lillian039 commited on
Commit
ca4c581
·
verified ·
1 Parent(s): 5cc97a8

Training in progress, step 3453

Browse files
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27a5308856976211ff04f4255b80332b27e7b1d42f92147815edf4f83e7c4735
3
  size 209799496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d2f554863018a78a364cb836451c264c8077e195355dae0e75c028bef5a328f
3
  size 209799496
tokenizer_config.json CHANGED
@@ -2072,6 +2072,7 @@
2072
  "model_max_length": 131072,
2073
  "pad_token": "<|finetune_right_pad_id|>",
2074
  "padding_side": "right",
 
2075
  "split_special_tokens": false,
2076
  "tokenizer_class": "PreTrainedTokenizerFast"
2077
  }
 
2072
  "model_max_length": 131072,
2073
  "pad_token": "<|finetune_right_pad_id|>",
2074
  "padding_side": "right",
2075
+ "processor_class": "MllamaProcessor",
2076
  "split_special_tokens": false,
2077
  "tokenizer_class": "PreTrainedTokenizerFast"
2078
  }
trainer_log.jsonl CHANGED
@@ -304,3 +304,49 @@
304
  {"current_steps": 2990, "total_steps": 3453, "loss": 0.0593, "lr": 5.379881373618295e-06, "epoch": 2.5977410947002606, "percentage": 86.59, "elapsed_time": "18:05:20", "remaining_time": "2:48:03"}
305
  {"current_steps": 3000, "total_steps": 3453, "loss": 0.0541, "lr": 5.154033937552238e-06, "epoch": 2.6064291920069502, "percentage": 86.88, "elapsed_time": "18:08:55", "remaining_time": "2:44:25"}
306
  {"current_steps": 3000, "total_steps": 3453, "eval_loss": 0.058555811643600464, "epoch": 2.6064291920069502, "percentage": 86.88, "elapsed_time": "18:11:20", "remaining_time": "2:44:47"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
304
  {"current_steps": 2990, "total_steps": 3453, "loss": 0.0593, "lr": 5.379881373618295e-06, "epoch": 2.5977410947002606, "percentage": 86.59, "elapsed_time": "18:05:20", "remaining_time": "2:48:03"}
305
  {"current_steps": 3000, "total_steps": 3453, "loss": 0.0541, "lr": 5.154033937552238e-06, "epoch": 2.6064291920069502, "percentage": 86.88, "elapsed_time": "18:08:55", "remaining_time": "2:44:25"}
306
  {"current_steps": 3000, "total_steps": 3453, "eval_loss": 0.058555811643600464, "epoch": 2.6064291920069502, "percentage": 86.88, "elapsed_time": "18:11:20", "remaining_time": "2:44:47"}
307
+ {"current_steps": 3010, "total_steps": 3453, "loss": 0.0555, "lr": 4.932771475965342e-06, "epoch": 2.6151172893136403, "percentage": 87.17, "elapsed_time": "18:15:24", "remaining_time": "2:41:13"}
308
+ {"current_steps": 3020, "total_steps": 3453, "loss": 0.0625, "lr": 4.7161166103513784e-06, "epoch": 2.6238053866203304, "percentage": 87.46, "elapsed_time": "18:18:59", "remaining_time": "2:37:34"}
309
+ {"current_steps": 3030, "total_steps": 3453, "loss": 0.0655, "lr": 4.5040914911313345e-06, "epoch": 2.63249348392702, "percentage": 87.75, "elapsed_time": "18:22:35", "remaining_time": "2:33:55"}
310
+ {"current_steps": 3040, "total_steps": 3453, "loss": 0.0647, "lr": 4.296717795388938e-06, "epoch": 2.6411815812337096, "percentage": 88.04, "elapsed_time": "18:26:10", "remaining_time": "2:30:16"}
311
+ {"current_steps": 3050, "total_steps": 3453, "loss": 0.0498, "lr": 4.094016724654359e-06, "epoch": 2.6498696785403997, "percentage": 88.33, "elapsed_time": "18:29:46", "remaining_time": "2:26:38"}
312
+ {"current_steps": 3060, "total_steps": 3453, "loss": 0.0601, "lr": 3.896009002736639e-06, "epoch": 2.6585577758470897, "percentage": 88.62, "elapsed_time": "18:33:21", "remaining_time": "2:22:59"}
313
+ {"current_steps": 3070, "total_steps": 3453, "loss": 0.0668, "lr": 3.702714873604862e-06, "epoch": 2.6672458731537794, "percentage": 88.91, "elapsed_time": "18:36:57", "remaining_time": "2:19:20"}
314
+ {"current_steps": 3080, "total_steps": 3453, "loss": 0.0595, "lr": 3.5141540993185286e-06, "epoch": 2.675933970460469, "percentage": 89.2, "elapsed_time": "18:40:32", "remaining_time": "2:15:42"}
