Training in progress, epoch 0

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.4,
-    "total_flos": 9545499876261888.0,
-    "train_loss": 1.3307077884674072,
-    "train_runtime": 26.0882,
-    "train_samples_per_second": 18.399,
-    "train_steps_per_second": 0.115
+    "epoch": 2.88,
+    "total_flos": 5.727299925757133e+16,
+    "train_loss": 1.1426812807718914,
+    "train_runtime": 417.2641,
+    "train_samples_per_second": 5.752,
+    "train_steps_per_second": 0.043
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6848aa2e2e2108126b7410ebeaf4967496a1eae7e865db546a85d7145c7acfbc
+oid sha256:18c3cb66951c057e21db0ced12483119238a8131cae523c129e0294c76353d67
 size 110352060

runs/Aug18_23-53-31_e8f7099b712a/events.out.tfevents.1724025679.e8f7099b712a.297.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc3f5402c97bd97e19525e86a5aff25eb522efd6878d1dda91fb7e8fae6a094e
+size 404

runs/Aug19_00-04-27_e8f7099b712a/events.out.tfevents.1724025873.e8f7099b712a.297.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eda5c25b905500eca524d41a7034fe7ea2c82043e5d6065fc21252b3b4b1bfa
+size 5878

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.4,
-    "total_flos": 9545499876261888.0,
-    "train_loss": 1.3307077884674072,
-    "train_runtime": 26.0882,
-    "train_samples_per_second": 18.399,
-    "train_steps_per_second": 0.115
+    "epoch": 2.88,
+    "total_flos": 5.727299925757133e+16,
+    "train_loss": 1.1426812807718914,
+    "train_runtime": 417.2641,
+    "train_samples_per_second": 5.752,
+    "train_steps_per_second": 0.043
 }

trainer_state.json

@@ -1,61 +1,68 @@
 {
-  "best_metric": 1.3222624063491821,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned/checkpoint-3",
-  "epoch": 2.4,
+  "best_metric": 1.0755484104156494,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned/checkpoint-18",
+  "epoch": 2.88,
   "eval_steps": 500,
-  "global_step": 3,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.8,
+      "epoch": 0.96,
       "eval_accuracy": {
-        "accuracy": 0.425
+        "accuracy": 0.415
       },
-      "eval_logLoss": 1.452716588973999,
-      "eval_loss": 1.452716588973999,
-      "eval_runtime": 0.9167,
-      "eval_samples_per_second": 43.635,
-      "eval_steps_per_second": 2.182,
-      "step": 1
+      "eval_logLoss": 1.196082353591919,
+      "eval_loss": 1.196082592010498,
+      "eval_runtime": 68.3725,
+      "eval_samples_per_second": 2.925,
+      "eval_steps_per_second": 0.102,
+      "step": 6
     },
     {
       "epoch": 1.6,
+      "grad_norm": 3.4481194019317627,
+      "learning_rate": 2.5e-05,
+      "loss": 1.2502,
+      "step": 10
+    },
+    {
+      "epoch": 1.92,
       "eval_accuracy": {
-        "accuracy": 0.4
+        "accuracy": 0.49
       },
-      "eval_logLoss": 1.3229997158050537,
-      "eval_loss": 1.3229997158050537,
-      "eval_runtime": 0.7445,
-      "eval_samples_per_second": 53.725,
-      "eval_steps_per_second": 2.686,
-      "step": 2
+      "eval_logLoss": 1.0786902904510498,
+      "eval_loss": 1.0786901712417603,
+      "eval_runtime": 4.6591,
+      "eval_samples_per_second": 42.927,
+      "eval_steps_per_second": 1.502,
+      "step": 12
     },
     {
-      "epoch": 2.4,
+      "epoch": 2.88,
       "eval_accuracy": {
-        "accuracy": 0.425
+        "accuracy": 0.48
       },
-      "eval_logLoss": 1.3222624063491821,
-      "eval_loss": 1.3222624063491821,
-      "eval_runtime": 1.3083,
-      "eval_samples_per_second": 30.575,
-      "eval_steps_per_second": 1.529,
-      "step": 3
+      "eval_logLoss": 1.0755484104156494,
+      "eval_loss": 1.0755484104156494,
+      "eval_runtime": 4.8873,
+      "eval_samples_per_second": 40.922,
+      "eval_steps_per_second": 1.432,
+      "step": 18
     },
     {
-      "epoch": 2.4,
-      "step": 3,
-      "total_flos": 9545499876261888.0,
-      "train_loss": 1.3307077884674072,
-      "train_runtime": 26.0882,
-      "train_samples_per_second": 18.399,
-      "train_steps_per_second": 0.115
+      "epoch": 2.88,
+      "step": 18,
+      "total_flos": 5.727299925757133e+16,
+      "train_loss": 1.1426812807718914,
+      "train_runtime": 417.2641,
+      "train_samples_per_second": 5.752,
+      "train_steps_per_second": 0.043
     }
   ],
   "logging_steps": 10,
-  "max_steps": 3,
+  "max_steps": 18,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
@@ -71,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9545499876261888.0,
+  "total_flos": 5.727299925757133e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8795c87ce3fac9f300c8d1c5eca4ea67de143dd1e0c834e5d2939f25395beb7
+oid sha256:776601c03cf5d73011085c6726d5efd93d6819be3f8baa0b4540e1fb6b0763b7
 size 5240