File size: 28,439 Bytes
263939c 053cbec 263939c |
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 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# HuggingFace challenge - Debugger notebook\n",
"Run this notebook to verify your libraries versions, check GPU config and run a quick training"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"id": "T2utsYSKszvv"
},
"outputs": [],
"source": [
"import platform\n",
"import multiprocessing\n",
"\n",
"import torch\n",
"import transformers\n",
"import datasets\n",
"\n",
"import soundfile"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Print main infos"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Check your GPU informations (if any)\n",
"If you launched an AI Training job with GPU resources, they should be listed below (Tesla V100s 32GB).\n",
"Driver and CUDA version "
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "TorMtpwPv6RQ"
},
"source": [
"## Quick training run with a dummy model and data\n",
"more information on https://github.com/huggingface/transformers/tree/master/examples/pytorch/speech-recognition"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "fevoJD15u4Ss",
"outputId": "5861d34e-745b-45ee-e780-ed363043e655"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--2022-01-31 17:09:10-- https://raw.githubusercontent.com/huggingface/transformers/master/examples/pytorch/speech-recognition/run_speech_recognition_ctc.py\n",
"Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.111.133, 185.199.108.133, 185.199.110.133, ...\n",
"Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.111.133|:443... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 30360 (30K) [text/plain]\n",
"Saving to: βrun_speech_recognition_ctc.pyβ\n",
"\n",
"run_speech_recognit 100%[===================>] 29.65K --.-KB/s in 0.001s \n",
"\n",
"2022-01-31 17:09:10 (55.6 MB/s) - βrun_speech_recognition_ctc.pyβ saved [30360/30360]\n",
"\n"
]
}
],
"source": [
"!wget -O run_speech_recognition_ctc.py https://raw.githubusercontent.com/huggingface/transformers/master/examples/pytorch/speech-recognition/run_speech_recognition_ctc.py"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Mz4bubhxxsad",
"outputId": "23398525-cc19-43c2-9fec-497e06214f29"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"01/31/2022 17:10:15 - WARNING - __main__ - Process rank: -1, device: cuda:0, n_gpu: 1distributed training: False, 16-bits training: True\n",
"01/31/2022 17:10:15 - INFO - __main__ - Training/evaluation parameters TrainingArguments(\n",
"_n_gpu=1,\n",
"adafactor=False,\n",
"adam_beta1=0.9,\n",
"adam_beta2=0.999,\n",
"adam_epsilon=1e-08,\n",
"bf16=False,\n",
"bf16_full_eval=False,\n",
"dataloader_drop_last=False,\n",
"dataloader_num_workers=0,\n",
"dataloader_pin_memory=True,\n",
"ddp_bucket_cap_mb=None,\n",
"ddp_find_unused_parameters=None,\n",
"debug=[],\n",
"deepspeed=None,\n",
"disable_tqdm=False,\n",
"do_eval=True,\n",
"do_predict=False,\n",
"do_train=True,\n",
"eval_accumulation_steps=None,\n",
"eval_steps=500,\n",
"evaluation_strategy=IntervalStrategy.STEPS,\n",
"fp16=True,\n",
"fp16_backend=auto,\n",
"fp16_full_eval=False,\n",
"fp16_opt_level=O1,\n",
"gradient_accumulation_steps=1,\n",
