Training in progress, epoch 1

config.json

@@ -48,6 +48,7 @@
   "out_indices": [
     4
   ],
+  "problem_type": "single_label_classification",
   "stage_names": [
     "stem",
     "stage1",

logs/events.out.tfevents.1740284504.a837d8c25e39.930.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a20ef5f0d171bad8bc022f1b0428bfdec03b60be83da7ba58a80cf79fa5d52f
-size 88
+oid sha256:bc76c8c2d41b07ebbb87412431c9d2f82ad6abbdecd844e27156fe31923be6b9
+size 6263

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:839860602f3a191ee8ba132b71280186bb2246bff269f4c6b563f35969aaee8f
+oid sha256:85767a6627f568c2d69712cc3bcd9a814fa125dc37b1607f764606474d7a7f0f
 size 94352152

trainer_state.json

@@ -1,263 +1,13 @@
 {
-  "best_metric": 0.8533294200897217,
-  "best_model_checkpoint": "./drive/Shareddrives/CS198-Drones/training_output/resnet-50_rice-leaf-disease-augmented-v2_fft/checkpoint-1750",
-  "epoch": 15.0,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0,
   "eval_steps": 500,
-  "global_step": 1875,
+  "global_step": 0,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 1.0,
-      "grad_norm": 1.1328648328781128,
-      "learning_rate": 6.684491978609626e-06,
-      "loss": 2.0458,
-      "step": 125
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.40773809523809523,
-      "eval_loss": 1.9620426893234253,
-      "eval_runtime": 13.3599,
-      "eval_samples_per_second": 25.15,
-      "eval_steps_per_second": 0.449,
-      "step": 125
-    },
-    {
-      "epoch": 2.0,
-      "grad_norm": 1.9301390647888184,
-      "learning_rate": 9.863149989091216e-06,
-      "loss": 1.8522,
-      "step": 250
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.5297619047619048,
-      "eval_loss": 1.7117981910705566,
-      "eval_runtime": 13.4512,
-      "eval_samples_per_second": 24.979,
-      "eval_steps_per_second": 0.446,
-      "step": 250
-    },
-    {
-      "epoch": 3.0,
-      "grad_norm": 2.323911666870117,
-      "learning_rate": 8.824900028711128e-06,
-      "loss": 1.6181,
-      "step": 375
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.5476190476190477,
-      "eval_loss": 1.511465072631836,
-      "eval_runtime": 13.4937,
-      "eval_samples_per_second": 24.901,
-      "eval_steps_per_second": 0.445,
-      "step": 375
-    },
-    {
-      "epoch": 4.0,
-      "grad_norm": 2.650306463241577,
-      "learning_rate": 6.973434279336284e-06,
-      "loss": 1.4376,
-      "step": 500
-    },
-    {
-      "epoch": 4.0,
-      "eval_accuracy": 0.6041666666666666,
-      "eval_loss": 1.3706637620925903,
-      "eval_runtime": 13.2381,
-      "eval_samples_per_second": 25.381,
-      "eval_steps_per_second": 0.453,
-      "step": 500
-    },
-    {
-      "epoch": 5.0,
-      "grad_norm": 2.9543614387512207,
-      "learning_rate": 4.7023947103966636e-06,
-      "loss": 1.3093,
-      "step": 625
-    },
-    {
-      "epoch": 5.0,
-      "eval_accuracy": 0.6220238095238095,
-      "eval_loss": 1.2791615724563599,
-      "eval_runtime": 13.3535,
-      "eval_samples_per_second": 25.162,
-      "eval_steps_per_second": 0.449,
-      "step": 625
-    },
-    {
-      "epoch": 6.0,
-      "grad_norm": 2.6454391479492188,
-      "learning_rate": 2.494629297272126e-06,
-      "loss": 1.2299,
-      "step": 750
-    },
-    {
-      "epoch": 6.0,
-      "eval_accuracy": 0.6369047619047619,
-      "eval_loss": 1.2290029525756836,
-      "eval_runtime": 13.6734,
-      "eval_samples_per_second": 24.573,
-      "eval_steps_per_second": 0.439,
-      "step": 750
-    },
-    {
-      "epoch": 7.0,
-      "grad_norm": 3.4624359607696533,
-      "learning_rate": 8.195332343135171e-07,
-      "loss": 1.1881,
-      "step": 875
-    },
-    {
-      "epoch": 7.0,
-      "eval_accuracy": 0.6398809523809523,
-      "eval_loss": 1.2191029787063599,
-      "eval_runtime": 13.6338,
-      "eval_samples_per_second": 24.645,
-      "eval_steps_per_second": 0.44,
-      "step": 875
-    },
-    {
-      "epoch": 8.0,
-      "grad_norm": 3.2420051097869873,
