Training in progress, step 5460, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23a471c8fcb909f1f72eeb98611fe5b31f87c04ebd115ad51541735a80fd4abf
+oid sha256:31474659831e8df96dc40d4ec7bb40a665028f76b343eb8b45bbba1f679c5714
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35be42e5a3364d7bcad3a2176a1e4c89665b18d2ac07fc17a9f1ec15ceef8b87
+oid sha256:d87f00aee34b59aa8b849e0667b0cc72d15bd4884d8dadb243cc848a47ffc87e
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68a8cb65b798fadf7d3e2fafe845d7af6abdb723873dca73b3f9df02d54cf284
+oid sha256:f1434b9eb8c94fed686a7fe223463da1465ed6372bdc68e98fbf2c22c10963e0
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 41.92307692307692,
+  "epoch": 42.0,
   "eval_steps": 500,
-  "global_step": 5450,
+  "global_step": 5460,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9818,6 +9818,24 @@
       "mean_token_accuracy": 0.6400933116674423,
       "num_tokens": 19876852.0,
       "step": 5450
+    },
+    {
+      "epoch": 41.96153846153846,
+      "grad_norm": 0.0,
+      "learning_rate": 2.273e-05,
+      "loss": 1.7577,
+      "mean_token_accuracy": 0.6475079268217087,
+      "num_tokens": 19894493.0,
+      "step": 5455
+    },
+    {
+      "epoch": 42.0,
+      "grad_norm": 0.0,
+      "learning_rate": 2.2705e-05,
+      "loss": 1.7518,
+      "mean_token_accuracy": 0.6474265098571778,
+      "num_tokens": 19912410.0,
+      "step": 5460
     }
   ],
   "logging_steps": 5,
@@ -9837,7 +9855,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0072555265182925e+18,
+  "total_flos": 1.0090119414339994e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null