Training in progress, epoch 1

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.1740283925.ca6c489f7bbc.211.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a3552fb4cd66c14f5fae71427cd63fa0add1088e1bd4f48172fa49d3b80301d
-size 88
+oid sha256:32954df55bade1fee3deeff8b772e548a50886daab72f7b113ff5604bb3de16b
+size 7019

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efa9afb7089f2aa3b84b697dbe29fea573bfcbadb182863f9bc6cda186ef29ff
+oid sha256:fec57a3f7dabbd92bcab71d9565d59359e5ab6a20ad1d28d7d1b25278093c81b
 size 343098784

trainer_state.json

@@ -1,263 +1,13 @@
 {
-  "best_metric": 0.3260420858860016,
-  "best_model_checkpoint": "./drive/Shareddrives/CS198-Drones/training_output/beit-base-patch16-224_rice-leaf-disease-augmented-v2_fft/checkpoint-375",
-  "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": 9.300188064575195,
-      "learning_rate": 6.524064171122996e-06,
-      "loss": 1.5633,
-      "step": 125
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.7797619047619048,
-      "eval_loss": 0.6928136944770813,
-      "eval_runtime": 12.0343,
-      "eval_samples_per_second": 27.92,
-      "eval_steps_per_second": 0.499,
-      "step": 125
-    },
-    {
-      "epoch": 2.0,
-      "grad_norm": 10.518802642822266,
-      "learning_rate": 9.883929099922349e-06,
-      "loss": 0.4092,
-      "step": 250
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.8690476190476191,
-      "eval_loss": 0.3738097846508026,
-      "eval_runtime": 12.1178,
-      "eval_samples_per_second": 27.728,
-      "eval_steps_per_second": 0.495,
-      "step": 250
-    },
-    {
-      "epoch": 3.0,
-      "grad_norm": 5.8602752685546875,
-      "learning_rate": 8.884167663453091e-06,
-      "loss": 0.1327,
-      "step": 375
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.9047619047619048,
-      "eval_loss": 0.3260420858860016,
-      "eval_runtime": 12.0126,
-      "eval_samples_per_second": 27.971,
-      "eval_steps_per_second": 0.499,
-      "step": 375
-    },
-    {
-      "epoch": 4.0,
-      "grad_norm": 4.471620082855225,
-      "learning_rate": 7.0585894873794514e-06,
-      "loss": 0.0433,
-      "step": 500
-    },
-    {
-      "epoch": 4.0,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_loss": 0.34726911783218384,
-      "eval_runtime": 11.5003,
-      "eval_samples_per_second": 29.217,
-      "eval_steps_per_second": 0.522,
-      "step": 500
-    },
-    {
-      "epoch": 5.0,
-      "grad_norm": 0.4554196298122406,
-      "learning_rate": 4.7953325584941465e-06,
-      "loss": 0.019,
-      "step": 625
-    },
-    {
-      "epoch": 5.0,
-      "eval_accuracy": 0.9196428571428571,
-      "eval_loss": 0.3815436065196991,
-      "eval_runtime": 12.0802,
-      "eval_samples_per_second": 27.814,
-      "eval_steps_per_second": 0.497,
-      "step": 625
-    },
-    {
-      "epoch": 6.0,
-      "grad_norm": 0.5961848497390747,
-      "learning_rate": 2.7317059402422887e-06,
-      "loss": 0.0116,
-      "step": 750
-    },
-    {
-      "epoch": 6.0,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_loss": 0.4082700312137604,
-      "eval_runtime": 10.577,
-      "eval_samples_per_second": 31.767,
-      "eval_steps_per_second": 0.567,
-      "step": 750
-    },
-    {
-      "epoch": 7.0,
-      "grad_norm": 0.2265198975801468,
-      "learning_rate": 9.989992910524462e-06,
-      "loss": 0.0072,
-      "step": 875
-    },
-    {
-      "epoch": 7.0,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_loss": 0.44227680563926697,
-      "eval_runtime": 10.7145,
-      "eval_samples_per_second": 31.359,
-      "eval_steps_per_second": 0.56,
-      "step": 875
-    },
-    {
-      "epoch": 8.0,
-      "grad_norm": 0.09561679512262344,
