Upload folder using huggingface_hub

README.md

@@ -0,0 +1,108 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224
+tags:
+- Image Regression
+datasets:
+- "tonyassi/tony__assi-ig-ds5"
+metrics:
+- accuracy
+model-index:
+- name: "tony__assi-ig-prediction"
+  results: []
+---
+
+# tony__assi-ig-prediction
+## IG Prediction
+
+This model was trained with [IGPrediction](https://github.com/TonyAssi/IGPrediction). It predicts how many likes an image will get.
+
+```python
+from IGPredict import predict_ig
+predict_ig(repo_id='tonyassi/tony__assi-ig-prediction',image_path='image.jpg')
+```
+
+---
+
+## Dataset
+Dataset: tonyassi/tony__assi-ig-ds5\
+Value Column:\
+Train Test Split: 0.2
+
+---
+
+## Training
+Base Model: [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224)\
+Epochs: 20\
+Learning Rate: 0.0001
+
+---
+
+## Usage
+
+### Download
+```bash
+git clone https://github.com/TonyAssi/IGPrediction.git
+cd IGPrediction
+```
+
+### Installation
+```bash
+pip install -r requirements.txt
+```
+
+### Import 
+```python
+from IGPredict import ig_download, upload_dataset, train_ig_model, upload_ig_model, predict_ig
+```
+
+### Download Instagram Images
+- **username** Instagram username
+- **num_images** maximum number of images to download
+```python
+ig_download(username='instagarm_username', num_images=100)
+```
+Instagram images will be downloaded to *'./images'* folder, each one named like so *"index-likes.jpg"*. E.g. *"3-17.jpg"* is the third image and has 17 likes.
+
+### Upload Dataset
+- **dataset_name** name of dataset to be uploaded
+- **token** go [here](https://huggingface.co/settings/tokens) to create a new 🤗 token
+```python
+upload_dataset(dataset_name='tonyassi/tony__assi-ig-ds5', token='YOUR_HF_TOKEN')
+```
+Go to your  🤗 profile to find your uploaded dataset, it should look similar to [tonyassi/tony__assi-ig-ds](https://huggingface.co/datasets/tonyassi/tony__assi-ig-ds).
+
+
+### Train Model
+- **dataset_id** 🤗 dataset id
+- **test_split** test split of the train/test split
+- **num_train_epochs** training epochs
+- **learning_rate** learning rate
+```python
+train_ig_model(dataset_id='tonyassi/tony__assi-ig-ds5',
+               test_split=0.2,
+               num_train_epochs=20,
+               learning_rate=0.0001)
+
+```
+The trainer will save the checkpoints in the 'results' folder. The model.safetensors are the trained weights you'll use for inference (predicton).
+
+### Upload Model
+This function will upload your model to the 🤗 Hub.
+- **model_id** the name of the model id
+- **token** go [here](https://huggingface.co/settings/tokens) to create a new 🤗 token
+- **checkpoint_dir** checkpoint folder that will be uploaded
+```python
+upload_ig_model(model_id='tony__assi-ig-prediction',
+             token='YOUR_HF_TOKEN',
+             checkpoint_dir='./results/checkpoint-940')
+```
+
+### Inference (Prediction)
+- **repo_id** 🤗 repo id of the model
+- **image_path** path to image
+```python
+predict_ig(repo_id='tonyassi/tony__assi-ig-prediction',
+        image_path='image.jpg')
+```
+The first time this function is called it'll download the safetensor model. Subsequent function calls will run faster.

metadata.json

@@ -0,0 +1,8 @@
+{
+    "dataset_id": "tonyassi/tony__assi-ig-ds5",
+    "value_column_name": "likes",
+    "test_split": 0.2,
+    "num_train_epochs": 20,
+    "learning_rate": 0.0001,
+    "max_value": 106
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4636e1e50f250102ea55feb997a3c4546b2cc0e6e5b9dfba805daa70b7943930
+size 345583444

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98f28ea68580bb2d79b75424d7f9c685bcbad07a26d694fb34e07d71219d9d01
+size 686557178

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8098b3ea1099554a17a75b08e08b0801f551831d4783349401defb321e1c1c1d
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce9ba9b1a5074d53eac331e90e43eb33ff190d28330a99d48dfa5f8761916744
+size 1064

