Training in progress, step 60

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.06532761454582214,
+    "eval_runtime": 1.8393,
+    "eval_samples_per_second": 31.533,
+    "eval_steps_per_second": 4.349,
+    "total_flos": 1.7978141590585344e+16,
+    "train_loss": 0.40461832682291665,
+    "train_runtime": 22.5515,
+    "train_samples_per_second": 10.288,
+    "train_steps_per_second": 2.661
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_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": "class_2",
+    "1": "class_1"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "class_1": "1",
+    "class_2": "0"
+  },
+  "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": "4.44.0"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.06532761454582214,
+    "eval_runtime": 1.8393,
+    "eval_samples_per_second": 31.533,
+    "eval_steps_per_second": 4.349
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fddb4a72ba62a69767bb5f740cefb51316298411672cd5fae7d3f414e562826a
+size 343223968

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
+  }
+}

runs/Aug30_08-17-40_7e2de4304170/events.out.tfevents.1725005861.7e2de4304170

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b96e1b338bc7e4c1780c38e6ceaf79d3fb9f68e9442d4d189368e0b4a736f614
+size 4850

runs/Aug30_08-18-36_7e2de4304170/events.out.tfevents.1725005916.7e2de4304170

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:585c66a9a7931a13859f48812f473cbddfee4edd89bfdfa67040496afd5c33b8
+size 6440

runs/Aug30_08-18-36_7e2de4304170/events.out.tfevents.1725005939.7e2de4304170

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc1c5ab80d51275f7cdd7f4a2410b23dcafcef62a38ec0bc8ee253a308d182c7
+size 357

runs/Aug30_08-20-43_7e2de4304170/events.out.tfevents.1725006044.7e2de4304170

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c97756481a5fcbfc55ee3309a4c17b9795e9f066c8c4b226df07b17e62bb87c
+size 6440

runs/Aug30_08-20-43_7e2de4304170/events.out.tfevents.1725006069.7e2de4304170

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15609014ea64c5285851d37b9c1622c2fa4a43e1221d43025282547dc871ee1f
+size 357

runs/Aug30_08-23-02_7e2de4304170/events.out.tfevents.1725006183.7e2de4304170

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcf470d42aee06b1b97d7bfa3fe5ef95d765dca28cd4a00e4c5b79c8865694b4
+size 6439

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 1.7978141590585344e+16,
+    "train_loss": 0.40461832682291665,
+    "train_runtime": 22.5515,
+    "train_samples_per_second": 10.288,
+    "train_steps_per_second": 2.661
+}

trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 100,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 2.283698558807373,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.6508,
+      "step": 10
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 2.1393485069274902,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.7352,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 8.583788871765137,
+      "learning_rate": 0.0001,
+      "loss": 0.5144,
+      "step": 30
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 2.3513376712799072,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.3221,
+      "step": 40
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.4516322910785675,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.1103,
+      "step": 50
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.6485121846199036,
+      "learning_rate": 0.0,
+      "loss": 0.095,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "step": 60,
+      "total_flos": 1.7978141590585344e+16,
+      "train_loss": 0.40461832682291665,
+      "train_runtime": 22.5515,
+      "train_samples_per_second": 10.288,
+      "train_steps_per_second": 2.661
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 60,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 1.7978141590585344e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6175005b8c3cdc9c40282d128588b2a7e996668cece2faa36aaa960cacf36340
+size 5176