Training in progress, epoch 5, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33679b90c81ec70a81304b8b849de1ce8ce936724ff0cef6feafd559b9c747c2
+oid sha256:ae7a9ca6ab0fec1cea4254066557780b09008a978be06a1d1db87d899fc39cc6
 size 598439784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1844db23b4c1d36666d68af91784970c8be7644ac5e88efc0ccdcac581c048f5
+oid sha256:4f84e7ef080d2cfa76caa28cabd57f4628b34fdcd19a3ec1b1b27985bf8a822b
 size 1196967418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36eb3c91b3077080e254ba8fd9a96b4afe9cf22aec04441fdc41ff8bc2a91d56
+oid sha256:47dd849695d6ba2ba0448f6d77e58f632a2646a71b44533d30e946c29dfb53ab
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dd5e7a8cc9e9d048bdba0d3a1186e4e84b17f6d916677b4fb46d7f12cbbd831
+oid sha256:690ada6aa1172c834d6bdad3b4bacc9a2c3dee70584c678a451c73ebc29299e1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6304912478825522,
   "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-276",
-  "epoch": 4.0,
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 368,
+  "global_step": 460,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -64,6 +64,22 @@
       "eval_samples_per_second": 12.851,
       "eval_steps_per_second": 3.213,
       "step": 368
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "grad_norm": 2.798123836517334,
+      "learning_rate": 4.130434782608696e-05,
+      "loss": 0.6315,
+      "step": 400
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.25077639751552794,
+      "eval_loss": 0.9374740719795227,
+      "eval_runtime": 7.2024,
+      "eval_samples_per_second": 12.773,
+      "eval_steps_per_second": 3.193,
+      "step": 460
     }
   ],
   "logging_steps": 100,
@@ -83,7 +99,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2526399967728000.0,
+  "total_flos": 3157999959660000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null