Training in progress, epoch 17, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd4ebc19581170d4e3e2289f89a6b6b5d0f29626415fdc205ee019874c846d0d
+oid sha256:34a34dbc85953b1cdb0bbdaeaaa03b802543a05a24f2a310fb563e061abb91e3
 size 598439784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8ac87d06385767c09b376f483d886f26b33863219332f0831983eb51aff3b09
+oid sha256:6d512c13bd93229b894e041a4d4fbf657700c4467bba68b92fa186e623ee6417
 size 1196967418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:913ac14e71df2a85f158bf8200b2600b5f905ccb544ef3db6dcd4313366367a9
+oid sha256:b32902f8553b01c87284a6114f412e32aef4bacd0c7545b1d42159c57be6ff4b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c831d2844bae6e5dfcbb7cfa2b1a0346a9004d27558539b670e94dfda48813
+oid sha256:3c19e7df21c0f0cd8077c7593f632ab8849023b3e4e1c28f2e05b1b3ded8bfeb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8181082820112143,
   "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": 12.694,
       "eval_steps_per_second": 3.174,
       "step": 1472
+    },
+    {
+      "epoch": 16.304347826086957,
+      "grad_norm": 0.004443590063601732,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 0.0764,
+      "step": 1500
+    },
+    {
+      "epoch": 17.0,
+      "eval_f1": 0.7634584417193113,
+      "eval_loss": 1.5010850429534912,
+      "eval_runtime": 7.2861,
+      "eval_samples_per_second": 12.627,
+      "eval_steps_per_second": 3.157,
+      "step": 1564
     }
   ],
   "logging_steps": 100,
@@ -268,7 +284,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0105599870912e+16,
+  "total_flos": 1.0737199862844e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null