vit-emotion-classification

README.md

@@ -0,0 +1,81 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- image-classification
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: vit-emotion-classification
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: FastJobs/Visual_Emotional_Analysis
+      type: imagefolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6125
+---
+
+<!-- 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-emotion-classification
+
+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 FastJobs/Visual_Emotional_Analysis dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3802
+- Accuracy: 0.6125
+
+## 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: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.8454        | 2.5   | 100  | 1.4373          | 0.4813   |
+| 0.2022        | 5.0   | 200  | 1.4067          | 0.55     |
+| 0.0474        | 7.5   | 300  | 1.3802          | 0.6125   |
+| 0.0368        | 10.0  | 400  | 1.4388          | 0.5938   |
+
+
+### Framework versions
+
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.6125,
+    "eval_loss": 1.3801825046539307,
+    "eval_runtime": 0.9514,
+    "eval_samples_per_second": 168.179,
+    "eval_steps_per_second": 21.022,
+    "total_flos": 4.959754037231616e+17,
+    "train_loss": 0.4905405020713806,
+    "train_runtime": 117.1653,
+    "train_samples_per_second": 54.624,
+    "train_steps_per_second": 3.414
+}

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "anger",
+    "1": "contempt",
+    "2": "disgust",
+    "3": "fear",
+    "4": "happy",
+    "5": "neutral",
+    "6": "sad",
+    "7": "surprise"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "anger": "0",
+    "contempt": "1",
+    "disgust": "2",
+    "fear": "3",
+    "happy": "4",
+    "neutral": "5",
+    "sad": "6",
+    "surprise": "7"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.6125,
+    "eval_loss": 1.3801825046539307,
+    "eval_runtime": 0.9514,
+    "eval_samples_per_second": 168.179,
+    "eval_steps_per_second": 21.022
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c96beb5c645ff28e350eeff2b83ba7add70bbd26c931fa952f14edf607627a74
+size 343242432

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTFeatureExtractor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

runs/Jan06_09-10-24_8008b6c70fb0/events.out.tfevents.1736154659.8008b6c70fb0.1523.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e431a970bf8a3c82fcb386cdd5728af4b2faa4aeb1ab7199b8d03623fe7f2917
+size 5295

runs/Jan06_09-12-00_8008b6c70fb0/events.out.tfevents.1736154727.8008b6c70fb0.1523.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dd17d98455858d87626a91f9f1147eeb7982d839b8d79966d32b08ea1cbbc81
+size 5295

runs/Jan06_09-13-05_8008b6c70fb0/events.out.tfevents.1736154791.8008b6c70fb0.1523.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55ca07998c95839663cf0ab14da4513f8eae3ed422bd3f62ce9f056c698332e1
+size 9294

runs/Jan06_09-13-05_8008b6c70fb0/events.out.tfevents.1736154913.8008b6c70fb0.1523.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:591589e0dadd9a67b21b4070d9e7b5456b852db0368cd0b19187cb45882e398f
+size 411

runs/Jan06_09-18-00_8008b6c70fb0/events.out.tfevents.1736155086.8008b6c70fb0.1523.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:758fb4832bf018795ecc0455cfd8f45976e2158d1bd66ef0c861620f2ae1a632
+size 16384

runs/Jan06_09-18-00_8008b6c70fb0/events.out.tfevents.1736155227.8008b6c70fb0.1523.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acb72e847ed367c25aa646f33dad1b128dd0beb4c5d578b08cf8bd7898b9f215
+size 411

runs/Jan06_09-32-39_8008b6c70fb0/events.out.tfevents.1736155985.8008b6c70fb0.1523.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1db3f0ed90d3c7e2f022d57396fb18dab94fe3367097ae970a380dfe740cad87
+size 15329

