Training in progress, epoch 16, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efbdd8e0cb1284b3725c88c302ef00a91885061c4fa07469655f71e00296ac23
+oid sha256:19aee6b5ea333beec71db593934a9adb9e6f944c7943814ed4eebedd4f6f80fe
 size 598442860

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81c27d997c6515668ad1ed4748d8b559f8d0d6a204177071a6f6df556a9a86b1
+oid sha256:2b606dfd82ecab109380fadabacae41aa51158a8212828c6929c654738f64fe4
 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:b604cae0dd7b3123ee29a4c730cc8b904cfff86463b91424f3f841bb58fa2dcd
+oid sha256:f2c831d2844bae6e5dfcbb7cfa2b1a0346a9004d27558539b670e94dfda48813
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6517068273092369,
   "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-644",
-  "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": 12.685,
       "eval_steps_per_second": 3.171,
       "step": 1380
+    },
+    {
+      "epoch": 15.217391304347826,
+      "grad_norm": 0.004288471303880215,
+      "learning_rate": 1.956521739130435e-05,
+      "loss": 0.058,
+      "step": 1400
+    },
+    {
+      "epoch": 16.0,
+      "eval_f1": 0.6272702158710237,
+      "eval_loss": 3.764718770980835,
+      "eval_runtime": 7.2572,
+      "eval_samples_per_second": 12.677,
+      "eval_steps_per_second": 3.169,
+      "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