Training in progress, epoch 6, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae7a9ca6ab0fec1cea4254066557780b09008a978be06a1d1db87d899fc39cc6
+oid sha256:cbe78db83f80e44a56d71c01113ab20f96731102522f454eea4b518d20a6cdd1
 size 598439784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f84e7ef080d2cfa76caa28cabd57f4628b34fdcd19a3ec1b1b27985bf8a822b
+oid sha256:28b237199d7a061460bc306c88e0fdf31c24ce530dfe29c16d2a2bb466702135
 size 1196967418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47dd849695d6ba2ba0448f6d77e58f632a2646a71b44533d30e946c29dfb53ab
+oid sha256:64b35a5dbf48e38ea0c5075e0936455402ab060974fea77a6c3c00c74f36d985
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:690ada6aa1172c834d6bdad3b4bacc9a2c3dee70584c678a451c73ebc29299e1
+oid sha256:10dddcf385ec4dbe433a5f8602b31d3b2947d119562dee7ace906d5e86629977
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6304912478825522,
   "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-276",
-  "epoch": 5.0,
+  "epoch": 6.0,
   "eval_steps": 500,
-  "global_step": 460,
+  "global_step": 552,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -80,6 +80,22 @@
       "eval_samples_per_second": 12.773,
       "eval_steps_per_second": 3.193,
       "step": 460
+    },
+    {
+      "epoch": 5.434782608695652,
+      "grad_norm": 3.6863114833831787,
+      "learning_rate": 3.91304347826087e-05,
+      "loss": 0.6522,
+      "step": 500
+    },
+    {
+      "epoch": 6.0,
+      "eval_f1": 0.588628762541806,
+      "eval_loss": 0.582027792930603,
+      "eval_runtime": 7.2495,
+      "eval_samples_per_second": 12.691,
+      "eval_steps_per_second": 3.173,
+      "step": 552
     }
   ],
   "logging_steps": 100,
@@ -99,7 +115,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3157999959660000.0,
+  "total_flos": 3789599951592000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null