"gradient_checkpointing=True,\n",
"greater_is_better=None,\n",
"group_by_length=True,\n",
"half_precision_backend=auto,\n",
"hub_model_id=None,\n",
"hub_strategy=HubStrategy.EVERY_SAVE,\n",
"hub_token=<HUB_TOKEN>,\n",
"ignore_data_skip=False,\n",
"label_names=None,\n",
"label_smoothing_factor=0.0,\n",
"learning_rate=0.0003,\n",
"length_column_name=input_length,\n",
"load_best_model_at_end=False,\n",
"local_rank=-1,\n",
"log_level=-1,\n",
"log_level_replica=-1,\n",
"log_on_each_node=True,\n",
"logging_dir=./runs/Jan31_17-10-15_job-6a6be32c-c82d-4385-805b-1f7606124d5b,\n",
"logging_first_step=False,\n",
"logging_nan_inf_filter=True,\n",
"logging_steps=500,\n",
"logging_strategy=IntervalStrategy.STEPS,\n",
"lr_scheduler_type=SchedulerType.LINEAR,\n",
"max_grad_norm=1.0,\n",
"max_steps=10,\n",
"metric_for_best_model=None,\n",
"mp_parameters=,\n",
"no_cuda=False,\n",
"num_train_epochs=3.0,\n",
"optim=OptimizerNames.ADAMW_HF,\n",
"output_dir=./,\n",
"overwrite_output_dir=True,\n",
"past_index=-1,\n",
"per_device_eval_batch_size=8,\n",
"per_device_train_batch_size=2,\n",
"prediction_loss_only=False,\n",
"push_to_hub=True,\n",
"push_to_hub_model_id=None,\n",
"push_to_hub_organization=None,\n",
"push_to_hub_token=<PUSH_TO_HUB_TOKEN>,\n",
"remove_unused_columns=True,\n",
"report_to=[],\n",
"resume_from_checkpoint=None,\n",
"run_name=./,\n",
"save_on_each_node=False,\n",
"save_steps=5,\n",
"save_strategy=IntervalStrategy.STEPS,\n",
"save_total_limit=1,\n",
"seed=42,\n",
"sharded_ddp=[],\n",
"skip_memory_metrics=True,\n",
"tf32=None,\n",
"tpu_metrics_debug=False,\n",
"tpu_num_cores=None,\n",
"use_legacy_prediction_loop=False,\n",
"warmup_ratio=0.0,\n",
"warmup_steps=0,\n",
"weight_decay=0.0,\n",
"xpu_backend=None,\n",
")\n",
"Downloading: 100%|βββββββββββββββββββββββββ| 10.1k/10.1k [00:00<00:00, 7.28MB/s]\n",
"Downloading: 100%|βββββββββββββββββββββββββ| 2.98k/2.98k [00:00<00:00, 3.39MB/s]\n",
"Downloading: 100%|ββββββββββββββββββββββββββ| 53.1k/53.1k [00:00<00:00, 325kB/s]\n",
"Downloading and preparing dataset common_voice/ab to /workspace/.cache/huggingface/datasets/mozilla-foundation___common_voice/ab/8.0.0/b8bc4d453193c06a43269b46cd87f075c70f152ac963b7f28f7a2760c45ec3e8...\n",
"Downloading: 100%|βββββββββββββββββββββββββ| 1.72G/1.72G [01:31<00:00, 18.8MB/s]\n",
"Dataset common_voice downloaded and prepared to /workspace/.cache/huggingface/datasets/mozilla-foundation___common_voice/ab/8.0.0/b8bc4d453193c06a43269b46cd87f075c70f152ac963b7f28f7a2760c45ec3e8. Subsequent calls will reuse this data.\n",
"01/31/2022 17:13:15 - WARNING - datasets.builder - Reusing dataset common_voice (/workspace/.cache/huggingface/datasets/mozilla-foundation___common_voice/ab/8.0.0/b8bc4d453193c06a43269b46cd87f075c70f152ac963b7f28f7a2760c45ec3e8)\n",
"remove special characters from datasets: 30002ex [00:05, 5673.36ex/s]\n",
"remove special characters from datasets: 9184ex [00:01, 5662.70ex/s]\n",
"loading configuration file https://huggingface.co/hf-test/xls-r-dummy/resolve/main/config.json from cache at /workspace/.cache/huggingface/transformers/8157526a5096028eb61c63d228d882e5437edef5cb8b1a033ae35bf6249d1568.80b921aeb31bf1fa045a15aafa0e6f7e2ac68d338c1d83a3c76c99e260b22a62\n",
"Model config Wav2Vec2Config {\n",
