Training in progress, step 9920, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af56401b392dfa449febbef254a236b3d4a4549caef9e0a62e30df4a81a6b9f8
+oid sha256:b545f2ac256a1ec934f08c21773adea843eb241aa5f58a3a75826b63ddc2bc0a
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c68ed44dbb459d2ea52d778ed5de2c1bbebed56281706923eaa761047cb6919
+oid sha256:695e8cb5033fd9aa348d65602b2210e61a59f5fc94ac74efdd3602e03d26a7c2
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad25673c9b7f86b336c39217e9425075be68970153a4ac6045584b1a31cf8fde
+oid sha256:c7a68bf6a1ee407daacf6969fc31e8f14203c55ddbc395e807ed319072927cc8
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 76.23076923076923,
+  "epoch": 76.3076923076923,
   "eval_steps": 500,
-  "global_step": 9910,
+  "global_step": 9920,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17846,6 +17846,24 @@
       "mean_token_accuracy": 0.6572551965713501,
       "num_tokens": 36141761.0,
       "step": 9910
+    },
+    {
+      "epoch": 76.26923076923077,
+      "grad_norm": 0.0,
+      "learning_rate": 4.3e-07,
+      "loss": 1.7517,
+      "mean_token_accuracy": 0.6524038553237915,
+      "num_tokens": 36159646.0,
+      "step": 9915
+    },
+    {
+      "epoch": 76.3076923076923,
+      "grad_norm": 0.0,
+      "learning_rate": 4.05e-07,
+      "loss": 1.8024,
+      "mean_token_accuracy": 0.6330039739608765,
+      "num_tokens": 36177566.0,
+      "step": 9920
     }
   ],
   "logging_steps": 5,
@@ -17865,7 +17883,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.832735446709207e+18,
+  "total_flos": 1.834522347220992e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null