Training in progress, step 115000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19abc838eebb3f9fb184c884e8c7255858388339a004d4b0a3c824ade1ac39a0
+oid sha256:4ef6d9164fcc63d8c31830cd53f13125e44952328cb65d273c6cbf03adac7b27
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fba3aff64c961e9e3a2514de51574394663e7b8e9ddc39a3e09e689cce5eacb
+oid sha256:c4efddb25cc5acacd62779c71a39f505bc1a51948e0fc2f65802d78f446003b2
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:704e7c644aae2a8569c0f8a64a088bdeaa8145c7a6e692e4af2abf3af6fc64e1
+oid sha256:7d01948163fe077dcd2468e825b9e50bf4fb6af26b29607313915bfeb893a809
 size 14942

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a05e1e35a513284408d3d6da7070f86a1480167321aa24eec511adde9a6364a8
+oid sha256:9945004b0a8ef62883a98355080d2c0b2c63cd785d60b4622fb16e6e6d8bcfd1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 27.45995423340961,
+  "epoch": 27.700831024930746,
   "eval_steps": 500,
-  "global_step": 114000,
+  "global_step": 115000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -805,6 +805,13 @@
       "learning_rate": 8.45579378463021e-05,
       "loss": 0.7598,
       "step": 114000
+    },
+    {
+      "epoch": 27.700831024930746,
+      "grad_norm": 0.6248263120651245,
+      "learning_rate": 7.652774431863809e-05,
+      "loss": 0.7584,
+      "step": 115000
     }
   ],
   "logging_steps": 1000,
@@ -824,7 +831,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1404144932689019e+18,
+  "total_flos": 1.1504183697494508e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null