VERSIL91 commited on
Commit
74e4997
·
verified ·
1 Parent(s): da33c2c

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 sha256:05952e5fbd7b2062781474ee6da30c91c9b55914504ef8310c1fb69732ae0d80
3
  size 27024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ac20dc36b7d865040d202cdadf095c55b66a7287f2c6c80233cef3a08a9bdc6
3
  size 27024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e5feecc7444f52f732d575bd7b47e4c9d4450cf67cd98f36ac6ded54cce0358
3
  size 63974
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c617d0d5823a84b068cdb55dfb653ab2fa079a7b3a09b1898c7e56ce6ca2177
3
  size 63974
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:652365ff63294ffff01ffedb52e831cc2560ab06b5699bca21d63e81dd0efbe7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2edc13c60910e9acd555e90579b2ee1807926bb393c7c79b1e24163c3f5bfc9f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.09401838179900557,
5
  "eval_steps": 13,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -312,6 +312,83 @@
312
  "eval_samples_per_second": 715.095,
313
  "eval_steps_per_second": 358.059,
314
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
315
  }
316
  ],
317
  "logging_steps": 1,
@@ -326,12 +403,12 @@
326
  "should_evaluate": false,
327
  "should_log": false,
328
  "should_save": true,
329
- "should_training_stop": false
330
  },
331
  "attributes": {}
332
  }
333
  },
334
- "total_flos": 8035983654912.0,
335
  "train_batch_size": 2,
336
  "trial_name": null,
337
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.12053638692180202,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
312
  "eval_samples_per_second": 715.095,
313
  "eval_steps_per_second": 358.059,
314
  "step": 39
315
+ },
316
+ {
317
+ "epoch": 0.09642910953744162,
318
+ "grad_norm": 0.23126229643821716,
319
+ "learning_rate": 1.4644660940672627e-05,
320
+ "loss": 11.7885,
321
+ "step": 40
322
+ },
323
+ {
324
+ "epoch": 0.09883983727587765,
325
+ "grad_norm": 0.21654988825321198,
326
+ "learning_rate": 1.1979701719998453e-05,
327
+ "loss": 11.7704,
328
+ "step": 41
329
+ },
330
+ {
331
+ "epoch": 0.10125056501431369,
332
+ "grad_norm": 0.2214740812778473,
333
+ "learning_rate": 9.549150281252633e-06,
334
+ "loss": 11.7851,
335
+ "step": 42
336
+ },
337
+ {
338
+ "epoch": 0.10366129275274974,
339
+ "grad_norm": 0.24273362755775452,
340
+ "learning_rate": 7.367991782295391e-06,
341
+ "loss": 11.7811,
342
+ "step": 43
343
+ },
344
+ {
345
+ "epoch": 0.10607202049118578,
346
+ "grad_norm": 0.2188863307237625,
347
+ "learning_rate": 5.449673790581611e-06,
348
+ "loss": 11.7789,
349
+ "step": 44
350
+ },
351
+ {
352
+ "epoch": 0.10848274822962181,
353
+ "grad_norm": 0.20905157923698425,
354
+ "learning_rate": 3.8060233744356633e-06,
355
+ "loss": 11.7927,
356
+ "step": 45
357
+ },
358
+ {
359
+ "epoch": 0.11089347596805786,
360
+ "grad_norm": 0.2186051905155182,
361
+ "learning_rate": 2.4471741852423237e-06,
362
+ "loss": 11.7862,
363
+ "step": 46
364
+ },
365
+ {
366
+ "epoch": 0.1133042037064939,
367
+ "grad_norm": 0.2207147777080536,
368
+ "learning_rate": 1.3815039801161721e-06,
369
+ "loss": 11.7808,
370
+ "step": 47
371
+ },
372
+ {
373
+ "epoch": 0.11571493144492993,
374
+ "grad_norm": 0.260870099067688,
375
+ "learning_rate": 6.15582970243117e-07,
376
+ "loss": 11.7878,
377
+ "step": 48
378
+ },
379
+ {
380
+ "epoch": 0.11812565918336598,
381
+ "grad_norm": 0.1919865906238556,
382
+ "learning_rate": 1.5413331334360182e-07,
383
+ "loss": 11.7874,
384
+ "step": 49
385
+ },
386
+ {
387
+ "epoch": 0.12053638692180202,
388
+ "grad_norm": 0.2674182653427124,
389
+ "learning_rate": 0.0,
390
+ "loss": 11.7881,
391
+ "step": 50
392
  }
393
  ],
394
  "logging_steps": 1,
 
403
  "should_evaluate": false,
404
  "should_log": false,
405
  "should_save": true,
406
+ "should_training_stop": true
407
  },
408
  "attributes": {}
409
  }
410
  },
411
+ "total_flos": 10295707336704.0,
412
  "train_batch_size": 2,
413
  "trial_name": null,
414
  "trial_params": null