" \"_name_or_path\": \"hf-test/xls-r-dummy\",\n",
" \"activation_dropout\": 0.1,\n",
" \"adapter_kernel_size\": 3,\n",
" \"adapter_stride\": 2,\n",
" \"add_adapter\": false,\n",
" \"apply_spec_augment\": true,\n",
" \"architectures\": [\n",
" \"Wav2Vec2Model\"\n",
" ],\n",
" \"attention_dropout\": 0.1,\n",
" \"bos_token_id\": 1,\n",
" \"classifier_proj_size\": 256,\n",
" \"codevector_dim\": 256,\n",
" \"contrastive_logits_temperature\": 0.1,\n",
" \"conv_bias\": false,\n",
" \"conv_dim\": [\n",
" 32,\n",
" 32,\n",
" 32\n",
" ],\n",
" \"conv_kernel\": [\n",
" 8,\n",
" 8,\n",
" 8\n",
" ],\n",
" \"conv_stride\": [\n",
" 4,\n",
" 4,\n",
" 4\n",
" ],\n",
" \"ctc_loss_reduction\": \"sum\",\n",
" \"ctc_zero_infinity\": false,\n",
" \"diversity_loss_weight\": 0.1,\n",
" \"do_stable_layer_norm\": true,\n",
" \"eos_token_id\": 2,\n",
" \"feat_extract_activation\": \"gelu\",\n",
" \"feat_extract_dropout\": 0.0,\n",
" \"feat_extract_norm\": \"layer\",\n",
" \"feat_proj_dropout\": 0.1,\n",
" \"feat_quantizer_dropout\": 0.0,\n",
" \"final_dropout\": 0.1,\n",
" \"gradient_checkpointing\": false,\n",
" \"hidden_act\": \"gelu\",\n",
" \"hidden_dropout\": 0.1,\n",
" \"hidden_dropout_prob\": 0.1,\n",
" \"hidden_size\": 16,\n",
" \"initializer_range\": 0.02,\n",
" \"intermediate_size\": 20,\n",
" \"layer_norm_eps\": 1e-05,\n",
" \"layerdrop\": 0.1,\n",
" \"mask_feature_length\": 10,\n",
" \"mask_feature_min_masks\": 0,\n",
" \"mask_feature_prob\": 0.0,\n",
" \"mask_time_length\": 10,\n",
" \"mask_time_min_masks\": 2,\n",
" \"mask_time_prob\": 0.05,\n",
" \"model_type\": \"wav2vec2\",\n",
" \"num_adapter_layers\": 3,\n",
" \"num_attention_heads\": 2,\n",
" \"num_codevector_groups\": 2,\n",
" \"num_codevectors_per_group\": 320,\n",
" \"num_conv_pos_embedding_groups\": 2,\n",
" \"num_conv_pos_embeddings\": 16,\n",
" \"num_feat_extract_layers\": 3,\n",
" \"num_hidden_layers\": 4,\n",
" \"num_negatives\": 10,\n",
" \"output_hidden_size\": 16,\n",
" \"pad_token_id\": 0,\n",
" \"proj_codevector_dim\": 256,\n",
" \"tdnn_dilation\": [\n",
" 1,\n",
" 2,\n",
" 3,\n",
" 1,\n",
" 1\n",
" ],\n",
" \"tdnn_dim\": [\n",
" 512,\n",
" 512,\n",
" 512,\n",
" 512,\n",
" 1500\n",
" ],\n",
" \"tdnn_kernel\": [\n",
" 5,\n",
" 3,\n",
" 3,\n",
" 1,\n",
" 1\n",
" ],\n",
" \"torch_dtype\": \"float32\",\n",
" \"transformers_version\": \"4.17.0.dev0\",\n",
" \"use_weighted_layer_sum\": false,\n",
" \"vocab_size\": 32,\n",
" \"xvector_output_dim\": 512\n",
"}\n",
"\n",
"100%|βββββββββββββββββββββββββββββββββββββββββββββ| 1/1 [00:00<00:00, 1.03ba/s]\n",
"100%|βββββββββββββββββββββββββββββββββββββββββββββ| 1/1 [00:00<00:00, 4.09ba/s]\n",
"Didn't find file ./tokenizer_config.json. We won't load it.\n",
"Didn't find file ./added_tokens.json. We won't load it.\n",
"Didn't find file ./special_tokens_map.json. We won't load it.\n",
"Didn't find file ./tokenizer.json. We won't load it.\n",
"loading file ./vocab.json\n",
"loading file None\n",
"loading file None\n",
"loading file None\n",
"loading file None\n",
"file ./config.json not found\n",
"Adding <s> to the vocabulary\n",
"Adding </s> to the vocabulary\n",
"Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n",
