lesso03 commited on
Commit
099b098
·
verified ·
1 Parent(s): 43e831a

Training in progress, step 30, 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:c055a2d43af63ccc2adfb41e71ec10b67b53883c2a9572b8b0493a2719ec6186
3
  size 200068512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:469a679eeb756a262472348bda337668568d088a5df024ffa1494301492d3b4e
3
  size 200068512
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46c6c2bc4089848952c63f72e67c9b66b50c3c380722115213d8c4895dacbc89
3
  size 400361770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a425ea94a7842985d72beff55ff2f169b63b321c7f7848647131bb61f0e4f6a
3
  size 400361770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01cc7cc1681edb073417d715b2c7513ade6f8d74705eb091e92b81340f3139d0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c468011fb97c3b7cdc14c090405f0453f96415cb4d8a60167bfab1e518df7214
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ddaa639affba9b89222fee046caf8a7f8b52a142c3b2d35ccd1f461973cfdc78
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5b325ea4e14a510f9eb0108f2923753e246a5ec70e919cdd84a9afd64b95afd
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.0009339030141719782,
5
  "eval_steps": 4,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -195,6 +195,92 @@
195
  "eval_samples_per_second": 7.705,
196
  "eval_steps_per_second": 1.927,
197
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
198
  }
199
  ],
200
  "logging_steps": 1,
@@ -209,12 +295,12 @@
209
  "should_evaluate": false,
210
  "should_log": false,
211
  "should_save": true,
212
- "should_training_stop": false
213
  },
214
  "attributes": {}
215
  }
216
  },
217
- "total_flos": 7668943615426560.0,
218
  "train_batch_size": 4,
219
  "trial_name": null,
220
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0014008545212579673,
5
  "eval_steps": 4,
6
+ "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
195
  "eval_samples_per_second": 7.705,
196
  "eval_steps_per_second": 1.927,
197
  "step": 20
198
+ },
199
+ {
200
+ "epoch": 0.0009805981648805771,
201
+ "grad_norm": 7.305593013763428,
202
+ "learning_rate": 2.871103542174637e-06,
203
+ "loss": 2.8879,
204
+ "step": 21
205
+ },
206
+ {
207
+ "epoch": 0.001027293315589176,
208
+ "grad_norm": 6.604673385620117,
209
+ "learning_rate": 2.320866025105016e-06,
210
+ "loss": 2.6268,
211
+ "step": 22
212
+ },
213
+ {
214
+ "epoch": 0.001073988466297775,
215
+ "grad_norm": 7.184069633483887,
216
+ "learning_rate": 1.8128800512565514e-06,
217
+ "loss": 2.789,
218
+ "step": 23
219
+ },
220
+ {
221
+ "epoch": 0.0011206836170063739,
222
+ "grad_norm": 7.4371538162231445,
223
+ "learning_rate": 1.3551568628929434e-06,
224
+ "loss": 2.9913,
225
+ "step": 24
226
+ },
227
+ {
228
+ "epoch": 0.0011206836170063739,
229
+ "eval_loss": 2.791896343231201,
230
+ "eval_runtime": 1170.987,
231
+ "eval_samples_per_second": 7.701,
232
+ "eval_steps_per_second": 1.926,
233
+ "step": 24
234
+ },
235
+ {
236
+ "epoch": 0.0011673787677149727,
237
+ "grad_norm": 7.216193675994873,
238
+ "learning_rate": 9.549150281252633e-07,
239
+ "loss": 3.0909,
240
+ "step": 25
241
+ },
242
+ {
243
+ "epoch": 0.0012140739184235718,
244
+ "grad_norm": 6.531351089477539,
245
+ "learning_rate": 6.184665997806832e-07,
246
+ "loss": 2.8438,
247
+ "step": 26
248
+ },
249
+ {
250
+ "epoch": 0.0012607690691321706,
251
+ "grad_norm": 6.790028095245361,
252
+ "learning_rate": 3.511175705587433e-07,
253
+ "loss": 2.5153,
254
+ "step": 27
255
+ },
256
+ {
257
+ "epoch": 0.0013074642198407694,
258
+ "grad_norm": 6.867988586425781,
259
+ "learning_rate": 1.5708419435684463e-07,
260
+ "loss": 2.7938,
261
+ "step": 28
262
+ },
263
+ {
264
+ "epoch": 0.0013074642198407694,
265
+ "eval_loss": 2.758043050765991,
266
+ "eval_runtime": 1170.5173,
267
+ "eval_samples_per_second": 7.704,
268
+ "eval_steps_per_second": 1.926,
269
+ "step": 28
270
+ },
271
+ {
272
+ "epoch": 0.0013541593705493685,
273
+ "grad_norm": 7.407482147216797,
274
+ "learning_rate": 3.9426493427611177e-08,
275
+ "loss": 2.8072,
276
+ "step": 29
277
+ },
278
+ {
279
+ "epoch": 0.0014008545212579673,
280
+ "grad_norm": 8.236345291137695,
281
+ "learning_rate": 0.0,
282
+ "loss": 2.8171,
283
+ "step": 30
284
  }
285
  ],
286
  "logging_steps": 1,
 
295
  "should_evaluate": false,
296
  "should_log": false,
297
  "should_save": true,
298
+ "should_training_stop": true
299
  },
300
  "attributes": {}
301
  }
302
  },
303
+ "total_flos": 1.150341542313984e+16,
304
  "train_batch_size": 4,
305
  "trial_name": null,
306
  "trial_params": null