Training in progress, epoch 1

all_results.json

@@ -1,13 +1,8 @@
 {
-    "epoch": 1.0,
-    "eval_accuracy": 0.78125,
-    "eval_loss": 0.660746157169342,
-    "eval_runtime": 2.4294,
-    "eval_samples_per_second": 13.172,
-    "eval_steps_per_second": 0.412,
-    "total_flos": 5924677556367360.0,
-    "train_loss": 2.0297837257385254,
-    "train_runtime": 23.3143,
-    "train_samples_per_second": 598.345,
-    "train_steps_per_second": 4.289
+    "epoch": 13.0,
+    "total_flos": 7.702080823277568e+16,
+    "train_loss": 1.9811313824775891,
+    "train_runtime": 3450.3358,
+    "train_samples_per_second": 4.043,
+    "train_steps_per_second": 0.029
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6a62e27f85591dc752f0b37a26e314bfd7da38290e78757298ec3e5c5e16540
+oid sha256:224b58631c5e2b3ba0ffaea37b124a52bd6753a485de45ac4e74c802c5e70a14
 size 94302952

runs/Jan09_05-37-46_a7a68c73dff9/events.out.tfevents.1736405236.a7a68c73dff9.381.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5fbdc71f0190782370124fdc5ad43317fc46f85528dccf70655d6273b1c8ef0
+size 5518

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 1.0,
-    "total_flos": 5924677556367360.0,
-    "train_loss": 2.0297837257385254,
-    "train_runtime": 23.3143,
-    "train_samples_per_second": 598.345,
-    "train_steps_per_second": 4.289
+    "epoch": 13.0,
+    "total_flos": 7.702080823277568e+16,
+    "train_loss": 1.9811313824775891,
+    "train_runtime": 3450.3358,
+    "train_samples_per_second": 4.043,
+    "train_steps_per_second": 0.029
 }

trainer_state.json

@@ -1,30 +1,159 @@
 {
-  "best_metric": 0.6875,
-  "best_model_checkpoint": "resnet-50-finetuned-eurosat/checkpoint-3",
-  "epoch": 1.0,
+  "best_metric": 0.5625,
+  "best_model_checkpoint": "resnet-50-finetuned-eurosat/checkpoint-9",
+  "epoch": 13.0,
   "eval_steps": 500,
-  "global_step": 3,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6875,
-      "eval_loss": 0.6569108963012695,
-      "eval_runtime": 3.4447,
-      "eval_samples_per_second": 9.29,
-      "eval_steps_per_second": 0.29,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.6890198588371277,
+      "eval_runtime": 9.1578,
+      "eval_samples_per_second": 3.494,
+      "eval_steps_per_second": 0.109,
       "step": 3
     },
     {
-      "epoch": 1.0,
-      "step": 3,
-      "total_flos": 5924677556367360.0,
-      "train_loss": 2.0297837257385254,
-      "train_runtime": 23.3143,
-      "train_samples_per_second": 598.345,
-      "train_steps_per_second": 4.289
+      "epoch": 2.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.6856250166893005,
+      "eval_runtime": 9.6892,
+      "eval_samples_per_second": 3.303,
+      "eval_steps_per_second": 0.103,
+      "step": 6
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5625,
+      "eval_loss": 0.6796374917030334,
+      "eval_runtime": 8.1871,
+      "eval_samples_per_second": 3.909,
+      "eval_steps_per_second": 0.122,
+      "step": 9
+    },
+    {
+      "epoch": 3.4444444444444446,
+      "grad_norm": 6.238272666931152,
+      "learning_rate": 5e-05,
+      "loss": 2.1334,
+      "step": 10
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.53125,
+      "eval_loss": 0.6711597442626953,
+      "eval_runtime": 11.5033,
+      "eval_samples_per_second": 2.782,
+      "eval_steps_per_second": 0.087,
+      "step": 12
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.53125,
+      "eval_loss": 0.6669355630874634,
+      "eval_runtime": 9.588,
+      "eval_samples_per_second": 3.338,
+      "eval_steps_per_second": 0.104,
+      "step": 15
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.53125,
+      "eval_loss": 0.6575976610183716,
+      "eval_runtime": 7.9262,
+      "eval_samples_per_second": 4.037,
+      "eval_steps_per_second": 0.126,
+      "step": 18
+    },
+    {
+      "epoch": 6.888888888888889,
+      "grad_norm": 4.825995445251465,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 2.0715,
+      "step": 20
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.53125,
+      "eval_loss": 0.6581233739852905,
+      "eval_runtime": 9.5086,
+      "eval_samples_per_second": 3.365,
+      "eval_steps_per_second": 0.105,
+      "step": 21
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5625,
+      "eval_loss": 0.6548225283622742,
+      "eval_runtime": 9.6182,
+      "eval_samples_per_second": 3.327,
+      "eval_steps_per_second": 0.104,
+      "step": 24
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.5625,
+      "eval_loss": 0.6479971408843994,
+      "eval_runtime": 9.7014,
+      "eval_samples_per_second": 3.298,
+      "eval_steps_per_second": 0.103,
+      "step": 27
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.082106828689575,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 1.8148,
+      "step": 30
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.5625,
+      "eval_loss": 0.6456948518753052,
+      "eval_runtime": 7.9377,
+      "eval_samples_per_second": 4.031,
+      "eval_steps_per_second": 0.126,
+      "step": 30
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.5625,
+      "eval_loss": 0.6377989649772644,
+      "eval_runtime": 9.4096,
+      "eval_samples_per_second": 3.401,
+      "eval_steps_per_second": 0.106,
+      "step": 33
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.5625,
+      "eval_loss": 0.6368027925491333,
+      "eval_runtime": 8.4914,
+      "eval_samples_per_second": 3.769,
+      "eval_steps_per_second": 0.118,
+      "step": 36
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.5625,
+      "eval_loss": 0.6324682235717773,
+      "eval_runtime": 9.2297,
+      "eval_samples_per_second": 3.467,
+      "eval_steps_per_second": 0.108,
+      "step": 39
+    },
+    {
+      "epoch": 13.0,
+      "step": 39,
+      "total_flos": 7.702080823277568e+16,
+      "train_loss": 1.9811313824775891,
+      "train_runtime": 3450.3358,
+      "train_samples_per_second": 4.043,
+      "train_steps_per_second": 0.029
     }
   ],
   "logging_steps": 10,
@@ -35,11 +164,11 @@
   "stateful_callbacks": {
     "EarlyStoppingCallback": {
       "args": {
-        "early_stopping_patience": 0,
+        "early_stopping_patience": 10,
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 10
       }
     },
     "TrainerControl": {
@@ -53,7 +182,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5924677556367360.0,
+  "total_flos": 7.702080823277568e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null