Training in progress, step 124000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3347db068ed8381d72d2614b99d290079b5c267bb2297bc18668d9746413ee
+oid sha256:68dfc7560d6b33287f16f326521b62bf70702c1316c8245d6e16f48e1915b6af
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d71f57dd221410708221eda3423c39de5dcd636994583f199f84f393a1e9480
+oid sha256:c93ce47d1bddb90dfde4ca121ebe6b20aa594737b837c06912e0fb1d73fd5d0f
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd569f1a705a1ad9d99351673332581a558f2e1131cc249f63637b426b1267b1
+oid sha256:adc788c14beb616c37b4d527a083c528730f2bcae41b83d45e653b9a89b038a9
 size 14942

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d32025f87bd47ef75385673d365a029e9e810c5fd5b698fddba7741fb9b51c62
+oid sha256:328afdc9a36cd91cd35c29d6d57aec2385befadcbc8db8a072ff5fd4f7b81320
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 29.627845357099844,
+  "epoch": 29.868722148620982,
   "eval_steps": 500,
-  "global_step": 123000,
+  "global_step": 124000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -868,6 +868,13 @@
       "learning_rate": 1.2286196097325946e-05,
       "loss": 0.7431,
       "step": 123000
+    },
+    {
+      "epoch": 29.868722148620982,
+      "grad_norm": 0.596747875213623,
+      "learning_rate": 4.256002569661929e-06,
+      "loss": 0.7426,
+      "step": 124000
     }
   ],
   "logging_steps": 1000,
@@ -887,7 +894,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2304473500743107e+18,
+  "total_flos": 1.2404512265548595e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null