Training in progress, step 7800, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d3d5046f8166490466a2240ca1b42c8010afe133cbd240ec33180ea5fcb9ed1
+oid sha256:4be09ed69daf45b63e81183b0681a764d24b4ee0466a7c9dea7783967259f1e7
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a20ef5b9fdbfa68a808af6a2be9c0f845ee00bc654282e021974177703899656
+oid sha256:5fee290d069e92f66bf13b528f52ba184d16e73b9b849efc88b4e2fc4a8585a3
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f5cb706354ab22cb6fac8efa3e55093c316ead63bd9960d0419d04658306734
+oid sha256:36674c0c8a8dc8277a05127c514e85d0b8cfd2001d5d8bc5fb009f11f208dbf2
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 59.92307692307692,
+  "epoch": 60.0,
   "eval_steps": 500,
-  "global_step": 7790,
+  "global_step": 7800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -14030,6 +14030,24 @@
       "mean_token_accuracy": 0.6455042749643326,
       "num_tokens": 28410567.0,
       "step": 7790
+    },
+    {
+      "epoch": 59.96153846153846,
+      "grad_norm": 0.0,
+      "learning_rate": 1.103e-05,
+      "loss": 1.817,
+      "mean_token_accuracy": 0.6328691780567169,
+      "num_tokens": 28427919.0,
+      "step": 7795
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 0.0,
+      "learning_rate": 1.1005e-05,
+      "loss": 1.7394,
+      "mean_token_accuracy": 0.6530990123748779,
+      "num_tokens": 28446300.0,
+      "step": 7800
     }
   ],
   "logging_steps": 5,
@@ -14049,7 +14067,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4405685799816397e+18,
+  "total_flos": 1.4423249948973466e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null