trainer_state.json

@@ -0,0 +1,344 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.472058296203613,
+      "learning_rate": 9.5e-05,
+      "loss": 0.2548,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.20547232031822205,
+      "eval_mse": 0.20547235012054443,
+      "eval_runtime": 1.3582,
+      "eval_samples_per_second": 14.725,
+      "eval_steps_per_second": 2.209,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 16.11898422241211,
+      "learning_rate": 9e-05,
+      "loss": 0.4596,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.10995284467935562,
+      "eval_mse": 0.10995285212993622,
+      "eval_runtime": 0.9281,
+      "eval_samples_per_second": 21.551,
+      "eval_steps_per_second": 3.233,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 6.556423187255859,
+      "learning_rate": 8.5e-05,
+      "loss": 0.0866,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.12321324646472931,
+      "eval_mse": 0.12321324646472931,
+      "eval_runtime": 0.8771,
+      "eval_samples_per_second": 22.803,
+      "eval_steps_per_second": 3.42,
+      "step": 30
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 10.101408958435059,
+      "learning_rate": 8e-05,
+      "loss": 0.0741,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.055902622640132904,
+      "eval_mse": 0.05590261146426201,
+      "eval_runtime": 0.8907,
+      "eval_samples_per_second": 22.455,
+      "eval_steps_per_second": 3.368,
+      "step": 40
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.8052617311477661,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0471,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.033162668347358704,
+      "eval_mse": 0.033162668347358704,
+      "eval_runtime": 0.8798,
+      "eval_samples_per_second": 22.732,
+      "eval_steps_per_second": 3.41,
+      "step": 50
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 4.320048809051514,
+      "learning_rate": 7e-05,
+      "loss": 0.0206,
+      "step": 60
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.0486394502222538,
+      "eval_mse": 0.0486394464969635,
+      "eval_runtime": 0.9146,
+      "eval_samples_per_second": 21.867,
+      "eval_steps_per_second": 3.28,
+      "step": 60
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 4.353482246398926,
+      "learning_rate": 6.500000000000001e-05,
+      "loss": 0.0136,
+      "step": 70
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.03369127959012985,
+      "eval_mse": 0.03369127959012985,
+      "eval_runtime": 0.9267,
+      "eval_samples_per_second": 21.582,
+      "eval_steps_per_second": 3.237,
+      "step": 70
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.3020066022872925,
+      "learning_rate": 6e-05,
+      "loss": 0.0065,
+      "step": 80
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.03295436501502991,
+      "eval_mse": 0.032954368740320206,
+      "eval_runtime": 0.8738,
+      "eval_samples_per_second": 22.889,
+      "eval_steps_per_second": 3.433,
+      "step": 80
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.6798593997955322,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0054,
+      "step": 90
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.03235679119825363,
+      "eval_mse": 0.03235679119825363,
+      "eval_runtime": 0.911,
+      "eval_samples_per_second": 21.953,
+      "eval_steps_per_second": 3.293,
+      "step": 90
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.5722326040267944,
+      "learning_rate": 5e-05,
+      "loss": 0.0023,
+      "step": 100
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.03351482003927231,
+      "eval_mse": 0.03351482003927231,
+      "eval_runtime": 0.9079,
+      "eval_samples_per_second": 22.029,
+      "eval_steps_per_second": 3.304,
+      "step": 100
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 1.5198137760162354,
+      "learning_rate": 4.5e-05,
+      "loss": 0.0035,
+      "step": 110
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 0.03029645048081875,
+      "eval_mse": 0.030296454206109047,
+      "eval_runtime": 0.8889,
+      "eval_samples_per_second": 22.5,
+      "eval_steps_per_second": 3.375,
+      "step": 110
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 2.942338705062866,
+      "learning_rate": 4e-05,
+      "loss": 0.0029,
+      "step": 120
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 0.03209378570318222,
+      "eval_mse": 0.03209378197789192,
+      "eval_runtime": 0.9137,
+      "eval_samples_per_second": 21.889,
+      "eval_steps_per_second": 3.283,
+      "step": 120
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 0.5375175476074219,
+      "learning_rate": 3.5e-05,
+      "loss": 0.0035,
+      "step": 130
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 0.03165650740265846,
+      "eval_mse": 0.03165651112794876,
+      "eval_runtime": 0.9157,
+      "eval_samples_per_second": 21.84,
+      "eval_steps_per_second": 3.276,
+      "step": 130
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 0.43184858560562134,
+      "learning_rate": 3e-05,
+      "loss": 0.0011,
+      "step": 140
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 0.03108842670917511,
+      "eval_mse": 0.03108843043446541,
+      "eval_runtime": 0.889,
+      "eval_samples_per_second": 22.498,
+      "eval_steps_per_second": 3.375,
+      "step": 140
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.3797425925731659,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0007,
+      "step": 150
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 0.029892250895500183,
+      "eval_mse": 0.029892250895500183,
+      "eval_runtime": 0.9199,
+      "eval_samples_per_second": 21.742,
+      "eval_steps_per_second": 3.261,
+      "step": 150
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 0.3728632926940918,
+      "learning_rate": 2e-05,
+      "loss": 0.0004,
+      "step": 160
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 0.029963841661810875,
+      "eval_mse": 0.029963845387101173,
+      "eval_runtime": 0.9532,
+      "eval_samples_per_second": 20.981,
+      "eval_steps_per_second": 3.147,
+      "step": 160
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 0.7130188941955566,
+      "learning_rate": 1.5e-05,
+      "loss": 0.0003,
+      "step": 170
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 0.03030126914381981,
+      "eval_mse": 0.03030126728117466,
+      "eval_runtime": 0.8824,
+      "eval_samples_per_second": 22.665,
+      "eval_steps_per_second": 3.4,
+      "step": 170
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 0.05147755146026611,
+      "learning_rate": 1e-05,
+      "loss": 0.0001,
+      "step": 180
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 0.03000779077410698,
+      "eval_mse": 0.03000778891146183,
+      "eval_runtime": 0.9309,
+      "eval_samples_per_second": 21.484,
+      "eval_steps_per_second": 3.223,
+      "step": 180
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 0.17308902740478516,
+      "learning_rate": 5e-06,
+      "loss": 0.0,
+      "step": 190
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 0.030044889077544212,
+      "eval_mse": 0.03004489280283451,
+      "eval_runtime": 0.8961,
+      "eval_samples_per_second": 22.32,
+      "eval_steps_per_second": 3.348,
+      "step": 190
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.0706406906247139,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d5c1796317df1902e01cb29a20c763200e732f6482b5e7f7e47862ce3a0b096
+size 5048