Training in progress, step 9950, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7175e95acfc10be1c99ef5be6dbb445950fe7960fa10215fa67d68cabea687c4
+oid sha256:5c1b4128965430e53abee98edf3adecd0010a553483ca7f62718c31fd214b454
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3979884e9579b87865c9c600e9840a852469fb52464c844b1e199bd519df6ccd
+oid sha256:718e253dbdea575c7a0998016d760d01dfb23c13bfe0d762ede53cb1f9fe432a
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db849a663e08cfe1040409170bc118f155064dad14c6346fb8073f2592cf7bdf
+oid sha256:612d2f797d5c655dcab151fdf2a22a703a22c83c938e91e54e165d0cfcd34af1
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 76.46153846153847,
+  "epoch": 76.53846153846153,
   "eval_steps": 500,
-  "global_step": 9940,
+  "global_step": 9950,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17900,6 +17900,24 @@
       "mean_token_accuracy": 0.6454123288393021,
       "num_tokens": 36250099.0,
       "step": 9940
+    },
+    {
+      "epoch": 76.5,
+      "grad_norm": 0.0,
+      "learning_rate": 2.8e-07,
+      "loss": 1.7129,
+      "mean_token_accuracy": 0.6584518551826477,
+      "num_tokens": 36268558.0,
+      "step": 9945
+    },
+    {
+      "epoch": 76.53846153846153,
+      "grad_norm": 0.0,
+      "learning_rate": 2.5500000000000005e-07,
+      "loss": 1.7443,
+      "mean_token_accuracy": 0.6507739454507828,
+      "num_tokens": 36286936.0,
+      "step": 9950
     }
   ],
   "logging_steps": 5,
@@ -17919,7 +17937,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.838176966829998e+18,
+  "total_flos": 1.8401131197392486e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null