Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8322b5283d76576b6243d188fe146f52a61201fd3c25ceb62074d59997bad9c2
+oid sha256:b8da66a9292141d41a6c48606ed339406a31277522edcf0302aa38aa658f2e9e
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a4cbaa339a503815e8f93b8496d408a46cf594a349bfa6e55b537a7341aed97
+oid sha256:d6e16c15bc4b1df3cf9e6fe1a2e38058b03a4f63c25e10991bd06af6c213d0c8
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17e30f2d5aa88fa3a0cef0484b7fc130d9829c04f56c17d8644266ef1a1405ee
+oid sha256:34caa8055744af1af91499eaae75425a5f72db08ebfbc7b0e342b4b8e68e6533
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e13ecaded8f565c1efc7f8c1f8e87f707a0c1e13fed3f11510caa036a76b90cf
+oid sha256:a00f8130c8c43ba3b86ef986c4fb4241ebc0a44808b15806e2c7f948b3aa8ef4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.142975893599335,
+  "epoch": 1.2468827930174564,
   "eval_steps": 500,
-  "global_step": 5500,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -92,6 +92,13 @@
       "learning_rate": 1.2384316985314493e-05,
       "loss": 0.3599,
       "step": 5500
+    },
+    {
+      "epoch": 1.2468827930174564,
+      "grad_norm": 0.49429360032081604,
+      "learning_rate": 1.1692989747852592e-05,
+      "loss": 0.3737,
+      "step": 6000
     }
   ],
   "logging_steps": 500,
@@ -111,7 +118,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6697927838269440.0,
+  "total_flos": 7306885728829440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null