Training in progress, step 500

config.json

@@ -0,0 +1,118 @@
+{
+  "_name_or_path": "facebook/wav2vec2-base",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 100000000000000,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffef46ba0d91b26720ade5a0764b8eb00dd4cd8b026b05ad7fdf73b5bba92b4e
+size 377611120

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

runs/May24_20-24-49_890e8b3ca76b/events.out.tfevents.1716582397.890e8b3ca76b.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ac75e4115e01a183622b5727806489948ea4e87bf47a2c8f2b5e1a6c5093191
+size 6307

runs/May24_20-31-07_890e8b3ca76b/events.out.tfevents.1716582710.890e8b3ca76b.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60e1e37f65bdcdc419a35133bd27dc8b7b05882f02164c87954e2907a0730392
+size 6307

runs/May24_20-34-06_890e8b3ca76b/events.out.tfevents.1716582886.890e8b3ca76b.34.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ad92b4a9897c1c7d2d22b7271691629c322b0f513667db5be7bde20694cc1ac
+size 6307

runs/May24_20-40-48_890e8b3ca76b/events.out.tfevents.1716583290.890e8b3ca76b.34.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6420e7a899ff2207f5231157234ae31754f5ffed0d5dbd936bd905f10d3b0e25
+size 6307

runs/May24_20-42-26_890e8b3ca76b/events.out.tfevents.1716583387.890e8b3ca76b.34.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e83eaf9821d5367c3e81a47f83ef3e3da22c3eb4e21e6a5edaa39136b4cd55fb
+size 6307

runs/May24_20-48-13_890e8b3ca76b/events.out.tfevents.1716583720.890e8b3ca76b.34.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5809329e6401c44df0ad3d49be3fd6b3e399b208768feecbf1e0e9f85d6c2341
+size 19288

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:141b8c574fad469c69f1096f214b83f7c7364266f51555c4dd421e97e70dca21
+size 4920