"loading configuration file https://huggingface.co/hf-test/xls-r-dummy/resolve/main/config.json from cache at /workspace/.cache/huggingface/transformers/8157526a5096028eb61c63d228d882e5437edef5cb8b1a033ae35bf6249d1568.80b921aeb31bf1fa045a15aafa0e6f7e2ac68d338c1d83a3c76c99e260b22a62\n",
"Model config Wav2Vec2Config {\n",
" \"_name_or_path\": \"hf-test/xls-r-dummy\",\n",
" \"activation_dropout\": 0.1,\n",
" \"adapter_kernel_size\": 3,\n",
" \"adapter_stride\": 2,\n",
" \"add_adapter\": false,\n",
" \"apply_spec_augment\": true,\n",
" \"architectures\": [\n",
" \"Wav2Vec2Model\"\n",
" ],\n",
" \"attention_dropout\": 0.1,\n",
" \"bos_token_id\": 1,\n",
" \"classifier_proj_size\": 256,\n",
" \"codevector_dim\": 256,\n",
" \"contrastive_logits_temperature\": 0.1,\n",
" \"conv_bias\": false,\n",
" \"conv_dim\": [\n",
" 32,\n",
" 32,\n",
" 32\n",
" ],\n",
" \"conv_kernel\": [\n",
" 8,\n",
" 8,\n",
" 8\n",
" ],\n",
" \"conv_stride\": [\n",
" 4,\n",
" 4,\n",
" 4\n",
" ],\n",
" \"ctc_loss_reduction\": \"sum\",\n",
" \"ctc_zero_infinity\": false,\n",
" \"diversity_loss_weight\": 0.1,\n",
" \"do_stable_layer_norm\": true,\n",
" \"eos_token_id\": 2,\n",
" \"feat_extract_activation\": \"gelu\",\n",
" \"feat_extract_dropout\": 0.0,\n",
" \"feat_extract_norm\": \"layer\",\n",
" \"feat_proj_dropout\": 0.1,\n",
" \"feat_quantizer_dropout\": 0.0,\n",
" \"final_dropout\": 0.1,\n",
" \"gradient_checkpointing\": false,\n",
" \"hidden_act\": \"gelu\",\n",
" \"hidden_dropout\": 0.1,\n",
" \"hidden_dropout_prob\": 0.1,\n",
" \"hidden_size\": 16,\n",
" \"initializer_range\": 0.02,\n",
" \"intermediate_size\": 20,\n",
" \"layer_norm_eps\": 1e-05,\n",
" \"layerdrop\": 0.1,\n",
" \"mask_feature_length\": 10,\n",
" \"mask_feature_min_masks\": 0,\n",
" \"mask_feature_prob\": 0.0,\n",
" \"mask_time_length\": 10,\n",
" \"mask_time_min_masks\": 2,\n",
" \"mask_time_prob\": 0.05,\n",
" \"model_type\": \"wav2vec2\",\n",
" \"num_adapter_layers\": 3,\n",
" \"num_attention_heads\": 2,\n",
" \"num_codevector_groups\": 2,\n",
" \"num_codevectors_per_group\": 320,\n",
" \"num_conv_pos_embedding_groups\": 2,\n",
" \"num_conv_pos_embeddings\": 16,\n",
" \"num_feat_extract_layers\": 3,\n",
" \"num_hidden_layers\": 4,\n",
" \"num_negatives\": 10,\n",
" \"output_hidden_size\": 16,\n",
" \"pad_token_id\": 0,\n",
" \"proj_codevector_dim\": 256,\n",
" \"tdnn_dilation\": [\n",
" 1,\n",
" 2,\n",
" 3,\n",
" 1,\n",
" 1\n",
" ],\n",
" \"tdnn_dim\": [\n",
" 512,\n",
" 512,\n",
" 512,\n",
" 512,\n",
" 1500\n",
" ],\n",
" \"tdnn_kernel\": [\n",
" 5,\n",
" 3,\n",
" 3,\n",
" 1,\n",
" 1\n",
" ],\n",
" \"torch_dtype\": \"float32\",\n",
" \"transformers_version\": \"4.17.0.dev0\",\n",
" \"use_weighted_layer_sum\": false,\n",
" \"vocab_size\": 32,\n",
" \"xvector_output_dim\": 512\n",
"}\n",
"\n",
"loading feature extractor configuration file https://huggingface.co/hf-test/xls-r-dummy/resolve/main/preprocessor_config.json from cache at /workspace/.cache/huggingface/transformers/0ba9471c5a13055b5740bbac451b95c783dcaead5aacc5d0175959022489c3aa.bd1cf6fc7017d09efe9b164cbc7b32f9bbc3b3bcc243032c6f8e87573bde4292\n",
"Feature extractor Wav2Vec2FeatureExtractor {\n",
" \"do_normalize\": true,\n",
" \"feature_extractor_type\": \"Wav2Vec2FeatureExtractor\",\n",
