Training in progress, epoch 5, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2639907b39e9287fc30fb2f169b8b0719e332db07ffa1b53b1080a4e49447c90
+oid sha256:5bb5180e9990f1dd89154a4a77346691c4158022986340dfeaf7005882b73fd7
 size 598442860

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ea202c16703886b5552b0170b5700a4d0c8dc6a0e9e5f0f8944c5e3dc82b4c0
+oid sha256:6bcd250b2f0572a7b7a7cc548880326a829e60fed2de64159f4f74b0692ec3b4
 size 1196973562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
+oid sha256:d245e05e72192c132e0f2edb6fdcae0c578c890f0fe912f17ec7b0bba2d38cc3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20da6727f873a83d1abd00f92a4cb1727d12d4e0e9bf6e453f25b70594840b9a
+oid sha256:60eb6098441abfa22a1abed72bd1e030fed2db1d5e0c1d30913c395a9df5a162
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.46725195094760313,
-  "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-368",
-  "epoch": 4.0,
+  "best_metric": 0.48917610522469857,
+  "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-460",
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 368,
+  "global_step": 460,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -64,6 +64,22 @@
       "eval_samples_per_second": 12.677,
       "eval_steps_per_second": 3.169,
       "step": 368
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "grad_norm": 11.217053413391113,
+      "learning_rate": 1.8357487922705315e-05,
+      "loss": 0.9918,
+      "step": 400
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.48917610522469857,
+      "eval_loss": 1.0969688892364502,
+      "eval_runtime": 7.2942,
+      "eval_samples_per_second": 12.613,
+      "eval_steps_per_second": 3.153,
+      "step": 460
     }
   ],
   "logging_steps": 100,
@@ -83,7 +99,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2526417482472000.0,
+  "total_flos": 3158021853090000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null