vocab.json

@@ -0,0 +1 @@
+{"\uc644": 0, "\uc800": 1, "\ub797": 2, "\ucabd": 3, "\uc5c7": 4, "\ubbf8": 5, "\uc7a0": 6, "\ub17c": 7, "\uac9f": 8, "\ucef7": 9, "\uba4b": 10, "\ub611": 11, "\ub534": 12, "\ube60": 13, "\ub189": 14, "\uc090": 15, "\ub36e": 16, "\uafb9": 17, "\ub370": 18, "\ud138": 19, "\uaf3c": 20, "\ub5a0": 21, "\uce61": 22, "\ud480": 23, "\uc70c": 24, "\uac74": 25, "\uc2f6": 26, "\uad75": 27, "\ubb54": 28, "\ud604": 29, "\uc798": 30, "\ube68": 31, "\uae4d": 32, "\uac70": 33, "\ub139": 34, "\ub108": 35, "\ub128": 36, "\ucd0c": 37, "\ub9ce": 38, "\ub518": 39, "\ucda9": 40, "\uc794": 41, "\ub9db": 42, "\uba69": 43, "\ub538": 44, "\uc811": 45, "\ub9c8": 46, "\ud55c": 47, "\uc90d": 48, "\ub1a7": 49, "\ubab0": 50, "\uc601": 51, "\uc5f0": 52, "\ub2f9": 53, "\ub123": 54, "\uc12c": 55, "\uc27d": 56, "\ud615": 57, "\ub04c": 58, "\ucc38": 59, "\ud31c": 60, "\ucd95": 61, "\uc500": 62, "\uc694": 63, "\uadc0": 64, "\ucce5": 65, "\ud504": 66, "\uc5d4": 67, "\uacac": 68, "\uc80a": 69, "\uc78e": 70, "\ud0c1": 71, "\ub2ee": 72, "\ucf54": 73, "\uc5d0": 74, "\uca6c": 75, "\uae08": 76, "\uc5c8": 77, "\ub77d": 78, "\ud6fc": 79, "\ucc44": 80, "\ub798": 81, "\ub4f1": 82, "\uac16": 83, "\ubc84": 84, "\ub728": 85, "\ubd09": 86, "\uafb8": 87, "\ubd14": 88, "\uac90": 89, "\ud5e8": 90, "\uba64": 91, "\uacc4": 92, "\uc4f8": 93, "\uae40": 94, "\uadfc": 95, "\ubcbd": 96, "\ub9bd": 97, "\uc608": 98, "\ub978": 99, "\ub0ad": 100, "\ucc98": 101, "\uc369": 102, "\uc820": 103, "\uba4d": 104, "\uc82f": 105, "\ub461": 106, "\ud2c0": 107, "\ucbe4": 108, "\ubbfc": 109, "\ubc00": 110, "\uc92d": 111, "\uc058": 112, "\uc0c9": 113, "\uac1d": 114, "\uba3c": 115, "\ub0d0": 116, "\ub499": 117, "\uac10": 118, "\ud1a0": 119, "\uaf48": 120, "\uaca1": 121, "\uc9f8": 122, "\uace4": 123, "\ub298": 124, "\ub0b8": 125, "\uac1c": 126, "\uba55": 127, "\ub460": 128, "\uad7d": 129, "\ub35c": 130, "\ub2d0": 131, "\uc464": 132, "\uc88b": 133, "\ub9dd": 134, "\ubb58": 135, "\ud63c": 136, "\ud31f": 137, "\ud5d0": 138, "\uc57d": 139, "\ud0c7": 140, "\ub625": 141, "\uce68": 142, "\ub374": 143, "\uc368": 144, "\ud070": 145, "\ubc29": 146, "\ubc1f": 147, "\uacaa": 148, "\ud310": 149, "\uc78a": 150, "\ub07c": 151, "\uce59": 152, "\ub8e9": 153, "\ud45c": 154, "\ud15d": 155, "\ub0c9": 156, "\uc904": 157, "\uadf8": 158, "\uad70": 159, "\ud5f4": 160, "\uc2eb": 161, "\uc2ac": 162, "\uac13": 163, "\uc8fd": 164, "\uad6c": 165, "\uc815": 166, "\uace1": 167, "\ub364": 168, "\uae68": 169, "\ub8fd": 170, "\uae50": 171, "\ub9b0": 172, "\ubb63": 173, "\ud0c4": 174, "\ub0a0": 175, "\uc5c5": 176, "\ub118": 177, "\uce60": 178, "\uc6b8": 179, "\ub791": 180, "\ubc8b": 181, "\ubcbc": 182, "\ub3cc": 183, "\uac8c": 184, "\uc5d8": 185, "\uacf0": 186, "\ub141": 187, "\ud758": 188, "\ube44": 189, "\ubb38": 190, "\ubcc4": 191, "\uafe9": 192, "\uae5c": 193, "\uad00": 194, "\ud3b8": 195, "\ub0ab": 196, "\ud3c9": 197, "\uce69": 198, "\uc797": 199, "\ud1b5": 200, "\ub290": 201, "\ubb18": 202, "\ud751": 203, "\uad7c": 204, "\ud074": 205, "\uc557": 206, "\uc190": 207, "\uc84b": 208, "\uaf2d": 209, ",": 210, "\uc911": 211, "\ubcfc": 212, "\uccd0": 213, "\uaddc": 214, "\ud314": 215, "\uc0c1": 216, "\uc2ed": 217, "\uc13c": 218, "\uc5bc": 219, "\ubb3b": 220, "\uc2b7": 221, "\uba65": 222, "\uc370": 223, "\ub51c": 224, "\uac78": 225, "\ub8cc": 226, "\ub2f5": 227, "\ub837": 228, "\uc790": 229, "\ub4f8": 230, "\ud321": 231, "\ubc8c": 232, "\uacf5": 233, "\ud0dc": 234, "\uba40": 235, "\ubd10": 236, "\uba38": 237, "\ubcf5": 238, "\ub7ff": 239, "\ub985": 240, "\ubeff": 241, "\ubc18": 242, "\uce78": 243, "\uc2ec": 244, "\ud48d": 245, "\uc18c": 246, "\ub2ff": 247, "\ucfe0": 248, "\uba39": 249, "\ub9b4": 250, "\uc77c": 251, "\ub808": 252, "\ub9bc": 253, "\ucc28": 254, "\ud154": 255, "\ub531": 256, "\uc384": 257, "\ub801": 258, "\ub418": 259, "\uad6d": 260, "\ub5b5": 261, "\ud130": 262, "\ud6a8": 263, "\uae38": 264, "\uc591": 265, "\uc218": 266, "\uc554": 267, "\uc124": 268, "\uc2f8": 269, "\ub7ec": 270, "\ub458": 271, "\ubc88": 272, "\uad74": 273, "\ub110": 274, "\ucd94": 275, "\ubabb": 276, "\uc0bc": 277, "\ub828": 278, "\ub46c": 279, "\ud37c": 280, "\uae5f": 281, "\uc9d1": 282, "\uc0cc": 283, "\uc606": 284, "\ud788": 285, "\uaca0": 286, "\uadf9": 287, "\ub97c": 288, "\uc704": 289, "\uacfc": 290, "\uc6b4": 291, "\ubcc0": 292, "\ube48": 293, "\uce74": 294, "\uc2dc": 295, "\uac00": 296, "\uc584": 297, "\ub550": 298, "\ub4ec": 299, "\ud5d8": 300, "\ub488": 301, "\uaf2c": 302, "\uc788": 303, "\ubaa8": 304, "\ud638": 305, "\uc2f1": 306, "\ub7c9": 307, "\uba67": 308, "\uaed1": 309, "\ub148": 310, "\uc14b": 311, "\ucf00": 312, "\uaf34": 313, "\ud280": 314, "\uc624": 315, "\ube57": 316, "\ud478": 317, "\ubb47": 318, "\uc2f9": 319, "\ubc25": 320, "\uc2a8": 321, "\uba70": 322, "\uc90f": 323, "\uada4": 324, "\uac11": 325, "\ud6cd": 326, "\ub179": 327, "\uc0b4": 328, "\ub4e4": 329, "\uc831": 330, "\ud559": 331, "\ud230": 332, "\uc52c": 333, "\uc838": 334, "\uc796": 335, "\ub150": 336, "\uc2a4": 337, "\ub048": 338, "\uc824": 339, "\ud5f7": 340, "\ucee4": 341, "\ub974": 342, "\ucc45": 343, "\ub151": 344, "\uc4f0": 345, "\ub2cc": 346, "\uc73c": 347, "\uc37b": 348, "\uaef4": 349, "\uce5c": 350, "\ubf51": 351, "\uc131": 352, "\ub0e5": 353, "\ub214": 354, "\uc5b5": 355, "\uc22b": 356, "\uacbd": 357, "\ub4a4": 358, "\ucf20": 359, "\ubabd": 360, "\uad58": 361, "\ub2f4": 362, "\uc881": 363, "\uc81c": 364, "\uae14": 365, "\uc548": 366, "\uc880": 367, "\uc740": 368, "\uccd4": 369, "\ub2ec": 370, "\uc0db": 371, "\ub530": 372, "\uc1a1": 373, "\ub840": 374, "?": 375, "\ub780": 376, "\ub9e4": 377, "\ucd5c": 378, "\uc83c": 379, "\ub807": 380, "\ub465": 381, "\uc538": 382, "\ub3c4": 383, "\uae30": 384, "\uc220": 385, "\ub8e8": 386, "\ub860": 387, "\uccad": 388, "\uc9c0": 389, "\ub0b3": 390, "\ud574": 391, "\uc545": 392, "\uace8": 393, "\ub824": 394, "\ud569": 395, "\uc14d": 396, "\ubfdc": 397, "\ubcd1": 398, "\ub481": 399, "\uc2c0": 400, "\ubb50": 401, "\ub4fc": 