Training in progress, step 9810, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d4a7c16fca1185f7b4ec8bba46d3d80f28aa0bb119a2a511c524970770650a2
+oid sha256:6d75d8086b3776abb2c3921778faeb279c698463d7e707ece989e24df98c7da6
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9b0961e73accf3bb914f7cf2298193a021ba07302282758a417bb77db106552
+oid sha256:493475ec763e0f57817baa071e0575720cf0ad65ea20b65cfe82c03403145eb9
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ba3dd4f37e1dad78fec8dc5e14481e73ae2ec26f976948fe1080d8d782c0520
+oid sha256:92ae5a6742c9fa8d2a3b37b31bbaaa18ec9d42c6b721e21933c85b468abd02bb
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 75.38461538461539,
+  "epoch": 75.46153846153847,
   "eval_steps": 500,
-  "global_step": 9800,
+  "global_step": 9810,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17648,6 +17648,24 @@
       "mean_token_accuracy": 0.647157472372055,
       "num_tokens": 35739283.0,
       "step": 9800
+    },
+    {
+      "epoch": 75.42307692307692,
+      "grad_norm": 0.0,
+      "learning_rate": 9.8e-07,
+      "loss": 1.7482,
+      "mean_token_accuracy": 0.6474371433258057,
+      "num_tokens": 35758040.0,
+      "step": 9805
+    },
+    {
+      "epoch": 75.46153846153847,
+      "grad_norm": 0.0,
+      "learning_rate": 9.55e-07,
+      "loss": 1.6272,
+      "mean_token_accuracy": 0.6756436079740524,
+      "num_tokens": 35777534.0,
+      "step": 9810
     }
   ],
   "logging_steps": 5,
@@ -17667,7 +17685,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8123755143451443e+18,
+  "total_flos": 1.8143893102569062e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null