9f23bf0d3a88663
+size 5903

runs/Oct28_17-46-40_7df710cc28e4/events.out.tfevents.1730137874.7df710cc28e4.6103.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d23113c50292a8d891ce1725f7fecde5aa0c19a034fd00eba36930f30fc6df1
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 3.205097416476426e+17,
+    "train_loss": 0.12177124903179132,
+    "train_runtime": 205.4405,
+    "train_samples_per_second": 20.132,
+    "train_steps_per_second": 2.531
+}