402, "\ud30c": 403, "\ub198": 404, "\ub355": 405, "\ub057": 406, "\uc6a9": 407, "\ub354": 408, "\ub178": 409, "\uae34": 410, "\ub5a8": 411, "\ubca1": 412, "\uad7f": 413, "\uc530": 414, "\uc54a": 415, "\ubcb5": 416, "\uc6c3": 417, "\uc870": 418, "\ud22c": 419, "\uba87": 420, "\uad50": 421, "\ud2b8": 422, "\ub871": 423, "\ubd84": 424, "\ub144": 425, "\ub420": 426, "\ub834": 427, "\uba74": 428, "\uc49c": 429, "\ud5f9": 430, "\uaecf": 431, "\ubc97": 432, "\ud68c": 433, "\ub2e8": 434, "\uc758": 435, "\uac19": 436, "\ubfcc": 437, "\uc6d0": 438, "\ucf69": 439, "\ub825": 440, "\ucc29": 441, "\uc9c8": 442, "\uc2e4": 443, "\ub294": 444, "\uc998": 445, "\uc778": 446, "\uacb8": 447, "\uaf07": 448, "\uc934": 449, "\ud2bf": 450, "\ud734": 451, "\uacb0": 452, "\ub839": 453, "\uacbb": 454, "\uccb4": 455, "\ub958": 456, "\ub7b5": 457, "\ubb34": 458, "\ud06c": 459, "\uc094": 460, "\ucef4": 461, "\uce6d": 462, "\uc9e4": 463, "\ub7f0": 464, "\ud544": 465, "\ubaa9": 466, "\ub9c9": 467, "\ub2a0": 468, "\ub9bf": 469, "\ub85d": 470, "\ub358": 471, "\uc544": 472, "\uaca9": 473, "\uc5f4": 474, "\ud655": 475, "\ub2e4": 476, "\ubc15": 477, "\uc9c1": 478, "\uaf3d": 479, "\uc313": 480, "\ub044": 481, "\ud5d9": 482, "\ucb64": 483, "\ub77c": 484, "\ub9cc": 485, "\ub274": 486, "\uc8fc": 487, "\ucc9c": 488, "\uc120": 489, "\ubc16": 490, "\uc5fc": 491, "\uc2b9": 492, "\ud5e4": 493, "\ub098": 494, "\ucc2e": 495, "\ubd05": 496, "\uc0dd": 497, "\ud640": 498, "\ub4b7": 499, "\ucabc": 500, "\uac83": 501, "\ud1f4": 502, "\uccb8": 503, "\ub299": 504, "\uacf1": 505, "\uc37d": 506, "\ub300": 507, "\ubc11": 508, "\ud6c4": 509, "\uba58": 510, "\uaff0": 511, "\ud5c8": 512, "\uacf3": 513, "\uc653": 514, "\uc751": 515, "\uc5e3": 516, "\uc784": 517, "\uca99": 518, "\uc7a5": 519, "\uc871": 520, "\ub194": 521, "\uade4": 522, "\uaed8": 523, "\ub73b": 524, "\uc158": 525, "\ub054": 526, "\ub4e0": 527, "\uc640": 528, "\ubb35": 529, "\uc57c": 530, "\ubc14": 531, "\ubcf4": 532, "\uc11d": 533, "\uac77": 534, "\uc5c6": 535, "\ucc1d": 536, "\ucd10": 537, "\ub81b": 538, "\ud65c": 539, "\ud0a4": 540, "\ub878": 541, "\ub4dc": 542, "\ub2b4": 543, "\ub3c5": 544, "\uc90c": 545, "\ud654": 546, "\uc60c": 547, "\uc918": 548, "\ud2f0": 549, "\uc75c": 550, "\ub5a1": 551, "\uc2dd": 552, "\uc529": 553, "\ubd81": 554, "\ucd9c": 555, "\uc74d": 556, "\ud568": 557, "\ud07c": 558, "\ub9ac": 559, "\uc988": 560, "\uc5c9": 561, "\uac15": 562, "\ub78c": 563, "\ubd90": 564, "\uc628": 565, "\uc300": 566, "\uba54": 567, "\ub2a6": 568, "\ud78c": 569, "\ud56d": 570, "\ud134": 571, "\uc0ac": 572, "\ub124": 573, "\ub369": 574, "\ub193": 575, "\u1161": 576, "\uc2b5": 577, "\uc167": 578, "\ub80c": 579, "\ub1a9": 580, "\uc7ac": 581, "\ub153": 582, "\uac24": 583, "\ubcb3": 584, "\ud1a7": 585, "\ubc24": 586, "\ud6c8": 587, "\uc61b": 588, "\ubd88": 589, "\uc6b1": 590, "\uc874": 591, "\uc6d4": 592, "\ub7fc": 593, "\uc785": 594, "\uc54c": 595, "\ube4c": 596, "\ub490": 597, "\ubed0": 598, "\ucd98": 599, "\u11af": 600, "\uc720": 601, "\ub47f": 602, "\ub1a4": 603, "\uc804": 604, "\uc816": 605, "\uba85": 606, "\ud488": 607, "\ubc85": 608, "\uc11c": 609, "\ud798": 610, "\uc250": 611, "\uc9c7": 612, "\uc55a": 613, "\ud0d1": 614, "\uac85": 615, "\uc721": 616, "\ud611": 617, "\uc74c": 618, "\uc30d": 619, "\uc598": 620, "\uc744": 621, "\uc774": 622, "\ub5bb": 623, "\uc791": 624, ".": 625, "\ub220": 626, "\ubca8": 627, "\uc495": 628, "\uacc1": 629, "\ub9f7": 630, "\ud3ec": 631, "\uc55e": 632, "\uac08": 633, "\ubbff": 634, "\uc5b8": 635, "\uace0": 636, "\ub3d9": 637, "\uafc0": 638, "\ubd25": 639, "\ud2b9": 640, "\ub8d0": 641, "\ucc30": 642, "\uac2f": 643, "\ub9de": 644, "\ub3fc": 645, "\uc7c1": 646, "\ubca0": 647, "\ub09c": 648, "\uae4c": 649, "\ud639": 650, "\ubc27": 651, "\ub78f": 652, "\ubcf8": 653, "\ucb49": 654, "\uc9d3": 655, "\uad82": 656, "\uc9f1": 657, "\ubc94": 658, "\uc787": 659, "\ubc95": 660, "\ud2bc": 661, "\ub20c": 662, "\uc5ec": 663, "\uc62e": 664, "\uc5b4": 665, "\ub984": 666, "\ud53c": 667, "\uac04": 668, "\ubd99": 669, "\ud14c": 670, "\ub9d0": 671, "\ud560": 672, "\ucca0": 673, "\uc138": 674, "\uac07": 675, "\uc5bd": 676, "\u1101": 677, "\uc50c": 678, "\uc6c5": 679, "\uc18d": 680, "\uc528": 681, "\ubc30": 682, "\uc559": 683, "\uc6e8": 684, "\ub2c8": 685, "\ub155": 686, "\ub9e8": 687, "\uc6b0": 688, "\ud750": 689, "\uc560": 690, "\uc5ed": 691, "\ub140": 692, "\uae61": 693, "\uc5ff": 694, "\ub54c": 695, "\ub7fd": 696, "\uc65c": 697, "\ubc1c": 698, "\uc84d": 699, "\ub137": 700, "\uc808": 701, "\ub0a8": 702, "\uca4c": 703, "\uc9d0": 704, "\ub055": 705, "\uad11": 706, "\uc580": 707, "\uc637": 708, "\ub0ae": 709, "\uc775": 710, "\ucf1c": 711, "\uca0b": 712, "\uc5e5": 713, "\uc678": 714, "\ub2d9": 715, "\ubd80": 716, "\uc26c": 717, "\ud5cc": 718, "\ud76c": 719, "\ud0d3": 720, "\ubb3c": 721, "\ub835": 722, "\uae00": 723, "\ub10c": 724, "\ub0bc": 725, "\uac01": 726, "\uc99d": 727, "\ubfd4": 728, "\ub35f": 729, "\ubd04": 730, "\uc2e0": 731, "\uc813": 732, "\ub610": 733, "\ub85c": 734, "\ud754": 735, "\uce6b": 736, "\ud0c0": 737, "\uc12f": 738, "\uac20": 739, "\uc9dd": 740, "\uaca8": 741, "\uae54": 742, "\uc655": 743, "\ub204": 744, "\ub498": 745, "\ub545": 746, "\ubc31": 747, "\ub5a4": 748, "\ub0b4": 749, "\ub385": 750, "\uc9c4": 751, "\ub2d8": 752, "\ub188": 753, "\ub3c8": 754, "\ub48c": 755, "\ub180": 756, "\ub05d": 757, "\ucacc": 758, "\uc21c": 759, "\uc0c8": 760, "\uc6c0": 762, "\uac81": 763, "\uc989": 764, "\ub450": 765, "\ud034": 766, "\uc0b0": 767, "\ud391": 768, "\ucc3e": 769, "\ub4ef": 770, "\ub81d": 771, "\uad81": 772, "\ub72c": 773, "\ucc0d": 774, "\ucc2c": 775, "\ubfd0": 776, "\ub2e5": 777, "\uc900": 778, "\uc885": 779, "\ubbc4": 780, "\uc6c1": 781, "\uac80": 782, "\ubc1b": 783, "\ud150": 784, "\ub18d": 785, "\ud2c8": 786, "\uc5bb": 787, "\uaebc": 788, "\ud558": 789, "\uce58": 790, "\ub514": 791, "\uc62c": 792, "\ucd08": 793, "\ubd23": 794, "\uc801": 795, "\uba83": 796, "\ub7ed": 797, "|": 761, "[UNK]": 798, "[PAD]": 799}

