Training in progress, step 16000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a026e071b1e9ccf305886c9f4b0fd1b2ff3a0c6f479e54c91760927ffe8534b
+oid sha256:2971a731e2fbc5382f203c313714874b6442c0ef407ba0b340fe6bd607cf0d81
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c8abbb5ace835107c998734168c52bca07dddaab2105fc321fdc2afa0796029
+oid sha256:927e00b3ef25dbe2d0c60c7010649323428184118ae870950e04c65465b8d66e
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb03875b0ff82321173ec7ebfdbb4756b9de0c0e7e17519178fc0be76b12441d
+oid sha256:a815d4b671b2f9d54ad695690d7a84e5c6eff4353f840b0741a667f1355175d5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1820545852d3566a9453339979bf92f6e10cdd9f597f504847d317ad3ff68c77
+oid sha256:34fd0dc259f4263e977c8cb3231c9f2408c2c6a6f820345c818e9c5127a7086f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.378759975445058,
+  "epoch": 2.4554941682013505,
   "eval_steps": 500,
-  "global_step": 15500,
+  "global_step": 16000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,13 +213,19 @@
       "learning_rate": 0.0005244014732965009,
       "loss": 0.5321,
       "step": 15500
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 0.000509085328422345,
+      "loss": 0.5271,
+      "step": 16000
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 8216994104475648.0,
+  "total_flos": 8481333560475648.0,
   "trial_name": null,
   "trial_params": null
 }