Training in progress, epoch 1

config.json

@@ -57,6 +57,7 @@
   ],
   "patch_size": 4,
   "path_norm": true,
+  "problem_type": "single_label_classification",
   "qkv_bias": true,
   "stage_names": [
     "stem",

logs/events.out.tfevents.1740281118.c59d799b8436.377.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f00bd5822379c857cc8b37027afe61b1b96dc308f913672f4b5d5c23b1dfa51
-size 88
+oid sha256:896215c191341dd1a8205cbc6455a3ed9524f79b681f3931847aeb26f08c2587
+size 6589

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8159ec2fc2e32290c999f338c3c4b05b8a5af21a1fe3b3d7ec6309b238fdaa4b
+oid sha256:c66f92bdf1001f104cec70620455422d1479bde4f8f6728a50cf0765622332fd
 size 347523416

trainer_state.json

@@ -1,158 +1,13 @@
 {
-  "best_metric": 0.3934735655784607,
-  "best_model_checkpoint": "./drive/Shareddrives/CS198-Drones/training_output/swin-base-patch4-window7-224_rice-leaf-disease-augmented-v2_fft/checkpoint-375",
-  "epoch": 9.0,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0,
   "eval_steps": 500,
-  "global_step": 1125,
+  "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": 7.30280876159668,
-      "learning_rate": 6.577540106951872e-06,
-      "loss": 1.6649,
-      "step": 125
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.7351190476190477,
-      "eval_loss": 0.8050427436828613,
-      "eval_runtime": 14.2308,
-      "eval_samples_per_second": 23.611,
-      "eval_steps_per_second": 0.422,
-      "step": 125
-    },
-    {
-      "epoch": 2.0,
-      "grad_norm": 6.75390100479126,
-      "learning_rate": 9.871664184437119e-06,
-      "loss": 0.431,
-      "step": 250
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.8511904761904762,
-      "eval_loss": 0.45273008942604065,
-      "eval_runtime": 13.8146,
-      "eval_samples_per_second": 24.322,
-      "eval_steps_per_second": 0.434,
-      "step": 250
-    },
-    {
-      "epoch": 3.0,
-      "grad_norm": 8.129321098327637,
-      "learning_rate": 8.848767222994402e-06,
-      "loss": 0.1233,
-      "step": 375
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.8928571428571429,
-      "eval_loss": 0.3934735655784607,
-      "eval_runtime": 14.0064,
-      "eval_samples_per_second": 23.989,
-      "eval_steps_per_second": 0.428,
-      "step": 375
-    },
-    {
-      "epoch": 4.0,
-      "grad_norm": 1.9338823556900024,
-      "learning_rate": 7.007580044706666e-06,
-      "loss": 0.0326,
-      "step": 500
-    },
-    {
-      "epoch": 4.0,
-      "eval_accuracy": 0.9077380952380952,
-      "eval_loss": 0.4275733530521393,
-      "eval_runtime": 13.7209,
-      "eval_samples_per_second": 24.488,
-      "eval_steps_per_second": 0.437,
-      "step": 500
-    },
-    {
-      "epoch": 5.0,
-      "grad_norm": 0.1951848417520523,
-      "learning_rate": 4.739559281809819e-06,
-      "loss": 0.01,
-      "step": 625
-    },
-    {
-      "epoch": 5.0,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_loss": 0.45519202947616577,
-      "eval_runtime": 13.6317,
-      "eval_samples_per_second": 24.648,
-      "eval_steps_per_second": 0.44,
-      "step": 625
-    },
-    {
-      "epoch": 6.0,
-      "grad_norm": 0.07782671600580215,
-      "learning_rate": 2.5674558357271096e-06,
-      "loss": 0.0049,
-      "step": 750
-    },
-    {
-      "epoch": 6.0,
-      "eval_accuracy": 0.9077380952380952,
-      "eval_loss": 0.4804078936576843,
-      "eval_runtime": 12.6134,
-      "eval_samples_per_second": 26.638,
-      "eval_steps_per_second": 0.476,
-      "step": 750
-    },
-    {
-      "epoch": 7.0,
-      "grad_norm": 0.7393015623092651,
-      "learning_rate": 9.974770025621516e-06,
-      "loss": 0.0024,
-      "step": 875
-    },
-    {
-      "epoch": 7.0,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_loss": 0.4863254427909851,
-      "eval_runtime": 12.7829,
-      "eval_samples_per_second": 26.285,
-      "eval_steps_per_second": 0.469,
-      "step": 875
-    },
-    {
-      "epoch": 8.0,
-      "grad_norm": 0.14619985222816467,
-      "learning_rate": 6.511415799458836e-06,
-      "loss": 0.005,
-      "step": 1000
-    },
-    {
-      "epoch": 8.0,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_loss": 0.5142239332199097,
-      "eval_runtime": 12.7007,
-      "eval_samples_per_second": 26.455,
-      "eval_steps_per_second": 0.472,
-      "step": 1000
-    },
-    {
-      "epoch": 9.0,
-      "grad_norm": 0.16888085007667542,
-      "learning_rate": 1.2234689624958324e-06,
-      "loss": 0.0026,
-      "step": 1125
-    },
-    {
-      "epoch": 9.0,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_loss": 0.5233145952224731,
-      "eval_runtime": 12.5815,
-      "eval_samples_per_second": 26.706,
-      "eval_steps_per_second": 0.477,
-      "step": 1125
-    }
-  ],
+  "log_history": [],
   "logging_steps": 500,
   "max_steps": 1875,
   "num_input_tokens_seen": 0,
@@ -164,13 +19,13 @@
         "should_epoch_stop": false,
         "should_evaluate": false,
         "should_log": false,
-        "should_save": true,
+        "should_save": false,
         "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.761627233139556e+18,
+  "total_flos": 0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null