Training in progress, epoch 0

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 9.6,
-    "total_flos": 5.876119984612147e+16,
-    "train_loss": 0.3996999263763428,
-    "train_runtime": 229.426,
-    "train_samples_per_second": 10.722,
-    "train_steps_per_second": 0.262
+    "epoch": 8.89,
+    "total_flos": 5.786635923932774e+16,
+    "train_loss": 0.40318952401479086,
+    "train_runtime": 239.9675,
+    "train_samples_per_second": 10.876,
+    "train_steps_per_second": 0.25
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e18401ae79f0eb7980f71ec062b3dab0bd2d7a2e12d76c839c8151a1579228c9
+oid sha256:e460638b4d529c4454281722190369db834fad322c2165720fc7bd2fe8c983f0
 size 110397937

runs/Jul19_18-55-35_d59d7adac7e1/events.out.tfevents.1689792946.d59d7adac7e1.10517.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1642621abf8512365c7bc99bdd1b0081aaef1b9b8dde72351cee2b4a226489bf
+size 4832

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 9.6,
-    "total_flos": 5.876119984612147e+16,
-    "train_loss": 0.3996999263763428,
-    "train_runtime": 229.426,
-    "train_samples_per_second": 10.722,
-    "train_steps_per_second": 0.262
+    "epoch": 8.89,
+    "total_flos": 5.786635923932774e+16,
+    "train_loss": 0.40318952401479086,
+    "train_runtime": 239.9675,
+    "train_samples_per_second": 10.876,
+    "train_steps_per_second": 0.25
 }

