Upload-checkpoint

checkpoint-13550/._model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede083d2d45b25d09ba401f084713cc713b32ea079ea480acb71d936373974e7
+size 4096

checkpoint-13550/._optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de5f832e0f64dec0e70e59f9055e6044c7aa5d8fe496cf7a21a6e908e37f8a8a
+size 4096

checkpoint-13550/._rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30442b277e2a067179f333d0634acd7ee9fe00aee2fc886a0035cd86b8b9785c
+size 4096

checkpoint-13550/._scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4c19220eba96acfa9b8621ef87926dda3b00cf0cb38930105affa7c6a34dd03
+size 4096

checkpoint-13550/._training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6574da8d4ca50728cea1e34978d1cb56436c898d75001b07c6b92970e8dca0d6
+size 4096

checkpoint-13550/config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "Bahriye/facial_emotions_detection",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "sad",
+    "1": "disgust",
+    "2": "angry",
+    "3": "neutral",
+    "4": "fear",
+    "5": "surprise",
+    "6": "happy"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "angry": 2,
+    "disgust": 1,
+    "fear": 4,
+    "happy": 6,
+    "neutral": 3,
+    "sad": 0,
+    "surprise": 5
+  },
+  "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": "4.43.3"
+}

checkpoint-13550/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f72b54d4fcb4b23111e90c028d01b0cc6edfbece14d71feea1e4a2c35fbc620
+size 343239356

checkpoint-13550/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3dc13357ed63345ee4e35924fd4b5be93a18d579d63b705d29fc4efde48d2d9
+size 686599610

checkpoint-13550/preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

checkpoint-13550/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8981a702abe7a36f5cd69e69b79dc2ca49b46a546b769c5fdb1f593a7a9e7306
+size 14244

checkpoint-13550/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6e9215b85fa294c5daba92f80106811feafced38368e170e7894c98993dfe83
+size 1064

