BayesTensor commited on
Commit
87e6d46
·
verified ·
1 Parent(s): 0e64adf

Training in progress, epoch 15, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd16e9b6f9345a4d55b0c6b3d9a0fe4562e07fba5825db705d2f8b1d40e04371
3
  size 598442860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5915cf781c75a5dee93ed65842e2c7fe214eb7dc3c5e73acab0497d91cd6bd0
3
  size 598442860
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d657efc862343e4ca0ff3dfe06b1a7a466d3b1dc217bb753b8649e31097031fb
3
  size 1196973562
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d695920a18d7ea155a2b0a58f3e393c131df0a77d659fab05d8a1a2a0bfce25
3
  size 1196973562
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55eb9a50a24203e1f00ac6c722a2a24e52518f0efb376c58a3d9a8931f29ae83
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c94c375fe5ad2903d244ca6b5cc2a1a6cba4c0c26196f3b9cbd9ddd170bb0b8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65e5841a697daa9e5cf070050f5e101ef959328015c7c818070e14f85bca96d7
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6453b784e07977b49796f9876a97e5ee37d02e3eaeb5ad15b539b50b34db08ac
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.6671065935820338,
3
  "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-1196",
4
- "epoch": 14.0,
5
  "eval_steps": 500,
6
- "global_step": 1288,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -217,6 +217,22 @@
217
  "eval_samples_per_second": 12.664,
218
  "eval_steps_per_second": 3.166,
219
  "step": 1288
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
220
  }
221
  ],
222
  "logging_steps": 100,
@@ -236,7 +252,7 @@
236
  "attributes": {}
237
  }
238
  },
239
- "total_flos": 8842461188652000.0,
240
  "train_batch_size": 4,
241
  "trial_name": null,
242
  "trial_params": null
 
1
  {
2
  "best_metric": 0.6671065935820338,
3
  "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-1196",
4
+ "epoch": 15.0,
5
  "eval_steps": 500,
6
+ "global_step": 1380,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
217
  "eval_samples_per_second": 12.664,
218
  "eval_steps_per_second": 3.166,
219
  "step": 1288
220
+ },
221
+ {
222
+ "epoch": 14.130434782608695,
223
+ "grad_norm": 12.201338768005371,
224
+ "learning_rate": 9.66183574879227e-06,
225
+ "loss": 0.2048,
226
+ "step": 1300
227
+ },
228
+ {
229
+ "epoch": 15.0,
230
+ "eval_f1": 0.6483390799764528,
231
+ "eval_loss": 3.1022789478302,
232
+ "eval_runtime": 7.3193,
233
+ "eval_samples_per_second": 12.569,
234
+ "eval_steps_per_second": 3.142,
235
+ "step": 1380
236
  }
237
  ],
238
  "logging_steps": 100,
 
252
  "attributes": {}
253
  }
254
  },
255
+ "total_flos": 9474065559270000.0,
256
  "train_batch_size": 4,
257
  "trial_name": null,
258
  "trial_params": null