Training in progress, epoch 23, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44fcdc2cfb219a2c3d6d06bb6b8f65f721af1da85763755c70ac45f1c76d0940
+oid sha256:ccaa285f634999614d76916fa26ad8586b367298697a9ba5d5674744d4bc4433
 size 598442860

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf7d32cb95a343ca2e2f6541c74e46395757dfb63b9b680af02fa19b05e27bce
+oid sha256:2897be83473030817c6ff78446c8bb0dfc829bb54d41c6eb71287e1885905e70
 size 1196973562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a446f0425374fa045ac6c683a19a8525794cbf14fa7b3d3378d950e0a4a18370
+oid sha256:23c03a4de3b86963ec287522a2181427c3374e2dc539cb28bf29e0a8cece77ca
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2781561764a9942969e7875697d4ccf980e5e34725eac1719d27c20514c80f73
+oid sha256:483f4ecfb311e0d8ab1c4c2d39a345ad988e3534065d1820a6f78e949cfb8296
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.685027729264332,
   "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-2024",
-  "epoch": 22.0,
+  "epoch": 23.0,
   "eval_steps": 500,
-  "global_step": 2024,
+  "global_step": 2116,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -345,6 +345,22 @@
       "eval_samples_per_second": 12.694,
       "eval_steps_per_second": 3.173,
       "step": 2024
+    },
+    {
+      "epoch": 22.82608695652174,
+      "grad_norm": 0.00998605228960514,
+      "learning_rate": 1.932367149758454e-06,
+      "loss": 0.0,
+      "step": 2100
+    },
+    {
+      "epoch": 23.0,
+      "eval_f1": 0.6675544814093237,
+      "eval_loss": 3.6375534534454346,
+      "eval_runtime": 7.3379,
+      "eval_samples_per_second": 12.538,
+      "eval_steps_per_second": 3.134,
+      "step": 2116
     }
   ],
   "logging_steps": 100,
@@ -364,7 +380,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3895296153596e+16,
+  "total_flos": 1.4526900524214e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null