Training in progress, step 114000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ff8fb4f9cb3d5afad8cdb40fd27f1c8fd8f854a8f3f3632dfbcc9d68ee558db
+oid sha256:19abc838eebb3f9fb184c884e8c7255858388339a004d4b0a3c824ade1ac39a0
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66eee158418f2861216bd0941caeb55ffb7fa69a3e6bdb7f0b35490a5d03eb93
+oid sha256:3fba3aff64c961e9e3a2514de51574394663e7b8e9ddc39a3e09e689cce5eacb
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df6871802ef6f60eaff38c1d182f0eedcea8dd6374065ee4d8c7a495afffbc58
+oid sha256:704e7c644aae2a8569c0f8a64a088bdeaa8145c7a6e692e4af2abf3af6fc64e1
 size 14942

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88585550cf269e91dd6373dae931042068a9ec046474a44c70af58569e076a0b
+oid sha256:a05e1e35a513284408d3d6da7070f86a1480167321aa24eec511adde9a6364a8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 27.219077441888473,
+  "epoch": 27.45995423340961,
   "eval_steps": 500,
-  "global_step": 113000,
+  "global_step": 114000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -798,6 +798,13 @@
       "learning_rate": 9.258813137396611e-05,
       "loss": 0.7619,
       "step": 113000
+    },
+    {
+      "epoch": 27.45995423340961,
+      "grad_norm": 0.6430843472480774,
+      "learning_rate": 8.45579378463021e-05,
+      "loss": 0.7598,
+      "step": 114000
     }
   ],
   "logging_steps": 1000,
@@ -817,7 +824,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.130410616788353e+18,
+  "total_flos": 1.1404144932689019e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null