Training in progress, step 4500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a1526ce35959c2aafc5ee860281c41c0885235aa4acf92b63b315011ed4da93
+oid sha256:296a3c6d309d1e85d28d84a70644a84db24c66100970c1560c1c1f4cc57b30b5
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bf30eb76d8e637486d38576ec2d8c3027b12ad2bd71cb6716b79761a591173f
+oid sha256:7757311822a5bbc6563a14ae734cc5c55ec098bd049b31c1a6eedd6462d9519a
 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": 0.4062,
       "step": 4000
+    },
+    {
+      "epoch": 0.9351620947630923,
+      "grad_norm": 1.4694277048110962,
+      "learning_rate": 1.3769742310889445e-05,
+      "loss": 0.4029,
+      "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