checkpoint-13550/trainer_state.json

@@ -0,0 +1,322 @@
+{
+  "best_metric": 0.5464449524879456,
+  "best_model_checkpoint": "facial_emotions_image_detection\\checkpoint-13550",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 13550,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.36900369003690037,
+      "grad_norm": 23.415620803833008,
+      "learning_rate": 9.666666666666666e-08,
+      "loss": 0.7948,
+      "step": 500
+    },
+    {
+      "epoch": 0.7380073800738007,
+      "grad_norm": 20.815876007080078,
+      "learning_rate": 9.296296296296295e-08,
+      "loss": 0.7554,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7974880631098193,
+      "eval_loss": 0.6861713528633118,
+      "eval_model_preparation_time": 0.002,
+      "eval_runtime": 155.7997,
+      "eval_samples_per_second": 185.507,
+      "eval_steps_per_second": 23.19,
+      "step": 1355
+    },
+    {
+      "epoch": 1.1070110701107012,
+      "grad_norm": 18.020723342895508,
+      "learning_rate": 8.925925925925925e-08,
+      "loss": 0.7143,
+      "step": 1500
+    },
+    {
+      "epoch": 1.4760147601476015,
+      "grad_norm": 34.10048294067383,
+      "learning_rate": 8.555555555555555e-08,
+      "loss": 0.6749,
+      "step": 2000
+    },
+    {
+      "epoch": 1.8450184501845017,
+      "grad_norm": 14.084087371826172,
+      "learning_rate": 8.185185185185185e-08,
+      "loss": 0.6664,
+      "step": 2500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8085253615666735,
+      "eval_loss": 0.6355780363082886,
+      "eval_model_preparation_time": 0.002,
+      "eval_runtime": 162.3093,
+      "eval_samples_per_second": 178.067,
+      "eval_steps_per_second": 22.26,
+      "step": 2710
+    },
+    {
+      "epoch": 2.2140221402214024,
+      "grad_norm": 11.958518028259277,
+      "learning_rate": 7.814814814814814e-08,
+      "loss": 0.6568,
+      "step": 3000
+    },
+    {
+      "epoch": 2.5830258302583027,
+      "grad_norm": 14.969853401184082,
+      "learning_rate": 7.444444444444444e-08,
+      "loss": 0.6275,
+      "step": 3500
+    },
+    {
+      "epoch": 2.952029520295203,
+      "grad_norm": 25.454679489135742,
+      "learning_rate": 7.074074074074074e-08,
+      "loss": 0.6228,
+      "step": 4000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8148225036329666,
+      "eval_loss": 0.6049506068229675,
+      "eval_model_preparation_time": 0.002,
+      "eval_runtime": 139.303,
+      "eval_samples_per_second": 207.476,
+      "eval_steps_per_second": 25.936,
+      "step": 4065
+    },
+    {
+      "epoch": 3.321033210332103,
+      "grad_norm": 16.002216339111328,
+      "learning_rate": 6.703703703703704e-08,
+      "loss": 0.6031,
+      "step": 4500
+    },
+    {
+      "epoch": 3.6900369003690034,
+      "grad_norm": 11.849915504455566,
+      "learning_rate": 6.333333333333333e-08,
+      "loss": 0.6113,
+      "step": 5000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8200816552487717,
+      "eval_loss": 0.585157573223114,
+      "eval_model_preparation_time": 0.002,
+      "eval_runtime": 139.0318,
+      "eval_samples_per_second": 207.881,
+      "eval_steps_per_second": 25.987,
+      "step": 5420
+    },
+    {
+      "epoch": 4.059040590405904,
+      "grad_norm": 19.117860794067383,
+      "learning_rate": 5.962962962962964e-08,
+      "loss": 0.5902,
+      "step": 5500
+    },
+    {
+      "epoch": 4.428044280442805,
+      "grad_norm": 16.87006378173828,
+      "learning_rate": 5.592592592592592e-08,
+      "loss": 0.5922,
+      "step": 6000
+    },
+    {
+      "epoch": 4.797047970479705,
+      "grad_norm": 13.993415832519531,
+      "learning_rate": 5.2222222222222224e-08,
+      "loss": 0.5721,
+      "step": 6500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8228150301017231,
+      "eval_loss": 0.5712991952896118,
+      "eval_model_preparation_time": 0.002,
+      "eval_runtime": 146.0715,
+      "eval_samples_per_second": 197.862,
+      "eval_steps_per_second": 24.734,
+      "step": 6775
+    },
+    {
+      "epoch": 5.166051660516605,
+      "grad_norm": 12.831026077270508,
+      "learning_rate": 4.8518518518518515e-08,
+      "loss": 0.5695,
+      "step": 7000
+    },
+    {
+      "epoch": 5.535055350553505,
+      "grad_norm": 16.916507720947266,
+      "learning_rate": 4.481481481481481e-08,
+      "loss": 0.5587,
+      "step": 7500
+    },
+    {
+      "epoch": 5.904059040590406,
+      "grad_norm": 24.268339157104492,
+      "learning_rate": 4.1111111111111104e-08,
+      "loss": 0.5709,
+      "step": 8000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8264825963601135,
+      "eval_loss": 0.5612380504608154,
+      "eval_model_preparation_time": 0.002,
+      "eval_runtime": 139.8175,
+      "eval_samples_per_second": 206.712,
+      "eval_steps_per_second": 25.841,
+      "step": 8130
+    },
+    {
+      "epoch": 6.273062730627307,
+      "grad_norm": 8.325817108154297,
+      "learning_rate": 3.74074074074074e-08,
+      "loss": 0.5614,
+      "step": 8500
+    },
+    {
+      "epoch": 6.642066420664206,
+      "grad_norm": 14.428152084350586,
+      "learning_rate": 3.37037037037037e-08,
+      "loss": 0.5503,
+      "step": 9000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8279357829907965,
+      "eval_loss": 0.5542047023773193,
+      "eval_model_preparation_time": 0.002,
+      "eval_runtime": 139.1187,
+      "eval_samples_per_second": 207.751,
+      "eval_steps_per_second": 25.971,
+      "step": 9485
+    },
+    {
+      "epoch": 7.011070110701107,
+      "grad_norm": 15.315733909606934,
+      "learning_rate": 3e-08,
+      "loss": 0.5587,
+      "step": 9500
+    },
+    {
+      "epoch": 7.380073800738008,
+      "grad_norm": 8.681608200073242,
+      "learning_rate": 2.6296296296296295e-08,
+      "loss": 0.5477,
+      "step": 10000
+    },
+    {
+      "epoch": 7.749077490774908,
+      "grad_norm": 14.193209648132324,
+      "learning_rate": 2.259259259259259e-08,
+      "loss": 0.5399,
+      "step": 10500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8292505708947477,
+      "eval_loss": 0.5495484471321106,
+      "eval_model_preparation_time": 0.002,
+      "eval_runtime": 139.8719,
+      "eval_samples_per_second": 206.632,
+      "eval_steps_per_second": 25.831,
+      "step": 10840
+    },
+    {
+      "epoch": 8.118081180811808,
+      "grad_norm": 14.175172805786133,
+      "learning_rate": 1.8888888888888887e-08,
+      "loss": 0.5509,
+      "step": 11000
+    },
+    {
+      "epoch": 8.487084870848708,
+      "grad_norm": 17.474815368652344,
+      "learning_rate": 1.5185185185185185e-08,
+      "loss": 0.5486,
+      "step": 11500
+    },
+    {
+      "epoch": 8.85608856088561,
+      "grad_norm": 23.74073028564453,
+      "learning_rate": 1.148148148148148e-08,
+      "loss": 0.5331,
+      "step": 12000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8304615597536502,
+      "eval_loss": 0.5470238924026489,
+      "eval_model_preparation_time": 0.002,
+      "eval_runtime": 139.3645,
+      "eval_samples_per_second": 207.384,
+      "eval_steps_per_second": 25.925,
+      "step": 12195
+    },
+    {
+      "epoch": 9.22509225092251,
+      "grad_norm": 24.150386810302734,
+      "learning_rate": 7.777777777777777e-09,
+      "loss": 0.5477,
+      "step": 12500
+    },
+    {
+      "epoch": 9.59409594095941,
+      "grad_norm": 25.278697967529297,
+      "learning_rate": 4.0740740740740745e-09,
+      "loss": 0.5472,
+      "step": 13000
+    },
+    {
+      "epoch": 9.96309963099631,
+      "grad_norm": 18.863086700439453,
+      "learning_rate": 3.7037037037037036e-10,
+      "loss": 0.5354,
+      "step": 13500
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8302885613452357,
+      "eval_loss": 0.5464449524879456,
+      "eval_model_preparation_time": 0.002,
+      "eval_runtime": 137.6366,
+      "eval_samples_per_second": 209.988,
+      "eval_steps_per_second": 26.25,
+      "step": 13550
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 13550,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.3595832814367703e+19,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-13550/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d7b94fef50f8696026af4a4aa1425cab2315891b831be1e266f904566a97989
+size 5176