Training in progress, step 9910, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bdd30d40fdc2f9ac50eab793f3110ea573c3a4adfe8b977d60752b4b983f47b
+oid sha256:af56401b392dfa449febbef254a236b3d4a4549caef9e0a62e30df4a81a6b9f8
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0610da09a40af0fe728bae3b4a3e71cfa910e3c97ca88c05b2bfd8ff6648b6e0
+oid sha256:4c68ed44dbb459d2ea52d778ed5de2c1bbebed56281706923eaa761047cb6919
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe8c49bf0ee0f969c8d0d2f9f2875e6bf6dd6d5801501cf21d7dc7ce760bcbdd
+oid sha256:ad25673c9b7f86b336c39217e9425075be68970153a4ac6045584b1a31cf8fde
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 76.15384615384616,
+  "epoch": 76.23076923076923,
   "eval_steps": 500,
-  "global_step": 9900,
+  "global_step": 9910,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17828,6 +17828,24 @@
       "mean_token_accuracy": 0.6411665916442871,
       "num_tokens": 36105433.0,
       "step": 9900
+    },
+    {
+      "epoch": 76.1923076923077,
+      "grad_norm": 0.0,
+      "learning_rate": 4.8e-07,
+      "loss": 1.7081,
+      "mean_token_accuracy": 0.658719289302826,
+      "num_tokens": 36123588.0,
+      "step": 9905
+    },
+    {
+      "epoch": 76.23076923076923,
+      "grad_norm": 0.0,
+      "learning_rate": 4.5500000000000004e-07,
+      "loss": 1.6927,
+      "mean_token_accuracy": 0.6572551965713501,
+      "num_tokens": 36141761.0,
+      "step": 9910
     }
   ],
   "logging_steps": 5,
@@ -17847,7 +17865,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.830894878845993e+18,
+  "total_flos": 1.832735446709207e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null