trainer_state.json

@@ -1,151 +1,142 @@
 {
-  "best_metric": 0.9545454545454546,
-  "best_model_checkpoint": "segformer-class-classWeights-augmentation/checkpoint-31",
-  "epoch": 9.6,
+  "best_metric": 0.9310344827586207,
+  "best_model_checkpoint": "segformer-class-classWeights-augmentation/checkpoint-40",
+  "epoch": 8.88888888888889,
   "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.96,
-      "eval_accuracy": 0.4772727272727273,
-      "eval_loss": 0.9944368600845337,
-      "eval_runtime": 1.008,
-      "eval_samples_per_second": 43.653,
-      "eval_steps_per_second": 4.961,
+      "epoch": 0.89,
+      "eval_accuracy": 0.5862068965517241,
+      "eval_loss": 1.0178804397583008,
+      "eval_runtime": 1.1426,
+      "eval_samples_per_second": 25.38,
+      "eval_steps_per_second": 2.626,
       "step": 6
     },
     {
-      "epoch": 1.6,
+      "epoch": 1.48,
       "learning_rate": 4.62962962962963e-05,
-      "loss": 1.0159,
+      "loss": 0.9897,
       "step": 10
     },
     {
-      "epoch": 1.92,
-      "eval_accuracy": 0.75,
-      "eval_loss": 0.694824755191803,
-      "eval_runtime": 0.9891,
-      "eval_samples_per_second": 44.486,
-      "eval_steps_per_second": 5.055,
-      "step": 12
+      "epoch": 1.93,
+      "eval_accuracy": 0.7241379310344828,
+      "eval_loss": 0.760027289390564,
+      "eval_runtime": 0.8084,
+      "eval_samples_per_second": 35.874,
+      "eval_steps_per_second": 3.711,
+      "step": 13
     },
     {
-      "epoch": 2.88,
-      "eval_accuracy": 0.9318181818181818,
-      "eval_loss": 0.34167394042015076,
-      "eval_runtime": 0.985,
-      "eval_samples_per_second": 44.669,
-      "eval_steps_per_second": 5.076,
-      "step": 18
+      "epoch": 2.96,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.5848,
+      "step": 20
     },
     {
-      "epoch": 3.2,
-      "learning_rate": 3.7037037037037037e-05,
-      "loss": 0.5444,
+      "epoch": 2.96,
+      "eval_accuracy": 0.5862068965517241,
+      "eval_loss": 0.8368268609046936,
+      "eval_runtime": 1.6581,
+      "eval_samples_per_second": 17.49,
+      "eval_steps_per_second": 1.809,
       "step": 20
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.9090909090909091,
-      "eval_loss": 0.26416999101638794,
-      "eval_runtime": 1.3817,
-      "eval_samples_per_second": 31.845,
-      "eval_steps_per_second": 3.619,
-      "step": 25
+      "eval_accuracy": 0.8620689655172413,
+      "eval_loss": 0.4708000719547272,
+      "eval_runtime": 0.8189,
+      "eval_samples_per_second": 35.414,
+      "eval_steps_per_second": 3.663,
+      "step": 27
     },
     {
-      "epoch": 4.8,
+      "epoch": 4.44,
       "learning_rate": 2.777777777777778e-05,
-      "loss": 0.2331,
+      "loss": 0.2747,
       "step": 30
     },
     {
-      "epoch": 4.96,
-      "eval_accuracy": 0.9545454545454546,
-      "eval_loss": 0.09864511340856552,
-      "eval_runtime": 1.0085,
-      "eval_samples_per_second": 43.627,
-      "eval_steps_per_second": 4.958,
-      "step": 31
+      "epoch": 4.89,
+      "eval_accuracy": 0.896551724137931,
+      "eval_loss": 0.37271812558174133,
+      "eval_runtime": 0.8067,
+      "eval_samples_per_second": 35.951,
+      "eval_steps_per_second": 3.719,
+      "step": 33
     },
     {
-      "epoch": 5.92,
-      "eval_accuracy": 0.9545454545454546,
-      "eval_loss": 0.17346793413162231,
-      "eval_runtime": 1.0084,
-      "eval_samples_per_second": 43.634,
-      "eval_steps_per_second": 4.958,
-      "step": 37
+      "epoch": 5.93,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 0.2259,
+      "step": 40
     },
     {
-      "epoch": 6.4,
-      "learning_rate": 1.8518518518518518e-05,
-      "loss": 0.2596,
+      "epoch": 5.93,
+      "eval_accuracy": 0.9310344827586207,
+      "eval_loss": 0.3100181221961975,
+      "eval_runtime": 1.1422,
+      "eval_samples_per_second": 25.389,
+      "eval_steps_per_second": 2.626,
       "step": 40
     },
     {
-      "epoch": 6.88,
-      "eval_accuracy": 0.9545454545454546,
-      "eval_loss": 0.1091495230793953,
-      "eval_runtime": 1.383,
-      "eval_samples_per_second": 31.815,
-      "eval_steps_per_second": 3.615,
-      "step": 43
+      "epoch": 6.96,
+      "eval_accuracy": 0.9310344827586207,
+      "eval_loss": 0.22938820719718933,
+      "eval_runtime": 0.7944,
+      "eval_samples_per_second": 36.504,
+      "eval_steps_per_second": 3.776,
+      "step": 47
     },
     {
-      "epoch": 8.0,
+      "epoch": 7.41,
       "learning_rate": 9.259259259259259e-06,
-      "loss": 0.1737,
+      "loss": 0.1596,
       "step": 50
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.9545454545454546,
-      "eval_loss": 0.0685076043009758,
-      "eval_runtime": 1.013,
-      "eval_samples_per_second": 43.435,
-      "eval_steps_per_second": 4.936,
-      "step": 50
-    },
-    {
-      "epoch": 8.96,
-      "eval_accuracy": 0.9545454545454546,
-      "eval_loss": 0.09951713681221008,
-      "eval_runtime": 1.0006,
-      "eval_samples_per_second": 43.975,
-      "eval_steps_per_second": 4.997,
-      "step": 56
+      "eval_accuracy": 0.896551724137931,
+      "eval_loss": 0.26314061880111694,
+      "eval_runtime": 1.212,
+      "eval_samples_per_second": 23.927,
+      "eval_steps_per_second": 2.475,
+      "step": 54
     },
     {
-      "epoch": 9.6,
+      "epoch": 8.89,
       "learning_rate": 0.0,
-      "loss": 0.1716,
+      "loss": 0.1844,
       "step": 60
     },
     {
-      "epoch": 9.6,
-      "eval_accuracy": 0.9545454545454546,
-      "eval_loss": 0.09269092231988907,
-      "eval_runtime": 1.0041,
-      "eval_samples_per_second": 43.822,
-      "eval_steps_per_second": 4.98,
+      "epoch": 8.89,
+      "eval_accuracy": 0.9310344827586207,
+      "eval_loss": 0.26064130663871765,
+      "eval_runtime": 0.8176,
+      "eval_samples_per_second": 35.469,
+      "eval_steps_per_second": 3.669,
       "step": 60
     },
     {
-      "epoch": 9.6,
+      "epoch": 8.89,
       "step": 60,
-      "total_flos": 5.876119984612147e+16,
-      "train_loss": 0.3996999263763428,
-      "train_runtime": 229.426,
-      "train_samples_per_second": 10.722,
-      "train_steps_per_second": 0.262
+      "total_flos": 5.786635923932774e+16,
+      "train_loss": 0.40318952401479086,
+      "train_runtime": 239.9675,
+      "train_samples_per_second": 10.876,
+      "train_steps_per_second": 0.25
     }
   ],
   "max_steps": 60,
   "num_train_epochs": 10,
-  "total_flos": 5.876119984612147e+16,
+  "total_flos": 5.786635923932774e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81dc38e5245c5a8cf5460d3e360997b3861cc2a3b09ccf88c9dd38ff9fc6e1b9
+oid sha256:840a4f8531ac04e05197743d10bdcafb29a5988b65b7d8acdadb673e998891a0
 size 4027