Training in progress, epoch 21, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:170668e0f882239f6d921c391d98d535e2dd0d797e483f542f28113b25e94747
+oid sha256:7a75e651b7dedf26c76800365f26f62ec83c75ac7eb4bc15e6dc3f953d658978
 size 598442860

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5cb54bebba1f486784e4f8ef5bfd42e3532aa41a4b5240748e5073470faef87
+oid sha256:a4cfe62004e5a561d9d643bca65ac0c62d1d489b276b30033f099d5b42b27b4c
 size 1196973562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58445eff8cfea6167d69710c1c3e8b46f4af1c16da39f8fe17f7ddecfb128b91
+oid sha256:6d2633b30d6f8bc95e53ac59f43880033523b63ea88408f92c1df3391a619329
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e5ab1dcb06669a31ebabc3e63609c7c26f69246b855cc653dd9ef7e33657817
+oid sha256:a0b2a69adca1463351b69368d25a268701f4b4da518acb587bddfef084570a7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6820012787723785,
   "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-1748",
-  "epoch": 20.0,
+  "epoch": 21.0,
   "eval_steps": 500,
-  "global_step": 1840,
+  "global_step": 1932,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -313,6 +313,22 @@
       "eval_samples_per_second": 12.561,
       "eval_steps_per_second": 3.14,
       "step": 1840
+    },
+    {
+      "epoch": 20.652173913043477,
+      "grad_norm": 0.002304959110915661,
+      "learning_rate": 3.864734299516908e-06,
+      "loss": 0.031,
+      "step": 1900
+    },
+    {
+      "epoch": 21.0,
+      "eval_f1": 0.6777883740084095,
+      "eval_loss": 3.6255407333374023,
+      "eval_runtime": 7.3281,
+      "eval_samples_per_second": 12.554,
+      "eval_steps_per_second": 3.139,
+      "step": 1932
     }
   ],
   "logging_steps": 100,
@@ -332,7 +348,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.263208741236e+16,
+  "total_flos": 1.3263691782978e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null