-      "learning_rate": 3.325035698205359e-08,
-      "loss": 1.1751,
-      "step": 1000
-    },
-    {
-      "epoch": 8.0,
-      "eval_accuracy": 0.6488095238095238,
-      "eval_loss": 1.2101922035217285,
-      "eval_runtime": 13.2305,
-      "eval_samples_per_second": 25.396,
-      "eval_steps_per_second": 0.453,
-      "step": 1000
-    },
-    {
-      "epoch": 9.0,
-      "grad_norm": 3.5106637477874756,
-      "learning_rate": 9.697046952264565e-06,
-      "loss": 1.1347,
-      "step": 1125
-    },
-    {
-      "epoch": 9.0,
-      "eval_accuracy": 0.6428571428571429,
-      "eval_loss": 1.1266306638717651,
-      "eval_runtime": 13.4879,
-      "eval_samples_per_second": 24.911,
-      "eval_steps_per_second": 0.445,
-      "step": 1125
-    },
-    {
-      "epoch": 10.0,
-      "grad_norm": 4.020257472991943,
-      "learning_rate": 8.428700450023544e-06,
-      "loss": 1.0039,
-      "step": 1250
-    },
-    {
-      "epoch": 10.0,
-      "eval_accuracy": 0.6726190476190477,
-      "eval_loss": 1.0349254608154297,
-      "eval_runtime": 13.2834,
-      "eval_samples_per_second": 25.295,
-      "eval_steps_per_second": 0.452,
-      "step": 1250
-    },
-    {
-      "epoch": 11.0,
-      "grad_norm": 4.034997463226318,
-      "learning_rate": 6.431374544200013e-06,
-      "loss": 0.907,
-      "step": 1375
-    },
-    {
-      "epoch": 11.0,
-      "eval_accuracy": 0.6934523809523809,
-      "eval_loss": 0.9688853025436401,
-      "eval_runtime": 13.1006,
-      "eval_samples_per_second": 25.648,
-      "eval_steps_per_second": 0.458,
-      "step": 1375
-    },
-    {
-      "epoch": 12.0,
-      "grad_norm": 3.91182804107666,
-      "learning_rate": 4.129722676764128e-06,
-      "loss": 0.8387,
-      "step": 1500
-    },
-    {
-      "epoch": 12.0,
-      "eval_accuracy": 0.6904761904761905,
-      "eval_loss": 0.9262328147888184,
-      "eval_runtime": 13.2928,
-      "eval_samples_per_second": 25.277,
-      "eval_steps_per_second": 0.451,
-      "step": 1500
-    },
-    {
-      "epoch": 13.0,
-      "grad_norm": 3.1170542240142822,
-      "learning_rate": 8.42870045002354e-06,
-      "loss": 0.791,
-      "step": 1625
-    },
-    {
-      "epoch": 13.0,
-      "eval_accuracy": 0.7142857142857143,
-      "eval_loss": 0.8774951696395874,
-      "eval_runtime": 13.2469,
-      "eval_samples_per_second": 25.364,
-      "eval_steps_per_second": 0.453,
-      "step": 1625
-    },
-    {
-      "epoch": 14.0,
-      "grad_norm": 4.423528671264648,
-      "learning_rate": 3.018018951921804e-06,
-      "loss": 0.7244,
-      "step": 1750
-    },
-    {
-      "epoch": 14.0,
-      "eval_accuracy": 0.7113095238095238,
-      "eval_loss": 0.8533294200897217,
-      "eval_runtime": 13.4659,
-      "eval_samples_per_second": 24.952,
-      "eval_steps_per_second": 0.446,
-      "step": 1750
-    },
-    {
-      "epoch": 15.0,
-      "grad_norm": 4.605622291564941,
-      "learning_rate": 0.0,
-      "loss": 0.691,
-      "step": 1875
-    },
-    {
-      "epoch": 15.0,
-      "eval_accuracy": 0.7202380952380952,
-      "eval_loss": 0.8547136187553406,
-      "eval_runtime": 15.5224,
-      "eval_samples_per_second": 21.646,
-      "eval_steps_per_second": 0.387,
-      "step": 1875
-    },
-    {
-      "epoch": 15.0,
-      "step": 1875,
-      "total_flos": 2.54958083702784e+18,
-      "train_loss": 0.14709369303385417,
-      "train_runtime": 1218.7812,
-      "train_samples_per_second": 98.459,
-      "train_steps_per_second": 1.538
-    }
-  ],
+  "log_history": [],
   "logging_steps": 500,
   "max_steps": 1875,
   "num_input_tokens_seen": 0,
@@ -269,13 +19,13 @@
         "should_epoch_stop": false,
         "should_evaluate": false,
         "should_log": false,
-        "should_save": true,
-        "should_training_stop": true
+        "should_save": false,
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.54958083702784e+18,
+  "total_flos": 0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null