" \"feature_size\": 1,\n",
" \"padding_side\": \"right\",\n",
" \"padding_value\": 0.0,\n",
" \"return_attention_mask\": false,\n",
" \"sampling_rate\": 16000\n",
"}\n",
"\n",
"loading weights file https://huggingface.co/hf-test/xls-r-dummy/resolve/main/pytorch_model.bin from cache at /workspace/.cache/huggingface/transformers/d374ffdefd19b7dca1d007484e8a16189d261a626cc06a3481bb034d23fe194a.4dc5ab5d8c52b8612a63c422a98f6d3de7e0bbf1469c52e89e028b4ec90e4b43\n",
"All model checkpoint weights were used when initializing Wav2Vec2ForCTC.\n",
"\n",
"Some weights of Wav2Vec2ForCTC were not initialized from the model checkpoint at hf-test/xls-r-dummy and are newly initialized: ['lm_head.bias', 'lm_head.weight']\n",
"You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n",
"preprocess datasets: 30002ex [03:40, 136.35ex/s]\n",
"preprocess datasets: 9184ex [01:06, 137.56ex/s]\n",
"100%|ββββββββββββββββββββββββββββββββββββββββββ| 31/31 [00:00<00:00, 809.78ba/s]\n",
"100%|ββββββββββββββββββββββββββββββββββββββββββ| 10/10 [00:00<00:00, 874.45ba/s]\n",
"Configuration saved in ./preprocessor_config.json\n",
"tokenizer config file saved in ./tokenizer_config.json\n",
"Special tokens file saved in ./special_tokens_map.json\n",
"added tokens file saved in ./added_tokens.json\n",
"Configuration saved in ./config.json\n",
"loading feature extractor configuration file ./preprocessor_config.json\n",
"loading configuration file ./config.json\n",
"Model config Wav2Vec2Config {\n",
" \"_name_or_path\": \"./\",\n",
" \"activation_dropout\": 0.0,\n",
" \"adapter_kernel_size\": 3,\n",
" \"adapter_stride\": 2,\n",
" \"add_adapter\": false,\n",
" \"apply_spec_augment\": true,\n",
" \"architectures\": [\n",
" \"Wav2Vec2Model\"\n",
" ],\n",
" \"attention_dropout\": 0.0,\n",
" \"bos_token_id\": 1,\n",
" \"classifier_proj_size\": 256,\n",
" \"codevector_dim\": 256,\n",
" \"contrastive_logits_temperature\": 0.1,\n",
" \"conv_bias\": false,\n",
" \"conv_dim\": [\n",
" 32,\n",
" 32,\n",
" 32\n",
" ],\n",
" \"conv_kernel\": [\n",
" 8,\n",
" 8,\n",
" 8\n",
" ],\n",
" \"conv_stride\": [\n",
" 4,\n",
" 4,\n",
" 4\n",
" ],\n",
" \"ctc_loss_reduction\": \"mean\",\n",
" \"ctc_zero_infinity\": false,\n",
" \"diversity_loss_weight\": 0.1,\n",
" \"do_stable_layer_norm\": true,\n",
" \"eos_token_id\": 2,\n",
" \"feat_extract_activation\": \"gelu\",\n",
" \"feat_extract_dropout\": 0.0,\n",
" \"feat_extract_norm\": \"layer\",\n",
" \"feat_proj_dropout\": 0.0,\n",
" \"feat_quantizer_dropout\": 0.0,\n",
" \"final_dropout\": 0.0,\n",
" \"hidden_act\": \"gelu\",\n",
" \"hidden_dropout\": 0.0,\n",
" \"hidden_dropout_prob\": 0.1,\n",
" \"hidden_size\": 16,\n",
" \"initializer_range\": 0.02,\n",
" \"intermediate_size\": 20,\n",
" \"layer_norm_eps\": 1e-05,\n",
" \"layerdrop\": 0.0,\n",
" \"mask_feature_length\": 10,\n",
" \"mask_feature_min_masks\": 0,\n",
" \"mask_feature_prob\": 0.0,\n",
" \"mask_time_length\": 10,\n",
" \"mask_time_min_masks\": 2,\n",
" \"mask_time_prob\": 0.05,\n",
" \"model_type\": \"wav2vec2\",\n",
" \"num_adapter_layers\": 3,\n",
" \"num_attention_heads\": 2,\n",
" \"num_codevector_groups\": 2,\n",
" \"num_codevectors_per_group\": 320,\n",
" \"num_conv_pos_embedding_groups\": 2,\n",