wandb/debug.log

@@ -0,0 +1,217 @@
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_setup.py:_flush():76] Current SDK version is 0.16.6
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_setup.py:_flush():76] Configure stats pid to 34
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_setup.py:_flush():76] Loading settings from /root/.config/wandb/settings
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_setup.py:_flush():76] Loading settings from /kaggle/working/wandb/settings
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program': '<python with no main file>'}
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_setup.py:_flush():76] Applying login settings: {}
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_setup.py:_flush():76] Applying login settings: {'api_key': '***REDACTED***'}
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_init.py:_log_setup():521] Logging user logs to /kaggle/working/wandb/run-20240524_202737-n1w0kmmv/logs/debug.log
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_init.py:_log_setup():522] Logging internal logs to /kaggle/working/wandb/run-20240524_202737-n1w0kmmv/logs/debug-internal.log
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_init.py:_jupyter_setup():467] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x785a802b9120>
+2024-05-24 20:27:37,418 INFO    MainThread:34 [wandb_init.py:init():561] calling init triggers
+2024-05-24 20:27:37,418 INFO    MainThread:34 [wandb_init.py:init():568] wandb.init called with sweep_config: {}
+config: {}
+2024-05-24 20:27:37,418 INFO    MainThread:34 [wandb_init.py:init():611] starting backend
+2024-05-24 20:27:37,418 INFO    MainThread:34 [wandb_init.py:init():615] setting up manager
+2024-05-24 20:27:37,420 INFO    MainThread:34 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-05-24 20:27:37,423 INFO    MainThread:34 [wandb_init.py:init():623] backend started and connected
+2024-05-24 20:27:37,434 INFO    MainThread:34 [wandb_run.py:_label_probe_notebook():1299] probe notebook
+2024-05-24 20:27:38,191 INFO    MainThread:34 [wandb_init.py:init():715] updated telemetry
+2024-05-24 20:27:38,195 INFO    MainThread:34 [wandb_init.py:init():748] communicating run to backend with 90.0 second timeout
+2024-05-24 20:27:38,448 INFO    MainThread:34 [wandb_run.py:_on_init():2357] communicating current version
+2024-05-24 20:27:38,512 INFO    MainThread:34 [wandb_run.py:_on_init():2366] got version response upgrade_message: "wandb version 0.17.0 is available!  To upgrade, please run:\n $ pip install wandb --upgrade"
+
+2024-05-24 20:27:38,514 INFO    MainThread:34 [wandb_init.py:init():799] starting run threads in backend
+2024-05-24 20:27:54,627 INFO    MainThread:34 [wandb_run.py:_console_start():2335] atexit reg
+2024-05-24 20:27:54,628 INFO    MainThread:34 [wandb_run.py:_redirect():2190] redirect: wrap_raw
+2024-05-24 20:27:54,628 INFO    MainThread:34 [wandb_run.py:_redirect():2255] Wrapping output streams.
+2024-05-24 20:27:54,629 INFO    MainThread:34 [wandb_run.py:_redirect():2280] Redirects installed.
+2024-05-24 20:27:54,630 INFO    MainThread:34 [wandb_init.py:init():842] run started, returning control to user process
+2024-05-24 20:27:54,637 INFO    MainThread:34 [wandb_run.py:_config_callback():1347] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['Wav2Vec2ForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 0, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/wav2vec2-base', 'transformers_version': '4.39.3', 'freeze_feat_extract_train': True, 'mask_channel_length': 10, 'mask_channel_min_space': 1, 'mask_channel_other': 0.0, 'mask_channel_prob': 0.0, 'mask_channel_selection': 'static', 'mask_time_min_space': 1, 'mask_time_other': 0.0, 'mask_time_selection': 'static', 'model_type': 'wav2vec2', 'no_mask_channel_overlap': False, 'no_mask_time_overlap': False, 'num_feat_extract_layers': 7, 'hidden_size': 768, 'feat_extract_norm': 'group', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': False, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 12, 'intermediate_size': 3072, 'hidden_act': 'gelu', 'num_attention_heads': 12, 'hidden_dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'feat_proj_dropout': 0.1, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 32, 'do_stable_layer_norm': False, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.05, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 256, 'proj_codevector_dim': 256, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'sum', 'ctc_zero_infinity': False, 'add_adapter': False, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 768, 'adapter_attn_dim': None, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 32, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0001, 'weight_decay': 0.005, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 30, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/May24_20-24-49_890e8b3ca76b', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 2, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': True, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
+2024-05-24 20:28:04,489 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:28:04,489 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:28:58,368 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:28:59,625 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:28:59,625 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:29:08,949 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:29:08,951 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:29:08,951 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:29:12,141 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:29:16,856 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:29:16,857 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:29:20,764 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:29:24,478 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:29:24,478 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:29:30,221 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:30:45,072 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:30:45,072 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:30:58,707 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:30:58,709 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:30:58,710 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:31:02,188 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:31:02,613 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:31:02,613 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:31:04,725 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:31:04,727 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:31:04,727 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:31:07,065 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:31:07,298 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:31:07,298 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:31:10,187 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:31:10,193 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:31:10,193 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:31:12,404 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:31:50,143 INFO    MainThread:34 [wandb_run.py:_config_callback():1347] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['Wav2Vec2ForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 0, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/wav2vec2-base', 'transformers_version': '4.39.3', 'freeze_feat_extract_train': True, 'mask_channel_length': 10, 'mask_channel_min_space': 1, 'mask_channel_other': 0.0, 'mask_channel_prob': 0.0, 'mask_channel_selection': 'static', 'mask_time_min_space': 1, 'mask_time_other': 0.0, 'mask_time_selection': 'static', 'model_type': 'wav2vec2', 'no_mask_channel_overlap': False, 'no_mask_time_overlap': False, 'num_feat_extract_layers': 7, 'hidden_size': 768, 'feat_extract_norm': 'group', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': False, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 12, 'intermediate_size': 3072, 'hidden_act': 'gelu', 'num_attention_heads': 12, 'hidden_dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'feat_proj_dropout': 0.1, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 32, 'do_stable_layer_norm': False, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.05, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 256, 'proj_codevector_dim': 256, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'sum', 'ctc_zero_infinity': False, 'add_adapter': False, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 768, 'adapter_attn_dim': None, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 32, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0001, 'weight_decay': 0.005, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 30, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/May24_20-31-07_890e8b3ca76b', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 2, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': True, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
+2024-05-24 20:31:58,626 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:31:58,626 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:34:06,571 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:34:06,717 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:34:06,717 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:34:10,001 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:34:46,464 INFO    MainThread:34 [wandb_run.py:_config_callback():1347] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['Wav2Vec2ForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 0, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/wav2vec2-base', 'transformers_version': '4.39.3', 'freeze_feat_extract_train': True, 'mask_channel_length': 10, 'mask_channel_min_space': 1, 'mask_channel_other': 0.0, 'mask_channel_prob': 0.0, 'mask_channel_selection': 'static', 'mask_time_min_space': 1, 'mask_time_other': 0.0, 'mask_time_selection': 'static', 'model_type': 'wav2vec2', 'no_mask_channel_overlap': False, 'no_mask_time_overlap': False, 'num_feat_extract_layers': 7, 'hidden_size': 768, 'feat_extract_norm': 'group', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': False, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 12, 'intermediate_size': 3072, 'hidden_act': 'gelu', 'num_attention_heads': 12, 'hidden_dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'feat_proj_dropout': 0.1, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 32, 'do_stable_layer_norm': False, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.05, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 256, 'proj_codevector_dim': 256, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'sum', 'ctc_zero_infinity': False, 'add_adapter': False, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 768, 'adapter_attn_dim': None, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 64, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0001, 'weight_decay': 0.005, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 30, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/May24_20-34-06_890e8b3ca76b', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 2, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': True, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
+2024-05-24 20:34:55,928 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:34:55,929 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:35:26,131 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:35:26,139 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:35:26,139 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:35:32,729 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:35:32,732 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:35:32,732 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:35:34,729 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:35:34,732 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:35:34,733 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:35:47,483 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:35:47,488 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:35:47,488 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:35:56,249 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:35:56,253 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:35:56,253 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:37:20,366 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:37:20,370 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:37:20,370 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:37:28,481 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:37:28,510 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:37:28,511 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:38:00,946 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:38:00,950 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:38:00,950 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:38:04,524 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:38:04,550 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:38:04,550 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:38:12,369 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:38:12,432 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:38:12,432 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:38:16,938 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:38:16,998 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:38:16,998 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:38:21,248 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:38:21,260 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:38:21,260 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:38:22,930 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:38:22,940 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:38:22,940 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:38:37,851 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:38:55,254 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:38:55,254 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:38:58,788 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:38:58,827 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:38:58,827 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:39:00,762 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:40:16,333 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:40:16,334 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:40:21,472 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:40:22,682 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:40:22,682 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:40:28,979 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:40:33,961 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:40:33,961 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:40:36,994 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:40:36,996 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:40:36,997 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:40:42,203 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:40:42,621 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:40:42,621 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:40:44,473 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:40:44,475 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:40:44,475 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:40:48,431 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:40:48,669 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:40:48,669 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:40:50,725 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:40:50,730 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:40:50,730 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:40:52,537 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:41:30,450 INFO    MainThread:34 [wandb_run.py:_config_callback():1347] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['Wav2Vec2ForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 0, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/wav2vec2-base', 'transformers_version': '4.39.3', 'freeze_feat_extract_train': True, 'mask_channel_length': 10, 'mask_channel_min_space': 1, 'mask_channel_other': 0.0, 'mask_channel_prob': 0.0, 'mask_channel_selection': 'static', 'mask_time_min_space': 1, 'mask_time_other': 0.0, 'mask_time_selection': 'static', 'model_type': 'wav2vec2', 'no_mask_channel_overlap': False, 'no_mask_time_overlap': False, 'num_feat_extract_layers': 7, 'hidden_size': 768, 'feat_extract_norm': 'group', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': False, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 12, 'intermediate_size': 3072, 'hidden_act': 'gelu', 'num_attention_heads': 12, 'hidden_dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'feat_proj_dropout': 0.1, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 32, 'do_stable_layer_norm': False, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.05, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 256, 'proj_codevector_dim': 256, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'sum', 'ctc_zero_infinity': False, 'add_adapter': False, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 768, 'adapter_attn_dim': None, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 64, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0001, 'weight_decay': 0.005, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 30, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/May24_20-40-48_890e8b3ca76b', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 2, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': True, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
+2024-05-24 20:41:39,043 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:41:39,044 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:42:26,950 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:42:27,128 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:42:27,128 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:42:29,871 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:43:07,276 INFO    MainThread:34 [wandb_run.py:_config_callback():1347] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['Wav2Vec2ForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 0, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/wav2vec2-base', 'transformers_version': '4.39.3', 'freeze_feat_extract_train': True, 'mask_channel_length': 10, 'mask_channel_min_space': 1, 'mask_channel_other': 0.0, 'mask_channel_prob': 0.0, 'mask_channel_selection': 'static', 'mask_time_min_space': 1, 'mask_time_other': 0.0, 'mask_time_selection': 'static', 'model_type': 'wav2vec2', 'no_mask_channel_overlap': False, 'no_mask_time_overlap': False, 'num_feat_extract_layers': 7, 'hidden_size': 768, 'feat_extract_norm': 'group', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': False, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 12, 'intermediate_size': 3072, 'hidden_act': 'gelu', 'num_attention_heads': 12, 'hidden_dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'feat_proj_dropout': 0.1, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 32, 'do_stable_layer_norm': False, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.05, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 256, 'proj_codevector_dim': 256, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'sum', 'ctc_zero_infinity': False, 'add_adapter': False, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 768, 'adapter_attn_dim': None, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 16, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0001, 'weight_decay': 0.005, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 30, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/May24_20-42-26_890e8b3ca76b', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 2, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': True, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
+2024-05-24 20:43:12,247 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:43:12,247 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:44:08,643 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:44:14,294 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:44:14,295 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:44:39,719 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:44:39,770 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:44:39,770 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:44:43,543 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:46:31,143 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:46:31,143 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:46:49,361 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:46:49,391 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:46:49,391 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:46:52,169 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:46:54,391 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:46:54,391 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:46:58,317 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:46:58,322 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:46:58,322 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:47:06,482 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:47:07,830 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:47:07,830 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:47:10,833 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:47:10,835 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:47:10,839 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:47:14,002 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:48:02,460 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:48:02,460 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:48:05,731 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:48:05,733 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:48:05,734 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:48:08,287 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:48:08,714 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:48:08,714 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:48:10,290 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:48:10,293 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:48:10,294 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:48:13,841 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:48:14,091 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:48:14,092 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:48:16,125 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:48:40,373 INFO    MainThread:34 [wandb_run.py:_config_callback():1347] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['Wav2Vec2ForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 0, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/wav2vec2-base', 'transformers_version': '4.39.3', 'freeze_feat_extract_train': True, 'mask_channel_length': 10, 'mask_channel_min_space': 1, 'mask_channel_other': 0.0, 'mask_channel_prob': 0.0, 'mask_channel_selection': 'static', 'mask_time_min_space': 1, 'mask_time_other': 0.0, 'mask_time_selection': 'static', 'model_type': 'wav2vec2', 'no_mask_channel_overlap': False, 'no_mask_time_overlap': False, 'num_feat_extract_layers': 7, 'hidden_size': 768, 'feat_extract_norm': 'group', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': False, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 12, 'intermediate_size': 3072, 'hidden_act': 'gelu', 'num_attention_heads': 12, 'hidden_dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'feat_proj_dropout': 0.1, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 32, 'do_stable_layer_norm': False, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.05, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 256, 'proj_codevector_dim': 256, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'sum', 'ctc_zero_infinity': False, 'add_adapter': False, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 768, 'adapter_attn_dim': None, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 16, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0001, 'weight_decay': 0.005, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 30, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/May24_20-48-13_890e8b3ca76b', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 2, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': True, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
+2024-05-24 20:48:42,631 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:48:42,632 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:49:00,381 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:49:00,425 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:49:00,425 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:49:03,721 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:49:03,725 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:49:03,726 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:49:08,089 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:49:08,455 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:49:08,456 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:51:52,779 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:51:52,781 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:51:52,781 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:51:56,593 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:52:22,759 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:52:22,759 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:52:49,570 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:52:49,572 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:52:49,572 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:52:52,107 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend

