Model save

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.39705882352941174
+      value: 0.75
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 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 imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5660
-- Accuracy: 0.3971
+- Loss: 0.8349
+- Accuracy: 0.75
 
 ## Model description
 
@@ -53,7 +53,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 0.0005
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -69,10 +69,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 1.8678        | 2.0833 | 50   | 1.8966          | 0.3088   |
-| 1.6483        | 4.1667 | 100  | 1.7938          | 0.3382   |
-| 1.3419        | 6.25   | 150  | 1.6614          | 0.3824   |
-| 1.1189        | 8.3333 | 200  | 1.5660          | 0.3971   |
+| 0.6802        | 4.1667 | 100  | 1.2561          | 0.5735   |
+| 0.3727        | 8.3333 | 200  | 0.8349          | 0.75     |
 
 
 ### Framework versions

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.39705882352941174,
+    "eval_loss": 1.5659970045089722,
+    "eval_runtime": 3.0691,
+    "eval_samples_per_second": 22.156,
+    "eval_steps_per_second": 2.932,
+    "total_flos": 2.9603266596900864e+17,
+    "train_loss": 1.4860339760780334,
+    "train_runtime": 184.3796,
+    "train_samples_per_second": 20.718,
+    "train_steps_per_second": 1.302
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.39705882352941174,
+    "eval_loss": 1.5659970045089722,
+    "eval_runtime": 3.0691,
+    "eval_samples_per_second": 22.156,
+    "eval_steps_per_second": 2.932
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:086b8fe62b0d5fed3e346f2a9d99dc00d9f5731dde320e3d0146aecb147105ea
+oid sha256:9250264f9ee9b224c3cc2adb649f3fde7d866700115a24a2b8b3186b8ca284a7
 size 343239356

runs/Dec05_11-51-50_edab03f22c59/events.out.tfevents.1733399836.edab03f22c59.4058.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c85b596a4b70410e666c80ce5c5b8bd15eeb3637a710f51028c97e990d4df701
+size 411

runs/Dec05_12-11-38_edab03f22c59/events.out.tfevents.1733400711.edab03f22c59.4058.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a82df69bf2cbd3cbacce46514636ed6646da2c08fcfefa5e81291f72dd0588ee
+size 11309

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "total_flos": 2.9603266596900864e+17,
+    "train_loss": 1.4860339760780334,
+    "train_runtime": 184.3796,
+    "train_samples_per_second": 20.718,
+    "train_steps_per_second": 1.302
+}

trainer_state.json

@@ -0,0 +1,246 @@
+{
+  "best_metric": 1.5659970045089722,
+  "best_model_checkpoint": "finetuned-websites/checkpoint-200",
+  "epoch": 10.0,
+  "eval_steps": 50,
+  "global_step": 240,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 4.125311851501465,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.9272,
+      "step": 10
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 3.0228281021118164,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.928,
+      "step": 20
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 2.5070629119873047,
+      "learning_rate": 3e-06,
+      "loss": 1.921,
+      "step": 30
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 2.7787866592407227,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.8972,
+      "step": 40
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 2.7862040996551514,
+      "learning_rate": 5e-06,
+      "loss": 1.8678,
+      "step": 50
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "eval_accuracy": 0.3088235294117647,
+      "eval_loss": 1.8965561389923096,
+      "eval_runtime": 2.6013,
+      "eval_samples_per_second": 26.141,
+      "eval_steps_per_second": 3.46,
+      "step": 50
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 3.540709972381592,
+      "learning_rate": 6e-06,
+      "loss": 1.8526,
+      "step": 60
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 3.426781415939331,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 1.8198,
+      "step": 70
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 4.007580757141113,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.7369,
+      "step": 80
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 4.467859745025635,
+      "learning_rate": 9e-06,
+      "loss": 1.7144,
+      "step": 90
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 3.9431729316711426,
+      "learning_rate": 1e-05,
+      "loss": 1.6483,
+      "step": 100
+    },
+    {
+      "epoch": 4.166666666666667,
+      "eval_accuracy": 0.3382352941176471,
+      "eval_loss": 1.793816089630127,
+      "eval_runtime": 2.9764,
+      "eval_samples_per_second": 22.847,
+      "eval_steps_per_second": 3.024,
+      "step": 100
+    },
+    {
+      "epoch": 4.583333333333333,
+      "grad_norm": 3.2608771324157715,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 1.5856,
+      "step": 110
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.638972520828247,
+      "learning_rate": 1.2e-05,
+      "loss": 1.5157,
+      "step": 120
+    },
+    {
+      "epoch": 5.416666666666667,
+      "grad_norm": 3.3878164291381836,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 1.4388,
+      "step": 130
+    },
+    {
+      "epoch": 5.833333333333333,
+      "grad_norm": 4.086641311645508,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 1.4522,
+      "step": 140
+    },
+    {
+      "epoch": 6.25,
+      "grad_norm": 3.5550928115844727,
+      "learning_rate": 1.5e-05,
+      "loss": 1.3419,
+      "step": 150
+    },
+    {
+      "epoch": 6.25,
+      "eval_accuracy": 0.38235294117647056,
+      "eval_loss": 1.6614487171173096,
+      "eval_runtime": 2.1852,
+      "eval_samples_per_second": 31.118,
+      "eval_steps_per_second": 4.119,
+      "step": 150
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 4.774816036224365,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.3147,
+      "step": 160
+    },
+    {
+      "epoch": 7.083333333333333,
+      "grad_norm": 4.092309951782227,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 1.2643,
+      "step": 170
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 4.992920398712158,
+      "learning_rate": 1.8e-05,
+      "loss": 1.1924,
+      "step": 180
+    },
+    {
+      "epoch": 7.916666666666667,
+      "grad_norm": 6.251681327819824,
+      "learning_rate": 1.9e-05,
+      "loss": 1.1461,
+      "step": 190
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 5.500473499298096,
+      "learning_rate": 2e-05,
+      "loss": 1.1189,
+      "step": 200
+    },
+    {
+      "epoch": 8.333333333333334,
+      "eval_accuracy": 0.39705882352941174,
+      "eval_loss": 1.5659970045089722,
+      "eval_runtime": 2.0786,
+      "eval_samples_per_second": 32.715,
+      "eval_steps_per_second": 4.33,
+      "step": 200
+    },
+    {
+      "epoch": 8.75,
+      "grad_norm": 4.436168670654297,
+      "learning_rate": 2.1e-05,
+      "loss": 1.0734,
+      "step": 210
+    },
+    {
+      "epoch": 9.166666666666666,
+      "grad_norm": 4.706101417541504,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.9833,
+      "step": 220
+    },
+    {
+      "epoch": 9.583333333333334,
+      "grad_norm": 4.173801898956299,
+      "learning_rate": 2.3000000000000003e-05,
+      "loss": 0.9902,
+      "step": 230
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 5.312504291534424,
+      "learning_rate": 2.4e-05,
+      "loss": 0.9339,
+      "step": 240
+    },
+    {
+      "epoch": 10.0,
+      "step": 240,
+      "total_flos": 2.9603266596900864e+17,
+      "train_loss": 1.4860339760780334,
+      "train_runtime": 184.3796,
+      "train_samples_per_second": 20.718,
+      "train_steps_per_second": 1.302
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 240,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.9603266596900864e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10a6bd5335dcbeb330a5b30b2ffd7d502c27ce6f6343e794c3eb34529d57ad1d
+oid sha256:8b822f209f4725765bf9a9906e6c85c98b9ec4359564482ae17ee767ae986067
 size 5240