Training in progress, epoch 1

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 13.33,
-    "total_flos": 8.682439554251366e+16,
-    "train_loss": 0.735786771774292,
-    "train_runtime": 315.7979,
-    "train_samples_per_second": 16.53,
-    "train_steps_per_second": 0.063
+    "total_flos": 8.7520382681131e+16,
+    "train_loss": 0.338924241065979,
+    "train_runtime": 348.466,
+    "train_samples_per_second": 14.98,
+    "train_steps_per_second": 0.057
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04e37299a31c8385299cdbfea3fb034a2e3bc8f602630cd17d863cb512a01615
+oid sha256:f6f633d95dc66ad7abecbfdc34e2ed30e516f694922f4f8d9b4e578fb340664f
 size 110397937

runs/Jul20_18-42-07_7c542bce262c/events.out.tfevents.1689878572.7c542bce262c.27782.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91d51e418516de5c5ff7f77952001ee150c765b69fdc9e416f9a244d7a3ca34e
+size 4834

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 13.33,
-    "total_flos": 8.682439554251366e+16,
-    "train_loss": 0.735786771774292,
-    "train_runtime": 315.7979,
-    "train_samples_per_second": 16.53,
-    "train_steps_per_second": 0.063
+    "total_flos": 8.7520382681131e+16,
+    "train_loss": 0.338924241065979,
+    "train_runtime": 348.466,
+    "train_samples_per_second": 14.98,
+    "train_steps_per_second": 0.057
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.7586206896551724,
+  "best_metric": 0.896551724137931,
   "best_model_checkpoint": "segformer-class-classWeights-augmentation/checkpoint-15",
   "epoch": 13.333333333333334,
   "global_step": 20,
@@ -8,156 +8,156 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.67,
+      "epoch": 1.0,
       "eval_accuracy": 0.3103448275862069,
-      "eval_loss": 1.2027289867401123,
-      "eval_runtime": 1.1652,
-      "eval_samples_per_second": 24.889,
-      "eval_steps_per_second": 0.858,
+      "eval_loss": 1.0387377738952637,
+      "eval_runtime": 0.934,
+      "eval_samples_per_second": 31.05,
+      "eval_steps_per_second": 1.071,
       "step": 1
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.3448275862068966,
-      "eval_loss": 1.121168851852417,
-      "eval_runtime": 0.8076,
-      "eval_samples_per_second": 35.908,
-      "eval_steps_per_second": 1.238,
+      "eval_accuracy": 0.6551724137931034,
+      "eval_loss": 1.0144158601760864,
+      "eval_runtime": 1.1602,
+      "eval_samples_per_second": 24.995,
+      "eval_steps_per_second": 0.862,
       "step": 3
     },
     {
-      "epoch": 2.67,
-      "eval_accuracy": 0.41379310344827586,
-      "eval_loss": 1.0648072957992554,
-      "eval_runtime": 0.7994,
-      "eval_samples_per_second": 36.278,
-      "eval_steps_per_second": 1.251,
-      "step": 4
+      "epoch": 3.0,
+      "eval_accuracy": 0.7241379310344828,
+      "eval_loss": 0.9569838047027588,
+      "eval_runtime": 0.8581,
+      "eval_samples_per_second": 33.797,
+      "eval_steps_per_second": 1.165,
+      "step": 5
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.5172413793103449,
-      "eval_loss": 0.9779136776924133,
-      "eval_runtime": 1.1072,
-      "eval_samples_per_second": 26.193,
-      "eval_steps_per_second": 0.903,
+      "eval_accuracy": 0.6551724137931034,
+      "eval_loss": 0.9074841737747192,
+      "eval_runtime": 0.8747,
+      "eval_samples_per_second": 33.152,
+      "eval_steps_per_second": 1.143,
       "step": 6
     },
     {
-      "epoch": 4.67,
-      "eval_accuracy": 0.5517241379310345,
-      "eval_loss": 0.9493536353111267,
-      "eval_runtime": 0.8027,
-      "eval_samples_per_second": 36.129,
-      "eval_steps_per_second": 1.246,
+      "epoch": 5.0,
+      "eval_accuracy": 0.7241379310344828,
+      "eval_loss": 0.8454705476760864,
+      "eval_runtime": 1.0773,
+      "eval_samples_per_second": 26.918,
+      "eval_steps_per_second": 0.928,
       "step": 7
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.5862068965517241,
-      "eval_loss": 0.9168237447738647,
-      "eval_runtime": 0.8186,
-      "eval_samples_per_second": 35.426,
-      "eval_steps_per_second": 1.222,
+      "eval_accuracy": 0.7931034482758621,
+      "eval_loss": 0.7622103095054626,
+      "eval_runtime": 1.2846,
+      "eval_samples_per_second": 22.575,
+      "eval_steps_per_second": 0.778,
       "step": 9
     },
     {
       "epoch": 6.67,
       "learning_rate": 2.777777777777778e-05,
-      "loss": 0.9535,
+      "loss": 0.4555,
       "step": 10
     },
     {
-      "epoch": 6.67,
-      "eval_accuracy": 0.6551724137931034,
