Training in progress, epoch 17, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:724bff78bd0f678b8831031c0aca3c5887d62da8b7d00a37e10f0aed78d9eb6e
+oid sha256:b6c19af4c4d716fc274dba296d078e9c325ebde1d6e288f8b13564a4cab5bf06
 size 598442860

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c8f7fbc3a9e4e45da26287e676aa6e4036aaf1901017bc32406c946c4cde278
+oid sha256:415ca9e83353840a5e74ffad366aae772726c75e9ee8d4adebc096d963dc0879
 size 1196973562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27a79239f98d586c6d293becfe4724cb48ad892f743d1e770886cde54b3333d6
+oid sha256:ed2a9e0df19c2b5851dd49c2343c8e5843eec54db2590ec44b0d194ed986edc6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b600900d5ce78511e6b57d84acdde68044b9be15567a898d0294c524b8b56176
+oid sha256:53f75f353a8bf0204c55d25ca5896c3bf1c86fe9d16d864ffded5a499d5fd7e4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6671065935820338,
   "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-1196",
-  "epoch": 16.0,
+  "epoch": 17.0,
   "eval_steps": 500,
-  "global_step": 1472,
+  "global_step": 1564,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -249,6 +249,22 @@
       "eval_samples_per_second": 12.6,
       "eval_steps_per_second": 3.15,
       "step": 1472
+    },
+    {
+      "epoch": 16.304347826086957,
+      "grad_norm": 0.04186500236392021,
+      "learning_rate": 7.729468599033817e-06,
+      "loss": 0.1236,
+      "step": 1500
+    },
+    {
+      "epoch": 17.0,
+      "eval_f1": 0.6535368679296716,
+      "eval_loss": 3.5499069690704346,
+      "eval_runtime": 7.3103,
+      "eval_samples_per_second": 12.585,
+      "eval_steps_per_second": 3.146,
+      "step": 1564
     }
   ],
   "logging_steps": 100,
@@ -268,7 +284,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0105669929888e+16,
+  "total_flos": 1.0737274300506e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null