Training in progress, step 116000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ef6d9164fcc63d8c31830cd53f13125e44952328cb65d273c6cbf03adac7b27
+oid sha256:21f69249304bdff1d3ea1ecc50476150900c1bf0c9f683b0251518026d12f1d7
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4efddb25cc5acacd62779c71a39f505bc1a51948e0fc2f65802d78f446003b2
+oid sha256:adce678223c82770dfb3566de88aa9d62135c9d2559228b69da7cb99ce928482
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d01948163fe077dcd2468e825b9e50bf4fb6af26b29607313915bfeb893a809
+oid sha256:7ca33b6eb1024f2f9bb905e02c31a76d10aa7c3bfb63988ff66fca3468990a68
 size 14942

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9945004b0a8ef62883a98355080d2c0b2c63cd785d60b4622fb16e6e6d8bcfd1
+oid sha256:245f8ce24920b8e2a7bc05eeae8c43d4ad36f729db05186d1669730818cd8914
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 27.700831024930746,
+  "epoch": 27.941707816451885,
   "eval_steps": 500,
-  "global_step": 115000,
+  "global_step": 116000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -812,6 +812,13 @@
       "learning_rate": 7.652774431863809e-05,
       "loss": 0.7584,
       "step": 115000
+    },
+    {
+      "epoch": 27.941707816451885,
+      "grad_norm": 0.6525952219963074,
+      "learning_rate": 6.849755079097407e-05,
+      "loss": 0.7536,
+      "step": 116000
     }
   ],
   "logging_steps": 1000,
@@ -831,7 +838,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1504183697494508e+18,
+  "total_flos": 1.1604222462299996e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null