File size: 11,155 Bytes
409a825 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 |
wandb_version: 1
_wandb:
desc: null
value:
python_version: 3.11.9
cli_version: 0.16.6
framework: huggingface
huggingface_version: 4.40.1
is_jupyter_run: false
is_kaggle_kernel: false
start_time: 1714147035.0
t:
1:
- 1
- 11
- 49
- 51
- 55
- 71
- 84
- 98
2:
- 1
- 11
- 49
- 51
- 55
- 71
- 84
- 98
3:
- 7
- 23
4: 3.11.9
5: 0.16.6
6: 4.40.1
8:
- 5
9:
1: transformers_trainer
13: linux-x86_64
m:
- 1: train/global_step
6:
- 3
- 1: train/loss
5: 1
6:
- 1
- 1: train/grad_norm
5: 1
6:
- 1
- 1: train/learning_rate
5: 1
6:
- 1
- 1: train/rewards/chosen
5: 1
6:
- 1
- 1: train/rewards/rejected
5: 1
6:
- 1
- 1: train/rewards/accuracies
5: 1
6:
- 1
- 1: train/rewards/margins
5: 1
6:
- 1
- 1: train/logps/rejected
5: 1
6:
- 1
- 1: train/logps/chosen
5: 1
6:
- 1
- 1: train/logits/rejected
5: 1
6:
- 1
- 1: train/logits/chosen
5: 1
6:
- 1
- 1: train/epoch
5: 1
6:
- 1
- 1: eval/loss
5: 1
6:
- 1
- 1: eval/runtime
5: 1
6:
- 1
- 1: eval/samples_per_second
5: 1
6:
- 1
- 1: eval/steps_per_second
5: 1
6:
- 1
- 1: eval/rewards/chosen
5: 1
6:
- 1
- 1: eval/rewards/rejected
5: 1
6:
- 1
- 1: eval/rewards/accuracies
5: 1
6:
- 1
- 1: eval/rewards/margins
5: 1
6:
- 1
- 1: eval/logps/rejected
5: 1
6:
- 1
- 1: eval/logps/chosen
5: 1
6:
- 1
- 1: eval/logits/rejected
5: 1
6:
- 1
- 1: eval/logits/chosen
5: 1
6:
- 1
vocab_size:
desc: null
value: 32000
max_position_embeddings:
desc: null
value: 32768
hidden_size:
desc: null
value: 4096
intermediate_size:
desc: null
value: 14336
num_hidden_layers:
desc: null
value: 6
num_attention_heads:
desc: null
value: 32
sliding_window:
desc: null
value: 4096
num_key_value_heads:
desc: null
value: 8
hidden_act:
desc: null
value: silu
initializer_range:
desc: null
value: 0.02
rms_norm_eps:
desc: null
value: 1.0e-05
use_cache:
desc: null
value: false
rope_theta:
desc: null
value: 10000.0
attention_dropout:
desc: null
value: 0.0
return_dict:
desc: null
value: true
output_hidden_states:
desc: null
value: false
output_attentions:
desc: null
value: false
torchscript:
desc: null
value: false
torch_dtype:
desc: null
value: null
use_bfloat16:
desc: null
value: false
tf_legacy_loss:
desc: null
value: false
pruned_heads:
desc: null
value: {}
tie_word_embeddings:
desc: null
value: false
chunk_size_feed_forward:
desc: null
value: 0
is_encoder_decoder:
desc: null
value: false
is_decoder:
desc: null
value: false
cross_attention_hidden_size:
desc: null
value: null
add_cross_attention:
desc: null
value: false
tie_encoder_decoder:
desc: null
value: false
max_length:
desc: null
value: 1024
min_length:
desc: null
value: 0
do_sample:
desc: null
value: false
early_stopping:
desc: null
value: false
num_beams:
desc: null
value: 1
num_beam_groups:
desc: null
value: 1
diversity_penalty:
desc: null
value: 0.0
temperature:
desc: null
value: 1.0
top_k:
desc: null
value: 50
top_p:
desc: null
value: 1.0
typical_p:
desc: null
value: 1.0
repetition_penalty:
desc: null
value: 1.0
length_penalty:
desc: null
value: 1.0
no_repeat_ngram_size:
desc: null
value: 0
encoder_no_repeat_ngram_size:
desc: null
value: 0
bad_words_ids:
desc: null
value: null
num_return_sequences:
desc: null
value: 1
output_scores:
desc: null
