Training in progress, step 23500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f9bc12fe7f41f93898a3565c578901a35ec95a444b8f6692576211509567d96
+oid sha256:2af21bcb234416212ea1f5b026d11d179220f6fbb3a2641ccba3f02dde45c3dd
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ee66b02457dc0fc065c4d48e1394ba39983aa3109a98f4e76a47452241872e6
+oid sha256:25ef7d9bf21993e077d3c1f4582bfea1ebb7c01c47e5cc086a69cbc49cac3765
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1fc454f69c4aebd0e72ac0743abb5fe7361ef86e1ac9dab17595186c249581e
+oid sha256:591801439d497d64b1d36c4d68d48d623a6198675bbf3bfc206f69a006b70528
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:118dcc20ed6d41cbe348cc80ba0f9406a17628cc49de57f87f8371d173dec1a0
+oid sha256:11f2f9e913d6dc22945b53e51010b8c3a78477d95df46ad1339d411474610a33
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.5297728667894415,
+  "epoch": 3.6065070595457334,
   "eval_steps": 500,
-  "global_step": 23000,
+  "global_step": 23500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -313,13 +313,19 @@
       "learning_rate": 0.0002943216697360344,
       "loss": 0.486,
       "step": 23000
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 0.00027897483118477593,
+      "loss": 0.4932,
+      "step": 23500
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1.2189800427159552e+16,
+  "total_flos": 1.2455218388140032e+16,
   "trial_name": null,
   "trial_params": null
 }