Upload folder using huggingface_hub

README.md

@@ -0,0 +1,34 @@
+
+---
+tags:
+- autotrain
+- transformers
+- image-classification
+base_model: google/vit-base-patch16-224
+widget:
+- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
+  example_title: Tiger
+- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
+  example_title: Teapot
+- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
+  example_title: Palace
+datasets:
+- AISOMA-Bittensor/roadworks_v2
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Image Classification
+
+## Validation Metrics
+loss: 0.1497480720281601
+
+f1: 0.9473684210526315
+
+precision: 0.908256880733945
+
+recall: 0.99
+
+auc: 0.9913000000000001
+
+accuracy: 0.945

checkpoint-375/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224",
+  "_num_labels": 2,
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0",
+    "1": "1"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "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": "4.48.0"
+}

checkpoint-375/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:611878881f18fae1f0f3b12c3678bdc3b5cf119aa8786285adc4ef5663cb30f8
+size 343223968

checkpoint-375/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:549ac473b0715e9622282b14457b10c9139f4da1e6aeea816fe37e93325f55b9
+size 686568890

checkpoint-375/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95b6047bd8cc6f4cdf7c46dea47edb8e542435510070c6cd1e0a7d9ccf5fd7da
+size 14244

checkpoint-375/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7502e1238d855a7f3a4b4b537be1e07c717c3546208cccb33c3dde5ae6823d05
+size 1064

