Training in progress, epoch 0

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 13.33,
     "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
+    "train_loss": 0.4070509672164917,
+    "train_runtime": 340.2477,
+    "train_samples_per_second": 15.342,
+    "train_steps_per_second": 0.059
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:226c105a1155aa9ecb03521447c5fcd75542204bab3ad0d8ee26fbfceed171c2
+oid sha256:24b5cd07556784177ad90bde2951be01dfeb3b7b16b9009cff7874912bc62403
 size 110397937

runs/Jul20_18-52-42_7c542bce262c/events.out.tfevents.1689879211.7c542bce262c.34175.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f32608a1da751c5b48bcfd6e305b4de0ae4c797ef57ffbd690a637feba97e3d9
+size 4832

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 13.33,
     "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
+    "train_loss": 0.4070509672164917,
+    "train_runtime": 340.2477,
+    "train_samples_per_second": 15.342,
+    "train_steps_per_second": 0.059
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_metric": 0.896551724137931,
-  "best_model_checkpoint": "segformer-class-classWeights-augmentation/checkpoint-15",
+  "best_model_checkpoint": "segformer-class-classWeights-augmentation/checkpoint-13",
   "epoch": 13.333333333333334,
   "global_step": 20,
   "is_hyper_param_search": false,
@@ -9,150 +9,150 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.3103448275862069,
-      "eval_loss": 1.0387377738952637,
-      "eval_runtime": 0.934,
-      "eval_samples_per_second": 31.05,
-      "eval_steps_per_second": 1.071,
+      "eval_accuracy": 0.27586206896551724,
+      "eval_loss": 1.1699918508529663,
+      "eval_runtime": 1.1929,
+      "eval_samples_per_second": 24.31,
+      "eval_steps_per_second": 0.838,
       "step": 1
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6551724137931034,
-      "eval_loss": 1.0144158601760864,
-      "eval_runtime": 1.1602,
-      "eval_samples_per_second": 24.995,
-      "eval_steps_per_second": 0.862,
+      "eval_accuracy": 0.3793103448275862,
+      "eval_loss": 1.0350514650344849,
+      "eval_runtime": 0.7976,
+      "eval_samples_per_second": 36.36,
+      "eval_steps_per_second": 1.254,
       "step": 3
     },
     {
       "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,
+      "eval_accuracy": 0.5172413793103449,
+      "eval_loss": 0.9730662107467651,
+      "eval_runtime": 0.8014,
+      "eval_samples_per_second": 36.186,
+      "eval_steps_per_second": 1.248,
       "step": 5
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6551724137931034,
-      "eval_loss": 0.9074841737747192,
-      "eval_runtime": 0.8747,
-      "eval_samples_per_second": 33.152,
-      "eval_steps_per_second": 1.143,
+      "eval_accuracy": 0.5172413793103449,
+      "eval_loss": 0.9361577033996582,
+      "eval_runtime": 1.0363,
+      "eval_samples_per_second": 27.984,
+      "eval_steps_per_second": 0.965,
       "step": 6
     },
     {
       "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,
+      "eval_accuracy": 0.5517241379310345,
+      "eval_loss": 0.8889826536178589,
+      "eval_runtime": 0.7918,
+      "eval_samples_per_second": 36.624,
+      "eval_steps_per_second": 1.263,
       "step": 7
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.7931034482758621,
-      "eval_loss": 0.7622103095054626,
-      "eval_runtime": 1.2846,
-      "eval_samples_per_second": 22.575,
-      "eval_steps_per_second": 0.778,
+      "eval_accuracy": 0.7586206896551724,
+      "eval_loss": 0.7596346735954285,
+      "eval_runtime": 0.8269,
+      "eval_samples_per_second": 35.071,
+      "eval_steps_per_second": 1.209,
       "step": 9
     },
