Training in progress, step 65500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd99d22f631d655bafa0ef921825bcac2b2df42c1345f4f9a951d158bf615583
+oid sha256:8dc8104f338da3f703a8c7db517ccd74a55483e325eb7b62d1677331f193b714
 size 891644712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:724bb64220f2c161eb3405e2f9cd8e66607b6d55bd8fd225e7c8e74e6dbcc62b
+oid sha256:3280d99d101d2df46382510e64aeceac2dfadb7368e5b404a835a52228aec872
 size 1783444357

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87df364b8a2ed1fef782c858fba27ed776a184876aa3b66d329ff8aa75bd7a24
+oid sha256:a5fa100f78ab19691d28ec992b81f2bc596df68215254a32c2ad7805080819ee
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1452c3e81c52ae774720bef3063ad9b20552f8d2905fb135042cced0dd4241c8
+oid sha256:ef43b45a6f4aff5695c7605473a85adfe75b0ff523db2d49fa1e5cfae822c330
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.416,
+  "epoch": 0.4192,
   "eval_steps": 500,
-  "global_step": 65000,
+  "global_step": 65500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -917,6 +917,13 @@
       "learning_rate": 3.9603840000000005e-05,
       "loss": 0.3234,
       "step": 65000
+    },
+    {
+      "epoch": 0.4192,
+      "grad_norm": 0.6800302863121033,
+      "learning_rate": 3.952384e-05,
+      "loss": 0.3224,
+      "step": 65500
     }
   ],
   "logging_steps": 500,
@@ -936,7 +943,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.166581030912e+17,
+  "total_flos": 3.1909393465344e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null