Training in progress, epoch 3, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74874d52f7cbbfa76ffc7607401873f007ee833060bc619b6e5d44da8f7ca856
+oid sha256:906255dbaf1285a12fa3508ab044d1b9a2429636fd191ac9acc29a23ad06c001
 size 598439784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88dbd6c5e3d796ad17799d4c8569579663913a90fafdcf88e07c396b8a6a9b5e
+oid sha256:157b03a45f0aa7419a7410e95459b5ad16a3f534102a8ac69eaf2dec18fc3a4c
 size 1196967418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee3528bf0ace792176d57cac1ea8e325db1e81a8856e3e8a6e53688b51f9516e
+oid sha256:1c92a95a97d689d636b085d406167a1d143dce26fb83ee64d21cf4b37a120302
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29515a795f42318c0b4340751f84ea735733a1e6cda14a74cb2f0c287dead1f9
+oid sha256:bac96f0435348f2377650b650afe5ab644220dd32681e25e46a381e4a99c48d6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5993395707209687,
-  "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-92",
-  "epoch": 2.0,
+  "best_metric": 0.6304912478825522,
+  "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-276",
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 184,
+  "global_step": 276,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -32,6 +32,22 @@
       "eval_samples_per_second": 12.826,
       "eval_steps_per_second": 3.206,
       "step": 184
+    },
+    {
+      "epoch": 2.1739130434782608,
+      "grad_norm": 1.3359662294387817,
+      "learning_rate": 4.565217391304348e-05,
+      "loss": 0.6589,
+      "step": 200
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.6304912478825522,
+      "eval_loss": 0.6631842851638794,
+      "eval_runtime": 7.1467,
+      "eval_samples_per_second": 12.873,
+      "eval_steps_per_second": 3.218,
+      "step": 276
     }
   ],
   "logging_steps": 100,
@@ -51,7 +67,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1263199983864000.0,
+  "total_flos": 1894799975796000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null