     {
       "epoch": 6.67,
       "learning_rate": 2.777777777777778e-05,
-      "loss": 0.4555,
+      "loss": 0.5024,
       "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,
+      "eval_accuracy": 0.8620689655172413,
+      "eval_loss": 0.6531320810317993,
+      "eval_runtime": 0.7953,
+      "eval_samples_per_second": 36.466,
+      "eval_steps_per_second": 1.257,
       "step": 11
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.8275862068965517,
-      "eval_loss": 0.6745181083679199,
-      "eval_runtime": 1.3057,
-      "eval_samples_per_second": 22.211,
-      "eval_steps_per_second": 0.766,
+      "eval_accuracy": 0.8620689655172413,
+      "eval_loss": 0.6170477271080017,
+      "eval_runtime": 1.0429,
+      "eval_samples_per_second": 27.806,
+      "eval_steps_per_second": 0.959,
       "step": 12
     },
     {
       "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,
+      "eval_accuracy": 0.896551724137931,
+      "eval_loss": 0.5878463387489319,
+      "eval_runtime": 0.7888,
+      "eval_samples_per_second": 36.767,
+      "eval_steps_per_second": 1.268,
       "step": 13
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.896551724137931,
-      "eval_loss": 0.5319176316261292,
-      "eval_runtime": 0.8719,
-      "eval_samples_per_second": 33.261,
-      "eval_steps_per_second": 1.147,
+      "eval_accuracy": 0.8620689655172413,
+      "eval_loss": 0.5418170094490051,
+      "eval_runtime": 0.8158,
+      "eval_samples_per_second": 35.546,
+      "eval_steps_per_second": 1.226,
       "step": 15
     },
     {
       "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,
+      "eval_accuracy": 0.8620689655172413,
+      "eval_loss": 0.5121886730194092,
+      "eval_runtime": 0.8148,
+      "eval_samples_per_second": 35.592,
+      "eval_steps_per_second": 1.227,
       "step": 17
     },
     {
       "epoch": 12.0,
-      "eval_accuracy": 0.896551724137931,
-      "eval_loss": 0.48956170678138733,
-      "eval_runtime": 0.8629,
-      "eval_samples_per_second": 33.607,
-      "eval_steps_per_second": 1.159,
+      "eval_accuracy": 0.8620689655172413,
+      "eval_loss": 0.5020919442176819,
+      "eval_runtime": 1.0894,
+      "eval_samples_per_second": 26.62,
+      "eval_steps_per_second": 0.918,
       "step": 18
     },
     {
       "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,
+      "eval_accuracy": 0.8620689655172413,
+      "eval_loss": 0.4927540421485901,
+      "eval_runtime": 0.8053,
+      "eval_samples_per_second": 36.014,
+      "eval_steps_per_second": 1.242,
       "step": 19
     },
     {
       "epoch": 13.33,
       "learning_rate": 0.0,
-      "loss": 0.2224,
+      "loss": 0.3117,
       "step": 20
     },
     {
       "epoch": 13.33,
-      "eval_accuracy": 0.896551724137931,
-      "eval_loss": 0.47683313488960266,
-      "eval_runtime": 1.2061,
-      "eval_samples_per_second": 24.045,
-      "eval_steps_per_second": 0.829,
+      "eval_accuracy": 0.8620689655172413,
+      "eval_loss": 0.4871620237827301,
+      "eval_runtime": 0.7941,
+      "eval_samples_per_second": 36.521,
+      "eval_steps_per_second": 1.259,
       "step": 20
     },
     {
       "epoch": 13.33,
       "step": 20,
       "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
+      "train_loss": 0.4070509672164917,
+      "train_runtime": 340.2477,
+      "train_samples_per_second": 15.342,
+      "train_steps_per_second": 0.059
     }
   ],
   "max_steps": 20,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5d220e4ea5edea36215e6d9f1d5f651614e5823e22560386378051521c71e6e
+oid sha256:7e0bd4c4ab6acae725cbfef3614dce3202e1ccd2cf8dad24c381b00efef59e88
 size 4027