Training in progress, epoch 21, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5218f8af5e122178108819c55ff9986079205f7a6a7d74fda8cd5140f9258c72
+oid sha256:eeef900ccf195604473b05a82c2b38cc81aa92d1f02ee56822ae6abda0d9e069
 size 598439784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb84cd784a908216d9ae0bcbf279833d869a838d7b6224336819fbdcd50e697e
+oid sha256:300103b6191005426a541c13f1c55cd16174a7af00abb4629fe88a1af268034e
 size 1196967418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1e0c75120694c14303d1f1057e38b3cd324e071e40d05f3ae763c9e7d264782
+oid sha256:6ff9ef144e2902e840e79b24cfc9ac61aa59315f6172b41e5f2ddc5913f5cf92
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:736cbdd4cd09732dc21dbb2f4050abbc24d22cbaa260b4ff80bdb4abddb3c2b0
+oid sha256:91e95c0caa75cf388628aced4e0f90b8dc76f7daf807db9cbc78ce58f6b41804
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8181082820112143,
   "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-1196",
-  "epoch": 20.0,
+  "epoch": 21.0,
   "eval_steps": 500,
-  "global_step": 1840,
+  "global_step": 1932,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -313,6 +313,22 @@
       "eval_samples_per_second": 12.77,
       "eval_steps_per_second": 3.193,
       "step": 1840
+    },
+    {
+      "epoch": 20.652173913043477,
+      "grad_norm": 0.0008984901360236108,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 0.0001,
+      "step": 1900
+    },
+    {
+      "epoch": 21.0,
+      "eval_f1": 0.7634584417193113,
+      "eval_loss": 1.82301926612854,
+      "eval_runtime": 7.2146,
+      "eval_samples_per_second": 12.752,
+      "eval_steps_per_second": 3.188,
+      "step": 1932
     }
   ],
   "logging_steps": 100,
@@ -332,7 +348,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.263199983864e+16,
+  "total_flos": 1.3263599830572e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null