value: false
return_dict_in_generate:
desc: null
value: false
forced_bos_token_id:
desc: null
value: null
forced_eos_token_id:
desc: null
value: null
remove_invalid_values:
desc: null
value: false
exponential_decay_length_penalty:
desc: null
value: null
suppress_tokens:
desc: null
value: null
begin_suppress_tokens:
desc: null
value: null
architectures:
desc: null
value:
- MistralForCausalLM
finetuning_task:
desc: null
value: null
id2label:
desc: null
value:
'0': LABEL_0
'1': LABEL_1
label2id:
desc: null
value:
LABEL_0: 0
LABEL_1: 1
tokenizer_class:
desc: null
value: null
prefix:
desc: null
value: null
bos_token_id:
desc: null
value: 1
pad_token_id:
desc: null
value: null
eos_token_id:
desc: null
value: 2
sep_token_id:
desc: null
value: null
decoder_start_token_id:
desc: null
value: null
task_specific_params:
desc: null
value: null
problem_type:
desc: null
value: null
_name_or_path:
desc: null
value: sanchit-gandhi/distil-zephyr-1.5b-ssft-ultrachat
transformers_version:
desc: null
value: 4.40.1
model_type:
desc: null
value: mistral
output_dir:
desc: null
value: ./
overwrite_output_dir:
desc: null
value: false
do_train:
desc: null
value: false
do_eval:
desc: null
value: true
do_predict:
desc: null
value: false
evaluation_strategy:
desc: null
value: steps
prediction_loss_only:
desc: null
value: false
per_device_train_batch_size:
desc: null
value: 8
per_device_eval_batch_size:
desc: null
value: 8
per_gpu_train_batch_size:
desc: null
value: null
per_gpu_eval_batch_size:
desc: null
value: null
gradient_accumulation_steps:
desc: null
value: 2
eval_accumulation_steps:
desc: null
value: null
eval_delay:
desc: null
value: 0
learning_rate:
desc: null
value: 5.0e-07
weight_decay:
desc: null
value: 0.0
adam_beta1:
desc: null
value: 0.9
adam_beta2:
desc: null
value: 0.999
adam_epsilon:
desc: null
value: 1.0e-08
max_grad_norm:
desc: null
value: 1.0
num_train_epochs:
desc: null
value: 1
max_steps:
desc: null
value: -1
lr_scheduler_type:
desc: null
value: cosine
lr_scheduler_kwargs:
desc: null
value: {}
warmup_ratio:
desc: null
value: 0.1
warmup_steps:
desc: null
value: 0
log_level:
desc: null
value: info
log_level_replica:
desc: null
value: warning
log_on_each_node:
desc: null
value: true
logging_dir:
desc: null
value: ./runs/Apr26_15-48-43_ip-26-0-160-225
logging_strategy:
desc: null
value: steps
logging_first_step:
desc: null
value: true
logging_steps:
desc: null
value: 25
logging_nan_inf_filter:
desc: null
value: true
save_strategy:
desc: null
value: steps
save_steps:
desc: null
value: 100
save_total_limit:
desc: null
value: 1
save_safetensors:
desc: null
value: true
save_on_each_node:
desc: null
value: false
save_only_model:
desc: null
value: false
no_cuda:
desc: null
value: false
use_cpu:
desc: null
value: false
use_mps_device:
desc: null
value: false
seed:
desc: null
value: 42
data_seed:
desc: null
value: null
jit_mode_eval:
desc: null
value: false
use_ipex:
desc: null
value: false
bf16:
desc: null
value: true
fp16:
desc: null
value: false
fp16_opt_level:
desc: null
value: O1
half_precision_backend:
desc: null
value: auto
bf16_full_eval:
desc: null
value: false
fp16_full_eval:
desc: null
value: false
tf32:
desc: null
value: null
local_rank:
desc: null
value: 0
