Training in progress, epoch 14

config.json

@@ -45,6 +45,7 @@
     12
   ],
   "patch_size": 14,
+  "problem_type": "single_label_classification",
   "qkv_bias": true,
   "reshape_hidden_states": true,
   "stage_names": [

logs/events.out.tfevents.1738202146.5bb5c7d49c13.381.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7538260c106844c4f8c040ac7a70aeb082fad1f0dacaa17f61fb8e7fa46cb48
-size 88
+oid sha256:88e4369ab3bae76ceb501cf55df139dab76c91c0b0dce0b3fe1749ae78277944
+size 7075

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccc157d0f6ffa181d3a99128cb109e0409f03d1ebe7bac5e05681ba7ac5dc3f5
+oid sha256:d73b6883683ecab6d38502fc1541c462cec0a09864e1fe6e7e78b8dfe05226bf
 size 346396816

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.03742993623018265,
-  "best_model_checkpoint": "./drive/Shareddrives/CS198-Drones/training_output/dinov2-base_rice-leaf-disease-augmented_fft_012825/checkpoint-1250",
-  "epoch": 5.0,
+  "best_metric": 0.012183231301605701,
+  "best_model_checkpoint": "./drive/Shareddrives/CS198-Drones/training_output/dinov2-base_rice-leaf-disease-augmented_fft_012825/checkpoint-2000",
+  "epoch": 12.0,
   "eval_steps": 500,
-  "global_step": 1250,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -87,6 +87,118 @@
       "eval_samples_per_second": 19.347,
       "eval_steps_per_second": 0.31,
       "step": 1250
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.008258991874754429,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.0052,
+      "step": 1500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.997,
+      "eval_loss": 0.012767890468239784,
+      "eval_runtime": 109.714,
+      "eval_samples_per_second": 18.229,
+      "eval_steps_per_second": 0.292,
+      "step": 1500
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.023719610646367073,
+      "learning_rate": 5.925925925925926e-06,
+      "loss": 0.0018,
+      "step": 1750
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9945,
+      "eval_loss": 0.013132033869624138,
+      "eval_runtime": 108.5519,
+      "eval_samples_per_second": 18.424,
+      "eval_steps_per_second": 0.295,
+      "step": 1750
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.1996152102947235,
+      "learning_rate": 5.185185185185185e-06,
+      "loss": 0.0027,
+      "step": 2000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.997,
+      "eval_loss": 0.012183231301605701,
+      "eval_runtime": 107.9106,
+      "eval_samples_per_second": 18.534,
+      "eval_steps_per_second": 0.297,
+      "step": 2000
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.008068982511758804,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.0004,
+      "step": 2250
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.997,
+      "eval_loss": 0.015290269628167152,
+      "eval_runtime": 108.9225,
+      "eval_samples_per_second": 18.362,
+      "eval_steps_per_second": 0.294,
+      "step": 2250
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.0013503103982657194,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 0.0013,
+      "step": 2500
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.997,
+      "eval_loss": 0.012768927030265331,
+      "eval_runtime": 107.1659,
+      "eval_samples_per_second": 18.663,
+      "eval_steps_per_second": 0.299,
+      "step": 2500
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 0.0178547166287899,
+      "learning_rate": 2.962962962962963e-06,
+      "loss": 0.0004,
+      "step": 2750
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.9965,
+      "eval_loss": 0.014693325385451317,
+      "eval_runtime": 116.2834,
+      "eval_samples_per_second": 17.199,
+      "eval_steps_per_second": 0.275,
+      "step": 2750
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 0.0006140907644294202,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.0004,
+      "step": 3000
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.997,
+      "eval_loss": 0.015538069419562817,
+      "eval_runtime": 106.5951,
+      "eval_samples_per_second": 18.763,
+      "eval_steps_per_second": 0.3,
+      "step": 3000
     }
   ],
   "logging_steps": 500,
@@ -106,7 +218,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.25662594514944e+18,
+  "total_flos": 1.5015902268358656e+19,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null