Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc283c82b5b098dc73fe2ddea55d22392b184b8467c61fdf7f6d1a931b702426
+oid sha256:9415856e807b29df4993d2b93aca936596036cd8ea77478081e28c5b1693b642
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10bccdb8d8a5d0741e794a3426fc654dd805cd0307df7076ad12f4bd75315681
+oid sha256:fd5250b12447318c0f90fbb87ee5bfada24895af5f76810a4e55372ceeb9068f
 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 sha256:74206ba2619c9d016ba1c129d7d0bc686d1e7317df183cf2d559f7293b5ce953
 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": 0.3594,
       "step": 5500
+    },
+    {
+      "epoch": 1.2468827930174564,
+      "grad_norm": 0.48619207739830017,
+      "learning_rate": 1.1691604322527017e-05,
+      "loss": 0.3736,
+      "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