Training in progress, step 8670, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10432662ffb3fe4e360028abe2479d00659b2b7f35ba62dada6fcf2de8ec113d
+oid sha256:e20bc0033c285a6bcae3da64252895aedd2efc710d9dc794c8389136103c8b4b
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e014dc309e4e976a73fc40c9603e67e1f05b2f51488da6aa1fd7195c755d1649
+oid sha256:d64192664e56df50d8444fab87615337b1709714f7ad31e6ef4b326db8949ebb
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3656f6e48aa7808dc0d30ce19947a758f543c8658f4e26a136b97f21e1554ba5
+oid sha256:b6e439c77e91e126d0a78e2a9677279363a996f785813f6fe7102bac995e049c
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 66.61538461538461,
+  "epoch": 66.6923076923077,
   "eval_steps": 500,
-  "global_step": 8660,
+  "global_step": 8670,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -15596,6 +15596,24 @@
       "mean_token_accuracy": 0.6479879409074784,
       "num_tokens": 31583762.0,
       "step": 8660
+    },
+    {
+      "epoch": 66.65384615384616,
+      "grad_norm": 0.0,
+      "learning_rate": 6.68e-06,
+      "loss": 1.7374,
+      "mean_token_accuracy": 0.6501346677541733,
+      "num_tokens": 31601864.0,
+      "step": 8665
+    },
+    {
+      "epoch": 66.6923076923077,
+      "grad_norm": 0.0,
+      "learning_rate": 6.655e-06,
+      "loss": 1.7447,
+      "mean_token_accuracy": 0.6492434620857239,
+      "num_tokens": 31619969.0,
+      "step": 8670
     }
   ],
   "logging_steps": 5,
@@ -15615,7 +15633,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6014780660267418e+18,
+  "total_flos": 1.6033287957553152e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null