DeepDream2045 commited on
Commit
31c5ab4
1 Parent(s): d1c9f64

Training in progress, step 42, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f5f76c9c8a87ba3f46be60f16932fbfcb6badaf74de88a3a5408e7aba33eb83
3
  size 400084608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aeaff7dde06e5e8f613330462c542ff815059aec57b658a2be8eb1bf0c715a0
3
  size 400084608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1264472565a80578aa5ab59e5cac7b0bf6aa97a67869c2b7feae9e8d7ff4fc5a
3
  size 800394282
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faa6122cffc5785ba88ec3121e8c48e14d955d6e6d2d1fff1cf91d7d4f8e6583
3
  size 800394282
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3326486c222c4e1bdd305fe9707b43ca73a8cd8704d44dd28187e5bbec2c7161
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:582a81d9ff457de50f6bfcf8f6851c1eaf52ea2144fb8d5dc1f4258ed0062862
3
  size 15024
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df107a67dba6f043fbc86d4f2efa1e1dd74df87dfdb2bbc88160116a6a5ef332
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c88600e5f080f1125d2f04ea8eef130774888f2e60904991fb4efad5df0fece6
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55adb0e546bf32aaf886c27dddd7fd5b21db7479fe93f9ea52b1d348d6437d2a
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:533760243a9c0dc2daf51b6226176abdf12f0221b4c71aafa6695249465c0617
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2eb96885ab8ba7ed6e1f4e5b1e1770f237ec207abffc750034244bdebf5d4e7f
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26346e4650f69bf13ae14da87221b0c80a213fc38f84e0e67e2073e38a2d6af1
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:270f031239c90143a69a5e3103494133e68e56d7495d4d43bd4cf80bb106050c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d29324a0d5877763002861a44f469da99d01dae7b8684c45bb1b74d6def2b49
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 1.697729229927063,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 1.7857142857142856,
5
  "eval_steps": 25,
6
- "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -198,6 +198,125 @@
198
  "eval_samples_per_second": 30.443,
199
  "eval_steps_per_second": 3.845,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
@@ -221,12 +340,12 @@
221
  "should_evaluate": false,
222
  "should_log": false,
223
  "should_save": true,
224
- "should_training_stop": false
225
  },
226
  "attributes": {}
227
  }
228
  },
229
- "total_flos": 3.087239672233984e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
  "best_metric": 1.697729229927063,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
+ "epoch": 3.0,
5
  "eval_steps": 25,
6
+ "global_step": 42,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
198
  "eval_samples_per_second": 30.443,
199
  "eval_steps_per_second": 3.845,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 1.8571428571428572,
204
+ "grad_norm": 1.2910879850387573,
205
+ "learning_rate": 3.4549150281252636e-05,
206
+ "loss": 1.6083,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 1.9285714285714286,
211
+ "grad_norm": 2.372886896133423,
212
+ "learning_rate": 3.086582838174551e-05,
213
+ "loss": 1.654,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 2.0,
218
+ "grad_norm": 1.5181156396865845,
219
+ "learning_rate": 2.7300475013022663e-05,
220
+ "loss": 1.5466,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 2.0714285714285716,
225
+ "grad_norm": 0.9630998969078064,
226
+ "learning_rate": 2.3875071764202563e-05,
227
+ "loss": 1.4119,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 2.142857142857143,
232
+ "grad_norm": 1.2351303100585938,
233
+ "learning_rate": 2.061073738537635e-05,
234
+ "loss": 1.5674,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 2.2142857142857144,
239
+ "grad_norm": 2.0758800506591797,
240
+ "learning_rate": 1.7527597583490822e-05,
241
+ "loss": 1.5598,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 2.2857142857142856,
246
+ "grad_norm": 1.076073169708252,
247
+ "learning_rate": 1.4644660940672627e-05,
248
+ "loss": 1.4146,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 2.357142857142857,
253
+ "grad_norm": 1.3192384243011475,
254
+ "learning_rate": 1.1979701719998453e-05,
255
+ "loss": 1.5492,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 2.4285714285714284,
260
+ "grad_norm": 1.5484938621520996,
261
+ "learning_rate": 9.549150281252633e-06,
262
+ "loss": 1.5209,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 2.5,
267
+ "grad_norm": 0.984063982963562,
268
+ "learning_rate": 7.367991782295391e-06,
269
+ "loss": 1.3867,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 2.571428571428571,
274
+ "grad_norm": 1.18297278881073,
275
+ "learning_rate": 5.449673790581611e-06,
276
+ "loss": 1.5152,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 2.642857142857143,
281
+ "grad_norm": 1.3486729860305786,
282
+ "learning_rate": 3.8060233744356633e-06,
283
+ "loss": 1.4508,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 2.7142857142857144,
288
+ "grad_norm": 1.0198802947998047,
289
+ "learning_rate": 2.4471741852423237e-06,
290
+ "loss": 1.3897,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 2.7857142857142856,
295
+ "grad_norm": 0.9609850645065308,
296
+ "learning_rate": 1.3815039801161721e-06,
297
+ "loss": 1.4722,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 2.857142857142857,
302
+ "grad_norm": 1.0965021848678589,
303
+ "learning_rate": 6.15582970243117e-07,
304
+ "loss": 1.4413,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 2.928571428571429,
309
+ "grad_norm": 1.669950008392334,
310
+ "learning_rate": 1.5413331334360182e-07,
311
+ "loss": 1.4793,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 3.0,
316
+ "grad_norm": 0.8596750497817993,
317
+ "learning_rate": 0.0,
318
+ "loss": 1.4315,
319
+ "step": 42
320
  }
321
  ],
322
  "logging_steps": 1,
 
340
  "should_evaluate": false,
341
  "should_log": false,
342
  "should_save": true,
343
+ "should_training_stop": true
344
  },
345
  "attributes": {}
346
  }
347
  },
348
+ "total_flos": 5.186562649353093e+17,
349
  "train_batch_size": 2,
350
  "trial_name": null,
351
  "trial_params": null