Training in progress, step 8500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c5b2419640fe13669a068fb7e26254322466c5d858313ef02de53677581c9d
+oid sha256:1dc2072ab9a0e445296ac3f8151eea455e3a58f3604a73d68130568942d05a3a
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89674eaeda206b838ac99ca2ee9263c40a01135163edaa0624d151c7c84fd452
+oid sha256:18afe885f408124fd9c4a843f52e43ad3cd190a9477afeaa42ec3c53365c26c3
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd79f2fefbaefbe9088e7c79a1da25f013e6ccd3483f5ddbddeb65ac105c1771
+oid sha256:0390b75aa632da72c0c84f21e08a92a40f781f7159c00fed0fdc797f3bb9d115
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f56c5e55013c47d62968ace7dd778a0c079a8e2b4cfdd3b2ddaacc49c8a8e75
+oid sha256:34364c2d46a6c353df83d4f0e0edfb9e1cd6fed16aeac57800bc7243c82339db
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2277470841006752,
+  "epoch": 1.3044812768569676,
   "eval_steps": 500,
-  "global_step": 8000,
+  "global_step": 8500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -113,13 +113,19 @@
       "learning_rate": 0.0007545119705340699,
       "loss": 0.5669,
       "step": 8000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.000739195825659914,
+      "loss": 0.5793,
+      "step": 8500
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 4240465882251264.0,
+  "total_flos": 4506129150246912.0,
   "trial_name": null,
   "trial_params": null
 }