Training in progress, step 4500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cbe649c71b516b094216fbea21197a8afdeff556e86902ecc63fac11ca9d235
+oid sha256:1bdcea07d77b677c78e6c852f8f008c8fae5d04a2f8735d08be078cf14a800a8
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:272c3de368eb938e5ec04ee3958d5faee41704c34b38097bf92699ca98709501
+oid sha256:a426c1319c8371c822d9a891ae4d493e112eab044e83da934efd1a314fdfeffd
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6909786b07113d046b6984022b8f3c1d4a309c9e0a18f83af53a35bec4523b1
+oid sha256:509ee6f2dc95c367cf1eda5ebb7ac0772535dbbc4fb915944d9e317d5b2f8b3a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09e9e60d2c8faf134da25c0954086bcd3b7f390c1be768462509e5eb18839183
+oid sha256:e2b5d040d5c740697a7c2dcc153f257910aea505a3c7139823305a169f6a1ef0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8312551953449709,
+  "epoch": 0.9351620947630923,
   "eval_steps": 500,
-  "global_step": 4000,
+  "global_step": 4500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,6 +63,13 @@
       "learning_rate": 1.446245497367692e-05,
       "loss": 0.4065,
       "step": 4000
+    },
+    {
+      "epoch": 0.9351620947630923,
+      "grad_norm": 1.4909119606018066,
+      "learning_rate": 1.3769742310889445e-05,
+      "loss": 0.4031,
+      "step": 4500
     }
   ],
   "logging_steps": 500,
@@ -82,7 +89,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4871663124480000.0,
+  "total_flos": 5480621015040000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null