ddp_backend:
desc: null
value: null
tpu_num_cores:
desc: null
value: null
tpu_metrics_debug:
desc: null
value: false
debug:
desc: null
value: []
dataloader_drop_last:
desc: null
value: false
eval_steps:
desc: null
value: 100
dataloader_num_workers:
desc: null
value: 0
dataloader_prefetch_factor:
desc: null
value: null
past_index:
desc: null
value: -1
run_name:
desc: null
value: ./
disable_tqdm:
desc: null
value: false
remove_unused_columns:
desc: null
value: false
label_names:
desc: null
value: null
load_best_model_at_end:
desc: null
value: false
metric_for_best_model:
desc: null
value: null
greater_is_better:
desc: null
value: null
ignore_data_skip:
desc: null
value: false
fsdp:
desc: null
value: []
fsdp_min_num_params:
desc: null
value: 0
fsdp_config:
desc: null
value:
min_num_params: 0
xla: false
xla_fsdp_v2: false
xla_fsdp_grad_ckpt: false
fsdp_transformer_layer_cls_to_wrap:
desc: null
value: null
accelerator_config:
desc: null
value:
split_batches: false
dispatch_batches: null
even_batches: true
use_seedable_sampler: true
gradient_accumulation_kwargs: null
deepspeed:
desc: null
value: null
label_smoothing_factor:
desc: null
value: 0.0
optim:
desc: null
value: adamw_torch
optim_args:
desc: null
value: null
adafactor:
desc: null
value: false
group_by_length:
desc: null
value: false
length_column_name:
desc: null
value: length
report_to:
desc: null
value:
- tensorboard
- wandb
ddp_find_unused_parameters:
desc: null
value: null
ddp_bucket_cap_mb:
desc: null
value: null
ddp_broadcast_buffers:
desc: null
value: null
dataloader_pin_memory:
desc: null
value: true
dataloader_persistent_workers:
desc: null
value: false
skip_memory_metrics:
desc: null
value: true
use_legacy_prediction_loop:
desc: null
value: false
push_to_hub:
desc: null
value: true
resume_from_checkpoint:
desc: null
value: null
hub_model_id:
desc: null
value: null
hub_strategy:
desc: null
value: every_save
hub_token:
desc: null
value: <HUB_TOKEN>
hub_private_repo:
desc: null
value: false
hub_always_push:
desc: null
value: false
gradient_checkpointing:
desc: null
value: true
gradient_checkpointing_kwargs:
desc: null
value:
use_reentrant: false
include_inputs_for_metrics:
desc: null
value: false
eval_do_concat_batches:
desc: null
value: true
fp16_backend:
desc: null
value: auto
push_to_hub_model_id:
desc: null
value: null
push_to_hub_organization:
desc: null
value: null
push_to_hub_token:
desc: null
value: <PUSH_TO_HUB_TOKEN>
mp_parameters:
desc: null
value: ''
auto_find_batch_size:
desc: null
value: false
full_determinism:
desc: null
value: false
torchdynamo:
desc: null
value: null
ray_scope:
desc: null
value: last
ddp_timeout:
desc: null
value: 1800
torch_compile:
desc: null
value: false
torch_compile_backend:
desc: null
value: null
torch_compile_mode:
desc: null
value: null
dispatch_batches:
desc: null
value: null
split_batches:
desc: null
value: null
include_tokens_per_second:
desc: null
value: false
include_num_input_tokens_seen:
desc: null
value: false
neftune_noise_alpha:
desc: null
value: null
optim_target_modules:
desc: null
value: null
beta:
desc: null
value: 0.01
hub_model_revision:
desc: null
value: main
max_prompt_length:
desc: null
value: 512
loss_type:
desc: null
value: sigmoid
|