-      "eval_loss": 0.8808135390281677,
-      "eval_runtime": 1.1217,
-      "eval_samples_per_second": 25.853,
-      "eval_steps_per_second": 0.891,
-      "step": 10
+      "epoch": 7.0,
+      "eval_accuracy": 0.7931034482758621,
+      "eval_loss": 0.7067170143127441,
+      "eval_runtime": 0.8517,
+      "eval_samples_per_second": 34.049,
+      "eval_steps_per_second": 1.174,
+      "step": 11
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.7241379310344828,
-      "eval_loss": 0.8135725855827332,
-      "eval_runtime": 0.8159,
-      "eval_samples_per_second": 35.544,
-      "eval_steps_per_second": 1.226,
+      "eval_accuracy": 0.8275862068965517,
+      "eval_loss": 0.6745181083679199,
+      "eval_runtime": 1.3057,
+      "eval_samples_per_second": 22.211,
+      "eval_steps_per_second": 0.766,
       "step": 12
     },
     {
-      "epoch": 8.67,
-      "eval_accuracy": 0.7241379310344828,
-      "eval_loss": 0.8014845848083496,
-      "eval_runtime": 0.8311,
-      "eval_samples_per_second": 34.894,
-      "eval_steps_per_second": 1.203,
+      "epoch": 9.0,
+      "eval_accuracy": 0.8620689655172413,
+      "eval_loss": 0.6107693314552307,
+      "eval_runtime": 0.9158,
+      "eval_samples_per_second": 31.668,
+      "eval_steps_per_second": 1.092,
       "step": 13
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.7586206896551724,
-      "eval_loss": 0.7727243900299072,
-      "eval_runtime": 0.8049,
-      "eval_samples_per_second": 36.028,
-      "eval_steps_per_second": 1.242,
+      "eval_accuracy": 0.896551724137931,
+      "eval_loss": 0.5319176316261292,
+      "eval_runtime": 0.8719,
+      "eval_samples_per_second": 33.261,
+      "eval_steps_per_second": 1.147,
       "step": 15
     },
     {
-      "epoch": 10.67,
-      "eval_accuracy": 0.7586206896551724,
-      "eval_loss": 0.7510485053062439,
-      "eval_runtime": 0.7895,
-      "eval_samples_per_second": 36.733,
-      "eval_steps_per_second": 1.267,
-      "step": 16
+      "epoch": 11.0,
+      "eval_accuracy": 0.896551724137931,
+      "eval_loss": 0.49429023265838623,
+      "eval_runtime": 0.8551,
+      "eval_samples_per_second": 33.915,
+      "eval_steps_per_second": 1.169,
+      "step": 17
     },
     {
       "epoch": 12.0,
-      "eval_accuracy": 0.7586206896551724,
-      "eval_loss": 0.6996777653694153,
-      "eval_runtime": 0.8164,
-      "eval_samples_per_second": 35.52,
-      "eval_steps_per_second": 1.225,
+      "eval_accuracy": 0.896551724137931,
+      "eval_loss": 0.48956170678138733,
+      "eval_runtime": 0.8629,
+      "eval_samples_per_second": 33.607,
+      "eval_steps_per_second": 1.159,
       "step": 18
     },
     {
-      "epoch": 12.67,
-      "eval_accuracy": 0.7586206896551724,
-      "eval_loss": 0.6856328248977661,
-      "eval_runtime": 1.1618,
-      "eval_samples_per_second": 24.961,
-      "eval_steps_per_second": 0.861,
+      "epoch": 13.0,
+      "eval_accuracy": 0.896551724137931,
+      "eval_loss": 0.4820307791233063,
+      "eval_runtime": 0.8493,
+      "eval_samples_per_second": 34.147,
+      "eval_steps_per_second": 1.177,
       "step": 19
     },
     {
       "epoch": 13.33,
       "learning_rate": 0.0,
-      "loss": 0.5181,
+      "loss": 0.2224,
       "step": 20
     },
     {
       "epoch": 13.33,
-      "eval_accuracy": 0.7586206896551724,
-      "eval_loss": 0.6802691221237183,
-      "eval_runtime": 1.6744,
-      "eval_samples_per_second": 17.32,
-      "eval_steps_per_second": 0.597,
+      "eval_accuracy": 0.896551724137931,
+      "eval_loss": 0.47683313488960266,
+      "eval_runtime": 1.2061,
+      "eval_samples_per_second": 24.045,
+      "eval_steps_per_second": 0.829,
       "step": 20
     },
     {
       "epoch": 13.33,
       "step": 20,
-      "total_flos": 8.682439554251366e+16,
-      "train_loss": 0.735786771774292,
-      "train_runtime": 315.7979,
-      "train_samples_per_second": 16.53,
-      "train_steps_per_second": 0.063
+      "total_flos": 8.7520382681131e+16,
+      "train_loss": 0.338924241065979,
+      "train_runtime": 348.466,
+      "train_samples_per_second": 14.98,
+      "train_steps_per_second": 0.057
     }
   ],
   "max_steps": 20,
   "num_train_epochs": 20,
-  "total_flos": 8.682439554251366e+16,
+  "total_flos": 8.7520382681131e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d5fc820a76557cedb905f2c4c0db81f9ab7e1e09f7a73b2089216b81ddd3aed
+oid sha256:f5d220e4ea5edea36215e6d9f1d5f651614e5823e22560386378051521c71e6e
 size 4027