wandb/run-20240524_202737-n1w0kmmv/files/config.yaml

@@ -0,0 +1,866 @@
+wandb_version: 1
+
+_wandb:
+  desc: null
+  value:
+    python_version: 3.10.13
+    cli_version: 0.16.6
+    framework: huggingface
+    huggingface_version: 4.39.3
+    is_jupyter_run: true
+    is_kaggle_kernel: true
+    start_time: 1716582457.0
+    t:
+      1:
+      - 1
+      - 2
+      - 3
+      - 5
+      - 11
+      - 12
+      - 49
+      - 51
+      - 53
+      - 55
+      - 71
+      - 105
+      2:
+      - 1
+      - 2
+      - 3
+      - 5
+      - 11
+      - 12
+      - 49
+      - 51
+      - 53
+      - 55
+      - 71
+      - 105
+      3:
+      - 7
+      - 23
+      4: 3.10.13
+      5: 0.16.6
+      6: 4.39.3
+      8:
+      - 1
+      - 2
+      - 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/epoch
+      5: 1
+      6:
+      - 1
+    - 1: eval/loss
+      5: 1
+      6:
+      - 1
+    - 1: eval/wer
+      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
+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: true
+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: 20
+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:
+  - Wav2Vec2ForPreTraining
+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: 0
+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: facebook/wav2vec2-base
+transformers_version:
+  desc: null
+  value: 4.39.3
+freeze_feat_extract_train:
+  desc: null
+  value: true
+mask_channel_length:
+  desc: null
+  value: 10
+mask_channel_min_space:
+  desc: null
+  value: 1
+mask_channel_other:
+  desc: null
+  value: 0.0
+mask_channel_prob:
+  desc: null
+  value: 0.0
+mask_channel_selection:
+  desc: null
+  value: static
+mask_time_min_space:
+  desc: null
+  value: 1
+mask_time_other:
+  desc: null
+  value: 0.0
+mask_time_selection:
+  desc: null
+  value: static
+model_type:
+  desc: null
+  value: wav2vec2
+no_mask_channel_overlap:
+  desc: null
+  value: false
+no_mask_time_overlap:
+  desc: null
+  value: false
+num_feat_extract_layers:
+  desc: null
+  value: 7
+hidden_size:
+  desc: null
+  value: 768
+feat_extract_norm:
+  desc: null
+  value: group
+feat_extract_activation:
+  desc: null
+  value: gelu
+conv_dim:
+  desc: null
+  value:
+  - 512
+  - 512
+  - 512
+  - 512
+  - 512
+  - 512
+  - 512
+conv_stride:
+  desc: null
+  value:
+  - 5
+  - 2
+  - 2
+  - 2
+  - 2
+  - 2
+  - 2
+conv_kernel:
+  desc: null
+  value:
+  - 10
+  - 3
+  - 3
+  - 3
+  - 3
+  - 2
+  - 2
+conv_bias:
+  desc: null
+  value: false
+num_conv_pos_embeddings:
+  desc: null
+  value: 128
+num_conv_pos_embedding_groups:
+  desc: null
+  value: 16
+num_hidden_layers:
+  desc: null
+  value: 12
+intermediate_size:
+  desc: null
+  value: 3072
+hidden_act:
+  desc: null
+  value: gelu
+num_attention_heads:
+  desc: null
+  value: 12
+hidden_dropout:
+  desc: null
+  value: 0.1
+attention_dropout:
+  desc: null
+  value: 0.1
+activation_dropout:
+  desc: null
+  value: 0.0
+feat_proj_dropout:
+  desc: null
+  value: 0.1
+final_dropout:
+  desc: null
+  value: 0.0
+layerdrop:
+  desc: null
+  value: 0.0
+layer_norm_eps:
+  desc: null
+  value: 1.0e-05
+initializer_range:
+  desc: null
+  value: 0.02
+vocab_size:
+  desc: null
+  value: 32
+do_stable_layer_norm:
+  desc: null
+  value: false
+use_weighted_layer_sum:
+  desc: null
+  value: false
+apply_spec_augment:
+  desc: null
+  value: true
+mask_time_prob:
+  desc: null
+  value: 0.05
+mask_time_length:
+  desc: null
+  value: 10
+mask_time_min_masks:
+  desc: null
+  value: 2
+mask_feature_prob:
+  desc: null
+  value: 0.0
+mask_feature_length:
+  desc: null
+  value: 10
+mask_feature_min_masks:
+  desc: null
+  value: 0
+num_codevectors_per_group:
+  desc: null
+  value: 320
+num_codevector_groups:
+  desc: null
+  value: 2
+contrastive_logits_temperature:
+  desc: null
+  value: 0.1
+feat_quantizer_dropout:
+  desc: null
+  value: 0.0
+num_negatives:
+  desc: null
+  value: 100
+codevector_dim:
+  desc: null
+  value: 256
+proj_codevector_dim:
+  desc: null
+  value: 256
+diversity_loss_weight:
+  desc: null
+  value: 0.1
+ctc_loss_reduction:
+  desc: null
+  value: sum
+ctc_zero_infinity:
+  desc: null
+  value: false
+add_adapter:
+  desc: null
+  value: false
+adapter_kernel_size:
+  desc: null
+  value: 3
+adapter_stride:
+  desc: null
+  value: 2
+num_adapter_layers:
+  desc: null
+  value: 3
+output_hidden_size:
+  desc: null
+  value: 768
+adapter_attn_dim:
+  desc: null
+  value: null
+classifier_proj_size:
+  desc: null
+  value: 256
+tdnn_dim:
+  desc: null
+  value:
+  - 512
+  - 512
+  - 512
+  - 512
+  - 1500
+tdnn_kernel:
+  desc: null
+  value:
+  - 5
+  - 3
+  - 3
+  - 1
+  - 1
+tdnn_dilation:
+  desc: null
+  value:
+  - 1
+  - 2
+  - 3
+  - 1
+  - 1
+xvector_output_dim:
+  desc: null
+  value: 512
+output_dir:
+  desc: null
+  value: /kaggle/working/
+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: 16
+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: 1
+eval_accumulation_steps:
+  desc: null
+  value: null
+eval_delay:
+  desc: null
+  value: 0
+learning_rate:
+  desc: null
+  value: 0.0001
+weight_decay:
+  desc: null
+  value: 0.005
+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: 30
+max_steps:
+  desc: null
+  value: -1
+lr_scheduler_type:
+  desc: null
+  value: linear
+lr_scheduler_kwargs:
+  desc: null
+  value: {}
+warmup_ratio:
+  desc: null
+  value: 0.0
+warmup_steps:
+  desc: null
+  value: 1000
+log_level:
+  desc: null
+  value: passive
+log_level_replica:
+  desc: null
+  value: warning
+log_on_each_node:
+  desc: null
+  value: true
+logging_dir:
+  desc: null
+  value: /kaggle/working/runs/May24_20-48-13_890e8b3ca76b
+logging_strategy:
+  desc: null
+  value: steps
+logging_first_step:
+  desc: null
+  value: false
+logging_steps:
+  desc: null
+  value: 500
+logging_nan_inf_filter:
+  desc: null
+  value: true
+save_strategy:
+  desc: null
+  value: steps
+save_steps:
+  desc: null
+  value: 500
+save_total_limit:
+  desc: null
+  value: 2
+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: false
+fp16:
+  desc: null
+  value: true
+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: 500
+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: /kaggle/working/
+disable_tqdm:
+  desc: null
+  value: false
+remove_unused_columns:
+  desc: null
+  value: true
+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
+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: true
+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: null
+include_inputs_for_metrics:
+  desc: null
+  value: false
+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