315
+ {"current_steps": 3090, "total_steps": 3453, "loss": 0.0541, "lr": 3.3303459580070695e-06, "epoch": 2.684622067767159, "percentage": 89.49, "elapsed_time": "18:44:07", "remaining_time": "2:12:03"}
316
+ {"current_steps": 3100, "total_steps": 3453, "loss": 0.0579, "lr": 3.1513092418988643e-06, "epoch": 2.6933101650738487, "percentage": 89.78, "elapsed_time": "18:47:43", "remaining_time": "2:08:24"}
317
+ {"current_steps": 3110, "total_steps": 3453, "loss": 0.0611, "lr": 2.9770622554000094e-06, "epoch": 2.7019982623805388, "percentage": 90.07, "elapsed_time": "18:51:18", "remaining_time": "2:04:46"}
318
+ {"current_steps": 3120, "total_steps": 3453, "loss": 0.0592, "lr": 2.807622813222871e-06, "epoch": 2.7106863596872284, "percentage": 90.36, "elapsed_time": "18:54:54", "remaining_time": "2:01:07"}
319
+ {"current_steps": 3130, "total_steps": 3453, "loss": 0.0553, "lr": 2.643008238564759e-06, "epoch": 2.7193744569939184, "percentage": 90.65, "elapsed_time": "18:58:29", "remaining_time": "1:57:29"}
320
+ {"current_steps": 3140, "total_steps": 3453, "loss": 0.0559, "lr": 2.4832353613367833e-06, "epoch": 2.728062554300608, "percentage": 90.94, "elapsed_time": "19:02:04", "remaining_time": "1:53:50"}
321
+ {"current_steps": 3150, "total_steps": 3453, "loss": 0.0555, "lr": 2.3283205164432884e-06, "epoch": 2.736750651607298, "percentage": 91.23, "elapsed_time": "19:05:40", "remaining_time": "1:50:12"}
322
+ {"current_steps": 3160, "total_steps": 3453, "loss": 0.0617, "lr": 2.1782795421116996e-06, "epoch": 2.7454387489139878, "percentage": 91.51, "elapsed_time": "19:09:15", "remaining_time": "1:46:33"}
323
+ {"current_steps": 3170, "total_steps": 3453, "loss": 0.0547, "lr": 2.033127778273308e-06, "epoch": 2.754126846220678, "percentage": 91.8, "elapsed_time": "19:12:50", "remaining_time": "1:42:55"}
324
+ {"current_steps": 3180, "total_steps": 3453, "loss": 0.0606, "lr": 1.892880064994934e-06, "epoch": 2.7628149435273675, "percentage": 92.09, "elapsed_time": "19:16:26", "remaining_time": "1:39:16"}
325
+ {"current_steps": 3190, "total_steps": 3453, "loss": 0.0569, "lr": 1.7575507409617053e-06, "epoch": 2.771503040834057, "percentage": 92.38, "elapsed_time": "19:20:01", "remaining_time": "1:35:38"}
326
+ {"current_steps": 3200, "total_steps": 3453, "loss": 0.06, "lr": 1.627153642011059e-06, "epoch": 2.780191138140747, "percentage": 92.67, "elapsed_time": "19:23:37", "remaining_time": "1:31:59"}
327
+ {"current_steps": 3210, "total_steps": 3453, "loss": 0.0572, "lr": 1.501702099718244e-06, "epoch": 2.788879235447437, "percentage": 92.96, "elapsed_time": "19:27:12", "remaining_time": "1:28:21"}
328
+ {"current_steps": 3220, "total_steps": 3453, "loss": 0.0568, "lr": 1.381208940033296e-06, "epoch": 2.797567332754127, "percentage": 93.25, "elapsed_time": "19:30:47", "remaining_time": "1:24:43"}
329
+ {"current_steps": 3230, "total_steps": 3453, "loss": 0.0605, "lr": 1.2656864819697189e-06, "epoch": 2.8062554300608165, "percentage": 93.54, "elapsed_time": "19:34:23", "remaining_time": "1:21:04"}
330
+ {"current_steps": 3240, "total_steps": 3453, "loss": 0.0609, "lr": 1.155146536345053e-06, "epoch": 2.8149435273675065, "percentage": 93.83, "elapsed_time": "19:37:58", "remaining_time": "1:17:26"}
331
+ {"current_steps": 3250, "total_steps": 3453, "loss": 0.0622, "lr": 1.0496004045733143e-06, "epoch": 2.8236316246741966, "percentage": 94.12, "elapsed_time": "19:41:33", "remaining_time": "1:13:48"}
332
+ {"current_steps": 3260, "total_steps": 3453, "loss": 0.0572, "lr": 9.490588775095733e-07, "epoch": 2.832319721980886, "percentage": 94.41, "elapsed_time": "19:45:09", "remaining_time": "1:10:09"}
333
+ {"current_steps": 3270, "total_steps": 3453, "loss": 0.0613, "lr": 8.535322343467322e-07, "epoch": 2.841007819287576, "percentage": 94.7, "elapsed_time": "19:48:44", "remaining_time": "1:06:31"}
