Training in progress, step 306500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e67cb24b5c7f8f8f4375b0db04500bcc197056ffee0d9ae806c274773498fc47
+oid sha256:51adf105e6f6a7ed906d29c700a302ed25a5f3762591fb828115de3db85e6428
 size 891644712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a35c508ec9ef02da634fb99ba732a8522e613b658a75aaa26a9b7b7f2493e0ac
+oid sha256:61e99f73129aa9790926d7e259881eb34dc636e42b1b114ed72b764955661475
 size 1783444357

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72a128c971ea8f9adfc8199f5d8881c46f465a1de9bd830d2e82fbc2fd4820cf
+oid sha256:de8a5728e1af3d048775ed91e97081b2078f2ef02825d44e2a1d3ed6f1e431ea
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e6c66490c6ad4b2efcb520faa311a87fdb2457e0dbd926b08a9eb8cc11d8971
+oid sha256:c5ef81669a76b9bc8adaca72bc010d0d224d425bd06e93da371512f70d617c1a
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9584000000000001,
+  "epoch": 1.9616,
   "eval_steps": 500,
-  "global_step": 306000,
+  "global_step": 306500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4291,6 +4291,13 @@
       "learning_rate": 1.05808e-06,
       "loss": 0.2484,
       "step": 306000
+    },
+    {
+      "epoch": 1.9616,
+      "grad_norm": 0.5446351170539856,
+      "learning_rate": 9.780799999999999e-07,
+      "loss": 0.2434,
+      "step": 306500
     }
   ],
   "logging_steps": 500,
@@ -4310,7 +4317,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.49072891609088e+18,
+  "total_flos": 1.49316474765312e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null