Training in progress, step 11000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a27d48d34b8ccad96e402eb4f94ec667bf372ecd65cd4746cd18d89a3ee31ae
+oid sha256:720eceeb2b357ad023a64f886e05d484eb7d9c0097f7eb7db6168cd2d52a3b5b
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96bc579cba2ba220a43642dd36ae216045b6c492a0b978a80ccd6cf9f5f30491
+oid sha256:c19224722ae663a153f5b72e8e4abd5762e71691698100f741aa39099196b03f
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d0ff9a7184dfef904a073aa76234f185ca283c0a479c1a8c903692aec73c4aa
+oid sha256:a6eb93bead6d30b6932224ec7fe6ef202eebeaf7927b1e6638dfda624b533562
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68bbf668b8239771e72cdecbaae5a40e09f6e926879b6dffd5fd09ed3de5395e
+oid sha256:723c1afc9409a31cc02de5b4cfab645904dc7aaa6048019bba9e3ae17f717c52
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.364089775561097,
+  "epoch": 4.57190357439734,
   "eval_steps": 500,
-  "global_step": 10500,
+  "global_step": 11000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -186,6 +186,13 @@
       "learning_rate": 2.550290939318371e-06,
       "loss": 0.3129,
       "step": 10500
+    },
+    {
+      "epoch": 4.57190357439734,
+      "grad_norm": 0.956358015537262,
+      "learning_rate": 1.7190357439733998e-06,
+      "loss": 0.3166,
+      "step": 11000
     }
   ],
   "logging_steps": 500,
@@ -205,7 +212,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.557379557195776e+16,
+  "total_flos": 2.679171135307776e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null