Training in progress, epoch 1

README.md

@@ -1,75 +1,60 @@
----
-license: apache-2.0
-base_model: google/vit-base-patch16-224-in21k
-tags:
-- generated_from_trainer
-metrics:
-- precision
-- recall
-- accuracy
-model-index:
-- name: vit-fire-detection
-  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-fire-detection
-
-This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.0250
-- Precision: 0.9934
-- Recall: 0.9934
-- Accuracy: 0.9934
-- F1score: 0.9934
-
-## 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: 64
-- eval_batch_size: 64
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 100
-- num_epochs: 10
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Accuracy | F1score |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:--------:|:-------:|
-| 0.5906        | 1.0   | 95   | 0.0594          | 0.9855    | 0.9854 | 0.9854   | 0.9854  |
-| 0.0812        | 2.0   | 190  | 0.0447          | 0.9908    | 0.9907 | 0.9907   | 0.9907  |
-| 0.0575        | 3.0   | 285  | 0.0779          | 0.9778    | 0.9762 | 0.9762   | 0.9762  |
-| 0.036         | 4.0   | 380  | 0.0242          | 0.9935    | 0.9934 | 0.9934   | 0.9934  |
-| 0.0395        | 5.0   | 475  | 0.0283          | 0.9921    | 0.9921 | 0.9921   | 0.9921  |
-| 0.0225        | 6.0   | 570  | 0.0169          | 0.9947    | 0.9947 | 0.9947   | 0.9947  |
-| 0.0165        | 7.0   | 665  | 0.0205          | 0.9934    | 0.9934 | 0.9934   | 0.9934  |
-| 0.0099        | 8.0   | 760  | 0.0180          | 0.9960    | 0.9960 | 0.9960   | 0.9960  |
-| 0.0074        | 9.0   | 855  | 0.0255          | 0.9947    | 0.9947 | 0.9947   | 0.9947  |
-| 0.0055        | 10.0  | 950  | 0.0250          | 0.9934    | 0.9934 | 0.9934   | 0.9934  |
-
-
-### Framework versions
-
-- Transformers 4.36.0
-- Pytorch 2.1.1+cpu
-- Datasets 2.15.0
-- Tokenizers 0.15.0
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- generated_from_trainer
+model-index:
+- name: vit-fire-detection
+  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-fire-detection
+
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.1693
+- eval_precision: 0.9500
+- eval_recall: 0.9484
+- eval_accuracy: 0.9484
+- eval_f1score: 0.9482
+- eval_runtime: 45.7316
+- eval_samples_per_second: 16.531
+- eval_steps_per_second: 0.525
+- epoch: 5.0
+- step: 950
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 10
+
+### Framework versions
+
+- Transformers 4.36.0
+- Pytorch 2.1.1+cpu
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -1,34 +1,34 @@
-{
-  "_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": "Fire",
-    "1": "Normal",
-    "2": "Smoke"
-  },
-  "image_size": 224,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "Fire": 0,
-    "Normal": 1,
-    "Smoke": 2
-  },
-  "layer_norm_eps": 1e-12,
-  "model_type": "vit",
-  "num_attention_heads": 12,
-  "num_channels": 3,
-  "num_hidden_layers": 12,
-  "patch_size": 32,
-  "problem_type": "single_label_classification",
-  "qkv_bias": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.36.0"
-}
+{
+  "_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": "Fire",
+    "1": "Normal",
+    "2": "Smoke"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Fire": 0,
+    "Normal": 1,
+    "Smoke": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 8,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 64,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36e43ff9f1792c04e6149b703d51cd72c84e740a2adafa5e12a0a36ff448f01b
-size 349853372
+oid sha256:b63630614b17796fa0c928b0794da306033a335f459ae98d8445d23bcc33d3fe
+size 378042076

preprocessor_config.json

@@ -1,22 +1,22 @@
-{
-  "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
-  }
-}
+{
+  "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/Apr04_12-15-02_Shravani/events.out.tfevents.1712213104.Shravani.24608.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caf740efde18049cf0a7b5674eca15a6fde110f9feb561646f35d22af56fb9ae
-size 10732
+oid sha256:e030a7deb1e6147cc3cb6d8b783222bf15d2577717cc20aa0c8acf4282263391
+size 15506

runs/May06_10-04-26_Shravani/events.out.tfevents.1714970067.Shravani.34392.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41627090b83c3343fe4701e805927bdbe26235aca3342c8c160d2272155a569d
+size 9784

runs/May22_06-52-46_Shravani/events.out.tfevents.1716340980.Shravani.27548.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86b67f009753185f610364f8d9156a72e0de4ef833540e710357620d83aa19c2
+size 5363

