Training in progress, epoch 22, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eeef900ccf195604473b05a82c2b38cc81aa92d1f02ee56822ae6abda0d9e069
+oid sha256:53c7c56d1fa1c5596d8b3e7ce307b3b4658dabb8813095da2822f1350ce1ad1f
 size 598439784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:300103b6191005426a541c13f1c55cd16174a7af00abb4629fe88a1af268034e
+oid sha256:3c04142ea8f72c8e2aada089e661502f815b94a08a051092058fa969ccc94e16
 size 1196967418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ff9ef144e2902e840e79b24cfc9ac61aa59315f6172b41e5f2ddc5913f5cf92
+oid sha256:5bb93b0897f0a2d0eedd0822b675ff0262c974238e1fd78d813058e1b42a7e83
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91e95c0caa75cf388628aced4e0f90b8dc76f7daf807db9cbc78ce58f6b41804
+oid sha256:b162cb27b552368316fbb0570cfe8d4df6e3a6cfa577a8c0205a3fd3869ff810
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8181082820112143,
   "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-1196",
-  "epoch": 21.0,
+  "epoch": 22.0,
   "eval_steps": 500,
-  "global_step": 1932,
+  "global_step": 2024,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -329,6 +329,22 @@
       "eval_samples_per_second": 12.752,
       "eval_steps_per_second": 3.188,
       "step": 1932
+    },
+    {
+      "epoch": 21.73913043478261,
+      "grad_norm": 0.0009025917970575392,
+      "learning_rate": 6.521739130434783e-06,
+      "loss": 0.0001,
+      "step": 2000
+    },
+    {
+      "epoch": 22.0,
+      "eval_f1": 0.7634584417193113,
+      "eval_loss": 1.8578201532363892,
+      "eval_runtime": 7.1765,
+      "eval_samples_per_second": 12.82,
+      "eval_steps_per_second": 3.205,
+      "step": 2024
     }
   ],
   "logging_steps": 100,
@@ -348,7 +364,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3263599830572e+16,
+  "total_flos": 1.3895199822504e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null