Training in progress, epoch 8, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edc722e2de5365cfeec2fc913b04dc080b1d0a8df2a77b935b8e7d687bb0a41c
+oid sha256:bddc58024cac58798dc47782522518234e05813633f09af0bda9f219ee1557a6
 size 598442860

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b00f472daa01b7422c27895a4a520d611143b4fd9e58668debdb120fe7ebf07c
+oid sha256:f9801229a53f0d6b17548870be4cd3265444e1ff624e0bc1f57607ecb3a9ba07
 size 1196973562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d3b7102895eb0637b0cab516bd672f216b2bf79078a83eb301011a90444f44c
+oid sha256:52cca5856c568bc52c683b690919168fa27bfbdfefc6e0a62355afa6011157c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34501ac964621bff9788a01b10e8298751b6c8e0d517313f2150b06ce29b2619
+oid sha256:3a62fe99ae2bc6dd491b0c6403e6bf2d58cbcc159f24eb2b275a62f33a2db9b9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6268890955591723,
   "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-644",
-  "epoch": 7.0,
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 644,
+  "global_step": 736,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -112,6 +112,22 @@
       "eval_samples_per_second": 12.658,
       "eval_steps_per_second": 3.165,
       "step": 644
+    },
+    {
+      "epoch": 7.608695652173913,
+      "grad_norm": 21.24846649169922,
+      "learning_rate": 1.5458937198067633e-05,
+      "loss": 0.8208,
+      "step": 700
+    },
+    {
+      "epoch": 8.0,
+      "eval_f1": 0.5480383816552855,
+      "eval_loss": 1.1408698558807373,
+      "eval_runtime": 7.2908,
+      "eval_samples_per_second": 12.619,
+      "eval_steps_per_second": 3.155,
+      "step": 736
     }
   ],
   "logging_steps": 100,
@@ -131,7 +147,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4421230594326000.0,
+  "total_flos": 5052834964944000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null