Training in progress, step 24000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2af21bcb234416212ea1f5b026d11d179220f6fbb3a2641ccba3f02dde45c3dd
+oid sha256:741c397041ed1b4648d0d7a107b64a0f1f3cdaafa5bf9d2c7fc3f7585a267cce
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25ef7d9bf21993e077d3c1f4582bfea1ebb7c01c47e5cc086a69cbc49cac3765
+oid sha256:df6c3b19e9b1481d812ed3ffe84d72bbe8bf551c321a11a94fb3e2f183b77833
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:591801439d497d64b1d36c4d68d48d623a6198675bbf3bfc206f69a006b70528
+oid sha256:4cc745f63e0fd4e3671c8f894e695796bb932dae2274cc3a6fcf22bb60f20151
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11f2f9e913d6dc22945b53e51010b8c3a78477d95df46ad1339d411474610a33
+oid sha256:eda1bc261c307bd721c949357fffd7c64b7728076e0d5fa1fe1ed6776a252464
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.6065070595457334,
+  "epoch": 3.6832412523020257,
   "eval_steps": 500,
-  "global_step": 23500,
+  "global_step": 24000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -319,13 +319,19 @@
       "learning_rate": 0.00027897483118477593,
       "loss": 0.4932,
       "step": 23500
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 0.00026365868631062,
+      "loss": 0.4951,
+      "step": 24000
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1.2455218388140032e+16,
+  "total_flos": 1.2721511841398784e+16,
   "trial_name": null,
   "trial_params": null
 }