dada22231 commited on
Commit
b6d5af0
1 Parent(s): 11dc24e

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 sha256:871be95bf71db9138b7e097d40f79e5c8523de983f8f0ba61f3c8c25b9938c9d
3
  size 100966336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:019e18add6ab50033a92825df292bfb8941dc2c843e2ac22c9a4f1ba55c4482d
3
  size 100966336
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b4296140da1d4f845b19ad6ff6d86103b7b18e0e3c8d8f388686bf3c8073630
3
  size 202110330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5677fa6aa787c6498da3db391b4f71b60cc9216406a245d152ee858eb92498f
3
  size 202110330
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4804cf6371185859667fb5b0fa4d43a9812a9bd3ab8b634638133d18aa929836
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc29e05449f31d2e94394fe59c01418c1e6241105ae91a574118848146584415
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 sha256:3671b4d31690114bcb2d3d21e46ebb94897ddd1b52e483e18e8d3e5027e39585
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b697b807dd856c5585e6f159ccc2fe3304e089d2f6a459585cd4bb7d8fc8c45
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:d2a509c06aa9aa8994390b832621ef1df7afbbe1ea85af2cb9d738b26a4ac119
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37348e8f1362242ee92b948ae1f313a93d616b75b1564899f7d36babda63ac7a
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 sha256:0b3def97aa272b8007a3a152648b9f21f696b29a91fabb8b7041dec4a935a84d
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90956b7fee71f0ca23ef07e1ec38592ba5c343271f722210bb44be50c5179e66
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f5c305e4a92be904895c02f0f0a1da666e6e7555f6043a8f089990c87f4ce88
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.653991460800171,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.7714561234329798,
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": 48.978,
199
  "eval_steps_per_second": 12.734,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
@@ -226,7 +409,7 @@
226
  "attributes": {}
227
  }
228
  },
229
- "total_flos": 4.169686374888243e+16,
230
  "train_batch_size": 1,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.457026958465576,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 1.5429122468659595,
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": 48.978,
199
  "eval_steps_per_second": 12.734,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.8023143683702989,
204
+ "grad_norm": 0.6692939400672913,
205
+ "learning_rate": 8.681980515339464e-05,
206
+ "loss": 2.6014,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.8331726133076182,
211
+ "grad_norm": 0.6837179660797119,
212
+ "learning_rate": 8.571489144483944e-05,
213
+ "loss": 2.614,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.8640308582449373,
218
+ "grad_norm": 0.7611942291259766,
219
+ "learning_rate": 8.457416554680877e-05,
220
+ "loss": 2.6286,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.8948891031822566,
225
+ "grad_norm": 0.8610087633132935,
226
+ "learning_rate": 8.339895749467238e-05,
227
+ "loss": 2.7091,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.9257473481195757,
232
+ "grad_norm": 0.9536398649215698,
233
+ "learning_rate": 8.219063752844926e-05,
234
+ "loss": 2.6736,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.9566055930568949,
239
+ "grad_norm": 1.5485323667526245,
240
+ "learning_rate": 8.095061449516903e-05,
241
+ "loss": 2.7427,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.9874638379942141,
246
+ "grad_norm": 2.791057586669922,
247
+ "learning_rate": 7.968033420621935e-05,
248
+ "loss": 2.9027,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 1.0183220829315334,
253
+ "grad_norm": 1.133805274963379,
254
+ "learning_rate": 7.838127775159452e-05,
255
+ "loss": 4.2342,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 1.0491803278688525,
260
+ "grad_norm": 0.5696182250976562,
261
+ "learning_rate": 7.705495977301078e-05,
262
+ "loss": 2.4703,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 1.0800385728061717,
267
+ "grad_norm": 0.7950026988983154,
268
+ "learning_rate": 7.570292669790186e-05,
269
+ "loss": 2.5597,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 1.1108968177434908,
274
+ "grad_norm": 0.8173376321792603,
275
+ "learning_rate": 7.43267549363537e-05,
276
+ "loss": 2.6145,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 1.14175506268081,
281
+ "grad_norm": 0.7578170895576477,
282
+ "learning_rate": 7.292804904308087e-05,
283
+ "loss": 2.4873,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 1.1726133076181293,
288
+ "grad_norm": 0.9220737814903259,
289
+ "learning_rate": 7.150843984658754e-05,
290
+ "loss": 2.6142,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 1.2034715525554485,
295
+ "grad_norm": 1.000977635383606,
296
+ "learning_rate": 7.006958254769438e-05,
297
+ "loss": 2.7668,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 1.2343297974927676,
302
+ "grad_norm": 1.9137243032455444,
303
+ "learning_rate": 6.861315478964841e-05,
304
+ "loss": 2.6618,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 1.2651880424300868,
309
+ "grad_norm": 1.144348382949829,
310
+ "learning_rate": 6.714085470206609e-05,
311
+ "loss": 2.2853,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 1.296046287367406,
316
+ "grad_norm": 0.494349867105484,
317
+ "learning_rate": 6.56543989209901e-05,
318
+ "loss": 2.4441,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 1.326904532304725,
323
+ "grad_norm": 0.6220836639404297,
324
+ "learning_rate": 6.415552058736854e-05,
325
+ "loss": 2.4758,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 1.3577627772420444,
330
+ "grad_norm": 0.6606362462043762,
331
+ "learning_rate": 6.264596732629e-05,
332
+ "loss": 2.5194,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 1.3886210221793636,
337
+ "grad_norm": 0.7131364345550537,
338
+ "learning_rate": 6.112749920933111e-05,
339
+ "loss": 2.4692,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 1.4194792671166827,
344
+ "grad_norm": 0.7623465061187744,
345
+ "learning_rate": 5.960188670239154e-05,
346
+ "loss": 2.4903,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 1.4503375120540019,
351
+ "grad_norm": 0.8568875193595886,
352
+ "learning_rate": 5.80709086014102e-05,
353
+ "loss": 2.6904,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 1.4811957569913212,
358
+ "grad_norm": 1.716271162033081,
359
+ "learning_rate": 5.653634995836856e-05,
360
+ "loss": 2.6191,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 1.5120540019286404,
365
+ "grad_norm": 1.0471079349517822,
366
+ "learning_rate": 5.500000000000001e-05,
367
+ "loss": 2.2445,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 1.5429122468659595,
372
+ "grad_norm": 0.5166476368904114,
373
+ "learning_rate": 5.346365004163145e-05,
374
+ "loss": 2.3682,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 1.5429122468659595,
379
+ "eval_loss": 2.457026958465576,
380
+ "eval_runtime": 1.0293,
381
+ "eval_samples_per_second": 48.575,
382
+ "eval_steps_per_second": 12.63,
383
+ "step": 50
384
  }
385
  ],
386
  "logging_steps": 1,
 
409
  "attributes": {}
410
  }
411
  },
412
+ "total_flos": 8.34067497043886e+16,
413
  "train_batch_size": 1,
414
  "trial_name": null,
415
  "trial_params": null