checkpoint-375/trainer_state.json

@@ -0,0 +1,606 @@
+{
+  "best_metric": 0.1497480720281601,
+  "best_model_checkpoint": "roadworks-v03/checkpoint-375",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "grad_norm": 6.77192497253418,
+      "learning_rate": 3.1746031746031746e-06,
+      "loss": 0.6718,
+      "step": 5
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 7.211616039276123,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 0.6975,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 7.735755443572998,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 0.5514,
+      "step": 15
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 6.399946689605713,
+      "learning_rate": 1.5079365079365079e-05,
+      "loss": 0.5547,
+      "step": 20
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 6.158491134643555,
+      "learning_rate": 1.9047619047619046e-05,
+      "loss": 0.5982,
+      "step": 25
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 6.432331085205078,
+      "learning_rate": 2.3015873015873015e-05,
+      "loss": 0.5344,
+      "step": 30
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 5.646385669708252,
+      "learning_rate": 2.6984126984126984e-05,
+      "loss": 0.5182,
+      "step": 35
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 6.791838645935059,
+      "learning_rate": 3.095238095238095e-05,
+      "loss": 0.5578,
+      "step": 40
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 9.820820808410645,
+      "learning_rate": 3.492063492063492e-05,
+      "loss": 0.4598,
+      "step": 45
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.121436595916748,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 0.4045,
+      "step": 50
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 9.997166633605957,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 0.414,
+      "step": 55
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.048161029815674,
+      "learning_rate": 4.682539682539683e-05,
+      "loss": 0.2863,
+      "step": 60
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 5.565995216369629,
+      "learning_rate": 4.991103202846975e-05,
+      "loss": 0.3097,
+      "step": 65
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 11.46843433380127,
+      "learning_rate": 4.946619217081851e-05,
+      "loss": 0.2775,
+      "step": 70
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 9.153308868408203,
+      "learning_rate": 4.9021352313167264e-05,
+      "loss": 0.4719,
+      "step": 75
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.6512370109558105,
+      "learning_rate": 4.8576512455516014e-05,
+      "loss": 0.3968,
+      "step": 80
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 6.675440788269043,
+      "learning_rate": 4.813167259786477e-05,
+      "loss": 0.4958,
+      "step": 85
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 5.5016255378723145,
+      "learning_rate": 4.768683274021353e-05,
+      "loss": 0.3175,
+      "step": 90
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 11.443060874938965,
+      "learning_rate": 4.7241992882562284e-05,
+      "loss": 0.4341,
+      "step": 95
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 10.607640266418457,
+      "learning_rate": 4.6797153024911034e-05,
+      "loss": 0.2514,
+      "step": 100
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.2904133796691895,
+      "learning_rate": 4.635231316725978e-05,
+      "loss": 0.208,
+      "step": 105
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 5.581171035766602,
+      "learning_rate": 4.590747330960855e-05,
+      "loss": 0.5327,
+      "step": 110
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.650892734527588,
+      "learning_rate": 4.5462633451957297e-05,
+      "loss": 0.2097,
+      "step": 115
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 4.023620128631592,
+      "learning_rate": 4.501779359430605e-05,
+      "loss": 0.402,
+      "step": 120
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.131962299346924,
+      "learning_rate": 4.45729537366548e-05,
+      "loss": 0.2362,
+      "step": 125
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.925,
+      "eval_auc": 0.9903,
+      "eval_f1": 0.9302325581395349,
+      "eval_loss": 0.21616950631141663,
+      "eval_precision": 0.8695652173913043,
+      "eval_recall": 1.0,
+      "eval_runtime": 41.9583,
+      "eval_samples_per_second": 4.767,
+      "eval_steps_per_second": 0.31,
+      "step": 125
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 3.238992214202881,
+      "learning_rate": 4.4128113879003566e-05,
+      "loss": 0.162,
+      "step": 130
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 5.616732597351074,
+      "learning_rate": 4.3683274021352316e-05,
+      "loss": 0.1262,
+      "step": 135
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 13.144268035888672,
+      "learning_rate": 4.3238434163701066e-05,
+      "loss": 0.3814,
+      "step": 140
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 5.483018398284912,
+      "learning_rate": 4.279359430604982e-05,
+      "loss": 0.3299,
+      "step": 145
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 4.637882709503174,
+      "learning_rate": 4.234875444839858e-05,
+      "loss": 0.4135,
+      "step": 150
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 5.869772911071777,
+      "learning_rate": 4.1903914590747336e-05,
+      "loss": 0.4157,
+      "step": 155
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 7.716390609741211,
+      "learning_rate": 4.1459074733096085e-05,
+      "loss": 0.3954,
+      "step": 160
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 7.516646385192871,
+      "learning_rate": 4.101423487544484e-05,
+      "loss": 0.2453,
+      "step": 165
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 5.264847278594971,
+      "learning_rate": 4.05693950177936e-05,
+      "loss": 0.3088,
+      "step": 170
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 4.23276424407959,
+      "learning_rate": 4.0124555160142355e-05,
+      "loss": 0.2162,
+      "step": 175
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 7.253166675567627,
+      "learning_rate": 3.9679715302491105e-05,
+      "loss": 0.2789,
+      "step": 180
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 2.861260414123535,
+      "learning_rate": 3.9234875444839855e-05,
+      "loss": 0.1843,
+      "step": 185
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 1.792879581451416,
+      "learning_rate": 3.879003558718861e-05,
+      "loss": 0.1735,
+      "step": 190
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 4.788372039794922,
+      "learning_rate": 3.834519572953737e-05,
+      "loss": 0.1698,
+      "step": 195
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 10.927083015441895,
+      "learning_rate": 3.7900355871886125e-05,
+      "loss": 0.6023,
+      "step": 200
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 13.062745094299316,
+      "learning_rate": 3.7455516014234874e-05,
+      "loss": 0.0789,
+      "step": 205
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 3.585115432739258,
+      "learning_rate": 3.701067615658363e-05,
+      "loss": 0.3483,
+      "step": 210
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 2.498121738433838,
+      "learning_rate": 3.656583629893239e-05,
+      "loss": 0.1994,
+      "step": 215
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 6.423818111419678,
+      "learning_rate": 3.6120996441281144e-05,
+      "loss": 0.2724,
+      "step": 220
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 7.244612216949463,
+      "learning_rate": 3.5676156583629894e-05,
+      "loss": 0.3302,
+      "step": 225
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.36374810338020325,
+      "learning_rate": 3.5231316725978644e-05,
+      "loss": 0.1132,
+      "step": 230
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.3828773498535156,
+      "learning_rate": 3.478647686832741e-05,
+      "loss": 0.2084,
+      "step": 235
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 5.8181986808776855,
+      "learning_rate": 3.434163701067616e-05,
+      "loss": 0.2595,
+      "step": 240
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 4.1658101081848145,
+      "learning_rate": 3.3896797153024914e-05,
+      "loss": 0.2149,
+      "step": 245
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.1452529430389404,
+      "learning_rate": 3.345195729537366e-05,
+      "loss": 0.1366,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.95,
+      "eval_auc": 0.99075,
+      "eval_f1": 0.9523809523809523,
+      "eval_loss": 0.15040092170238495,
+      "eval_precision": 0.9090909090909091,
+      "eval_recall": 1.0,
+      "eval_runtime": 41.217,
+      "eval_samples_per_second": 4.852,
+      "eval_steps_per_second": 0.315,
+      "step": 250
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 2.9181268215179443,
+      "learning_rate": 3.300711743772243e-05,
+      "loss": 0.4332,
+      "step": 255
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 12.673237800598145,
+      "learning_rate": 3.2562277580071177e-05,
+      "loss": 0.2365,
+      "step": 260
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 5.242711067199707,
+      "learning_rate": 3.2117437722419926e-05,
+      "loss": 0.3013,
+      "step": 265
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.458162784576416,
+      "learning_rate": 3.167259786476868e-05,
+      "loss": 0.4029,
+      "step": 270
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.8767010569572449,
+      "learning_rate": 3.122775800711744e-05,
+      "loss": 0.2046,
+      "step": 275
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.6946662664413452,
+      "learning_rate": 3.0782918149466196e-05,
+      "loss": 0.1422,
+      "step": 280
+    },
+    {
+      "epoch": 2.2800000000000002,
+      "grad_norm": 8.177674293518066,
+      "learning_rate": 3.0338078291814946e-05,
+      "loss": 0.1535,
+      "step": 285
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 1.9587541818618774,
+      "learning_rate": 2.98932384341637e-05,
+      "loss": 0.1129,
+      "step": 290
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 6.240828514099121,
+      "learning_rate": 2.944839857651246e-05,
+      "loss": 0.3531,
+      "step": 295
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 8.415582656860352,
+      "learning_rate": 2.9003558718861212e-05,
+      "loss": 0.1724,
+      "step": 300
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.7639751434326172,
+      "learning_rate": 2.8558718861209965e-05,
+      "loss": 0.172,
+      "step": 305
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.5846173167228699,
+      "learning_rate": 2.811387900355872e-05,
+      "loss": 0.4912,
+      "step": 310
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 2.0510966777801514,
+      "learning_rate": 2.766903914590748e-05,
+      "loss": 0.192,
+      "step": 315
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 7.825207710266113,
+      "learning_rate": 2.7224199288256232e-05,
+      "loss": 0.247,
+      "step": 320
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 6.270692825317383,
+      "learning_rate": 2.677935943060498e-05,
+      "loss": 0.1365,
+      "step": 325
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 5.071442604064941,
+      "learning_rate": 2.6334519572953735e-05,
+      "loss": 0.2845,
+      "step": 330
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.7615436911582947,
+      "learning_rate": 2.5889679715302495e-05,
+      "loss": 0.0296,
+      "step": 335
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 1.9423273801803589,
+      "learning_rate": 2.5444839857651248e-05,
+      "loss": 0.048,
+      "step": 340
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 1.2762203216552734,
+      "learning_rate": 2.5e-05,
+      "loss": 0.269,
+      "step": 345
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.6899875998497009,
+      "learning_rate": 2.4555160142348754e-05,
+      "loss": 0.1853,
+      "step": 350
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 7.342668533325195,
+      "learning_rate": 2.411032028469751e-05,
+      "loss": 0.3235,
+      "step": 355
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 1.7423521280288696,
+      "learning_rate": 2.3665480427046264e-05,
+      "loss": 0.1906,
+      "step": 360
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 6.497461795806885,
+      "learning_rate": 2.322064056939502e-05,
+      "loss": 0.1881,
+      "step": 365
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 3.9244940280914307,
+      "learning_rate": 2.277580071174377e-05,
+      "loss": 0.0934,
+      "step": 370
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.22751639783382416,
+      "learning_rate": 2.2330960854092527e-05,
+      "loss": 0.1747,
+      "step": 375
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.945,
+      "eval_auc": 0.9913000000000001,
+      "eval_f1": 0.9473684210526315,
+      "eval_loss": 0.1497480720281601,
+      "eval_precision": 0.908256880733945,
+      "eval_recall": 0.99,
+      "eval_runtime": 41.2437,
+      "eval_samples_per_second": 4.849,
+      "eval_steps_per_second": 0.315,
+      "step": 375
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 625,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 1
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.32475968843776e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-375/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e3ce664c7f624cce4c89b20bf61acc5a4bc621f533224fe5f5f4e0861b3e9f1
+size 5368

