DeepDream2045 commited on
Commit
fda4f4c
1 Parent(s): f3515a2

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34af20bcef7fb8e8251fba8521ba6426b4041c7cd4b7b2b1cd50e75805514a03
3
  size 237402
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3b4bee45cca67f8dcb7fec47cf5d456e61e8bb6d7369ad5a6c4f2b03bf44346
3
  size 237402
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50cabd9dc83c18129b335632a16fd557bec16a588206bc3bc5b97fade4ffd79c
3
  size 222294
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7735decf2f790ce4ed53faf188ff446c12cb6678ba3ca503234d6851368fe095
3
  size 222294
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21804e0659579bc3c091b62468da2a34b7283d447de95c2cab7d7efc6bd80ef4
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca196d2e5b2cc875247ac8c87698807ebf040b63f91cd32d1f475f76c3d15c8e
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 sha256:45e7cc14241a0465196c7ac0d5154d92a8c29ad063cc3dcb93e3498433cc3396
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:336ef79bc6a15c92a673f389fc42a6ccb07650b9fca39d2779a47361337cfea0
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:e76ebc656ed5a8eff85192b9633507d746dd6f0bb5a0d9401d9d4f93206cf280
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c05005ddf000a89251878fdd4b4415fcbb5d6a54cd8e72cf5bdceee7c3a89165
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:c459cd714b97edcd3bb3ba3c56148b5772653a2ccca1712f1d7d5ed98b315c83
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df127ff648e0d8edc31be65fd538afd0efe0920edd35b2953ddbe012d16b9a8e
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 6.917348861694336,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.20629190304280556,
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 +198,189 @@
198
  "eval_samples_per_second": 1022.73,
199
  "eval_steps_per_second": 128.937,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
@@ -221,12 +404,12 @@
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": 2852978688000.0,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 6.911670684814453,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.4125838060856111,
5
  "eval_steps": 25,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
198
  "eval_samples_per_second": 1022.73,
199
  "eval_steps_per_second": 128.937,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.2145435791645178,
204
+ "grad_norm": 0.20306411385536194,
205
+ "learning_rate": 5e-05,
206
+ "loss": 6.8609,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.22279525528623,
211
+ "grad_norm": 0.21225464344024658,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 6.8381,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.23104693140794225,
218
+ "grad_norm": 0.22277817130088806,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 6.8217,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.23929860752965446,
225
+ "grad_norm": 0.20864786207675934,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 6.8098,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.2475502836513667,
232
+ "grad_norm": 0.19844458997249603,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 6.7979,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.2558019597730789,
239
+ "grad_norm": 0.2161320596933365,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 6.7851,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.26405363589479114,
246
+ "grad_norm": 0.220876544713974,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 6.7751,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.2723053120165034,
253
+ "grad_norm": 0.23456600308418274,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 6.7556,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.28055698813821556,
260
+ "grad_norm": 0.2240019291639328,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 6.7395,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.2888086642599278,
267
+ "grad_norm": 0.24339325726032257,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 6.7011,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.29706034038164003,
274
+ "grad_norm": 0.24602070450782776,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 6.6213,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.30531201650335227,
281
+ "grad_norm": 0.3220696449279785,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 6.4113,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.31356369262506445,
288
+ "grad_norm": 0.1950099915266037,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 6.8109,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.3218153687467767,
295
+ "grad_norm": 0.21527087688446045,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 6.8417,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.3300670448684889,
302
+ "grad_norm": 0.22541527450084686,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 6.827,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.33831872099020116,
309
+ "grad_norm": 0.2274940013885498,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 6.8097,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.34657039711191334,
316
+ "grad_norm": 0.21498613059520721,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 6.7978,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.3548220732336256,
323
+ "grad_norm": 0.21291977167129517,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 6.7875,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.3630737493553378,
330
+ "grad_norm": 0.21820193529129028,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 6.7742,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.37132542547705005,
337
+ "grad_norm": 0.22569087147712708,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 6.7579,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.37957710159876223,
344
+ "grad_norm": 0.23315046727657318,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 6.7395,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.38782877772047447,
351
+ "grad_norm": 0.24797138571739197,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 6.7078,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.3960804538421867,
358
+ "grad_norm": 0.26854848861694336,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 6.6595,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.4043321299638989,
365
+ "grad_norm": 0.25083285570144653,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 6.531,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.4125838060856111,
372
+ "grad_norm": 0.267659991979599,
373
+ "learning_rate": 0.0,
374
+ "loss": 6.2156,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.4125838060856111,
379
+ "eval_loss": 6.911670684814453,
380
+ "eval_runtime": 0.828,
381
+ "eval_samples_per_second": 986.759,
382
+ "eval_steps_per_second": 124.402,
383
+ "step": 50
384
  }
385
  ],
386
  "logging_steps": 1,
 
404
  "should_evaluate": false,
405
  "should_log": false,
406
  "should_save": true,
407
+ "should_training_stop": true
408
  },
409
  "attributes": {}
410
  }
411
  },
412
+ "total_flos": 5705957376000.0,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null