" \"num_conv_pos_embeddings\": 16,\n",
" \"num_feat_extract_layers\": 3,\n",
" \"num_hidden_layers\": 4,\n",
" \"num_negatives\": 10,\n",
" \"output_hidden_size\": 16,\n",
" \"pad_token_id\": 51,\n",
" \"proj_codevector_dim\": 256,\n",
" \"tdnn_dilation\": [\n",
" 1,\n",
" 2,\n",
" 3,\n",
" 1,\n",
" 1\n",
" ],\n",
" \"tdnn_dim\": [\n",
" 512,\n",
" 512,\n",
" 512,\n",
" 512,\n",
" 1500\n",
" ],\n",
" \"tdnn_kernel\": [\n",
" 5,\n",
" 3,\n",
" 3,\n",
" 1,\n",
" 1\n",
" ],\n",
" \"torch_dtype\": \"float32\",\n",
" \"transformers_version\": \"4.17.0.dev0\",\n",
" \"use_weighted_layer_sum\": false,\n",
" \"vocab_size\": 54,\n",
" \"xvector_output_dim\": 512\n",
"}\n",
"\n",
"loading feature extractor configuration file ./preprocessor_config.json\n",
"Feature extractor Wav2Vec2FeatureExtractor {\n",
" \"do_normalize\": true,\n",
" \"feature_extractor_type\": \"Wav2Vec2FeatureExtractor\",\n",
" \"feature_size\": 1,\n",
" \"padding_side\": \"right\",\n",
" \"padding_value\": 0.0,\n",
" \"return_attention_mask\": false,\n",
" \"sampling_rate\": 16000\n",
"}\n",
"\n",
"Didn't find file ./tokenizer.json. We won't load it.\n",
"loading file ./vocab.json\n",
"loading file ./tokenizer_config.json\n",
"loading file ./added_tokens.json\n",
"loading file ./special_tokens_map.json\n",
"loading file None\n",
"Adding <s> to the vocabulary\n",
"Adding </s> to the vocabulary\n",
"/workspace/xls-r-ab-test/./ is already a clone of https://huggingface.co/masapasa/xls-r-ab-test. Make sure you pull the latest changes with `repo.git_pull()`.\n",
"01/31/2022 17:18:19 - WARNING - huggingface_hub.repository - /workspace/xls-r-ab-test/./ is already a clone of https://huggingface.co/masapasa/xls-r-ab-test. Make sure you pull the latest changes with `repo.git_pull()`.\n",
"max_steps is given, it will override any value given in num_train_epochs\n",
"Using amp half precision backend\n",
"The following columns in the training set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.\n",
"/opt/conda/lib/python3.8/site-packages/transformers/optimization.py:306: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use thePyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning\n",
" warnings.warn(\n",
"***** Running training *****\n",
" Num examples = 30002\n",
" Num Epochs = 1\n",
" Instantaneous batch size per device = 2\n",
" Total train batch size (w. parallel, distributed & accumulation) = 2\n",
" Gradient Accumulation steps = 1\n",
" Total optimization steps = 10\n",
" 50%|ββββββββββββββββββββββ | 5/10 [00:00<00:00, 10.35it/s]Saving model checkpoint to ./checkpoint-5\n",
"Configuration saved in ./checkpoint-5/config.json\n",
"Model weights saved in ./checkpoint-5/pytorch_model.bin\n",
"Configuration saved in ./checkpoint-5/preprocessor_config.json\n",
"Configuration saved in ./preprocessor_config.json\n",
" 90%|ββββββββββββββββββββββββββββββββββββββββ | 9/10 [00:03<00:00, 2.20it/s]Saving model checkpoint to ./checkpoint-10\n",
"Configuration saved in ./checkpoint-10/config.json\n",
"Model weights saved in ./checkpoint-10/pytorch_model.bin\n",
"Configuration saved in ./checkpoint-10/preprocessor_config.json\n",
"Deleting older checkpoint [checkpoint-5] due to args.save_total_limit\n",