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224",
+  "_num_labels": 2,
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0",
+    "1": "1"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "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": "4.48.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:611878881f18fae1f0f3b12c3678bdc3b5cf119aa8786285adc4ef5663cb30f8
+size 343223968

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": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

runs/Jun12_16-01-54_r-aisoma-bittensor-streetvision-rx1r66oz-79cb4-x0ge5/events.out.tfevents.1749744116.r-aisoma-bittensor-streetvision-rx1r66oz-79cb4-x0ge5.70.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bb8b6cc6ddb59d787a3dd1486c89fed513bb25c9d32f395c099a66a5b7a9b64
-size 24239
+oid sha256:f6177e15e584609050b66c4ddff5130bfe5954dfa1d88faab9ae784e1be41f2e
+size 34282

runs/Jun12_16-01-54_r-aisoma-bittensor-streetvision-rx1r66oz-79cb4-x0ge5/events.out.tfevents.1749745954.r-aisoma-bittensor-streetvision-rx1r66oz-79cb4-x0ge5.70.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:647a348eb8d8a7a6dce35703dd11cd181f2ea3b6c81cb7a6d9e9738c0d7d2528
+size 607

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e3ce664c7f624cce4c89b20bf61acc5a4bc621f533224fe5f5f4e0861b3e9f1
+size 5368

training_params.json

@@ -0,0 +1,29 @@
+{
+    "data_path": "AISOMA-Bittensor/roadworks_v2",
+    "model": "google/vit-base-patch16-224",
+    "username": "AISOMA-Bittensor",
+    "lr": 5e-05,
+    "epochs": 5,
+    "batch_size": 8,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "train_split": "train",
+    "valid_split": "test",
+    "logging_steps": -1,
+    "project_name": "roadworks-v03",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "image_column": "image",
+    "target_column": "label",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}