lesso11 commited on
Commit
c50a6e2
·
verified ·
1 Parent(s): d0d8454

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 sha256:3a74db401ec781dfd78149b2528981c93ae271ad49a87e9f33479d3ac4bad8aa
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96a6d413211c5c6002abcd64f85c2e01ca0327d7aaac39ac8b649b81da034e87
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f92e533e4544df8e9703bfe29c475ef385b49ffff3ef6bc687a3d0b8debc976
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b4a6ec2c5f1d852892a64bbae7f224e9f55d49b00af3d1e9258ceedd5c95037
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cda721b5035b6c32d7353550a38d047ddb776a25e42cd15a85a63cb30e818647
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a537322ad8b13e53e04e7307211efb0c953aabdad90bc42ba3149fe4980cca8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
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": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.04655493482309125,
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,
@@ -230,6 +230,221 @@
230
  "eval_samples_per_second": 9.189,
231
  "eval_steps_per_second": 1.156,
232
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
233
  }
234
  ],
235
  "logging_steps": 1,
@@ -244,12 +459,12 @@
244
  "should_evaluate": false,
245
  "should_log": false,
246
  "should_save": true,
247
- "should_training_stop": false
248
  },
249
  "attributes": {}
250
  }
251
  },
252
- "total_flos": 1.85471820890112e+16,
253
  "train_batch_size": 8,
254
  "trial_name": null,
255
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0931098696461825,
5
  "eval_steps": 5,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
230
  "eval_samples_per_second": 9.189,
231
  "eval_steps_per_second": 1.156,
232
  "step": 25
233
+ },
234
+ {
235
+ "epoch": 0.048417132216014895,
236
+ "grad_norm": 1.0937061309814453,
237
+ "learning_rate": 6.545084971874738e-05,
238
+ "loss": 2.1448,
239
+ "step": 26
240
+ },
241
+ {
242
+ "epoch": 0.05027932960893855,
243
+ "grad_norm": 1.082903265953064,
244
+ "learning_rate": 6.167226819279528e-05,
245
+ "loss": 2.0361,
246
+ "step": 27
247
+ },
248
+ {
249
+ "epoch": 0.0521415270018622,
250
+ "grad_norm": 1.4357037544250488,
251
+ "learning_rate": 5.782172325201155e-05,
252
+ "loss": 2.2307,
253
+ "step": 28
254
+ },
255
+ {
256
+ "epoch": 0.054003724394785846,
257
+ "grad_norm": 1.0995923280715942,
258
+ "learning_rate": 5.392295478639225e-05,
259
+ "loss": 2.0975,
260
+ "step": 29
261
+ },
262
+ {
263
+ "epoch": 0.055865921787709494,
264
+ "grad_norm": 1.0289602279663086,
265
+ "learning_rate": 5e-05,
266
+ "loss": 1.8657,
267
+ "step": 30
268
+ },
269
+ {
270
+ "epoch": 0.055865921787709494,
271
+ "eval_loss": 2.066453695297241,
272
+ "eval_runtime": 49.2696,
273
+ "eval_samples_per_second": 9.194,
274
+ "eval_steps_per_second": 1.157,
275
+ "step": 30
276
+ },
277
+ {
278
+ "epoch": 0.05772811918063315,
279
+ "grad_norm": 1.096411943435669,
280
+ "learning_rate": 4.607704521360776e-05,
281
+ "loss": 2.0965,
282
+ "step": 31
283
+ },
284
+ {
285
+ "epoch": 0.0595903165735568,
286
+ "grad_norm": 1.0694092512130737,
287
+ "learning_rate": 4.2178276747988446e-05,
288
+ "loss": 2.0698,
289
+ "step": 32
290
+ },
291
+ {
292
+ "epoch": 0.061452513966480445,
293
+ "grad_norm": 1.118601679801941,
294
+ "learning_rate": 3.832773180720475e-05,
295
+ "loss": 2.1493,
296
+ "step": 33
297
+ },
298
+ {
299
+ "epoch": 0.0633147113594041,
300
+ "grad_norm": 1.0171372890472412,
301
+ "learning_rate": 3.4549150281252636e-05,
302
+ "loss": 2.0332,
303
+ "step": 34
304
+ },
305
+ {
306
+ "epoch": 0.06517690875232775,
307
+ "grad_norm": 1.0827255249023438,
308
+ "learning_rate": 3.086582838174551e-05,
309
+ "loss": 1.993,
310
+ "step": 35
311
+ },
312
+ {
313
+ "epoch": 0.06517690875232775,
314