tmp-checkpoint-950/config.json

@@ -0,0 +1,34 @@
+{
+  "_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": "Fire",
+    "1": "Normal",
+    "2": "Smoke"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Fire": 0,
+    "Normal": 1,
+    "Smoke": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 64,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0"
+}

tmp-checkpoint-950/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6a65b77379eca120d8e3d90989bf2e410faf837999c9266cbd24823b86c5706
+size 378042076

tmp-checkpoint-950/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1edea7193a8d5e1476b5dfbf448d7aeb2d9816c98c12781d68a4e193bcf89c78
+size 756199354

tmp-checkpoint-950/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": "ViTFeatureExtractor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

tmp-checkpoint-950/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:732bc5c09c2a93ecaa4de1b7485a4b0dd21972a86253092ca4e305dd3458a309
+size 13990

tmp-checkpoint-950/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbbcbb5ee6fa58bcafa461d5f254dbe3cd942dd5f6dcb4603ef82163ccb9b68e
+size 1064

tmp-checkpoint-950/trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_metric": 0.1471855193376541,
+  "best_model_checkpoint": "Shravanig/vit-fire-detection\\checkpoint-570",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 950,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0001,
+      "loss": 0.9828,
+      "step": 50
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002,
+      "loss": 0.6565,
+      "step": 100
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00019444444444444446,
+      "loss": 0.4455,
+      "step": 150
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9113756613756614,
+      "eval_f1score": 0.909933626964354,
+      "eval_loss": 0.2449590563774109,
+      "eval_precision": 0.911608601120207,
+      "eval_recall": 0.9113756613756614,
+      "eval_runtime": 55.8003,
+      "eval_samples_per_second": 13.548,
+      "eval_steps_per_second": 0.43,
+      "step": 190
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00018888888888888888,
+      "loss": 0.3878,
+      "step": 200
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00018333333333333334,
+      "loss": 0.4043,
+      "step": 250
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 0.3663,
+      "step": 300
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00017222222222222224,
+      "loss": 0.3198,
+      "step": 350
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9431216931216931,
+      "eval_f1score": 0.9430234733391375,
+      "eval_loss": 0.15777449309825897,
+      "eval_precision": 0.9432524221092315,
+      "eval_recall": 0.9431216931216931,
+      "eval_runtime": 58.5248,
+      "eval_samples_per_second": 12.918,
+      "eval_steps_per_second": 0.41,
+      "step": 380
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.2777,
+      "step": 400
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 0.0001611111111111111,
+      "loss": 0.3112,
+      "step": 450
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 0.2555,
+      "step": 500
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.2768,
+      "step": 550
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9470899470899471,
+      "eval_f1score": 0.9469968822663881,
+      "eval_loss": 0.1471855193376541,
+      "eval_precision": 0.9475131567523525,
+      "eval_recall": 0.9470899470899471,
+      "eval_runtime": 32.47,
+      "eval_samples_per_second": 23.283,
+      "eval_steps_per_second": 0.739,
+      "step": 570
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 0.00014444444444444444,
+      "loss": 0.235,
+      "step": 600
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 0.2715,
+      "step": 650
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.2444,
+      "step": 700
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 0.00012777777777777776,
+      "loss": 0.2283,
+      "step": 750
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9431216931216931,
+      "eval_f1score": 0.9432838391066171,
+      "eval_loss": 0.15458014607429504,
+      "eval_precision": 0.9448779078440028,
+      "eval_recall": 0.9431216931216931,
+      "eval_runtime": 59.6685,
+      "eval_samples_per_second": 12.67,
+      "eval_steps_per_second": 0.402,
+      "step": 760
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 0.00012222222222222224,
+      "loss": 0.2014,
+      "step": 800
+    },
+    {
+      "epoch": 4.47,
+      "learning_rate": 0.00011666666666666668,
+      "loss": 0.2085,
+      "step": 850
+    },
+    {
+      "epoch": 4.74,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 0.2231,
+      "step": 900
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.00010555555555555557,
+      "loss": 0.201,
+      "step": 950
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9484126984126984,
+      "eval_f1score": 0.9482271168351205,
+      "eval_loss": 0.169330894947052,
+      "eval_precision": 0.9499665185939696,
+      "eval_recall": 0.9484126984126984,
+      "eval_runtime": 45.7316,
+      "eval_samples_per_second": 16.531,
+      "eval_steps_per_second": 0.525,
+      "step": 950
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1900,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 2.586214904516813e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

tmp-checkpoint-950/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4794393befeb5f69568a4ecfefe1735cfba604c435f1d5a8a1261f6b843fc7f
+size 4792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec4a79f15a63d9ba638f9b0ec493d2d92b8b6a9b0c2ff24587d8e7a60e70b477
+oid sha256:270b5928caae40c5bca0e7cca3827e413320f661f75cdabd732e310d4ec2bcd3
 size 4792