Training in progress, step 9840, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aefe2b45d031a5d4e5dcbf3cdaad0644aa9e53d6ad4cd193f60e75b95a288004
+oid sha256:52fa49c9aee53eccacfc20fa0a53e81c66a2d9d79fadbf39a861f03d505a8dc4
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:947ba22482f94b95d6f1447f0652a064adc8f020db2ac62e7395d0b9e1cbcbda
+oid sha256:c16a6ae3dbdee2c3d74d8c96a643a478a246c38052a582fabe164c53a454d5b0
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adec07227d7ba5680587967ee4f0d7098eef3788ca01b6957fb6773f23de5be0
+oid sha256:c7f8d076674adacf33d6e96dcffeac08e85cb7bfeb9c3481b82797b68933114a
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 75.61538461538461,
+  "epoch": 75.6923076923077,
   "eval_steps": 500,
-  "global_step": 9830,
+  "global_step": 9840,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17702,6 +17702,24 @@
       "mean_token_accuracy": 0.6422079712152481,
       "num_tokens": 35850712.0,
       "step": 9830
+    },
+    {
+      "epoch": 75.65384615384616,
+      "grad_norm": 0.0,
+      "learning_rate": 8.300000000000001e-07,
+      "loss": 1.7786,
+      "mean_token_accuracy": 0.6427565932273864,
+      "num_tokens": 35868743.0,
+      "step": 9835
+    },
+    {
+      "epoch": 75.6923076923077,
+      "grad_norm": 0.0,
+      "learning_rate": 8.05e-07,
+      "loss": 1.7353,
+      "mean_token_accuracy": 0.657978093624115,
+      "num_tokens": 35886399.0,
+      "step": 9840
     }
   ],
   "logging_steps": 5,
@@ -17721,7 +17739,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8180486932402995e+18,
+  "total_flos": 1.8198268608990413e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null