wandb/run-20240524_202737-n1w0kmmv/files/output.log

@@ -0,0 +1,171 @@
+/opt/conda/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:156: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.
+  warnings.warn(
+/opt/conda/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
+  warnings.warn(
+Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+/opt/conda/lib/python3.10/site-packages/transformers/configuration_utils.py:363: UserWarning: Passing `gradient_checkpointing` to a config initialization is deprecated and will be removed in v5 Transformers. Using `model.gradient_checkpointing_enable()` instead, or if you are using the `Trainer` API, pass `gradient_checkpointing=True` in your `TrainingArguments`.
+  warnings.warn(
+Some weights of Wav2Vec2ForCTC were not initialized from the model checkpoint at facebook/wav2vec2-base and are newly initialized: ['lm_head.bias', 'lm_head.weight', 'wav2vec2.encoder.pos_conv_embed.conv.parametrizations.weight.original0', 'wav2vec2.encoder.pos_conv_embed.conv.parametrizations.weight.original1']
+You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+/opt/conda/lib/python3.10/site-packages/datasets/load.py:756: FutureWarning: The repository for wer contains custom code which must be executed to correctly load the metric. You can inspect the repository content at https://raw.githubusercontent.com/huggingface/datasets/2.18.0/metrics/wer/wer.py
+You can avoid this message in future by passing the argument `trust_remote_code=True`.
+Passing `trust_remote_code=True` will be mandatory to load this metric from the next major release of `datasets`.
+  warnings.warn(
+/opt/conda/lib/python3.10/site-packages/accelerate/accelerator.py:436: FutureWarning: Passing the following arguments to `Accelerator` is deprecated and will be removed in version 1.0 of Accelerate: dict_keys(['dispatch_batches', 'split_batches', 'even_batches', 'use_seedable_sampler']). Please pass an `accelerate.DataLoaderConfiguration` instead:
+dataloader_config = DataLoaderConfiguration(dispatch_batches=None, split_batches=False, even_batches=True, use_seedable_sampler=True)
+  warnings.warn(
+wandb: WARNING Calling wandb.login() after wandb.init() has no effect.
+/opt/conda/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:156: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.
+  warnings.warn(
+/opt/conda/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
+  warnings.warn(
+/opt/conda/lib/python3.10/site-packages/accelerate/accelerator.py:436: FutureWarning: Passing the following arguments to `Accelerator` is deprecated and will be removed in version 1.0 of Accelerate: dict_keys(['dispatch_batches', 'split_batches', 'even_batches', 'use_seedable_sampler']). Please pass an `accelerate.DataLoaderConfiguration` instead:
+dataloader_config = DataLoaderConfiguration(dispatch_batches=None, split_batches=False, even_batches=True, use_seedable_sampler=True)
+  warnings.warn(
+/opt/conda/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:156: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.
+  warnings.warn(
+/opt/conda/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
+  warnings.warn(
+0      지금부터 그러면 본격적으로 우리가 도련동�� 대해서 조사를 할 거라 예? 이 마을이 ...
+1                  예, 그건 한 칠백년 전에 이제 그 설촌이 시작이 되었다고 헙니다.
+2      예. 칠백년 전에 설촌이 뒈엇는데 이제 그루후에 이제 성씨들이 여러 성씨들이 많이 ...
+3           예. 그러면은 칠백년부터 허는데 설촌할 때 어떤 성씨들이 헷덴 말도 이신가마씨?
+4                       그 다음 양씨. 고씨. 마 대략적으로 요런 순서가 뒘서양.
+                             ...
+995    이제 뭘 부린다고 허까. 이제 사람이면 그 살짝살짝 빼여지곡 뭐허곡 헹근에 일을 아...
+996    그런 그 뭐가 잇는데. 에 짐 실런 오단에 그 구루마 찬, 참 그 마차 찬 차 그냥...
+997    것도 딴 거 보민 그 소가 그 좀 소머리도 그런 거 보민 영리허긴 영 리헌 거라. ...
+998    아무 거 그런 거 저런 거 안 보면은 묵묵히 일을 잘허는데, 그런 거 보면은 이제 ...
+999              이제 힘이 좀 약헌 사름안티 가면은 그냥 제멋대로 임잘 막 놀려먹 주.
+Name: text, Length: 1000, dtype: object
+1000
+                                                   file  \
+0     /kaggle/input/prepared-dataset/jss-dataset/wav...
+1     /kaggle/input/prepared-dataset/jss-dataset/wav...
+2     /kaggle/input/prepared-dataset/jss-dataset/wav...
+3     /kaggle/input/prepared-dataset/jss-dataset/wav...
+4     /kaggle/input/prepared-dataset/jss-dataset/wav...
+...                                                 ...
+9995  /kaggle/input/prepared-dataset/jss-dataset/wav...
+9996  /kaggle/input/prepared-dataset/jss-dataset/wav...
+9997  /kaggle/input/prepared-dataset/jss-dataset/wav...
+9998  /kaggle/input/prepared-dataset/jss-dataset/wav...
+9999  /kaggle/input/prepared-dataset/jss-dataset/wav...
+                                                   text
+0     지금부터 그러면 본격적으로 우리가 도련동에 대해서 조사를 할 거라 예? 이 마을이 ...
+1                 예, 그건 한 칠백년 전에 이제 그 설촌이 시작이 되었다고 헙니다.
+2     예. 칠백년 전에 설촌이 뒈엇는데 이제 그루후에 이제 성씨들이 여러 성씨들이 많이 ...
+3          예. 그러면은 칠백년부터 허는데 설촌할 때 어떤 성씨들이 헷덴 말도 이신가마씨?
+4                      그 다음 양씨. 고씨. 마 대략적으로 요런 순서가 뒘서양.
+...                                                 ...
+9995  메족메족 날 때 뜨셔가지고 서리 안 내리겟다 허당 자당 보민 뒷날 아첵이 서리 내리...
+9996                                  서리 내릴 땐 어떵헤야 뒈마씨?
+9997                   게난 서리 내릴 때는 흑을 덮어줭은에. 흑을 덮어줘야 돼.
+9998                                실시를 많이 허주게. 일찍 놧당은.
+9999  게난 요즘은 비니루가 이시니까. 비니루에도 고망 아이 뚜러지민 워낙 열 받으민 것도...
+[10000 rows x 2 columns]
+Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+/opt/conda/lib/python3.10/site-packages/transformers/configuration_utils.py:363: UserWarning: Passing `gradient_checkpointing` to a config initialization is deprecated and will be removed in v5 Transformers. Using `model.gradient_checkpointing_enable()` instead, or if you are using the `Trainer` API, pass `gradient_checkpointing=True` in your `TrainingArguments`.
+  warnings.warn(
+Some weights of Wav2Vec2ForCTC were not initialized from the model checkpoint at facebook/wav2vec2-base and are newly initialized: ['lm_head.bias', 'lm_head.weight', 'wav2vec2.encoder.pos_conv_embed.conv.parametrizations.weight.original0', 'wav2vec2.encoder.pos_conv_embed.conv.parametrizations.weight.original1']
+You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+/opt/conda/lib/python3.10/site-packages/datasets/load.py:756: FutureWarning: The repository for wer contains custom code which must be executed to correctly load the metric. You can inspect the repository content at https://raw.githubusercontent.com/huggingface/datasets/2.18.0/metrics/wer/wer.py
+You can avoid this message in future by passing the argument `trust_remote_code=True`.
+Passing `trust_remote_code=True` will be mandatory to load this metric from the next major release of `datasets`.
+  warnings.warn(
+/opt/conda/lib/python3.10/site-packages/accelerate/accelerator.py:436: FutureWarning: Passing the following arguments to `Accelerator` is deprecated and will be removed in version 1.0 of Accelerate: dict_keys(['dispatch_batches', 'split_batches', 'even_batches', 'use_seedable_sampler']). Please pass an `accelerate.DataLoaderConfiguration` instead:
