Training in progress, epoch 16, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18d6f02ce80cc4da6ff5dc5d729a22ffa9bbadd92d73c483add17bfa6d1a6124
+oid sha256:dd4ebc19581170d4e3e2289f89a6b6b5d0f29626415fdc205ee019874c846d0d
 size 598439784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:769f7d258ccb85a2e7803b7507a411edf5732fe2da0915d07e26c7f6f5b4ae64
+oid sha256:d8ac87d06385767c09b376f483d886f26b33863219332f0831983eb51aff3b09
 size 1196967418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d7793d0691719328c173827f0542bcfde3dd39ca36616559c39213d0dbbfb87
+oid sha256:913ac14e71df2a85f158bf8200b2600b5f905ccb544ef3db6dcd4313366367a9
 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": 0.8181082820112143,
   "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": 12.722,
       "eval_steps_per_second": 3.181,
       "step": 1380
+    },
+    {
+      "epoch": 15.217391304347826,
+      "grad_norm": 0.007132470607757568,
+      "learning_rate": 1.956521739130435e-05,
+      "loss": 0.0324,
+      "step": 1400
+    },
+    {
+      "epoch": 16.0,
+      "eval_f1": 0.7419546636937941,
+      "eval_loss": 1.6500256061553955,
+      "eval_runtime": 7.2475,
+      "eval_samples_per_second": 12.694,
+      "eval_steps_per_second": 3.174,
+      "step": 1472
     }
   ],
   "logging_steps": 100,
@@ -252,7 +268,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9473999878980000.0,
+  "total_flos": 1.0105599870912e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null