Training in progress, epoch 10, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb1ef752e446c854a94ade10d307e728bce27c4a7e0d4e1fd16bc4250b6cfadd
+oid sha256:4a946aba52e0dad4e04728416363ba3fb666015328dce74301dbdf37be65fc39
 size 598439784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b608f698e6840212a965978806f5673947f2ada5e14c543c355bb26e87a6c88
+oid sha256:2367d7318da26155cd5a93cdb34993624f84780df391e9cf296faa3f50232bcb
 size 1196967418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d84c4b4c1481d1143e59c8a8b087fe5b406091ae3b357cd125375068961147a6
+oid sha256:de773a2cb0ba4b7f7d26731893c8e6a45c1e35ab31738065907b40eff7c937a4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dca223214a3cbbe71e8e93e50221e24ff6254045ecabf2702a8d7a9b5e8fa056
+oid sha256:6ab9750f71f478ef278b0d10c6e7e3ed70d0f273dfd6e4e4528f7a4c58502c87
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7776872198363687,
-  "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-828",
-  "epoch": 9.0,
+  "best_metric": 0.7831521739130435,
+  "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-920",
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 828,
+  "global_step": 920,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,22 @@
       "eval_samples_per_second": 12.788,
       "eval_steps_per_second": 3.197,
       "step": 828
+    },
+    {
+      "epoch": 9.782608695652174,
+      "grad_norm": 1.3677582740783691,
+      "learning_rate": 3.0434782608695656e-05,
+      "loss": 0.4858,
+      "step": 900
+    },
+    {
+      "epoch": 10.0,
+      "eval_f1": 0.7831521739130435,
+      "eval_loss": 0.7452064156532288,
+      "eval_runtime": 7.2905,
+      "eval_samples_per_second": 12.619,
+      "eval_steps_per_second": 3.155,
+      "step": 920
     }
   ],
   "logging_steps": 100,
@@ -163,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5684399927388000.0,
+  "total_flos": 6315999919320000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null