Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bddc58024cac58798dc47782522518234e05813633f09af0bda9f219ee1557a6
+oid sha256:1cefd1df3df842292c4355b6f1a59b7648390d5100a31a3e3fa9ded677340b69
 size 598442860

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9801229a53f0d6b17548870be4cd3265444e1ff624e0bc1f57607ecb3a9ba07
+oid sha256:5bd0044bc7e70ee4bce2001bb76aba2174d3fd9b460f4d5599c2b5f3bbf12301
 size 1196973562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52cca5856c568bc52c683b690919168fa27bfbdfefc6e0a62355afa6011157c3
+oid sha256:adbac4581908b419c3039e502a4aacf8ebe77d7c5097a659c9e661f2ab321b78
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a62fe99ae2bc6dd491b0c6403e6bf2d58cbcc159f24eb2b275a62f33a2db9b9
+oid sha256:d2ed391fda08c7b0751f36fcdd0a1c20476c32f4319ac53042702da5d27d8e51
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6268890955591723,
   "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-644",
-  "epoch": 8.0,
+  "epoch": 9.0,
   "eval_steps": 500,
-  "global_step": 736,
+  "global_step": 828,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -128,6 +128,22 @@
       "eval_samples_per_second": 12.619,
       "eval_steps_per_second": 3.155,
       "step": 736
+    },
+    {
+      "epoch": 8.695652173913043,
+      "grad_norm": 45.331424713134766,
+      "learning_rate": 1.4492753623188407e-05,
+      "loss": 0.645,
+      "step": 800
+    },
+    {
+      "epoch": 9.0,
+      "eval_f1": 0.5747727830999755,
+      "eval_loss": 1.728603482246399,
+      "eval_runtime": 7.2891,
+      "eval_samples_per_second": 12.622,
+      "eval_steps_per_second": 3.155,
+      "step": 828
     }
   ],
   "logging_steps": 100,
@@ -147,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5052834964944000.0,
+  "total_flos": 5684439335562000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null