Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1e71b4b34ce14ab12c846dddc82aba1a575ef3f52dcf2bc079fc03c4fa65a21
+oid sha256:bb1ef752e446c854a94ade10d307e728bce27c4a7e0d4e1fd16bc4250b6cfadd
 size 598439784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba36ae94145066678168b1dfee88ac45b5cda28b97d5fa48adc1480fe40eda34
+oid sha256:1b608f698e6840212a965978806f5673947f2ada5e14c543c355bb26e87a6c88
 size 1196967418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38fbaa4aaa427747240a6b65afd267f1edcb968fa67c3bf21b881737ad1b8da3
+oid sha256:d84c4b4c1481d1143e59c8a8b087fe5b406091ae3b357cd125375068961147a6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:244ce4fd3658ddcb28dc8a129920777dbc8318f1e4ef2f800b915621e43cbf2a
+oid sha256:dca223214a3cbbe71e8e93e50221e24ff6254045ecabf2702a8d7a9b5e8fa056
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6857289002557545,
-  "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-644",
-  "epoch": 8.0,
+  "best_metric": 0.7776872198363687,
+  "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-828",
+  "epoch": 9.0,
   "eval_steps": 500,
-  "global_step": 736,
+  "global_step": 828,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -128,6 +128,22 @@
       "eval_samples_per_second": 12.773,
       "eval_steps_per_second": 3.193,
       "step": 736
+    },
+    {
+      "epoch": 8.695652173913043,
+      "grad_norm": 7.914676666259766,
+      "learning_rate": 3.260869565217392e-05,
+      "loss": 0.496,
+      "step": 800
+    },
+    {
+      "epoch": 9.0,
+      "eval_f1": 0.7776872198363687,
+      "eval_loss": 0.7307997345924377,
+      "eval_runtime": 7.1943,
+      "eval_samples_per_second": 12.788,
+      "eval_steps_per_second": 3.197,
+      "step": 828
     }
   ],
   "logging_steps": 100,
@@ -147,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5052799935456000.0,
+  "total_flos": 5684399927388000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null