+dataloader_config = DataLoaderConfiguration(dispatch_batches=None, split_batches=False, even_batches=True, use_seedable_sampler=True)
+  warnings.warn(
+wandb: WARNING Calling wandb.login() after wandb.init() has no effect.
+/opt/conda/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:156: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.
+  warnings.warn(
+/opt/conda/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
+  warnings.warn(
+/opt/conda/lib/python3.10/site-packages/accelerate/accelerator.py:436: FutureWarning: Passing the following arguments to `Accelerator` is deprecated and will be removed in version 1.0 of Accelerate: dict_keys(['dispatch_batches', 'split_batches', 'even_batches', 'use_seedable_sampler']). Please pass an `accelerate.DataLoaderConfiguration` instead:
+dataloader_config = DataLoaderConfiguration(dispatch_batches=None, split_batches=False, even_batches=True, use_seedable_sampler=True)
+  warnings.warn(
+/opt/conda/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:156: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.
+  warnings.warn(
+/opt/conda/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
+  warnings.warn(
+                                                   file  \
+0     /kaggle/input/prepared-dataset/jss-dataset/wav...
+1     /kaggle/input/prepared-dataset/jss-dataset/wav...
+2     /kaggle/input/prepared-dataset/jss-dataset/wav...
+3     /kaggle/input/prepared-dataset/jss-dataset/wav...
+4     /kaggle/input/prepared-dataset/jss-dataset/wav...
+...                                                 ...
+9995  /kaggle/input/prepared-dataset/jss-dataset/wav...
+9996  /kaggle/input/prepared-dataset/jss-dataset/wav...
+9997  /kaggle/input/prepared-dataset/jss-dataset/wav...
+9998  /kaggle/input/prepared-dataset/jss-dataset/wav...
+9999  /kaggle/input/prepared-dataset/jss-dataset/wav...
+                                                   text
+0     지금부터 그러면 본격적으로 우리가 도련동에 대해서 조사를 할 거라 예? 이 마을이 ...
+1                 예, 그건 한 칠백년 전에 이제 그 설촌이 시작이 되었다고 헙니다.
+2     예. 칠백년 전에 설촌이 뒈엇는데 이제 그루후에 이제 성씨들이 여러 성씨들이 많이 ...
+3          예. 그러면은 칠백년부터 허는데 설촌할 때 어떤 성씨들이 헷덴 말도 이신가마씨?
+4                      그 다음 양씨. 고씨. 마 대략적으로 요런 순서가 뒘서양.
+...                                                 ...
+9995  메족메족 날 때 뜨셔가지고 서리 안 내리겟다 허당 자당 보민 뒷날 아첵이 서리 내리...
+9996                                  서리 내릴 땐 어떵헤야 뒈마씨?
+9997                   게난 서리 내릴 때는 흑을 덮어줭은에. 흑을 덮어줘야 돼.
+9998                                실시를 많이 허주게. 일찍 놧당은.
+9999  게난 요즘은 비니루가 이시니까. 비니루에도 고망 아이 뚜러지민 워낙 열 받으민 것도...
+[10000 rows x 2 columns]
+                                                   file  \
+0     /kaggle/input/prepared-dataset/jss-dataset/wav...
+1     /kaggle/input/prepared-dataset/jss-dataset/wav...
+2     /kaggle/input/prepared-dataset/jss-dataset/wav...
+3     /kaggle/input/prepared-dataset/jss-dataset/wav...
+4     /kaggle/input/prepared-dataset/jss-dataset/wav...
+...                                                 ...
+9995  /kaggle/input/prepared-dataset/jss-dataset/wav...
+9996  /kaggle/input/prepared-dataset/jss-dataset/wav...
+9997  /kaggle/input/prepared-dataset/jss-dataset/wav...
+9998  /kaggle/input/prepared-dataset/jss-dataset/wav...
+9999  /kaggle/input/prepared-dataset/jss-dataset/wav...
+                                                   text  \
+0     지금부터 그러면 본격적으로 우리가 도련동에 대해서 조사를 할 거라 예? 이 마을이 ...
+1                 예, 그건 한 칠백년 전에 이제 그 설촌이 시작이 되었다고 헙니다.
+2     예. 칠백년 전에 설촌이 뒈엇는데 ���제 그루후에 이제 성씨들이 여러 성씨들이 많이 ...
+3          예. 그러면은 칠백년부터 허는데 설촌할 때 어떤 성씨들이 헷덴 말도 이신가마씨?
+4                      그 다음 양씨. 고씨. 마 대략적으로 요런 순서가 뒘서양.
+...                                                 ...
+9995  메족메족 날 때 뜨셔가지고 서리 안 내리겟다 허당 자당 보민 뒷날 아첵이 서리 내리...
+9996                                  서리 내릴 땐 어떵헤야 뒈마씨?
+9997                   게난 서리 내릴 때는 흑을 덮어줭은에. 흑을 덮어줘야 돼.
+9998                                실시를 많이 허주게. 일찍 놧당은.
+9999  게난 요즘은 비니루가 이시니까. 비니루에도 고망 아이 뚜러지민 워낙 열 받으민 것도...
+                                                  audio
+0     {'array': [8.564606e-05, -4.7375994e-05, 2.878...
+1     {'array': [-0.000804591, -0.00090140395, -0.00...
+2     {'array': [0.0007377937, 0.00092779216, 0.0005...
+3     {'array': [0.00077229546, 0.0008207406, 0.0001...
+4     {'array': [0.00037264611, 0.00073660095, 0.000...
+...                                                 ...
+9995  {'array': [-0.00028759346, -0.00042953866, -0....
+9996  {'array': [0.00026829867, 0.0003072208, -0.000...
+9997  {'array': [0.00016293344, 0.00022468295, -5.42...
+9998  {'array': [0.00092347193, 0.0012520454, 0.0012...
+9999  {'array': [0.00054650987, 0.0008459267, 0.0008...
+[10000 rows x 3 columns]
+Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+/opt/conda/lib/python3.10/site-packages/transformers/configuration_utils.py:363: UserWarning: Passing `gradient_checkpointing` to a config initialization is deprecated and will be removed in v5 Transformers. Using `model.gradient_checkpointing_enable()` instead, or if you are using the `Trainer` API, pass `gradient_checkpointing=True` in your `TrainingArguments`.
+  warnings.warn(
+Some weights of Wav2Vec2ForCTC were not initialized from the model checkpoint at facebook/wav2vec2-base and are newly initialized: ['lm_head.bias', 'lm_head.weight', 'wav2vec2.encoder.pos_conv_embed.conv.parametrizations.weight.original0', 'wav2vec2.encoder.pos_conv_embed.conv.parametrizations.weight.original1']
+You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+/opt/conda/lib/python3.10/site-packages/datasets/load.py:756: FutureWarning: The repository for wer contains custom code which must be executed to correctly load the metric. You can inspect the repository content at https://raw.githubusercontent.com/huggingface/datasets/2.18.0/metrics/wer/wer.py
+You can avoid this message in future by passing the argument `trust_remote_code=True`.
+Passing `trust_remote_code=True` will be mandatory to load this metric from the next major release of `datasets`.
+  warnings.warn(
+/opt/conda/lib/python3.10/site-packages/accelerate/accelerator.py:436: FutureWarning: Passing the following arguments to `Accelerator` is deprecated and will be removed in version 1.0 of Accelerate: dict_keys(['dispatch_batches', 'split_batches', 'even_batches', 'use_seedable_sampler']). Please pass an `accelerate.DataLoaderConfiguration` instead:
+dataloader_config = DataLoaderConfiguration(dispatch_batches=None, split_batches=False, even_batches=True, use_seedable_sampler=True)
+  warnings.warn(
+/opt/conda/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:156: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.
+  warnings.warn(
+/opt/conda/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
+  warnings.warn(
+/opt/conda/lib/python3.10/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:156: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.
+  warnings.warn(
+/opt/conda/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.

