Training in progress, epoch 14

config.json

@@ -55,6 +55,7 @@
     3,
     6
   ],
+  "problem_type": "single_label_classification",
   "reshape_hidden_states": true,
   "semantic_loss_ignore_index": 255,
   "stage_names": [

logs/events.out.tfevents.1738411542.6d188e23525e.4440.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9793614b6671004b3bac0e96204fdd9c1354cae4adb5e32ba1fc083d4bc39ba0
-size 88
+oid sha256:4360dece7a30ab822062a5a2a25e15221c5e2346771053a47a16768bfde8aa55
+size 7003

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baa6fa2bbfa95f79bf67d497356fa5120c2c6e7ea80c951a4d8807e664ec2ff1
+oid sha256:1ad2d525de9a8fc14d75c1342d1226bfa2449b2d58b1edbb474a2147e6e88224
 size 343098784

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5041353702545166,
-  "best_model_checkpoint": "./drive/Shareddrives/CS198-Drones/training_output/beit-base-patch16-224_rice-leaf-disease-augmented_tl_020125/checkpoint-1750",
-  "epoch": 7.0,
+  "best_metric": 0.43980079889297485,
+  "best_model_checkpoint": "./drive/Shareddrives/CS198-Drones/training_output/beit-base-patch16-224_rice-leaf-disease-augmented_tl_020125/checkpoint-3250",
+  "epoch": 13.0,
   "eval_steps": 500,
-  "global_step": 1750,
+  "global_step": 3250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,102 @@
       "eval_samples_per_second": 22.807,
       "eval_steps_per_second": 0.365,
       "step": 1750
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.690420150756836,
+      "learning_rate": 5.185185185185185e-05,
+      "loss": 0.5244,
+      "step": 2000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.844,
+      "eval_loss": 0.4841882288455963,
+      "eval_runtime": 89.4014,
+      "eval_samples_per_second": 22.371,
+      "eval_steps_per_second": 0.358,
+      "step": 2000
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 3.189504623413086,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.5081,
+      "step": 2250
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.843,
+      "eval_loss": 0.4707326591014862,
+      "eval_runtime": 89.3049,
+      "eval_samples_per_second": 22.395,
+      "eval_steps_per_second": 0.358,
+      "step": 2250
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.4485363960266113,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.493,
+      "step": 2500
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8475,
+      "eval_loss": 0.4588555097579956,
+      "eval_runtime": 87.1428,
+      "eval_samples_per_second": 22.951,
+      "eval_steps_per_second": 0.367,
+      "step": 2500
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 2.1555464267730713,
+      "learning_rate": 2.962962962962963e-05,
+      "loss": 0.4824,
+      "step": 2750
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.85,
+      "eval_loss": 0.45093804597854614,
+      "eval_runtime": 86.5567,
+      "eval_samples_per_second": 23.106,
+      "eval_steps_per_second": 0.37,
+      "step": 2750
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 2.3292956352233887,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.4759,
+      "step": 3000
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.853,
+      "eval_loss": 0.4436955153942108,
+      "eval_runtime": 86.9601,
+      "eval_samples_per_second": 22.999,
+      "eval_steps_per_second": 0.368,
+      "step": 3000
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 2.5893406867980957,
+      "learning_rate": 1.4814814814814815e-05,
+      "loss": 0.4677,
+      "step": 3250
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.855,
+      "eval_loss": 0.43980079889297485,
+      "eval_runtime": 87.1496,
+      "eval_samples_per_second": 22.949,
+      "eval_steps_per_second": 0.367,
+      "step": 3250
     }
   ],
   "logging_steps": 500,
@@ -138,7 +234,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.675860015742976e+18,
+  "total_flos": 1.6112311457808384e+19,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null