Training in progress, step 1040, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3575a999e797fc5155b79274b4093c9c818c5fd61950baa0bb86e93f0eb70ea7
+oid sha256:962d5177814c6ee8399ad94a21fc553a1649b94c812fc4886942d4582ae43304
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:543fda8f6c9cab078ada3ac64dbdb165b92616a9d67c0b93daa5bba89ba8fd37
+oid sha256:7e532e72b772198085f5edd494c11c15dc3b405b3a4dcf855aee0a87cebae70b
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:251bd5f36fbadbb095d0a85d64fa03d515a0c8e3017761f97432bf0276b02e56
+oid sha256:4a6ce544f81ee17f0b9d1278b572a0947398a6c7758a01181fa321dc8527a648
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.923076923076923,
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 1030,
+  "global_step": 1040,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1862,6 +1862,24 @@
       "mean_token_accuracy": 0.6694303750991821,
       "num_tokens": 3757638.0,
       "step": 1030
+    },
+    {
+      "epoch": 7.961538461538462,
+      "grad_norm": 0.0,
+      "learning_rate": 4.483e-05,
+      "loss": 1.8101,
+      "mean_token_accuracy": 0.6355878323316574,
+      "num_tokens": 3775161.0,
+      "step": 1035
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.0,
+      "learning_rate": 4.4805e-05,
+      "loss": 1.7585,
+      "mean_token_accuracy": 0.6487736940383911,
+      "num_tokens": 3792840.0,
+      "step": 1040
     }
   ],
   "logging_steps": 5,
@@ -1881,7 +1899,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9054593124909056e+17,
+  "total_flos": 1.9229678889467904e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null