runs/Jan06_09-32-39_8008b6c70fb0/events.out.tfevents.1736156140.8008b6c70fb0.1523.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:635945efba2d48f0e76c34aa440e563eca2a234a3b4fd956114c4fd49ab9ef0b
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "total_flos": 4.959754037231616e+17,
+    "train_loss": 0.4905405020713806,
+    "train_runtime": 117.1653,
+    "train_samples_per_second": 54.624,
+    "train_steps_per_second": 3.414
+}

trainer_state.json

@@ -0,0 +1,358 @@
+{
+  "best_metric": 1.3801825046539307,
+  "best_model_checkpoint": "./vit-emotion-classification/checkpoint-300",
+  "epoch": 10.0,
+  "eval_steps": 100,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "grad_norm": 2.134533643722534,
+      "learning_rate": 0.000195,
+      "loss": 2.0279,
+      "step": 10
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.939251184463501,
+      "learning_rate": 0.00019,
+      "loss": 1.7986,
+      "step": 20
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.8353347778320312,
+      "learning_rate": 0.00018500000000000002,
+      "loss": 1.6841,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.401373863220215,
+      "learning_rate": 0.00018,
+      "loss": 1.5968,
+      "step": 40
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 2.080655813217163,
+      "learning_rate": 0.000175,
+      "loss": 1.3349,
+      "step": 50
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 2.146280527114868,
+      "learning_rate": 0.00017,
+      "loss": 1.2608,
+      "step": 60
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 2.722163438796997,
+      "learning_rate": 0.000165,
+      "loss": 1.2728,
+      "step": 70
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.9687062501907349,
+      "learning_rate": 0.00016,
+      "loss": 1.1254,
+      "step": 80
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 2.55076265335083,
+      "learning_rate": 0.000155,
+      "loss": 0.8877,
+      "step": 90
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 2.256789445877075,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.8454,
+      "step": 100
+    },
+    {
+      "epoch": 2.5,
+      "eval_accuracy": 0.48125,
+      "eval_loss": 1.4373115301132202,
+      "eval_runtime": 0.8376,
+      "eval_samples_per_second": 191.019,
+      "eval_steps_per_second": 23.877,
+      "step": 100
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 2.4422082901000977,
+      "learning_rate": 0.000145,
+      "loss": 0.8337,
+      "step": 110
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.179633140563965,
+      "learning_rate": 0.00014,
+      "loss": 0.882,
+      "step": 120
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 1.4560832977294922,
+      "learning_rate": 0.00013500000000000003,
+      "loss": 0.5198,
+      "step": 130
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 2.0190017223358154,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 0.4344,
+      "step": 140
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 3.2591023445129395,
+      "learning_rate": 0.000125,
+      "loss": 0.4698,
+      "step": 150
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.652550220489502,
+      "learning_rate": 0.00012,
+      "loss": 0.54,
+      "step": 160
+    },
+    {
+      "epoch": 4.25,
+      "grad_norm": 0.5937463641166687,
+      "learning_rate": 0.00011499999999999999,
+      "loss": 0.2737,
+      "step": 170
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 1.0296827554702759,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 0.2402,
+      "step": 180
+    },
+    {
+      "epoch": 4.75,
+      "grad_norm": 3.007828712463379,
+      "learning_rate": 0.000105,
+      "loss": 0.1952,
+      "step": 190
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.936133623123169,
+      "learning_rate": 0.0001,
+      "loss": 0.2022,
+      "step": 200
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.55,
+      "eval_loss": 1.406724214553833,
+      "eval_runtime": 0.8264,
