Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77bc596fba1eaefecb79510ac76ae8a790122557a720d1c3fba802366d309ad7
+oid sha256:74874d52f7cbbfa76ffc7607401873f007ee833060bc619b6e5d44da8f7ca856
 size 598439784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaa31c74dffb446932954321bc66ebd6b0b5820b11f76b30c1cde8aac29e62db
+oid sha256:88dbd6c5e3d796ad17799d4c8569579663913a90fafdcf88e07c396b8a6a9b5e
 size 1196967418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2e155718eaa0de9768e57816e6e6874ba931ec4489afb1c2874db91c97f7a96
+oid sha256:ee3528bf0ace792176d57cac1ea8e325db1e81a8856e3e8a6e53688b51f9516e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40f7853ae8f9bd5119e6435e73044e4eaccdadd4c58eff5131a9bb8b91736361
+oid sha256:29515a795f42318c0b4340751f84ea735733a1e6cda14a74cb2f0c287dead1f9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5993395707209687,
   "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-92",
-  "epoch": 1.0,
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 92,
+  "global_step": 184,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -16,6 +16,22 @@
       "eval_samples_per_second": 12.927,
       "eval_steps_per_second": 3.232,
       "step": 92
+    },
+    {
+      "epoch": 1.0869565217391304,
+      "grad_norm": 3.5607712268829346,
+      "learning_rate": 4.782608695652174e-05,
+      "loss": 0.7932,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.5993395707209687,
+      "eval_loss": 0.6113200187683105,
+      "eval_runtime": 7.1729,
+      "eval_samples_per_second": 12.826,
+      "eval_steps_per_second": 3.206,
+      "step": 184
     }
   ],
   "logging_steps": 100,
@@ -35,7 +51,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 631599991932000.0,
+  "total_flos": 1263199983864000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null