BayesTensor commited on
Commit
e079385
·
verified ·
1 Parent(s): fa65e46

Training in progress, epoch 11, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a946aba52e0dad4e04728416363ba3fb666015328dce74301dbdf37be65fc39
3
  size 598439784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:791547e19316d3dcdb62fcbc2346b82c4449c7ed382306e07db8b84aa7a120ed
3
  size 598439784
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2367d7318da26155cd5a93cdb34993624f84780df391e9cf296faa3f50232bcb
3
  size 1196967418
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81b2c97140b2144100b47d632499964a480404d3c18b67efe244a35a1a8211a6
3
  size 1196967418
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de773a2cb0ba4b7f7d26731893c8e6a45c1e35ab31738065907b40eff7c937a4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ceca872404f155cf0d9853014eb18c0cc7e23cd52acf7a31c07149383dc6f9e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ab9750f71f478ef278b0d10c6e7e3ed70d0f273dfd6e4e4528f7a4c58502c87
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76a5a9e0d565ef7922121097812cbabe4336d3a63b17101a73128343475fef97
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.7831521739130435,
3
  "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-920",
4
- "epoch": 10.0,
5
  "eval_steps": 500,
6
- "global_step": 920,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -160,6 +160,22 @@
160
  "eval_samples_per_second": 12.619,
161
  "eval_steps_per_second": 3.155,
162
  "step": 920
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163
  }
164
  ],
165
  "logging_steps": 100,
@@ -179,7 +195,7 @@
179
  "attributes": {}
180
  }
181
  },
182
- "total_flos": 6315999919320000.0,
183
  "train_batch_size": 4,
184
  "trial_name": null,
185
  "trial_params": null
 
1
  {
2
  "best_metric": 0.7831521739130435,
3
  "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-920",
4
+ "epoch": 11.0,
5
  "eval_steps": 500,
6
+ "global_step": 1012,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
160
  "eval_samples_per_second": 12.619,
161
  "eval_steps_per_second": 3.155,
162
  "step": 920
163
+ },
164
+ {
165
+ "epoch": 10.869565217391305,
166
+ "grad_norm": 12.851914405822754,
167
+ "learning_rate": 2.826086956521739e-05,
168
+ "loss": 0.4181,
169
+ "step": 1000
170
+ },
171
+ {
172
+ "epoch": 11.0,
173
+ "eval_f1": 0.7798831927319922,
174
+ "eval_loss": 0.7523320913314819,
175
+ "eval_runtime": 7.2341,
176
+ "eval_samples_per_second": 12.718,
177
+ "eval_steps_per_second": 3.179,
178
+ "step": 1012
179
  }
180
  ],
181
  "logging_steps": 100,
 
195
  "attributes": {}
196
  }
197
  },
198
+ "total_flos": 6947599911252000.0,
199
  "train_batch_size": 4,
200
  "trial_name": null,
201
  "trial_params": null