Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -21,17 +21,16 @@
   "hidden_activation": "gelu",
   "hidden_size": 768,
   "id2label": {
-    "0": "no",
-    "1": "undetermined",
-    "2": "yes"
+    "0": "undetermined",
+    "1": "yes"
   },
   "initializer_cutoff_factor": 2.0,
   "initializer_range": 0.02,
   "intermediate_size": 1152,
   "label2id": {
     "no": 0,
-    "undetermined": 1,
-    "yes": 2
+    "undetermined": 0,
+    "yes": 1
   },
   "layer_norm_eps": 1e-05,
   "local_attention": 128,

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19aee6b5ea333beec71db593934a9adb9e6f944c7943814ed4eebedd4f6f80fe
-size 598442860
+oid sha256:77bc596fba1eaefecb79510ac76ae8a790122557a720d1c3fba802366d309ad7
+size 598439784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b606dfd82ecab109380fadabacae41aa51158a8212828c6929c654738f64fe4
-size 1196973562
+oid sha256:aaa31c74dffb446932954321bc66ebd6b0b5820b11f76b30c1cde8aac29e62db
+size 1196967418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27a79239f98d586c6d293becfe4724cb48ad892f743d1e770886cde54b3333d6
+oid sha256:f2e155718eaa0de9768e57816e6e6874ba931ec4489afb1c2874db91c97f7a96
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c831d2844bae6e5dfcbb7cfa2b1a0346a9004d27558539b670e94dfda48813
+oid sha256:40f7853ae8f9bd5119e6435e73044e4eaccdadd4c58eff5131a9bb8b91736361
 size 1064

