Training in progress, epoch 14, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f182ddc6a42f969c70c3ba45c6b66632e4c2357bc2d736ef52aebb2d32d424d0
+oid sha256:fd16e9b6f9345a4d55b0c6b3d9a0fe4562e07fba5825db705d2f8b1d40e04371
 size 598442860

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e100b9ab84b2ed7eba0c8e1e9d9d999e12f2ff3b481ee0e28a17333b39dc4c61
+oid sha256:d657efc862343e4ca0ff3dfe06b1a7a466d3b1dc217bb753b8649e31097031fb
 size 1196973562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21c2425b85b819f329f6809df4ca360e34a2b44b18e94e8e0472ab0b59df0b2a
+oid sha256:55eb9a50a24203e1f00ac6c722a2a24e52518f0efb376c58a3d9a8931f29ae83
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:347def11e7102864029b8bcdabdb4164ecba7c15bc54daa499824d15db0ad9cc
+oid sha256:65e5841a697daa9e5cf070050f5e101ef959328015c7c818070e14f85bca96d7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6671065935820338,
   "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-1196",
-  "epoch": 13.0,
+  "epoch": 14.0,
   "eval_steps": 500,
-  "global_step": 1196,
+  "global_step": 1288,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -201,6 +201,22 @@
       "eval_samples_per_second": 12.589,
       "eval_steps_per_second": 3.147,
       "step": 1196
+    },
+    {
+      "epoch": 13.043478260869565,
+      "grad_norm": 5.261804580688477,
+      "learning_rate": 1.0628019323671499e-05,
+      "loss": 0.4901,
+      "step": 1200
+    },
+    {
+      "epoch": 14.0,
+      "eval_f1": 0.6347571828121027,
+      "eval_loss": 2.9827301502227783,
+      "eval_runtime": 7.2649,
+      "eval_samples_per_second": 12.664,
+      "eval_steps_per_second": 3.166,
+      "step": 1288
     }
   ],
   "logging_steps": 100,
@@ -220,7 +236,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8210856818034000.0,
+  "total_flos": 8842461188652000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null