Training in progress, step 9970, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9abb2da57c0370b1f14aa563b68ddec35263d994da8cae1e7932066cff64c462
+oid sha256:6cdb2a5a901c63b779f1866ebf5cde2e6a49a922c05207376e7847a8df285914
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c2dc023be3ca362601ab3f8e11e9042b1276b01b6df27ff4330c647c55b2394
+oid sha256:36579bea99df82fd100f51f078b75ec7090161b4f6090440eb87c9a54ca32412
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d1028be78b68d90fd2885810eacd8831cc358fd14f37f26d78823fdf07cb424
+oid sha256:26906f9180f00219fff96ef9a710000390990b70abeaa78af7e691112ec5c682
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 76.61538461538461,
+  "epoch": 76.6923076923077,
   "eval_steps": 500,
-  "global_step": 9960,
+  "global_step": 9970,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17936,6 +17936,24 @@
       "mean_token_accuracy": 0.6495934307575226,
       "num_tokens": 36324168.0,
       "step": 9960
+    },
+    {
+      "epoch": 76.65384615384616,
+      "grad_norm": 0.0,
+      "learning_rate": 1.8e-07,
+      "loss": 1.7612,
+      "mean_token_accuracy": 0.6480752646923065,
+      "num_tokens": 36342496.0,
+      "step": 9965
+    },
+    {
+      "epoch": 76.6923076923077,
+      "grad_norm": 0.0,
+      "learning_rate": 1.55e-07,
+      "loss": 1.6781,
+      "mean_token_accuracy": 0.6652602583169938,
+      "num_tokens": 36360871.0,
+      "step": 9970
     }
   ],
   "logging_steps": 5,
@@ -17955,7 +17973,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8420394283414323e+18,
+  "total_flos": 1.8439063535429222e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null