Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:906255dbaf1285a12fa3508ab044d1b9a2429636fd191ac9acc29a23ad06c001
+oid sha256:33679b90c81ec70a81304b8b849de1ce8ce936724ff0cef6feafd559b9c747c2
 size 598439784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:157b03a45f0aa7419a7410e95459b5ad16a3f534102a8ac69eaf2dec18fc3a4c
+oid sha256:1844db23b4c1d36666d68af91784970c8be7644ac5e88efc0ccdcac581c048f5
 size 1196967418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c92a95a97d689d636b085d406167a1d143dce26fb83ee64d21cf4b37a120302
+oid sha256:36eb3c91b3077080e254ba8fd9a96b4afe9cf22aec04441fdc41ff8bc2a91d56
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bac96f0435348f2377650b650afe5ab644220dd32681e25e46a381e4a99c48d6
+oid sha256:6dd5e7a8cc9e9d048bdba0d3a1186e4e84b17f6d916677b4fb46d7f12cbbd831
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6304912478825522,
   "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-276",
-  "epoch": 3.0,
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 276,
+  "global_step": 368,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -48,6 +48,22 @@
       "eval_samples_per_second": 12.873,
       "eval_steps_per_second": 3.218,
       "step": 276
+    },
+    {
+      "epoch": 3.260869565217391,
+      "grad_norm": 3.4564907550811768,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 0.6418,
+      "step": 300
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.5993395707209687,
+      "eval_loss": 0.6268433928489685,
+      "eval_runtime": 7.1588,
+      "eval_samples_per_second": 12.851,
+      "eval_steps_per_second": 3.213,
+      "step": 368
     }
   ],
   "logging_steps": 100,
@@ -67,7 +83,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1894799975796000.0,
+  "total_flos": 2526399967728000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null