"\n",
"\n",
"Training completed. Do not forget to share your model on huggingface.co/models =)\n",
"\n",
"\n",
"{'train_runtime': 3.7102, 'train_samples_per_second': 5.391, 'train_steps_per_second': 2.695, 'train_loss': 67.9575927734375, 'epoch': 0.0}\n",
"100%|βββββββββββββββββββββββββββββββββββββββββββ| 10/10 [00:03<00:00, 2.70it/s]\n",
"Saving model checkpoint to ./\n",
"Configuration saved in ./config.json\n",
"Model weights saved in ./pytorch_model.bin\n",
"Configuration saved in ./preprocessor_config.json\n",
"Saving model checkpoint to ./\n",
"Configuration saved in ./config.json\n",
"Model weights saved in ./pytorch_model.bin\n",
"Configuration saved in ./preprocessor_config.json\n",
"Several commits (2) will be pushed upstream.\n",
"01/31/2022 17:18:26 - WARNING - huggingface_hub.repository - Several commits (2) will be pushed upstream.\n",
"The progress bars may be unreliable.\n",
"01/31/2022 17:18:26 - WARNING - huggingface_hub.repository - The progress bars may be unreliable.\n",
"Everything up-to-date\n",
"\n",
"01/31/2022 17:18:27 - WARNING - huggingface_hub.repository - Everything up-to-date\n",
"\n",
"Dropping the following result as it does not have all the necessary fields:\n",
"{'dataset': {'name': 'common_voice', 'type': 'common_voice', 'args': 'ab'}}\n",
"To https://huggingface.co/masapasa/xls-r-ab-test\n",
" b50c32e..4e53539 main -> main\n",
"\n",
"01/31/2022 17:18:33 - WARNING - huggingface_hub.repository - To https://huggingface.co/masapasa/xls-r-ab-test\n",
" b50c32e..4e53539 main -> main\n",
"\n",
"***** train metrics *****\n",
" epoch = 0.0\n",
" train_loss = 67.9576\n",
" train_runtime = 0:00:03.71\n",
" train_samples = 30002\n",
" train_samples_per_second = 5.391\n",
" train_steps_per_second = 2.695\n",
"01/31/2022 17:18:36 - INFO - __main__ - *** Evaluate ***\n",
"The following columns in the evaluation set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.\n",
"***** Running Evaluation *****\n",
" Num examples = 9184\n",
" Batch size = 8\n",
" 68%|βββββββββββββββββββββββββββ | 777/1148 [02:07<01:06, 5.55it/s]"
]
}
],
"source": [
"!python run_speech_recognition_ctc.py \\\n",
"\t--dataset_name=\"mozilla-foundation/common_voice_8_0\" \\\n",
"\t--model_name_or_path=\"hf-test/xls-r-dummy\" \\\n",
"\t--dataset_config_name=\"ab\" \\\n",
"\t--output_dir=\"./\" \\\n",
"\t--overwrite_output_dir \\\n",
"\t--max_steps=\"10\" \\\n",
"\t--per_device_train_batch_size=\"2\" \\\n",
"\t--learning_rate=\"3e-4\" \\\n",
"\t--save_total_limit=\"1\" \\\n",
"\t--evaluation_strategy=\"steps\" \\\n",
"\t--text_column_name=\"sentence\" \\\n",
"\t--length_column_name=\"input_length\" \\\n",
"\t--save_steps=\"5\" \\\n",
"\t--layerdrop=\"0.0\" \\\n",
"\t--freeze_feature_encoder \\\n",
"\t--gradient_checkpointing \\\n",
"\t--fp16 \\\n",
"\t--group_by_length \\\n",
"\t--push_to_hub \\\n",
"\t--use_auth_token \\\n",
"\t--do_train --do_eva"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"authorship_tag": "ABX9TyM3OaMlm9YQtKpl28c8gBBd",
"include_colab_link": true,
"name": "DebugOVHTransformers.ipynb",
"provenance": []
},
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.8"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
|