Training in progress, step 11500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c7272b6a36a11e729b1592c76cb3df2e65bd737e0f9f83fdb0e8089e1fc3958
+oid sha256:39160a24f518bb39d40c921eba0157cfc79a62682458140df4d9769685c1b068
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbfdf0d65172ed8f162d02e6aeb02d5176731446f5c5a18e66c538df8a33eab7
+oid sha256:d03737474f4b5464ab0a16f2d16328dec5ad6f74a4ba7ae94e673a76a8d897bb
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81366beb45812d30c24b5a5034071dc5850a14e0029b0be5806b5186ffb17322
+oid sha256:4bc45ac1a35f5f4645973545cd88afbd0064272773488fa12a6e4551c2656024
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:976d1f52844e987390213cc75aaff01e7bbae8d7552dcf3147571e784e111d4d
+oid sha256:034840a84c5a8ab5df6df26a6069c2f569beaac573ff6922f4d724159461eb57
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.28595178719867,
+  "epoch": 2.3898586866167912,
   "eval_steps": 500,
-  "global_step": 11000,
+  "global_step": 11500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -177,6 +177,13 @@
       "learning_rate": 4.767248545303408e-06,
       "loss": 0.3383,
       "step": 11000
+    },
+    {
+      "epoch": 2.3898586866167912,
+      "grad_norm": 1.5681509971618652,
+      "learning_rate": 4.074535882515933e-06,
+      "loss": 0.3412,
+      "step": 11500
     }
   ],
   "logging_steps": 500,
@@ -196,7 +203,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.339585567653888e+16,
+  "total_flos": 1.400481356709888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null