Training in progress, epoch 14, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:326fda762aefd0e396db654b8bf575536d763a1ac8f4182fb886477130140525
+oid sha256:8c0579b01cbc8e0f2d4501770af4fd63df528851f74a9cb74832e98ca0467462
 size 598439784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a47ba09a68b495feb4b16cfdbf8029f045ce7e2deaafe64ea35bef4d351ffea4
+oid sha256:4651b070514a496efedf94f5d00729c23c74ef220c731d2cb3cd6b55eb27ee4f
 size 1196967418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7a05a91179e57ce882a94e7176a0d8d08b3c683c558671fef0f2e8c9edaab16
+oid sha256:f4f89cb36b601f974d23c1b90c479fbff0e4e7e10520cf1430c3e530f136fcb4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a454a7570ce4146266d9dbb139e531c812ebc1923ec38200d59b12e1ac599499
+oid sha256:1661c9e91b622543adf601555c0e0456670e42a586dd35749175d83eeaa341a1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7831521739130435,
-  "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-920",
-  "epoch": 12.0,
+  "best_metric": 0.8181082820112143,
+  "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-1196",
+  "epoch": 14.0,
   "eval_steps": 500,
-  "global_step": 1104,
+  "global_step": 1288,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -192,6 +192,31 @@
       "eval_samples_per_second": 12.754,
       "eval_steps_per_second": 3.188,
       "step": 1104
+    },
+    {
+      "epoch": 13.0,
+      "eval_f1": 0.8181082820112143,
+      "eval_loss": 0.7770065069198608,
+      "eval_runtime": 7.1902,
+      "eval_samples_per_second": 12.795,
+      "eval_steps_per_second": 3.199,
+      "step": 1196
+    },
+    {
+      "epoch": 13.043478260869565,
+      "grad_norm": 0.024596206843852997,
+      "learning_rate": 2.391304347826087e-05,
+      "loss": 0.2375,
+      "step": 1200
+    },
+    {
+      "epoch": 14.0,
+      "eval_f1": 0.77725724787834,
+      "eval_loss": 1.149732232093811,
+      "eval_runtime": 7.2423,
+      "eval_samples_per_second": 12.703,
+      "eval_steps_per_second": 3.176,
+      "step": 1288
     }
   ],
   "logging_steps": 100,
@@ -211,7 +236,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7579199903184000.0,
+  "total_flos": 8842399887048000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null