Training in progress, step 8700, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50d3e9ba44efab12fe25c02e567a41c06de65d6b7f5d9fc624fdd6d1d73597cc
+oid sha256:4c5632b928ce436548cf0ce8e746008781f62c041027a4d04d6b21cddc635c16
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eccd57cc03a59a61b2c5e295944a25ca007779f3ad15ff6b42c07a65783c187
+oid sha256:454080d12dc731aa548a42c0da964bddc20ed5e2220fb0a91d73e28902cbb0be
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30e2b70c1a5be73196ed3a872efcfa909a0c3ff6b48e6e02572188fca792cc14
+oid sha256:93c602b635cd21ef510f4a68235f97f160f0b0e00d50613d42acf48145fb469a
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 66.84615384615384,
+  "epoch": 66.92307692307692,
   "eval_steps": 500,
-  "global_step": 8690,
+  "global_step": 8700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -15650,6 +15650,24 @@
       "mean_token_accuracy": 0.6432503432035446,
       "num_tokens": 31692632.0,
       "step": 8690
+    },
+    {
+      "epoch": 66.88461538461539,
+      "grad_norm": 0.0,
+      "learning_rate": 6.53e-06,
+      "loss": 1.8144,
+      "mean_token_accuracy": 0.6369650483131408,
+      "num_tokens": 31710059.0,
+      "step": 8695
+    },
+    {
+      "epoch": 66.92307692307692,
+      "grad_norm": 0.0,
+      "learning_rate": 6.505e-06,
+      "loss": 1.6865,
+      "mean_token_accuracy": 0.6562155693769455,
+      "num_tokens": 31729323.0,
+      "step": 8700
     }
   ],
   "logging_steps": 5,
@@ -15669,7 +15687,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6069962764751667e+18,
+  "total_flos": 1.6088630428975104e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null