Training in progress, epoch 7

config.json

@@ -37,6 +37,7 @@
   "num_channels": 3,
   "num_hidden_layers": 12,
   "patch_size": 16,
+  "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
   "transformers_version": "4.48.3"

logs/events.out.tfevents.1740279507.ca6c489f7bbc.211.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5ee7d589489c266f9817061978e4cc9387ac795e990cd1c66d1592b877a06fa
-size 88
+oid sha256:fb8b86891810f646b16aac0f694cb07a0885020038f9cfddb880b19fdb0f4ea6
+size 6207

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da2f6462bca9e2f26378c0f3b365eebd7400b0cf3315bf37696cfa18cb9f561b
+oid sha256:e990f741f3d16a7e2400e3454a86abcfac9513d6eb304b9337bd55af5e696b2a
 size 343242432

trainer_state.json

@@ -1,13 +1,110 @@
 {
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0,
+  "best_metric": 0.33733510971069336,
+  "best_model_checkpoint": "./drive/Shareddrives/CS198-Drones/training_output/deit-base-patch16-224_rice-leaf-disease-augmented-v2_fft/checkpoint-625",
+  "epoch": 6.0,
   "eval_steps": 500,
-  "global_step": 0,
+  "global_step": 750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
-  "log_history": [],
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.686120510101318,
+      "learning_rate": 6.648936170212767e-06,
+      "loss": 1.7917,
+      "step": 125
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6577380952380952,
+      "eval_loss": 1.1504415273666382,
+      "eval_runtime": 11.3266,
+      "eval_samples_per_second": 29.665,
+      "eval_steps_per_second": 0.53,
+      "step": 125
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.867942810058594,
+      "learning_rate": 9.703046095022297e-06,
+      "loss": 0.6305,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8363095238095238,
+      "eval_loss": 0.4746471643447876,
+      "eval_runtime": 9.8952,
+      "eval_samples_per_second": 33.956,
+      "eval_steps_per_second": 0.606,
+      "step": 250
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.280466079711914,
+      "learning_rate": 7.5107439088023845e-06,
+      "loss": 0.1802,
+      "step": 375
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8630952380952381,
+      "eval_loss": 0.3663015365600586,
+      "eval_runtime": 10.04,
+      "eval_samples_per_second": 33.466,
+      "eval_steps_per_second": 0.598,
+      "step": 375
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.4570915400981903,
+      "learning_rate": 4.142968791110455e-06,
+      "loss": 0.0508,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8690476190476191,
+      "eval_loss": 0.35500943660736084,
+      "eval_runtime": 11.1518,
+      "eval_samples_per_second": 30.13,
+      "eval_steps_per_second": 0.538,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.29631155729293823,
+      "learning_rate": 1.1764361035781708e-06,
+      "loss": 0.0152,
+      "step": 625
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8839285714285714,
+      "eval_loss": 0.33733510971069336,
+      "eval_runtime": 11.3148,
+      "eval_samples_per_second": 29.695,
+      "eval_steps_per_second": 0.53,
+      "step": 625
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.2556553781032562,
+      "learning_rate": 8.669807672334606e-12,
+      "loss": 0.0092,
+      "step": 750
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8839285714285714,
+      "eval_loss": 0.34325936436653137,
+      "eval_runtime": 10.8405,
+      "eval_samples_per_second": 30.995,
+      "eval_steps_per_second": 0.553,
+      "step": 750
+    }
+  ],
   "logging_steps": 500,
   "max_steps": 1875,
   "num_input_tokens_seen": 0,
@@ -19,13 +116,13 @@
         "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": 3.719815527923712e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null