Training in progress, epoch 12, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2988738ce94384a0bf3a6b69e7d46da88efa424a7dfdb50c6cc2bd10f4ad4d3e
+oid sha256:4936d3abaf4c591f21a275c13649ef17c3b008c1c6f74f8520e5536919da73dd
 size 598442860

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:062e53aac31560bbe4525e6a713c38aa9b51550b359e5d64fe3af1b3f3fc6349
+oid sha256:47271d746acc61c537b3eaff14f5f95a402fe0baf69c910409cba6ce858c3d48
 size 1196973562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ec28ea0c416565eeac14a0e9c944f185ac250f4ed4bd15c84ff77ed78ba9301
+oid sha256:d5f38f6446ba43bb9ae0be4911c150b41c5adfbe2712844ea3cb854b62ee2432
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d5b5e75d8e3b798930c594345a5e5270a6260fb2002699a0403dfb2b335d387
+oid sha256:6729363e24d65871ce15d720090948e9d1a3d1af2bc79987c084f511930d640a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.662759974441483,
   "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-1012",
-  "epoch": 11.0,
+  "epoch": 12.0,
   "eval_steps": 500,
-  "global_step": 1012,
+  "global_step": 1104,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -176,6 +176,22 @@
       "eval_samples_per_second": 12.63,
       "eval_steps_per_second": 3.157,
       "step": 1012
+    },
+    {
+      "epoch": 11.956521739130435,
+      "grad_norm": 127.6854476928711,
+      "learning_rate": 1.1594202898550726e-05,
+      "loss": 0.517,
+      "step": 1100
+    },
+    {
+      "epoch": 12.0,
+      "eval_f1": 0.617952852218392,
+      "eval_loss": 3.094771385192871,
+      "eval_runtime": 7.2912,
+      "eval_samples_per_second": 12.618,
+      "eval_steps_per_second": 3.155,
+      "step": 1104
     }
   ],
   "logging_steps": 100,
@@ -195,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6947648076798000.0,
+  "total_flos": 7579252447416000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null