Training in progress, step 28000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b64bf1ebf51d694fdeb9bca1a73e68a759d5f8f5c94a4f4197023b270a5f74b6
+oid sha256:ddaa72deb8ab44e6b062f6762445853e6cbb361c09cd5f5ca7250588ef827f6a
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:219fc53d62837117473847c70028456e7d7441f74f337dc27b72ae302eb20251
+oid sha256:fa38d7628f4b5efece14b6017eb194c8d0f5bb07dd80fa4cb3a1b986649e1b3c
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c52f344ac7ec92d77a075d151f1a470c012f516bcc11d7f83acfeb94aba37af
+oid sha256:3bad8f074d634b0b7f7ecbd77330c361a45090adb1753e3cd2b0453d620c49cb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a9597bf6b4c68d872ba3fdb9fcdf4f05ecc611643dfedee62c13aced510caee
+oid sha256:eacef275294161468a385a147f2879c9e08ddcbb47ca8cc9e49fdd2dffa3b0be
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.220380601596071,
+  "epoch": 4.297114794352363,
   "eval_steps": 500,
-  "global_step": 27500,
+  "global_step": 28000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -377,13 +377,19 @@
       "learning_rate": 0.00015626151012891346,
       "loss": 0.454,
       "step": 27500
+    },
+    {
+      "epoch": 4.3,
+      "learning_rate": 0.00014094536525475752,
+      "loss": 0.4547,
+      "step": 28000
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1.4580021229780992e+16,
+  "total_flos": 1.4845312307822592e+16,
   "trial_name": null,
   "trial_params": null
 }