Training in progress, epoch 8

config.json

@@ -67,6 +67,7 @@
   "num_channels": 3,
   "num_hidden_layers": 12,
   "patch_size": 1,
+  "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
   "transformers_version": "4.48.3",

logs/events.out.tfevents.1740307209.b73576bf569b.1066.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:639d8303c6d10d9bb5f0ebb40de7b18a7eb233d24a873efe349307630eec5e72
-size 88
+oid sha256:3655772916dddd7f99243beb1e09cbdb8149297fd3385fb9f52f7a50822850d8
+size 6780

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:038def7598ab97d17cd7ed8cddf70e3af5c1443b4ee33ebf1cc906d0ad061296
+oid sha256:bd39e4cd9ccf9077db5c440de7994f01765df643b48cc24f10fb459097fdc53f
 size 392799384

trainer_state.json

@@ -1,13 +1,126 @@
 {
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0,
+  "best_metric": 0.31206899881362915,
+  "best_model_checkpoint": "./drive/Shareddrives/CS198-Drones/training_output/vit-hybrid-base-bit-384_rice-leaf-disease-augmented-v2_fft/checkpoint-500",
+  "epoch": 7.0,
   "eval_steps": 500,
-  "global_step": 0,
+  "global_step": 1750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
-  "log_history": [],
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.522961616516113,
+      "learning_rate": 6.640000000000001e-06,
+      "loss": 1.203,
+      "step": 250
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8511904761904762,
+      "eval_loss": 0.4458940923213959,
+      "eval_runtime": 17.2925,
+      "eval_samples_per_second": 19.43,
+      "eval_steps_per_second": 0.636,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.191310882568359,
+      "learning_rate": 9.703220280030607e-06,
+      "loss": 0.1159,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9077380952380952,
+      "eval_loss": 0.31206899881362915,
+      "eval_runtime": 17.1167,
+      "eval_samples_per_second": 19.63,
+      "eval_steps_per_second": 0.643,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.6064174175262451,
+      "learning_rate": 7.512082232294491e-06,
+      "loss": 0.0136,
+      "step": 750
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9226190476190477,
+      "eval_loss": 0.3433467745780945,
+      "eval_runtime": 17.1077,
+      "eval_samples_per_second": 19.64,
+      "eval_steps_per_second": 0.643,
+      "step": 750
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.01187341008335352,
+      "learning_rate": 4.145512989383618e-06,
+      "loss": 0.001,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9226190476190477,
+      "eval_loss": 0.3376821279525757,
+      "eval_runtime": 17.0783,
+      "eval_samples_per_second": 19.674,
+      "eval_steps_per_second": 0.644,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.026375439018011093,
+      "learning_rate": 1.178767715305455e-06,
+      "loss": 0.0003,
+      "step": 1250
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9226190476190477,
+      "eval_loss": 0.3365038335323334,
+      "eval_runtime": 17.2601,
+      "eval_samples_per_second": 19.467,
+      "eval_steps_per_second": 0.637,
+      "step": 1250
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.0165720134973526,
+      "learning_rate": 1.9495502197042214e-11,
+      "loss": 0.0002,
+      "step": 1500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9285714285714286,
+      "eval_loss": 0.33658862113952637,
+      "eval_runtime": 17.208,
+      "eval_samples_per_second": 19.526,
+      "eval_steps_per_second": 0.639,
+      "step": 1500
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.004472899716347456,
+      "learning_rate": 8.839182277652986e-06,
+      "loss": 0.0002,
+      "step": 1750
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9285714285714286,
+      "eval_loss": 0.3431926965713501,
+      "eval_runtime": 17.2537,
+      "eval_samples_per_second": 19.474,
+      "eval_steps_per_second": 0.638,
+      "step": 1750
+    }
+  ],
   "logging_steps": 500,
   "max_steps": 3750,
   "num_input_tokens_seen": 0,
@@ -19,13 +132,13 @@
         "should_epoch_stop": false,
         "should_evaluate": false,
         "should_log": false,
-        "should_save": false,
+        "should_save": true,
         "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 0,
+  "total_flos": 1.4594252463931392e+19,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null