lesso02 commited on
Commit
9ede67a
·
verified ·
1 Parent(s): 8d794b0

Training in progress, step 25, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41016c28e22aa7e4c61c57d2b9f97ce778494f79840477c6a0f6093deaf6a241
3
  size 109009752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2338e3d3a12e66f629d49df870ceea9a7fbc9160cfb26aaa166192cc4d5fb420
3
  size 109009752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c366c4c2cb4e19e8661d021d841bd1f0d7a0b5c40d92eb30463f5cc67f33f67
3
  size 56088148
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f911cbb06ea99c5067b0efaa27fab87f9ac98af50ba74d7925dc52e469f2e7d6
3
  size 56088148
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b65a3cff5730f6b3792e6180642fe02ba01c1869d91aad63a83938f8c222c9d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6f006942153cd9c52c94fc2200848ba62f56f65c89e875122956c392364dc0a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.7211201190948486,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-20",
4
- "epoch": 0.0015690273991409574,
5
  "eval_steps": 5,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -187,6 +187,49 @@
187
  "eval_samples_per_second": 3.001,
188
  "eval_steps_per_second": 1.501,
189
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
190
  }
191
  ],
192
  "logging_steps": 1,
@@ -210,12 +253,12 @@
210
  "should_evaluate": false,
211
  "should_log": false,
212
  "should_save": true,
213
- "should_training_stop": false
214
  },
215
  "attributes": {}
216
  }
217
  },
218
- "total_flos": 8131903425085440.0,
219
  "train_batch_size": 2,
220
  "trial_name": null,
221
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.7028899192810059,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
+ "epoch": 0.0019612842489261967,
5
  "eval_steps": 5,
6
+ "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
187
  "eval_samples_per_second": 3.001,
188
  "eval_steps_per_second": 1.501,
189
  "step": 20
190
+ },
191
+ {
192
+ "epoch": 0.0016474787690980053,
193
+ "grad_norm": 0.7469911575317383,
194
+ "learning_rate": 3.308693936411421e-05,
195
+ "loss": 1.6775,
196
+ "step": 21
197
+ },
198
+ {
199
+ "epoch": 0.0017259301390550531,
200
+ "grad_norm": 0.8389664888381958,
201
+ "learning_rate": 1.9098300562505266e-05,
202
+ "loss": 1.5515,
203
+ "step": 22
204
+ },
205
+ {
206
+ "epoch": 0.0018043815090121012,
207
+ "grad_norm": 0.7729347348213196,
208
+ "learning_rate": 8.645454235739903e-06,
209
+ "loss": 1.6718,
210
+ "step": 23
211
+ },
212
+ {
213
+ "epoch": 0.001882832878969149,
214
+ "grad_norm": 0.998233437538147,
215
+ "learning_rate": 2.1852399266194314e-06,
216
+ "loss": 1.7309,
217
+ "step": 24
218
+ },
219
+ {
220
+ "epoch": 0.0019612842489261967,
221
+ "grad_norm": 0.9571971297264099,
222
+ "learning_rate": 0.0,
223
+ "loss": 1.6594,
224
+ "step": 25
225
+ },
226
+ {
227
+ "epoch": 0.0019612842489261967,
228
+ "eval_loss": 1.7028899192810059,
229
+ "eval_runtime": 1794.3519,
230
+ "eval_samples_per_second": 2.992,
231
+ "eval_steps_per_second": 1.496,
232
+ "step": 25
233
  }
234
  ],
235
  "logging_steps": 1,
 
253
  "should_evaluate": false,
254
  "should_log": false,
255
  "should_save": true,
256
+ "should_training_stop": true
257
  },
258
  "attributes": {}
259
  }
260
  },
261
+ "total_flos": 1.013847699750912e+16,
262
  "train_batch_size": 2,
263
  "trial_name": null,
264
  "trial_params": null