+ "eval_loss": 2.005394697189331,
315
+ "eval_runtime": 49.3447,
316
+ "eval_samples_per_second": 9.18,
317
+ "eval_steps_per_second": 1.155,
318
+ "step": 35
319
+ },
320
+ {
321
+ "epoch": 0.0670391061452514,
322
+ "grad_norm": 1.0604010820388794,
323
+ "learning_rate": 2.7300475013022663e-05,
324
+ "loss": 1.8807,
325
+ "step": 36
326
+ },
327
+ {
328
+ "epoch": 0.06890130353817504,
329
+ "grad_norm": 1.0425511598587036,
330
+ "learning_rate": 2.3875071764202563e-05,
331
+ "loss": 1.9859,
332
+ "step": 37
333
+ },
334
+ {
335
+ "epoch": 0.07076350093109869,
336
+ "grad_norm": 1.0914885997772217,
337
+ "learning_rate": 2.061073738537635e-05,
338
+ "loss": 1.9077,
339
+ "step": 38
340
+ },
341
+ {
342
+ "epoch": 0.07262569832402235,
343
+ "grad_norm": 1.1516059637069702,
344
+ "learning_rate": 1.7527597583490822e-05,
345
+ "loss": 2.2016,
346
+ "step": 39
347
+ },
348
+ {
349
+ "epoch": 0.074487895716946,
350
+ "grad_norm": 1.0635038614273071,
351
+ "learning_rate": 1.4644660940672627e-05,
352
+ "loss": 2.0021,
353
+ "step": 40
354
+ },
355
+ {
356
+ "epoch": 0.074487895716946,
357
+ "eval_loss": 1.9731868505477905,
358
+ "eval_runtime": 49.321,
359
+ "eval_samples_per_second": 9.185,
360
+ "eval_steps_per_second": 1.156,
361
+ "step": 40
362
+ },
363
+ {
364
+ "epoch": 0.07635009310986965,
365
+ "grad_norm": 1.2229695320129395,
366
+ "learning_rate": 1.1979701719998453e-05,
367
+ "loss": 2.0167,
368
+ "step": 41
369
+ },
370
+ {
371
+ "epoch": 0.0782122905027933,
372
+ "grad_norm": 1.044442057609558,
373
+ "learning_rate": 9.549150281252633e-06,
374
+ "loss": 1.8081,
375
+ "step": 42
376
+ },
377
+ {
378
+ "epoch": 0.08007448789571694,
379
+ "grad_norm": 1.0942388772964478,
380
+ "learning_rate": 7.367991782295391e-06,
381
+ "loss": 2.2174,
382
+ "step": 43
383
+ },
384
+ {
385
+ "epoch": 0.08193668528864059,
386
+ "grad_norm": 1.0910190343856812,
387
+ "learning_rate": 5.449673790581611e-06,
388
+ "loss": 2.1796,
389
+ "step": 44
390
+ },
391
+ {
392
+ "epoch": 0.08379888268156424,
393
+ "grad_norm": 1.2429304122924805,
394
+ "learning_rate": 3.8060233744356633e-06,
395
+ "loss": 1.7848,
396
+ "step": 45
397
+ },
398
+ {
399
+ "epoch": 0.08379888268156424,
400
+ "eval_loss": 1.9582425355911255,
401
+ "eval_runtime": 49.2697,
402
+ "eval_samples_per_second": 9.194,
403
+ "eval_steps_per_second": 1.157,
404
+ "step": 45
405
+ },
406
+ {
407
+ "epoch": 0.0856610800744879,
408
+ "grad_norm": 0.9983396530151367,
409
+ "learning_rate": 2.4471741852423237e-06,
410
+ "loss": 1.8316,
411
+ "step": 46
412
+ },
413
+ {
414
+ "epoch": 0.08752327746741155,
415
+ "grad_norm": 1.012921690940857,
416
+ "learning_rate": 1.3815039801161721e-06,
417
+ "loss": 1.8607,
418
+ "step": 47
419
+ },
420
+ {
421
+ "epoch": 0.0893854748603352,
422
+ "grad_norm": 0.9606110453605652,
423
+ "learning_rate": 6.15582970243117e-07,
424
+ "loss": 1.886,
425
+ "step": 48
426
+ },
427
+ {
428
+ "epoch": 0.09124767225325885,
429
+ "grad_norm": 1.0702084302902222,
430
+ "learning_rate": 1.5413331334360182e-07,
431
+ "loss": 2.1066,
432
+ "step": 49
433
+ },
434
+ {
435
+ "epoch": 0.0931098696461825,
436
+ "grad_norm": 1.0214251279830933,
437
+ "learning_rate": 0.0,
438
+ "loss": 2.0748,
439
+ "step": 50
440
+ },
441
+ {
442
+ "epoch": 0.0931098696461825,
443
+ "eval_loss": 1.9558095932006836,
444
+ "eval_runtime": 49.3038,
445
+ "eval_samples_per_second": 9.188,
446
+ "eval_steps_per_second": 1.156,
447
+ "step": 50
448
  }
449
  ],
450
  "logging_steps": 1,
 
459
  "should_evaluate": false,
460
  "should_log": false,
461
  "should_save": true,
462
+ "should_training_stop": true
463
  },
464
  "attributes": {}
465
  }
466
  },
467
+ "total_flos": 3.70943641780224e+16,
468
  "train_batch_size": 8,
469
  "trial_name": null,
470
  "trial_params": null