+      "eval_samples_per_second": 193.601,
+      "eval_steps_per_second": 24.2,
+      "step": 200
+    },
+    {
+      "epoch": 5.25,
+      "grad_norm": 0.3376343250274658,
+      "learning_rate": 9.5e-05,
+      "loss": 0.1086,
+      "step": 210
+    },
+    {
+      "epoch": 5.5,
+      "grad_norm": 2.637477397918701,
+      "learning_rate": 9e-05,
+      "loss": 0.109,
+      "step": 220
+    },
+    {
+      "epoch": 5.75,
+      "grad_norm": 3.05291485786438,
+      "learning_rate": 8.5e-05,
+      "loss": 0.0957,
+      "step": 230
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.055624485015869,
+      "learning_rate": 8e-05,
+      "loss": 0.136,
+      "step": 240
+    },
+    {
+      "epoch": 6.25,
+      "grad_norm": 0.30109065771102905,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0741,
+      "step": 250
+    },
+    {
+      "epoch": 6.5,
+      "grad_norm": 0.19268257915973663,
+      "learning_rate": 7e-05,
+      "loss": 0.0664,
+      "step": 260
+    },
+    {
+      "epoch": 6.75,
+      "grad_norm": 0.15611745417118073,
+      "learning_rate": 6.500000000000001e-05,
+      "loss": 0.0559,
+      "step": 270
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.21113821864128113,
+      "learning_rate": 6e-05,
+      "loss": 0.0599,
+      "step": 280
+    },
+    {
+      "epoch": 7.25,
+      "grad_norm": 0.160753071308136,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.049,
+      "step": 290
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 0.13460688292980194,
+      "learning_rate": 5e-05,
+      "loss": 0.0474,
+      "step": 300
+    },
+    {
+      "epoch": 7.5,
+      "eval_accuracy": 0.6125,
+      "eval_loss": 1.3801825046539307,
+      "eval_runtime": 0.8118,
+      "eval_samples_per_second": 197.084,
+      "eval_steps_per_second": 24.635,
+      "step": 300
+    },
+    {
+      "epoch": 7.75,
+      "grad_norm": 0.13902044296264648,
+      "learning_rate": 4.5e-05,
+      "loss": 0.0452,
+      "step": 310
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.12478330731391907,
+      "learning_rate": 4e-05,
+      "loss": 0.0424,
+      "step": 320
+    },
+    {
+      "epoch": 8.25,
+      "grad_norm": 0.11532563716173172,
+      "learning_rate": 3.5e-05,
+      "loss": 0.0409,
+      "step": 330
+    },
+    {
+      "epoch": 8.5,
+      "grad_norm": 0.11974634230136871,
+      "learning_rate": 3e-05,
+      "loss": 0.0395,
+      "step": 340
+    },
+    {
+      "epoch": 8.75,
+      "grad_norm": 0.1203409880399704,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0393,
+      "step": 350
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.13047201931476593,
+      "learning_rate": 2e-05,
+      "loss": 0.0386,
+      "step": 360
+    },
+    {
+      "epoch": 9.25,
+      "grad_norm": 0.10817253589630127,
+      "learning_rate": 1.5e-05,
+      "loss": 0.0376,
+      "step": 370
+    },
+    {
+      "epoch": 9.5,
+      "grad_norm": 0.12842506170272827,
+      "learning_rate": 1e-05,
+      "loss": 0.037,
+      "step": 380
+    },
+    {
+      "epoch": 9.75,
+      "grad_norm": 0.12066592276096344,
+      "learning_rate": 5e-06,
+      "loss": 0.0371,
+      "step": 390
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.13028773665428162,
+      "learning_rate": 0.0,
+      "loss": 0.0368,
+      "step": 400
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.59375,
+      "eval_loss": 1.4388375282287598,
+      "eval_runtime": 0.8121,
+      "eval_samples_per_second": 197.013,
+      "eval_steps_per_second": 24.627,
+      "step": 400
+    },
+    {
+      "epoch": 10.0,
+      "step": 400,
+      "total_flos": 4.959754037231616e+17,
+      "train_loss": 0.4905405020713806,
+      "train_runtime": 117.1653,
+      "train_samples_per_second": 54.624,
+      "train_steps_per_second": 3.414
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.959754037231616e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4e554804ca69ba63c5dfc5d687264a589bf43c750133db4f89df8bdafce4473
+size 5304