Training in progress, step 48, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c4048ab4f9a52bda607705c3f5bb13958a649c75b8765f2ac41060997a2703d
+oid sha256:8785178ab67973d156e1bf32e0bd7e58b58ed5bbeb60e7d49dea8c6e1fb8bc6b
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56493e7ecd4aec71b70e1f846eade27edc70447ddf6a39a2642358dcc3382d73
+oid sha256:06befea34ff2bfd28b299135677677cb8125609004f72f75f1e909cf7c3d734a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ed6431293c03d1e193e9501dc8ed4f4955bf079fba7f2c1c309a3efed166e50
+oid sha256:6a946ba862c9290cf73cbdcd016309ecac1eb5b3695453bc8a42a8a259a1c695
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.20114285714285715,
+  "epoch": 0.21942857142857142,
   "eval_steps": 4,
-  "global_step": 44,
+  "global_step": 48,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -411,6 +411,42 @@
       "eval_samples_per_second": 22.991,
       "eval_steps_per_second": 11.619,
       "step": 44
+    },
+    {
+      "epoch": 0.2057142857142857,
+      "grad_norm": NaN,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.2102857142857143,
+      "grad_norm": NaN,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.21485714285714286,
+      "grad_norm": NaN,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.21942857142857142,
+      "grad_norm": NaN,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.21942857142857142,
+      "eval_loss": NaN,
+      "eval_runtime": 4.0555,
+      "eval_samples_per_second": 22.932,
+      "eval_steps_per_second": 11.589,
+      "step": 48
     }
   ],
   "logging_steps": 1,
@@ -430,7 +466,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5747582882021376.0,
+  "total_flos": 6270090416750592.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null