last-checkpoint/trainer_state.json

@@ -1,254 +1,21 @@
 {
-  "best_metric": 0.6517068273092369,
-  "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-644",
-  "epoch": 16.0,
+  "best_metric": 0.5993395707209687,
+  "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-92",
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 1472,
+  "global_step": 92,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_f1": 0.1245394252026529,
-      "eval_loss": 1.186600685119629,
-      "eval_runtime": 7.2474,
-      "eval_samples_per_second": 12.694,
-      "eval_steps_per_second": 3.174,
+      "eval_f1": 0.5993395707209687,
+      "eval_loss": 0.6179381608963013,
+      "eval_runtime": 7.1172,
+      "eval_samples_per_second": 12.927,
+      "eval_steps_per_second": 3.232,
       "step": 92
-    },
-    {
-      "epoch": 1.0869565217391304,
-      "grad_norm": 6.962858200073242,
-      "learning_rate": 4.782608695652174e-05,
-      "loss": 1.1512,
-      "step": 100
-    },
-    {
-      "epoch": 2.0,
-      "eval_f1": 0.24499471388925595,
-      "eval_loss": 1.1582348346710205,
-      "eval_runtime": 7.2045,
-      "eval_samples_per_second": 12.77,
-      "eval_steps_per_second": 3.192,
-      "step": 184
-    },
-    {
-      "epoch": 2.1739130434782608,
-      "grad_norm": 4.156102180480957,
-      "learning_rate": 4.565217391304348e-05,
-      "loss": 1.0796,
-      "step": 200
-    },
-    {
-      "epoch": 3.0,
-      "eval_f1": 0.2952572796170722,
-      "eval_loss": 1.1547307968139648,
-      "eval_runtime": 7.2693,
-      "eval_samples_per_second": 12.656,
-      "eval_steps_per_second": 3.164,
-      "step": 276
-    },
-    {
-      "epoch": 3.260869565217391,
-      "grad_norm": 2.388090133666992,
-      "learning_rate": 4.347826086956522e-05,
-      "loss": 1.0442,
-      "step": 300
-    },
-    {
-      "epoch": 4.0,
-      "eval_f1": 0.5448336721861624,
-      "eval_loss": 0.8885797262191772,
-      "eval_runtime": 7.2318,
-      "eval_samples_per_second": 12.722,
-      "eval_steps_per_second": 3.18,
-      "step": 368
-    },
-    {
-      "epoch": 4.3478260869565215,
-      "grad_norm": 4.2581706047058105,
-      "learning_rate": 4.130434782608696e-05,
-      "loss": 0.9398,
-      "step": 400
-    },
-    {
-      "epoch": 5.0,
-      "eval_f1": 0.48839037927844586,
-      "eval_loss": 1.2717714309692383,
-      "eval_runtime": 7.2533,
-      "eval_samples_per_second": 12.684,
-      "eval_steps_per_second": 3.171,
-      "step": 460
-    },
-    {
-      "epoch": 5.434782608695652,
-      "grad_norm": 5.4986958503723145,
-      "learning_rate": 3.91304347826087e-05,
-      "loss": 0.7828,
-      "step": 500
-    },
-    {
-      "epoch": 6.0,
-      "eval_f1": 0.5729643728067567,
-      "eval_loss": 1.0950413942337036,
-      "eval_runtime": 7.281,
-      "eval_samples_per_second": 12.636,
-      "eval_steps_per_second": 3.159,
-      "step": 552
-    },
-    {
-      "epoch": 6.521739130434782,
-      "grad_norm": 26.316652297973633,
-      "learning_rate": 3.695652173913043e-05,
-      "loss": 0.745,
-      "step": 600
-    },
-    {
-      "epoch": 7.0,
-      "eval_f1": 0.6517068273092369,
-      "eval_loss": 1.0166062116622925,
-      "eval_runtime": 7.2614,
-      "eval_samples_per_second": 12.67,
-      "eval_steps_per_second": 3.167,
-      "step": 644
-    },
-    {
-      "epoch": 7.608695652173913,
-      "grad_norm": 18.56678581237793,
-      "learning_rate": 3.478260869565218e-05,
-      "loss": 0.5448,
-      "step": 700
-    },
-    {
-      "epoch": 8.0,
-      "eval_f1": 0.5310328299677284,
-      "eval_loss": 1.2965337038040161,
-      "eval_runtime": 7.2664,
-      "eval_samples_per_second": 12.661,
-      "eval_steps_per_second": 3.165,
-      "step": 736
-    },
-    {
-      "epoch": 8.695652173913043,
-      "grad_norm": 0.15497922897338867,
-      "learning_rate": 3.260869565217392e-05,
-      "loss": 0.5092,
-      "step": 800
-    },
-    {
-      "epoch": 9.0,
-      "eval_f1": 0.5372670807453416,
-      "eval_loss": 1.7213834524154663,
-      "eval_runtime": 7.2641,
-      "eval_samples_per_second": 12.665,
-      "eval_steps_per_second": 3.166,
-      "step": 828
-    },
-    {
-      "epoch": 9.782608695652174,
-      "grad_norm": 6.492677688598633,
-      "learning_rate": 3.0434782608695656e-05,
-      "loss": 0.4739,
-      "step": 900
-    },
-    {
-      "epoch": 10.0,
-      "eval_f1": 0.6301521225203002,
-      "eval_loss": 1.8338028192520142,
-      "eval_runtime": 7.3043,
-      "eval_samples_per_second": 12.595,
-      "eval_steps_per_second": 3.149,
-      "step": 920
-    },
-    {
-      "epoch": 10.869565217391305,
-      "grad_norm": 0.35981327295303345,
-      "learning_rate": 2.826086956521739e-05,
-      "loss": 0.1945,
-      "step": 1000
-    },
-    {
-      "epoch": 11.0,
-      "eval_f1": 0.651234139028047,
-      "eval_loss": 2.594071388244629,
-      "eval_runtime": 7.3078,
-      "eval_samples_per_second": 12.589,
-      "eval_steps_per_second": 3.147,
-      "step": 1012
-    },
-    {
-      "epoch": 11.956521739130435,
-      "grad_norm": 16.604412078857422,
-      "learning_rate": 2.608695652173913e-05,
-      "loss": 0.2657,
-      "step": 1100
-    },
-    {
-      "epoch": 12.0,
-      "eval_f1": 0.6426501035196688,
-      "eval_loss": 2.2563436031341553,
-      "eval_runtime": 7.2107,
-      "eval_samples_per_second": 12.759,
-      "eval_steps_per_second": 3.19,
-      "step": 1104
-    },
-    {
-      "epoch": 13.0,
-      "eval_f1": 0.5287792536369386,
-      "eval_loss": 4.812737464904785,
-      "eval_runtime": 7.2823,
-      "eval_samples_per_second": 12.633,
-      "eval_steps_per_second": 3.158,
-      "step": 1196
-    },
-    {
-      "epoch": 13.043478260869565,
-      "grad_norm": 0.001741077285259962,
-      "learning_rate": 2.391304347826087e-05,
-      "loss": 0.1151,
-      "step": 1200
-    },
-    {
-      "epoch": 14.0,
-      "eval_f1": 0.6272702158710237,
-      "eval_loss": 3.9568803310394287,
-      "eval_runtime": 7.25,
-      "eval_samples_per_second": 12.69,
-      "eval_steps_per_second": 3.172,
-      "step": 1288
-    },
-    {
-      "epoch": 14.130434782608695,
-      "grad_norm": 26.904157638549805,
-      "learning_rate": 2.173913043478261e-05,
-      "loss": 0.1093,
-      "step": 1300
-    },
-    {
-      "epoch": 15.0,
-      "eval_f1": 0.5996500201911428,
-      "eval_loss": 4.489804744720459,
-      "eval_runtime": 7.2529,
-      "eval_samples_per_second": 12.685,
-      "eval_steps_per_second": 3.171,
-      "step": 1380
-    },
-    {
-      "epoch": 15.217391304347826,
-      "grad_norm": 0.004288471303880215,
-      "learning_rate": 1.956521739130435e-05,
-      "loss": 0.058,
-      "step": 1400
-    },
-    {
-      "epoch": 16.0,
-      "eval_f1": 0.6272702158710237,
-      "eval_loss": 3.764718770980835,
-      "eval_runtime": 7.2572,
-      "eval_samples_per_second": 12.677,
-      "eval_steps_per_second": 3.169,
-      "step": 1472
     }
   ],
   "logging_steps": 100,
@@ -268,7 +35,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0105669929888e+16,
+  "total_flos": 631599991932000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffb105172ee7a5024f77d6f45999cc09430c7cd036201e1f5d70ce683b84886c
+oid sha256:b7328b3b82d74097e3578d8ec360a3b4618539c7ff39b0d2fab35fa19a4d431d
 size 5432