Training in progress, step 8800, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f5719b49c985e99447815b6b3001dcba30277a29573a88a40d27b865e1c4f56
+oid sha256:65fac079012d2743e2d7b401cf1954e67e3f37531082186c09998649ede646e5
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60b191938c8f31d4fef1cf5fed78065b4323c489da59ab05689d87892e9875ed
+oid sha256:3ba1c930ef5ea9d94774effd84b8cceeb3e5f7a878575457ba9c8d7dddfdd35d
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4404ecd15d394ad464005ce3f748ae71faa509ab95d5a9abfb24e1679dcb2df4
+oid sha256:a48c4a740cb79a9695b2411ffb80d0d58c6e7b3834d88c8f8bb5a97b3fb8584f
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 67.61538461538461,
+  "epoch": 67.6923076923077,
   "eval_steps": 500,
-  "global_step": 8790,
+  "global_step": 8800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -15830,6 +15830,24 @@
       "mean_token_accuracy": 0.6468034237623215,
       "num_tokens": 32055491.0,
       "step": 8790
+    },
+    {
+      "epoch": 67.65384615384616,
+      "grad_norm": 0.0,
+      "learning_rate": 6.03e-06,
+      "loss": 1.7737,
+      "mean_token_accuracy": 0.6413617432117462,
+      "num_tokens": 32073407.0,
+      "step": 8795
+    },
+    {
+      "epoch": 67.6923076923077,
+      "grad_norm": 0.0,
+      "learning_rate": 6.005e-06,
+      "loss": 1.733,
+      "mean_token_accuracy": 0.6513085424900055,
+      "num_tokens": 32092096.0,
+      "step": 8800
     }
   ],
   "logging_steps": 5,
@@ -15849,7 +15867,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6254608621705626e+18,
+  "total_flos": 1.6272596711183155e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null