Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eed9be38557b8695a95b58cf18cc535284220e68d6e1d7a407b2fad78a88b52
+oid sha256:59df7af61b4c7771227501b0834a7372aa186caff25d1888cabfa478ae52abad
 size 101948208

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a772ec38d17901d3771e3a8fe66c984bed05038bc9c47afb72eb696c971c982e
+oid sha256:0be770c77c3c19350855b298c733caf15a902a09d3e9fedcc23389802cb35391
 size 203962810

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d91d2b1ae50bd9bb1dda7981bcdcfea49e460cc439c62f449bcf30d2a71066f9
+oid sha256:ce1698bbd40089491cfcd0d2c2bb280426dc9ee89a6596df59ffe8fad725ed49
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08614159896630082,
+  "epoch": 0.08911199893065601,
   "eval_steps": 500,
-  "global_step": 5800,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -84,6 +84,13 @@
       "learning_rate": 0.0019836628001960463,
       "loss": 5.4899,
       "step": 5500
+    },
+    {
+      "epoch": 0.08911199893065601,
+      "grad_norm": 0.41542890667915344,
+      "learning_rate": 0.001982177600213869,
+      "loss": 5.4649,
+      "step": 6000
     }
   ],
   "logging_steps": 500,
@@ -103,7 +110,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 304594865356800.0,
+  "total_flos": 315098136576000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null