Training in progress, step 21500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dedc0dc44de6bcf8533e592ce68c222b528cd994a150b2d3f296a68000653f10
+oid sha256:fcd5b5e98539c95081b5b5cda62d0f55989ce2c2997ed431ceaa4bdcfdd2a30b
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b1427a38d6b61ba213a6bebe4cba12227f4c5384edabf96a158902c0aa4ece1
+oid sha256:863bc484be501956f7b5ff35b1fe9ce7c27b91dc95b58397452133338a3bdfe2
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:801adf4445dd3769164c30f6179bdb3feeab15fc26be81439ffeae1b23a90b17
+oid sha256:f16e59c81cf6235061b0589b42cafd62d82376bb7aaeb85fff669f16f33825a7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46368ba620b42094a299a9c06a36f3d28acb525d16404e7926726905b6d401be
+oid sha256:0872affebfd17ba535a2248c0d62d819df48f4a22e7602d164fd972b0b4870cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.2228360957642725,
+  "epoch": 3.299570288520565,
   "eval_steps": 500,
-  "global_step": 21000,
+  "global_step": 21500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -289,13 +289,19 @@
       "learning_rate": 0.0003556783302639656,
       "loss": 0.4917,
       "step": 21000
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 0.00034033149171270715,
+      "loss": 0.4841,
+      "step": 21500
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1.1130310969786368e+16,
+  "total_flos": 1.13955682123776e+16,
   "trial_name": null,
   "trial_params": null
 }