Training in progress, epoch 16, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5915cf781c75a5dee93ed65842e2c7fe214eb7dc3c5e73acab0497d91cd6bd0
+oid sha256:724bff78bd0f678b8831031c0aca3c5887d62da8b7d00a37e10f0aed78d9eb6e
 size 598442860

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d695920a18d7ea155a2b0a58f3e393c131df0a77d659fab05d8a1a2a0bfce25
+oid sha256:4c8f7fbc3a9e4e45da26287e676aa6e4036aaf1901017bc32406c946c4cde278
 size 1196973562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c94c375fe5ad2903d244ca6b5cc2a1a6cba4c0c26196f3b9cbd9ddd170bb0b8
+oid sha256:27a79239f98d586c6d293becfe4724cb48ad892f743d1e770886cde54b3333d6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6453b784e07977b49796f9876a97e5ee37d02e3eaeb5ad15b539b50b34db08ac
+oid sha256:b600900d5ce78511e6b57d84acdde68044b9be15567a898d0294c524b8b56176
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6671065935820338,
   "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-1196",
-  "epoch": 15.0,
+  "epoch": 16.0,
   "eval_steps": 500,
-  "global_step": 1380,
+  "global_step": 1472,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -233,6 +233,22 @@
       "eval_samples_per_second": 12.569,
       "eval_steps_per_second": 3.142,
       "step": 1380
+    },
+    {
+      "epoch": 15.217391304347826,
+      "grad_norm": 0.27592945098876953,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 0.1188,
+      "step": 1400
+    },
+    {
+      "epoch": 16.0,
+      "eval_f1": 0.6331910652276784,
+      "eval_loss": 3.7382447719573975,
+      "eval_runtime": 7.3015,
+      "eval_samples_per_second": 12.6,
+      "eval_steps_per_second": 3.15,
+      "step": 1472
     }
   ],
   "logging_steps": 100,
@@ -252,7 +268,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9474065559270000.0,
+  "total_flos": 1.0105669929888e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null