Training in progress, step 9990, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7790db1cbcec3751495fdd44579dedc5ab72558fd38144d6ff0afd0bec6da03
+oid sha256:afefba1d1a51b0c0c5707c5f0d300dff53e678f1bc0b7cae11abdff5b79cefc0
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5186a963c4bbb62c9b5731d6c65fa0aadbeff1c2051f9ef31571be06d9388864
+oid sha256:9fe3f3900165b5bced47c1cd85cce00417cc154ca7b7ab18ccb1333c93d6629c
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea4d37eccc5be27331c5c923a231c3d00483b5e7cd0ef06b413ba155456540dd
+oid sha256:6103aa69cb523c885f825e3681c3fc82e661052d714c68ca14488001d0b4c231
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 76.76923076923077,
+  "epoch": 76.84615384615384,
   "eval_steps": 500,
-  "global_step": 9980,
+  "global_step": 9990,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17972,6 +17972,24 @@
       "mean_token_accuracy": 0.6534163296222687,
       "num_tokens": 36398038.0,
       "step": 9980
+    },
+    {
+      "epoch": 76.8076923076923,
+      "grad_norm": 0.0,
+      "learning_rate": 8e-08,
+      "loss": 1.7521,
+      "mean_token_accuracy": 0.6514124810695648,
+      "num_tokens": 36415958.0,
+      "step": 9985
+    },
+    {
+      "epoch": 76.84615384615384,
+      "grad_norm": 0.0,
+      "learning_rate": 5.5e-08,
+      "loss": 1.7213,
+      "mean_token_accuracy": 0.6536638140678406,
+      "num_tokens": 36434047.0,
+      "step": 9990
     }
   ],
   "logging_steps": 5,
@@ -17991,7 +18009,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8457508908847923e+18,
+  "total_flos": 1.84751445086208e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null