Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b082d9f7f07aa3218c210cddb092957f01f3072c9ec6bf41b03953a6ec3da23d
+oid sha256:2639907b39e9287fc30fb2f169b8b0719e332db07ffa1b53b1080a4e49447c90
 size 598442860

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ed1975b50a000839c6999b4cbd155ecd04a9bab206b47eb28bcff6fbf95376d
+oid sha256:4ea202c16703886b5552b0170b5700a4d0c8dc6a0e9e5f0f8944c5e3dc82b4c0
 size 1196973562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
+oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f17bc159752e862802fb5566308be6d1ff306dc0599471317a224de8cb8930a4
+oid sha256:20da6727f873a83d1abd00f92a4cb1727d12d4e0e9bf6e453f25b70594840b9a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.2623751468860165,
-  "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-276",
-  "epoch": 3.0,
+  "best_metric": 0.46725195094760313,
+  "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-368",
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 276,
+  "global_step": 368,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -48,6 +48,22 @@
       "eval_samples_per_second": 12.708,
       "eval_steps_per_second": 3.177,
       "step": 276
+    },
+    {
+      "epoch": 3.260869565217391,
+      "grad_norm": 8.205018997192383,
+      "learning_rate": 1.932367149758454e-05,
+      "loss": 1.0924,
+      "step": 300
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.46725195094760313,
+      "eval_loss": 0.9543380737304688,
+      "eval_runtime": 7.257,
+      "eval_samples_per_second": 12.677,
+      "eval_steps_per_second": 3.169,
+      "step": 368
     }
   ],
   "logging_steps": 100,
@@ -67,7 +83,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1894813111854000.0,
+  "total_flos": 2526417482472000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null