Training in progress, epoch 24, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da50fd6ff5e188e7bced8edcb55391aa936af7ba85eeb1d26e329f9b210d8380
+oid sha256:219eccff007c0e370835316bb089b78b72b5f14b76be94392f3dc75728fe9e39
 size 598439784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6986d17fb92eab486b7d08f62b1272a5913a9e49d104c16cd56884d1b43718d0
+oid sha256:fafdb36da12f76514a9bb8248fa0988c9ede29267cdc790d678b9194974ccfd7
 size 1196967418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5039aedbc3d214b70da23bccb7aa6e6409f52c6f35e7556e5f0a066397eb7606
+oid sha256:572ed1aa15ce8f8aed234d431c888a5ee9318c9ef239c3f25a51346de4c681db
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90ce521353c67eb5594c5e7da3fb6e3773c189ef97bc80ca0c88bc374639da34
+oid sha256:dadbb0c2548c50b49bb39f2ba86a4c33336520be2d6c262605200619683d2787
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8181082820112143,
   "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-1196",
-  "epoch": 23.0,
+  "epoch": 24.0,
   "eval_steps": 500,
-  "global_step": 2116,
+  "global_step": 2208,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -361,6 +361,22 @@
       "eval_samples_per_second": 12.823,
       "eval_steps_per_second": 3.206,
       "step": 2116
+    },
+    {
+      "epoch": 23.91304347826087,
+      "grad_norm": 0.003843324724584818,
+      "learning_rate": 2.173913043478261e-06,
+      "loss": 0.0,
+      "step": 2200
+    },
+    {
+      "epoch": 24.0,
+      "eval_f1": 0.7634584417193113,
+      "eval_loss": 1.8845328092575073,
+      "eval_runtime": 7.1501,
+      "eval_samples_per_second": 12.867,
+      "eval_steps_per_second": 3.217,
+      "step": 2208
     }
   ],
   "logging_steps": 100,
@@ -380,7 +396,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4526799814436e+16,
+  "total_flos": 1.5158399806368e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null