Training in progress, epoch 8, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51408732b655a2dfb6e7bf3e309c9410b13496f6df35524dc654def6cf309e78
+oid sha256:e1e71b4b34ce14ab12c846dddc82aba1a575ef3f52dcf2bc079fc03c4fa65a21
 size 598439784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6a58f30c9a2218e3c402c09328bc00ed493fed3e8d44aded8054c392e28d608
+oid sha256:ba36ae94145066678168b1dfee88ac45b5cda28b97d5fa48adc1480fe40eda34
 size 1196967418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d2832d03d3fb6cbb91ea98f5322ac5af4656fbe22723cdd1394d7fa1e740165
+oid sha256:38fbaa4aaa427747240a6b65afd267f1edcb968fa67c3bf21b881737ad1b8da3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:315dcc590c85422fa00dd75e1cf3185167f7979dd20636fe3d14baaeb9dd6950
+oid sha256:244ce4fd3658ddcb28dc8a129920777dbc8318f1e4ef2f800b915621e43cbf2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6857289002557545,
   "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-644",
-  "epoch": 7.0,
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 644,
+  "global_step": 736,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -112,6 +112,22 @@
       "eval_samples_per_second": 12.857,
       "eval_steps_per_second": 3.214,
       "step": 644
+    },
+    {
+      "epoch": 7.608695652173913,
+      "grad_norm": 11.184236526489258,
+      "learning_rate": 3.478260869565218e-05,
+      "loss": 0.6136,
+      "step": 700
+    },
+    {
+      "epoch": 8.0,
+      "eval_f1": 0.6735976418570376,
+      "eval_loss": 0.5223021507263184,
+      "eval_runtime": 7.2029,
+      "eval_samples_per_second": 12.773,
+      "eval_steps_per_second": 3.193,
+      "step": 736
     }
   ],
   "logging_steps": 100,
@@ -131,7 +147,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4421199943524000.0,
+  "total_flos": 5052799935456000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null