Training in progress, epoch 11

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.1738541012.b7e596cebf8e.5776.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52a3357c170cc7a7145c6c09b4767d9d3a31ef3fc9bc9751b0ad45c37b4bfd9d
-size 88
+oid sha256:3073f44578b399f9d4ce8fb77dccc21b04a1bf7d062807f0deacedaefd927274
+size 6535

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:928a086c95ce1b001b4053d933778e881e77cf1e5279985e397e773e17ac4d4d
+oid sha256:4d3e256c94cba90f4d2445d12c7ac054cf13b37f8a96e2b2d11d3563898fe880
 size 346396816

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.047148410230875015,
-  "best_model_checkpoint": "./drive/Shareddrives/CS198-Drones/training_output/dinov2-base_rice-leaf-disease-augmented_t_020225/checkpoint-750",
-  "epoch": 3.0,
+  "best_metric": 0.00931523460894823,
+  "best_model_checkpoint": "./drive/Shareddrives/CS198-Drones/training_output/dinov2-base_rice-leaf-disease-augmented_t_020225/checkpoint-1750",
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 750,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -55,6 +55,118 @@
       "eval_samples_per_second": 18.689,
       "eval_steps_per_second": 0.299,
       "step": 750
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 11.413514137268066,
+      "learning_rate": 8.148148148148148e-06,
+      "loss": 0.0177,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.986,
+      "eval_loss": 0.047092683613300323,
+      "eval_runtime": 116.0163,
+      "eval_samples_per_second": 17.239,
+      "eval_steps_per_second": 0.276,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.018265413120388985,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.0101,
+      "step": 1250
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9945,
+      "eval_loss": 0.016437631100416183,
+      "eval_runtime": 115.0025,
+      "eval_samples_per_second": 17.391,
+      "eval_steps_per_second": 0.278,
+      "step": 1250
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.26411858201026917,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.008,
+      "step": 1500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.992,
+      "eval_loss": 0.029763367027044296,
+      "eval_runtime": 116.4617,
+      "eval_samples_per_second": 17.173,
+      "eval_steps_per_second": 0.275,
+      "step": 1500
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.0010479438351467252,
+      "learning_rate": 5.925925925925926e-06,
+      "loss": 0.0014,
+      "step": 1750
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9965,
+      "eval_loss": 0.00931523460894823,
+      "eval_runtime": 114.6198,
+      "eval_samples_per_second": 17.449,
+      "eval_steps_per_second": 0.279,
+      "step": 1750
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.007462013512849808,
+      "learning_rate": 5.185185185185185e-06,
+      "loss": 0.0008,
+      "step": 2000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.997,
+      "eval_loss": 0.013774478808045387,
+      "eval_runtime": 117.2101,
+      "eval_samples_per_second": 17.063,
+      "eval_steps_per_second": 0.273,
+      "step": 2000
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.0013718679547309875,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.0007,
+      "step": 2250
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.997,
+      "eval_loss": 0.010827419348061085,
+      "eval_runtime": 115.4895,
+      "eval_samples_per_second": 17.318,
+      "eval_steps_per_second": 0.277,
+      "step": 2250
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.0020830812864005566,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 0.0013,
+      "step": 2500
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9975,
+      "eval_loss": 0.011723974719643593,
+      "eval_runtime": 116.8921,
+      "eval_samples_per_second": 17.11,
+      "eval_steps_per_second": 0.274,
+      "step": 2500
     }
   ],
   "logging_steps": 500,
@@ -74,7 +186,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.753975567089664e+18,
+  "total_flos": 1.251325189029888e+19,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null