334
+ {"current_steps": 3280, "total_steps": 3453, "loss": 0.054, "lr": 7.630302415645774e-07, "epoch": 2.849695916594266, "percentage": 94.99, "elapsed_time": "19:52:19", "remaining_time": "1:02:53"}
335
+ {"current_steps": 3290, "total_steps": 3453, "loss": 0.0558, "lr": 6.775621519312713e-07, "epoch": 2.8583840139009555, "percentage": 95.28, "elapsed_time": "19:55:55", "remaining_time": "0:59:15"}
336
+ {"current_steps": 3300, "total_steps": 3453, "loss": 0.0611, "lr": 5.971367035573771e-07, "epoch": 2.8670721112076456, "percentage": 95.57, "elapsed_time": "19:59:30", "remaining_time": "0:55:36"}
337
+ {"current_steps": 3310, "total_steps": 3453, "loss": 0.0592, "lr": 5.217621190024779e-07, "epoch": 2.8757602085143352, "percentage": 95.86, "elapsed_time": "20:03:05", "remaining_time": "0:51:58"}
338
+ {"current_steps": 3320, "total_steps": 3453, "loss": 0.0496, "lr": 4.5144610443454414e-07, "epoch": 2.8844483058210253, "percentage": 96.15, "elapsed_time": "20:06:41", "remaining_time": "0:48:20"}
339
+ {"current_steps": 3330, "total_steps": 3453, "loss": 0.058, "lr": 3.8619584884201367e-07, "epoch": 2.893136403127715, "percentage": 96.44, "elapsed_time": "20:10:16", "remaining_time": "0:44:42"}
340
+ {"current_steps": 3340, "total_steps": 3453, "loss": 0.061, "lr": 3.2601802329886857e-07, "epoch": 2.901824500434405, "percentage": 96.73, "elapsed_time": "20:13:52", "remaining_time": "0:41:04"}
341
+ {"current_steps": 3350, "total_steps": 3453, "loss": 0.0575, "lr": 2.709187802825364e-07, "epoch": 2.9105125977410946, "percentage": 97.02, "elapsed_time": "20:17:27", "remaining_time": "0:37:25"}
342
+ {"current_steps": 3360, "total_steps": 3453, "loss": 0.0583, "lr": 2.2090375304489874e-07, "epoch": 2.9192006950477847, "percentage": 97.31, "elapsed_time": "20:21:03", "remaining_time": "0:33:47"}
343
+ {"current_steps": 3370, "total_steps": 3453, "loss": 0.0611, "lr": 1.7597805503637432e-07, "epoch": 2.9278887923544743, "percentage": 97.6, "elapsed_time": "20:24:38", "remaining_time": "0:30:09"}
344
+ {"current_steps": 3380, "total_steps": 3453, "loss": 0.0566, "lr": 1.3614627938309809e-07, "epoch": 2.9365768896611644, "percentage": 97.89, "elapsed_time": "20:28:13", "remaining_time": "0:26:31"}
345
+ {"current_steps": 3390, "total_steps": 3453, "loss": 0.0597, "lr": 1.0141249841734146e-07, "epoch": 2.945264986967854, "percentage": 98.18, "elapsed_time": "20:31:48", "remaining_time": "0:22:53"}
346
+ {"current_steps": 3400, "total_steps": 3453, "loss": 0.0607, "lr": 7.178026326115639e-08, "epoch": 2.953953084274544, "percentage": 98.47, "elapsed_time": "20:35:24", "remaining_time": "0:19:15"}
347
+ {"current_steps": 3410, "total_steps": 3453, "loss": 0.0592, "lr": 4.725260346333804e-08, "epoch": 2.9626411815812337, "percentage": 98.75, "elapsed_time": "20:38:59", "remaining_time": "0:15:37"}
348
+ {"current_steps": 3420, "total_steps": 3453, "loss": 0.0592, "lr": 2.7832026689650347e-08, "epoch": 2.9713292788879233, "percentage": 99.04, "elapsed_time": "20:42:35", "remaining_time": "0:11:59"}
349
+ {"current_steps": 3430, "total_steps": 3453, "loss": 0.0588, "lr": 1.3520518466481058e-08, "epoch": 2.9800173761946134, "percentage": 99.33, "elapsed_time": "20:46:10", "remaining_time": "0:08:21"}
350
+ {"current_steps": 3440, "total_steps": 3453, "loss": 0.0578, "lr": 4.319541977831909e-09, "epoch": 2.9887054735013034, "percentage": 99.62, "elapsed_time": "20:49:45", "remaining_time": "0:04:43"}
351
+ {"current_steps": 3450, "total_steps": 3453, "loss": 0.0581, "lr": 2.300379157160748e-10, "epoch": 2.997393570807993, "percentage": 99.91, "elapsed_time": "20:53:21", "remaining_time": "0:01:05"}
352
+ {"current_steps": 3453, "total_steps": 3453, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "20:54:54", "remaining_time": "0:00:00"}