Training in progress, epoch 24, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccaa285f634999614d76916fa26ad8586b367298697a9ba5d5674744d4bc4433
+oid sha256:e2bf762a1c693117661a2e6b5acd9ba79de90c623d4bbf4b865e56acdcdda157
 size 598442860

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2897be83473030817c6ff78446c8bb0dfc829bb54d41c6eb71287e1885905e70
+oid sha256:207a6393b2e42b1dd59e4c718a34f25d22c300d23a0e6f1db931caddef4b10c3
 size 1196973562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23c03a4de3b86963ec287522a2181427c3374e2dc539cb28bf29e0a8cece77ca
+oid sha256:618ef55f6c5423457249c94a2577645800716eebc494bf2745faa205a24bad51
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:483f4ecfb311e0d8ab1c4c2d39a345ad988e3534065d1820a6f78e949cfb8296
+oid sha256:0d4a23bf331c10255c622291f489aea6f2f24812a9bd3d5febfd9dade1a88b34
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.685027729264332,
   "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-2024",
-  "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": 12.538,
       "eval_steps_per_second": 3.134,
       "step": 2116
+    },
+    {
+      "epoch": 23.91304347826087,
+      "grad_norm": 0.0006493396940641105,
+      "learning_rate": 9.66183574879227e-07,
+      "loss": 0.0001,
+      "step": 2200
+    },
+    {
+      "epoch": 24.0,
+      "eval_f1": 0.6675544814093237,
+      "eval_loss": 3.64399790763855,
+      "eval_runtime": 7.3823,
+      "eval_samples_per_second": 12.462,
+      "eval_steps_per_second": 3.116,
+      "step": 2208
     }
   ],
   "logging_steps": 100,
@@ -380,7 +396,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4526900524214e+16,
+  "total_flos": 1.5158504894832e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null