lesso03 commited on
Commit
730372a
·
verified ·
1 Parent(s): 8b1ab65

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:f2c7c60ed9fd96e27accc7e6b4a0497340bf5bd4eaaee84821c9f97ccf832e16
3
  size 5327496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:703d1a34212de85ef9b520c5dce4153090c519e52aca65a25f25ef12def73307
3
  size 5327496
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9a2d81d72d09894d9c2185c0090a09ac2e052e93cbde4c2da5bb801c71b731a
3
  size 2857722
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0de69f54ea0b82fd76ef48f32b72952bdc8e2e8cdabc4babbc805bdace1081a0
3
  size 2857722
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:748f8baeb359c613a040afbdeb042e4b894db935681bb8895080ba5386a11218
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae706e1c688ab007216c98f3264cbc3be576a6922244a6aed8473cb990717f7a
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": 2.142345428466797,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-20",
4
- "epoch": 0.02115842369743454,
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": 25.113,
188
  "eval_steps_per_second": 12.556,
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": 84890867466240.0,
219
  "train_batch_size": 2,
220
  "trial_name": null,
221
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.136247396469116,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
+ "epoch": 0.026448029621793177,
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": 25.113,
188
  "eval_steps_per_second": 12.556,
189
  "step": 20
190
+ },
191
+ {
192
+ "epoch": 0.02221634488230627,
193
+ "grad_norm": 1.3518919944763184,
194
+ "learning_rate": 3.308693936411421e-05,
195
+ "loss": 8.7511,
196
+ "step": 21
197
+ },
198
+ {
199
+ "epoch": 0.023274266067177994,
200
+ "grad_norm": 1.1811498403549194,
201
+ "learning_rate": 1.9098300562505266e-05,
202
+ "loss": 8.5067,
203
+ "step": 22
204
+ },
205
+ {
206
+ "epoch": 0.024332187252049723,
207
+ "grad_norm": 1.134123682975769,
208
+ "learning_rate": 8.645454235739903e-06,
209
+ "loss": 7.6642,
210
+ "step": 23
211
+ },
212
+ {
213
+ "epoch": 0.02539010843692145,
214
+ "grad_norm": 1.0653655529022217,
215
+ "learning_rate": 2.1852399266194314e-06,
216
+ "loss": 8.563,
217
+ "step": 24
218
+ },
219
+ {
220
+ "epoch": 0.026448029621793177,
221
+ "grad_norm": 1.0673073530197144,
222
+ "learning_rate": 0.0,
223
+ "loss": 7.9308,
224
+ "step": 25
225
+ },
226
+ {
227
+ "epoch": 0.026448029621793177,
228
+ "eval_loss": 2.136247396469116,
229
+ "eval_runtime": 15.8772,
230
+ "eval_samples_per_second": 25.067,
231
+ "eval_steps_per_second": 12.534,
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": 106113584332800.0,
262
  "train_batch_size": 2,
263
  "trial_name": null,
264
  "trial_params": null