Training in progress, step 117000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21f69249304bdff1d3ea1ecc50476150900c1bf0c9f683b0251518026d12f1d7
+oid sha256:d4693ab1d7b89c8b62f59e3b745ac1d26958661e43128d0951c45a8dae2b0449
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adce678223c82770dfb3566de88aa9d62135c9d2559228b69da7cb99ce928482
+oid sha256:46a245f6ed22667309e57e9a46319a8b2fe7b589321a520f67f07d4b72b056ac
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ca33b6eb1024f2f9bb905e02c31a76d10aa7c3bfb63988ff66fca3468990a68
+oid sha256:ca5192042f50a136fba0493cd299946cbaf57e870dcaa2fe525804417d01654b
 size 14942

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:245f8ce24920b8e2a7bc05eeae8c43d4ad36f729db05186d1669730818cd8914
+oid sha256:988ef2aca538b3b817a541deff8ad816e9a0af759270c4a157b0d1aedf5cd77c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 27.941707816451885,
+  "epoch": 28.182584607973023,
   "eval_steps": 500,
-  "global_step": 116000,
+  "global_step": 117000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -819,6 +819,13 @@
       "learning_rate": 6.849755079097407e-05,
       "loss": 0.7536,
       "step": 116000
+    },
+    {
+      "epoch": 28.182584607973023,
+      "grad_norm": 0.64836186170578,
+      "learning_rate": 6.046735726331005e-05,
+      "loss": 0.7535,
+      "step": 117000
     }
   ],
   "logging_steps": 1000,
@@ -838,7 +845,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1604222462299996e+18,
+  "total_flos": 1.170425106950783e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null