Training in progress, step 22000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd5b5e98539c95081b5b5cda62d0f55989ce2c2997ed431ceaa4bdcfdd2a30b
+oid sha256:37070adb1e33476e3806a9c8d12ec561ecd3eec0a996712be9bf7a6982dac5cf
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:863bc484be501956f7b5ff35b1fe9ce7c27b91dc95b58397452133338a3bdfe2
+oid sha256:a07839cf5c2c047c6ec7045fe3b167c8502e524aa77ddc607feffd450b175220
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f16e59c81cf6235061b0589b42cafd62d82376bb7aaeb85fff669f16f33825a7
+oid sha256:910d48a0ba4119bf4888050d8ec05abd1572fc598bf775e782280221ed11bfe6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0872affebfd17ba535a2248c0d62d819df48f4a22e7602d164fd972b0b4870cd
+oid sha256:3a105f87913482f13a1534e0e0f4c8fdbb51cb7a7965de26ac387af13c367440
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.299570288520565,
+  "epoch": 3.376304481276857,
   "eval_steps": 500,
-  "global_step": 21500,
+  "global_step": 22000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -295,13 +295,19 @@
       "learning_rate": 0.00034033149171270715,
       "loss": 0.4841,
       "step": 21500
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 0.00032501534683855126,
+      "loss": 0.4906,
+      "step": 22000
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1.13955682123776e+16,
+  "total_flos": 1.1660778931224576e+16,
   "trial_name": null,
   "trial_params": null
 }