Training in progress, step 200, checkpoint

checkpoint-200/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bc9380a831f85d3b9908a8ba41371e777acc0a767a283ea6eb76f2d2bd1f557
+oid sha256:6bafe9677d96eb63bae43314ebe31a30361b1347d590fab78e657d5093cda7e5
 size 1474893317

checkpoint-200/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b7511b52f20dd02d2703e7e44318cf5908bd01588cd51cce0f7fcdfeb37be13
+oid sha256:7b06790aa3e1d971e160c719ebdd5ee22a691c28aff1977c8a9e4b150aaeac7a
 size 737457141

checkpoint-200/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84709f6d9c1533f7f23a098ed0b25c34f2bbc10611fbeb71c88a308a8846e0ed
+oid sha256:8f3284e82c30f90f720fbb01dfc9a4aa926d82378c51e59b01cb9aa4aa352e1b
 size 14575

checkpoint-200/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28635ac4e12d078e632eeed3d7a0151748b7fe2eb5d64a612000c08dddfa0646
+oid sha256:f2099172cf643e0621a49c4fd812f032200315a0b3fd63d5198b626196954959
 size 627

checkpoint-200/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5637454986572266,
+  "best_metric": 0.5658872723579407,
   "best_model_checkpoint": "/kaggle/output/checkpoint-200",
   "epoch": 0.4132231404958678,
   "eval_steps": 50,
@@ -10,44 +10,44 @@
   "log_history": [
     {
       "epoch": 0.0,
-      "learning_rate": 2.777777777777778e-07,
-      "loss": 0.664,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.6979,
       "step": 1
     },
     {
       "epoch": 0.1,
       "eval_accuracy": 0.75,
-      "eval_loss": 0.5625454783439636,
-      "eval_runtime": 28.0598,
-      "eval_samples_per_second": 42.196,
-      "eval_steps_per_second": 21.098,
+      "eval_loss": 0.6723740696907043,
+      "eval_runtime": 28.903,
+      "eval_samples_per_second": 40.965,
+      "eval_steps_per_second": 20.482,
       "step": 50
     },
     {
       "epoch": 0.21,
       "eval_accuracy": 0.75,
-      "eval_loss": 0.5684965252876282,
-      "eval_runtime": 27.869,
-      "eval_samples_per_second": 42.485,
-      "eval_steps_per_second": 21.242,
+      "eval_loss": 0.6272028088569641,
+      "eval_runtime": 28.756,
+      "eval_samples_per_second": 41.174,
+      "eval_steps_per_second": 20.587,
       "step": 100
     },
     {
       "epoch": 0.31,
       "eval_accuracy": 0.75,
-      "eval_loss": 0.5661544799804688,
-      "eval_runtime": 29.0027,
-      "eval_samples_per_second": 40.824,
-      "eval_steps_per_second": 20.412,
+      "eval_loss": 0.5726658701896667,
+      "eval_runtime": 28.7791,
+      "eval_samples_per_second": 41.141,
+      "eval_steps_per_second": 20.57,
       "step": 150
     },
     {
       "epoch": 0.41,
       "eval_accuracy": 0.75,
-      "eval_loss": 0.5637454986572266,
-      "eval_runtime": 27.8992,
-      "eval_samples_per_second": 42.439,
-      "eval_steps_per_second": 21.219,
+      "eval_loss": 0.5658872723579407,
+      "eval_runtime": 28.8005,
+      "eval_samples_per_second": 41.11,
+      "eval_steps_per_second": 20.555,
       "step": 200
     }
   ],
@@ -55,7 +55,7 @@
   "max_steps": 1000,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 634000068849168.0,
+  "total_flos": 648800331133968.0,
   "trial_name": null,
   "trial_params": null
 }

checkpoint-200/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359ac16579635edbe192e2a03146d3aa8c5fab4b7a991e049fba5f7b90d4807f
+oid sha256:fbe5e88ca49040823bdb83dc035b8a4470c58ae105b0482f624b7d48f5e08cbe
 size 4027