Training in progress, step 9820, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d75d8086b3776abb2c3921778faeb279c698463d7e707ece989e24df98c7da6
+oid sha256:9d97a344f611bf88b07c4c49556a87d104482df1de54099e12139e55de265c51
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:493475ec763e0f57817baa071e0575720cf0ad65ea20b65cfe82c03403145eb9
+oid sha256:161609c14d79ac3db6d3ef916ae1f192e793fa78e9690cc49fa5d490c1ec9b2f
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92ae5a6742c9fa8d2a3b37b31bbaaa18ec9d42c6b721e21933c85b468abd02bb
+oid sha256:e1c1a84afb2b92569e90caecd4eea7fbc4ccf9e5513d7c86f84f93ad1b1c6459
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 75.46153846153847,
+  "epoch": 75.53846153846153,
   "eval_steps": 500,
-  "global_step": 9810,
+  "global_step": 9820,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17666,6 +17666,24 @@
       "mean_token_accuracy": 0.6756436079740524,
       "num_tokens": 35777534.0,
       "step": 9810
+    },
+    {
+      "epoch": 75.5,
+      "grad_norm": 0.0,
+      "learning_rate": 9.3e-07,
+      "loss": 1.6917,
+      "mean_token_accuracy": 0.6589653193950653,
+      "num_tokens": 35796039.0,
+      "step": 9815
+    },
+    {
+      "epoch": 75.53846153846153,
+      "grad_norm": 0.0,
+      "learning_rate": 9.050000000000001e-07,
+      "loss": 1.7085,
+      "mean_token_accuracy": 0.6560279041528702,
+      "num_tokens": 35814453.0,
+      "step": 9820
     }
   ],
   "logging_steps": 5,
@@ -17685,7 +17703,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8143893102569062e+18,
+  "total_flos": 1.8162417865560883e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null