Training in progress, step 11500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720eceeb2b357ad023a64f886e05d484eb7d9c0097f7eb7db6168cd2d52a3b5b
+oid sha256:3866dd2a6475ce2b7385f181f047f2dde98048fd09569a5804ff351fd5e9912f
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c19224722ae663a153f5b72e8e4abd5762e71691698100f741aa39099196b03f
+oid sha256:9fa541d3192bd288c7edb3660d558e142b5e462f59453619d7373f84590e81f7
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6eb93bead6d30b6932224ec7fe6ef202eebeaf7927b1e6638dfda624b533562
+oid sha256:8fe8dfec12d6b343eb28ee2b43b75b45c3ae2d185dfc75ecd757d9ec7c567e31
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:723c1afc9409a31cc02de5b4cfab645904dc7aaa6048019bba9e3ae17f717c52
+oid sha256:2504d9c9451078f79b98032c170c402f3ffeb92d11496a90427e835bd48cd055
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.57190357439734,
+  "epoch": 4.7797173732335825,
   "eval_steps": 500,
-  "global_step": 11000,
+  "global_step": 11500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -193,6 +193,13 @@
       "learning_rate": 1.7190357439733998e-06,
       "loss": 0.3166,
       "step": 11000
+    },
+    {
+      "epoch": 4.7797173732335825,
+      "grad_norm": 0.7600696682929993,
+      "learning_rate": 8.89443059019119e-07,
+      "loss": 0.3117,
+      "step": 11500
     }
   ],
   "logging_steps": 500,
@@ -212,7 +219,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.679171135307776e+16,
+  "total_flos": 2.800962713419776e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null