Training in progress, epoch 20, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34a34dbc85953b1cdb0bbdaeaaa03b802543a05a24f2a310fb563e061abb91e3
+oid sha256:5218f8af5e122178108819c55ff9986079205f7a6a7d74fda8cd5140f9258c72
 size 598439784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d512c13bd93229b894e041a4d4fbf657700c4467bba68b92fa186e623ee6417
+oid sha256:eb84cd784a908216d9ae0bcbf279833d869a838d7b6224336819fbdcd50e697e
 size 1196967418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b32902f8553b01c87284a6114f412e32aef4bacd0c7545b1d42159c57be6ff4b
+oid sha256:c1e0c75120694c14303d1f1057e38b3cd324e071e40d05f3ae763c9e7d264782
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c19e7df21c0f0cd8077c7593f632ab8849023b3e4e1c28f2e05b1b3ded8bfeb
+oid sha256:736cbdd4cd09732dc21dbb2f4050abbc24d22cbaa260b4ff80bdb4abddb3c2b0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8181082820112143,
   "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-1196",
-  "epoch": 17.0,
+  "epoch": 20.0,
   "eval_steps": 500,
-  "global_step": 1564,
+  "global_step": 1840,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -265,6 +265,54 @@
       "eval_samples_per_second": 12.627,
       "eval_steps_per_second": 3.157,
       "step": 1564
+    },
+    {
+      "epoch": 17.391304347826086,
+      "grad_norm": 8.947516441345215,
+      "learning_rate": 1.5217391304347828e-05,
+      "loss": 0.0244,
+      "step": 1600
+    },
+    {
+      "epoch": 18.0,
+      "eval_f1": 0.75442242114237,
+      "eval_loss": 1.5790338516235352,
+      "eval_runtime": 7.2916,
+      "eval_samples_per_second": 12.617,
+      "eval_steps_per_second": 3.154,
+      "step": 1656
+    },
+    {
+      "epoch": 18.47826086956522,
+      "grad_norm": 0.016934270039200783,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 0.0002,
+      "step": 1700
+    },
+    {
+      "epoch": 19.0,
+      "eval_f1": 0.7539112050739958,
+      "eval_loss": 1.929887056350708,
+      "eval_runtime": 7.2258,
+      "eval_samples_per_second": 12.732,
+      "eval_steps_per_second": 3.183,
+      "step": 1748
+    },
+    {
+      "epoch": 19.565217391304348,
+      "grad_norm": 0.02545306272804737,
+      "learning_rate": 1.0869565217391305e-05,
+      "loss": 0.0004,
+      "step": 1800
+    },
+    {
+      "epoch": 20.0,
+      "eval_f1": 0.7634584417193113,
+      "eval_loss": 1.7885226011276245,
+      "eval_runtime": 7.2042,
+      "eval_samples_per_second": 12.77,
+      "eval_steps_per_second": 3.193,
+      "step": 1840
     }
   ],
   "logging_steps": 100,
@@ -284,7 +332,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0737199862844e+16,
+  "total_flos": 1.263199983864e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null