Training in progress, step 9860, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67368ddbf8acaee4b2e60cc9ba051abf07b5d10e051dcc5182ce50369b432dfe
+oid sha256:4dc96fdce5dd977bc8ed6ddd183da2e20f9d175e6f2659b1d5dcda7229aaa29f
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54f5cdb890790a8f1f38ce61319d076a5cdd3cfeecff92d19d4ab2ef594e650d
+oid sha256:0667df74cf1a80e1bd1ed11ba360e47cc43579a830092053300c08b4c60b96bf
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42ddc652bb0436a0cd163a32dd0eb325e68cb34ddcfcb9b1bf0806c257f0cc63
+oid sha256:0b54d3746e7ba0df80197975861f45ba1f898e1da86fe37a21a87be38d43f919
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 75.76923076923077,
+  "epoch": 75.84615384615384,
   "eval_steps": 500,
-  "global_step": 9850,
+  "global_step": 9860,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17738,6 +17738,24 @@
       "mean_token_accuracy": 0.6488775163888931,
       "num_tokens": 35921829.0,
       "step": 9850
+    },
+    {
+      "epoch": 75.8076923076923,
+      "grad_norm": 0.0,
+      "learning_rate": 7.3e-07,
+      "loss": 1.8236,
+      "mean_token_accuracy": 0.6332837879657746,
+      "num_tokens": 35939046.0,
+      "step": 9855
+    },
+    {
+      "epoch": 75.84615384615384,
+      "grad_norm": 0.0,
+      "learning_rate": 7.05e-07,
+      "loss": 1.6545,
+      "mean_token_accuracy": 0.6667064487934112,
+      "num_tokens": 35957880.0,
+      "step": 9860
     }
   ],
   "logging_steps": 5,
@@ -17757,7 +17775,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.821597089600471e+18,
+  "total_flos": 1.8233619198109286e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null