Training in progress, step 26000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7d31294180b76c51dcf0dc671b4869fcce074d14559be647a6612c0a2eb4bca
+oid sha256:3e97e80e6df5989f5c91ab63ea43f5b2ca8a05f152fe5e6129ec6bf8c679d959
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:388586f813cd158a5ff0d60eea6aef06f769451c7809e59b115d1db1488b7f08
+oid sha256:17a81e2763c1f90c3086db2122c1b6693ed8e7d0c40e266496964112de03041b
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc1a9bd02c25634a7155b50fa998953c4b02c376844d9fda4b7d6baa7f3e9c31
+oid sha256:15c30e5b3c62da6ee4bd3e3e0e8cb7d4b01db5d518a133414f644382a3b9f465
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f6bbdc041e242a8994ac2149fe65ed83fc69ebc45ef59d4e5c03aaec2e6f319
+oid sha256:eb570b21cb9f69d323d96201074116d11f52a4be1f81a137b4684e199ff7f56a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.9134438305709023,
+  "epoch": 3.9901780233271946,
   "eval_steps": 500,
-  "global_step": 25500,
+  "global_step": 26000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -343,13 +343,19 @@
       "learning_rate": 0.00021761817065684468,
       "loss": 0.4874,
       "step": 25500
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 0.00020230202578268877,
+      "loss": 0.488,
+      "step": 26000
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1.3519148748374016e+16,
+  "total_flos": 1.3784841622388736e+16,
   "trial_name": null,
   "trial_params": null
 }