Training in progress, epoch 18, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6c19af4c4d716fc274dba296d078e9c325ebde1d6e288f8b13564a4cab5bf06
+oid sha256:41dbfadd76298b8ce2acce4bd94bf946d338f275b7150e1476878b11df17f4c3
 size 598442860

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:415ca9e83353840a5e74ffad366aae772726c75e9ee8d4adebc096d963dc0879
+oid sha256:2104e1ab97cf5bb43e42cb85495abf03b3537839ba5c906eab731887f8f9ec97
 size 1196973562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed2a9e0df19c2b5851dd49c2343c8e5843eec54db2590ec44b0d194ed986edc6
+oid sha256:f86f749dc73bc16a2502fef2f98f5c00b4400cb2c67fbe62653b7ed104d13779
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53f75f353a8bf0204c55d25ca5896c3bf1c86fe9d16d864ffded5a499d5fd7e4
+oid sha256:869fa5198b295c8d42420c3ab715241472a9d0f7514ef186c77f71e58a4fd5eb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6671065935820338,
   "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-1196",
-  "epoch": 17.0,
+  "epoch": 18.0,
   "eval_steps": 500,
-  "global_step": 1564,
+  "global_step": 1656,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -265,6 +265,22 @@
       "eval_samples_per_second": 12.585,
       "eval_steps_per_second": 3.146,
       "step": 1564
+    },
+    {
+      "epoch": 17.391304347826086,
+      "grad_norm": 0.7084795236587524,
+      "learning_rate": 6.76328502415459e-06,
+      "loss": 0.0828,
+      "step": 1600
+    },
+    {
+      "epoch": 18.0,
+      "eval_f1": 0.6533094924399271,
+      "eval_loss": 3.6281237602233887,
+      "eval_runtime": 7.3293,
+      "eval_samples_per_second": 12.552,
+      "eval_steps_per_second": 3.138,
+      "step": 1656
     }
   ],
   "logging_steps": 100,
@@ -284,7 +300,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0737274300506e+16,
+  "total_flos": 1.1368878671124e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null