Training in progress, step 500, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5805072dd72dbaa444aa95ea79904fe117bd9e08603dd8903d889b35eb5d72c
+oid sha256:700544197588712cbd24925d79ebf512ccf55a8d291b4bbb7d2bc30f996e614d
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b50dc3b8d7f6527e6deb35523fc5f4f66de87b59bae32d7b673859cc29de173
+oid sha256:81febf7d39716c7adbb764e3bc21e58f5f8a1c1c6135c7bb64981adb8fb01d11
 size 1540661735

last-checkpoint/trainer_state.json

@@ -11,82 +11,82 @@
   "log_history": [
     {
       "epoch": 0.1,
-      "grad_norm": 1.0159783363342285,
+      "grad_norm": 1.026106834411621,
       "learning_rate": 0.003920764340590609,
-      "loss": 67.322138671875,
+      "loss": 68.1809814453125,
       "step": 100
     },
     {
       "epoch": 0.1,
-      "eval_accuracy": 0.1363150684931507,
-      "eval_loss": 62.45854568481445,
-      "eval_runtime": 15.2216,
-      "eval_samples_per_second": 8.212,
-      "eval_steps_per_second": 0.263,
+      "eval_accuracy": 0.13532681017612525,
+      "eval_loss": 63.20947265625,
+      "eval_runtime": 14.9666,
+      "eval_samples_per_second": 8.352,
+      "eval_steps_per_second": 0.267,
       "step": 100
     },
     {
       "epoch": 0.2,
-      "grad_norm": 1.178174614906311,
+      "grad_norm": 1.1686949729919434,
       "learning_rate": 0.003650943793925548,
-      "loss": 60.51267578125,
+      "loss": 61.33072265625,
       "step": 200
     },
     {
       "epoch": 0.2,
-      "eval_accuracy": 0.14354794520547945,
-      "eval_loss": 59.48474884033203,
-      "eval_runtime": 3.1576,
-      "eval_samples_per_second": 39.587,
-      "eval_steps_per_second": 1.267,
+      "eval_accuracy": 0.14370254403131116,
+      "eval_loss": 60.317352294921875,
+      "eval_runtime": 3.2913,
+      "eval_samples_per_second": 37.979,
+      "eval_steps_per_second": 1.215,
       "step": 200
     },
     {
       "epoch": 0.3,
-      "grad_norm": 0.9601056575775146,
+      "grad_norm": 0.9769435524940491,
       "learning_rate": 0.0032162636906540357,
-      "loss": 58.783408203125,
+      "loss": 59.6425439453125,
       "step": 300
     },
     {
       "epoch": 0.3,
-      "eval_accuracy": 0.14687671232876712,
-      "eval_loss": 58.058326721191406,
-      "eval_runtime": 3.3957,
-      "eval_samples_per_second": 36.812,
-      "eval_steps_per_second": 1.178,
+      "eval_accuracy": 0.14733463796477494,
+      "eval_loss": 58.926719665527344,
+      "eval_runtime": 3.3852,
+      "eval_samples_per_second": 36.925,
+      "eval_steps_per_second": 1.182,
       "step": 300
     },
     {
       "epoch": 0.4,
-      "grad_norm": 0.6054814457893372,
+      "grad_norm": 0.6136718392372131,
       "learning_rate": 0.0026601302141692667,
-      "loss": 57.62333984375,
+      "loss": 58.5160546875,
       "step": 400
     },
     {
       "epoch": 0.4,
-      "eval_accuracy": 0.1496399217221135,
-      "eval_loss": 57.01893615722656,
-      "eval_runtime": 3.9547,
-      "eval_samples_per_second": 31.608,
-      "eval_steps_per_second": 1.011,
+      "eval_accuracy": 0.149293542074364,
+      "eval_loss": 57.94895935058594,
+      "eval_runtime": 3.1596,
+      "eval_samples_per_second": 39.562,
+      "eval_steps_per_second": 1.266,
       "step": 400
     },
     {
       "epoch": 0.5,
-      "grad_norm": 0.638672411441803,
+      "grad_norm": 0.6485599875450134,
       "learning_rate": 0.002038077610206693,
-      "loss": 56.62125,
+      "loss": 57.5463623046875,
       "step": 500
     },
     {
       "epoch": 0.5,
-      "eval_accuracy": 0.151720156555773,
-      "eval_loss": 56.300567626953125,
-      "eval_runtime": 3.3169,
-      "eval_samples_per_second": 37.686,
-      "eval_steps_per_second": 1.206,
+      "eval_accuracy": 0.15155577299412915,
+      "eval_loss": 57.233314514160156,
+      "eval_runtime": 3.1982,
+      "eval_samples_per_second": 39.085,
+      "eval_steps_per_second": 1.251,
       "step": 500
     }
   ],