-      "learning_rate": 6.687734491723899e-06,
-      "loss": 0.0078,
-      "step": 1000
-    },
-    {
-      "epoch": 8.0,
-      "eval_accuracy": 0.9226190476190477,
-      "eval_loss": 0.48087066411972046,
-      "eval_runtime": 10.6527,
-      "eval_samples_per_second": 31.541,
-      "eval_steps_per_second": 0.563,
-      "step": 1000
-    },
-    {
-      "epoch": 9.0,
-      "grad_norm": 0.06357914209365845,
-      "learning_rate": 1.3799679245093633e-06,
-      "loss": 0.007,
-      "step": 1125
-    },
-    {
-      "epoch": 9.0,
-      "eval_accuracy": 0.9196428571428571,
-      "eval_loss": 0.4225828945636749,
-      "eval_runtime": 9.622,
-      "eval_samples_per_second": 34.92,
-      "eval_steps_per_second": 0.624,
-      "step": 1125
-    },
-    {
-      "epoch": 10.0,
-      "grad_norm": 1.7639108896255493,
-      "learning_rate": 9.601392291702693e-06,
-      "loss": 0.0053,
-      "step": 1250
-    },
-    {
-      "epoch": 10.0,
-      "eval_accuracy": 0.9047619047619048,
-      "eval_loss": 0.5498608946800232,
-      "eval_runtime": 11.0412,
-      "eval_samples_per_second": 30.431,
-      "eval_steps_per_second": 0.543,
-      "step": 1250
-    },
-    {
-      "epoch": 11.0,
-      "grad_norm": 0.150970920920372,
-      "learning_rate": 5.074442573016012e-06,
-      "loss": 0.0064,
-      "step": 1375
-    },
-    {
-      "epoch": 11.0,
-      "eval_accuracy": 0.9077380952380952,
-      "eval_loss": 0.5284379720687866,
-      "eval_runtime": 10.8395,
-      "eval_samples_per_second": 30.998,
-      "eval_steps_per_second": 0.554,
-      "step": 1375
-    },
-    {
-      "epoch": 12.0,
-      "grad_norm": 0.03461284562945366,
-      "learning_rate": 4.396198449987288e-07,
-      "loss": 0.0037,
-      "step": 1500
-    },
-    {
-      "epoch": 12.0,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_loss": 0.5137431621551514,
-      "eval_runtime": 10.6292,
-      "eval_samples_per_second": 31.611,
-      "eval_steps_per_second": 0.564,
-      "step": 1500
-    },
-    {
-      "epoch": 13.0,
-      "grad_norm": 1.6548749208450317,
-      "learning_rate": 8.689877388713784e-06,
-      "loss": 0.0056,
-      "step": 1625
-    },
-    {
-      "epoch": 13.0,
-      "eval_accuracy": 0.9136904761904762,
-      "eval_loss": 0.555907666683197,
-      "eval_runtime": 10.5418,
-      "eval_samples_per_second": 31.873,
-      "eval_steps_per_second": 0.569,
-      "step": 1625
-    },
-    {
-      "epoch": 14.0,
-      "grad_norm": 0.4239642322063446,
-      "learning_rate": 3.453145092452331e-06,
-      "loss": 0.0077,
-      "step": 1750
-    },
-    {
-      "epoch": 14.0,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_loss": 0.5193145275115967,
-      "eval_runtime": 10.5774,
-      "eval_samples_per_second": 31.766,
-      "eval_steps_per_second": 0.567,
-      "step": 1750
-    },
-    {
-      "epoch": 15.0,
-      "grad_norm": 0.052128296345472336,
-      "learning_rate": 2.1633234416539305e-08,
-      "loss": 0.0037,
-      "step": 1875
-    },
-    {
-      "epoch": 15.0,
-      "eval_accuracy": 0.9136904761904762,
-      "eval_loss": 0.5215830206871033,
-      "eval_runtime": 21.3118,
-      "eval_samples_per_second": 15.766,
-      "eval_steps_per_second": 0.282,
-      "step": 1875
-    },
-    {
-      "epoch": 15.0,
-      "step": 1875,
-      "total_flos": 9.29556430258176e+18,
-      "train_loss": 0.0018048280239105225,
-      "train_runtime": 1746.5831,
-      "train_samples_per_second": 68.706,
-      "train_steps_per_second": 1.074
-    }
-  ],
+  "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": 9.29556430258176e+18,
+  "total_flos": 0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null