wandb/run-20240524_202737-n1w0kmmv/files/requirements.txt

@@ -0,0 +1,862 @@
+Babel==2.14.0
+Boruta==0.3
+Brotli==1.0.9
+CVXcanon==0.1.2
+Cartopy==0.23.0
+Cython==3.0.8
+Deprecated==1.2.14
+Farama-Notifications==0.0.4
+Flask==3.0.3
+Geohash==1.0
+GitPython==3.1.41
+ImageHash==4.3.1
+Janome==0.5.0
+Jinja2==3.1.2
+LunarCalendar==0.0.9
+Mako==1.3.3
+Markdown==3.5.2
+MarkupSafe==2.1.3
+MarkupSafe==2.1.5
+Pillow==9.5.0
+PuLP==2.8.0
+PyArabic==0.6.15
+PyJWT==2.8.0
+PyMeeus==0.5.12
+PySocks==1.7.1
+PyUpSet==0.1.1.post7
+PyWavelets==1.5.0
+PyYAML==6.0.1
+Pygments==2.17.2
+Pympler==1.0.1
+QtPy==2.4.1
+Rtree==1.2.0
+SQLAlchemy==2.0.25
+SecretStorage==3.3.3
+Send2Trash==1.8.2
+Shapely==1.8.5.post1
+Shimmy==1.3.0
+SimpleITK==2.3.1
+TPOT==0.12.1
+Theano-PyMC==1.1.2
+Theano==1.0.5
+Wand==0.6.13
+Werkzeug==3.0.2
+absl-py==1.4.0
+accelerate==0.29.3
+access==1.1.9
+affine==2.4.0
+aiobotocore==2.12.3
+aiofiles==22.1.0
+aiohttp-cors==0.7.0
+aiohttp==3.9.1
+aioitertools==0.11.0
+aiorwlock==1.3.0
+aiosignal==1.3.1
+aiosqlite==0.19.0
+albumentations==1.4.0
+alembic==1.13.1
+altair==5.3.0
+annotated-types==0.6.0
+annoy==1.17.3
+anyio==4.2.0
+apache-beam==2.46.0
+aplus==0.11.0
+appdirs==1.4.4
+archspec==0.2.3
+argon2-cffi-bindings==21.2.0
+argon2-cffi==23.1.0
+array-record==0.5.0
+arrow==1.3.0
+arviz==0.18.0
+astroid==3.1.0
+astropy-iers-data==0.2024.4.15.2.45.49
+astropy==6.0.1
+asttokens==2.4.1
+astunparse==1.6.3
+async-lru==2.0.4
+async-timeout==4.0.3
+attrs==23.2.0
+audioread==3.0.1
+autopep8==2.0.4
+backoff==2.2.1
+bayesian-optimization==1.4.3
+beatrix_jupyterlab==2023.128.151533
+beautifulsoup4==4.12.2
+blake3==0.2.1
+bleach==6.1.0
+blessed==1.20.0
+blinker==1.7.0
+blis==0.7.10
+blosc2==2.6.2
+bokeh==3.4.1
+boltons==23.1.1
+boto3==1.26.100
+botocore==1.34.69
+bq_helper==0.4.1
+bqplot==0.12.43
+branca==0.7.1
+brewer2mpl==1.4.1
+brotlipy==0.7.0
+cached-property==1.5.2
+cachetools==4.2.4
+cachetools==5.3.2
+catalogue==2.0.10
+catalyst==22.4
+catboost==1.2.3
+category-encoders==2.6.3
+certifi==2024.2.2
+cesium==0.12.1
+cffi==1.16.0
+charset-normalizer==3.3.2
+chex==0.1.86
+cleverhans==4.0.0
+click-plugins==1.1.1
+click==8.1.7
+cligj==0.7.2
+cloud-tpu-client==0.10
+cloud-tpu-profiler==2.4.0
+cloudpathlib==0.16.0
+cloudpickle==2.2.1
+cloudpickle==3.0.0
+cmdstanpy==1.2.2
+colorama==0.4.6
+colorcet==3.1.0
+colorful==0.5.6
+colorlog==6.8.2
+colorlover==0.3.0
+comm==0.2.1
+conda-libmamba-solver==23.7.0
+conda-package-handling==2.2.0
+conda==23.7.4
+conda_package_streaming==0.9.0
+confection==0.1.4
+contextily==1.6.0
+contourpy==1.2.0
+contourpy==1.2.1
+convertdate==2.4.0
+crcmod==1.7
+cryptography==41.0.7
+cuda-python==12.4.0
+cudf==23.8.0
+cufflinks==0.17.3
+cuml==23.8.0
+cupy==13.0.0
+cycler==0.12.1
+cymem==2.0.8
+cytoolz==0.12.3
+daal4py==2024.3.0
+daal==2024.3.0
+dacite==1.8.1
+dask-cuda==23.8.0
+dask-cudf==23.8.0
+dask-expr==1.0.11
+dask==2024.4.1
+dataclasses-json==0.6.4
+dataproc_jupyter_plugin==0.1.66
+datasets==2.18.0
+datashader==0.16.0
+datatile==1.0.3
+db-dtypes==1.2.0
+deap==1.4.1
+debugpy==1.8.0
+decorator==5.1.1
+deepdiff==7.0.1
+defusedxml==0.7.1
+deprecation==2.1.0
+descartes==1.1.0
+dill==0.3.8
+dipy==1.9.0
+distlib==0.3.8
+distributed==2023.7.1
+distro==1.9.0
+dm-tree==0.1.8
+docker-pycreds==0.4.0
+docker==7.0.0
+docopt==0.6.2
+docstring-parser==0.15
+docstring-to-markdown==0.15
+docutils==0.21.1
+earthengine-api==0.1.399
+easydict==1.13
+easyocr==1.7.1
+ecos==2.0.13
+eli5==0.13.0
+emoji==2.11.0
+en-core-web-lg==3.7.1
+en-core-web-sm==3.7.1
+entrypoints==0.4
+ephem==4.1.5
+esda==2.5.1
+essentia==2.1b6.dev1110
+et-xmlfile==1.1.0
+etils==1.6.0
+exceptiongroup==1.2.0
+executing==2.0.1
+explainable-ai-sdk==1.3.3
+fastai==2.7.14
+fastapi==0.108.0
+fastavro==1.9.3
+fastcore==1.5.29
+fastdownload==0.0.7
+fasteners==0.19
+fastjsonschema==2.19.1
+fastprogress==1.0.3
+fastrlock==0.8.2
+fasttext==0.9.2
+feather-format==0.4.1
+featuretools==1.30.0
+filelock==3.13.1
+fiona==1.9.6
+fitter==1.7.0
+flake8==7.0.0
+flashtext==2.7
+flatbuffers==23.5.26
+flax==0.8.2
+folium==0.16.0
+fonttools==4.47.0
+fonttools==4.51.0
+fqdn==1.5.1
+frozendict==2.4.2
+frozenlist==1.4.1
+fsspec==2024.2.0
+fsspec==2024.3.1
+funcy==2.0
+fury==0.10.0
+future==1.0.0
+fuzzywuzzy==0.18.0
+gast==0.5.4
+gatspy==0.3
+gcsfs==2024.2.0
+gensim==4.3.2
+geographiclib==2.0
+geojson==3.1.0
+geopandas==0.14.3
+geoplot==0.5.1
+geopy==2.4.1
+geoviews==1.12.0
+ggplot==0.11.5
+giddy==2.3.5
+gitdb==4.0.11
+google-ai-generativelanguage==0.6.2
+google-api-core==2.11.1
+google-api-core==2.18.0
+google-api-python-client==2.126.0
+google-apitools==0.5.31
+google-auth-httplib2==0.2.0
+google-auth-oauthlib==1.2.0
+google-auth==2.26.1
+google-cloud-aiplatform==0.6.0a1
+google-cloud-artifact-registry==1.10.0
+google-cloud-automl==1.0.1
+google-cloud-bigquery==2.34.4
+google-cloud-bigtable==1.7.3
+google-cloud-core==2.4.1
+google-cloud-datastore==2.19.0
+google-cloud-dlp==3.14.0
+google-cloud-jupyter-config==0.0.5
+google-cloud-language==2.13.3
+google-cloud-monitoring==2.18.0
+google-cloud-pubsub==2.19.0
+google-cloud-pubsublite==1.9.0
+google-cloud-recommendations-ai==0.7.1
+google-cloud-resource-manager==1.11.0
+google-cloud-spanner==3.40.1
+google-cloud-storage==1.44.0
+google-cloud-translate==3.12.1
+google-cloud-videointelligence==2.13.3
+google-cloud-vision==2.8.0
+google-crc32c==1.5.0
+google-generativeai==0.5.1
+google-pasta==0.2.0
+google-resumable-media==2.7.0
+googleapis-common-protos==1.62.0
+gplearn==0.4.2
+gpustat==1.0.0
+gpxpy==1.6.2
+graphviz==0.20.3
+greenlet==3.0.3
+grpc-google-iam-v1==0.12.7
+grpcio-status==1.48.1
+grpcio-status==1.48.2
+grpcio==1.51.1
+grpcio==1.60.0
+gviz-api==1.10.0
+gym-notices==0.0.8
+gym==0.26.2
+gymnasium==0.29.0
+h11==0.14.0
+h2o==3.46.0.1
+h5netcdf==1.3.0
+h5py==3.10.0
+haversine==2.8.1
+hdfs==2.7.3
+hep-ml==0.7.2
+hijri-converter==2.3.1
+hmmlearn==0.3.2
+holidays==0.24
+holoviews==1.18.3
+hpsklearn==0.1.0
+html5lib==1.1
+htmlmin==0.1.12
+httpcore==1.0.5
+httplib2==0.21.0
+httptools==0.6.1
+httpx==0.27.0
+huggingface-hub==0.22.2
+hunspell==0.5.5
+hydra-slayer==0.5.0
+hyperopt==0.2.7
+hypertools==0.8.0
+idna==3.6
+igraph==0.11.4
+imagecodecs==2024.1.1
+imageio==2.33.1
+imbalanced-learn==0.12.2
+imgaug==0.4.0
+importlib-metadata==6.11.0
+importlib-metadata==7.0.1
+importlib-resources==6.1.1
+inequality==1.0.1
+iniconfig==2.0.0
+ipydatawidgets==4.3.5
+ipykernel==6.28.0
+ipyleaflet==0.18.2
+ipympl==0.7.0
+ipython-genutils==0.2.0
+ipython-genutils==0.2.0
+ipython-sql==0.5.0
+ipython==8.20.0
+ipyvolume==0.6.3
+ipyvue==1.11.0
+ipyvuetify==1.9.4
+ipywebrtc==0.6.0
+ipywidgets==7.7.1
+isoduration==20.11.0
+isort==5.13.2
+isoweek==1.3.3
+itsdangerous==2.2.0
+jaraco.classes==3.3.0
+jax-jumpy==1.0.0
+jax==0.4.23
+jaxlib==0.4.23.dev20240116
+jedi==0.19.1
+jeepney==0.8.0
+jieba==0.42.1
+jiwer==3.0.4
+jmespath==1.0.1
+joblib==1.4.0
+json5==0.9.14
+jsonpatch==1.33
+jsonpointer==2.4
+jsonschema-specifications==2023.12.1
+jsonschema==4.20.0
+jupyter-console==6.6.3
+jupyter-events==0.9.0
+jupyter-http-over-ws==0.0.8
+jupyter-lsp==1.5.1
+jupyter-server-mathjax==0.2.6
+jupyter-ydoc==0.2.5
+jupyter_client==7.4.9
+jupyter_client==8.6.0
+jupyter_core==5.7.1
+jupyter_server==2.12.5
+jupyter_server_fileid==0.9.1
+jupyter_server_proxy==4.1.0
+jupyter_server_terminals==0.5.1
+jupyter_server_ydoc==0.8.0
+jupyterlab-lsp==5.1.0
+jupyterlab-widgets==3.0.9
+jupyterlab==4.1.6
+jupyterlab_git==0.44.0
+jupyterlab_pygments==0.3.0
+jupyterlab_server==2.25.2
+jupytext==1.16.0
+kaggle-environments==1.14.3
+kaggle==1.6.12
+kagglehub==0.2.3
+keras-cv==0.8.2
+keras-nlp==0.9.3
+keras-tuner==1.4.6
+keras==3.2.1
+kernels-mixer==0.0.7
+keyring==24.3.0
+keyrings.google-artifactregistry-auth==1.1.2
+kfp-pipeline-spec==0.2.2
+kfp-server-api==2.0.5
+kfp==2.5.0
+kiwisolver==1.4.5
+kmapper==2.0.1
+kmodes==0.12.2
+korean-lunar-calendar==0.3.1
+kornia==0.7.2
+kornia_rs==0.1.3
+kt-legacy==1.0.5
+kubernetes==26.1.0
+langcodes==3.3.0
+langid==1.1.6
+lazy_loader==0.3
+learntools==0.3.4
+leven==1.0.4
+libclang==16.0.6
+libmambapy==1.5.0
+libpysal==4.9.2
+librosa==0.10.1
+lightgbm==4.2.0
+lightning-utilities==0.11.2
+lime==0.2.0.1
+line-profiler==4.1.2
+linkify-it-py==2.0.3
+llvmlite==0.41.1
+llvmlite==0.42.0
+lml==0.1.0
+locket==1.0.0
+loguru==0.7.2
+lxml==5.2.1
+lz4==4.3.3
+mamba==1.5.0
+mapclassify==2.6.1
+markdown-it-py==3.0.0
+marshmallow==3.21.1
+matplotlib-inline==0.1.6
+matplotlib-venn==0.11.10
+matplotlib==3.7.5
+matplotlib==3.8.4
+mccabe==0.7.0
+mdit-py-plugins==0.4.0
+mdurl==0.1.2
+memory-profiler==0.61.0
+menuinst==2.0.1
+mercantile==1.2.1
+mgwr==2.2.1
+missingno==0.5.2
+mistune==0.8.4
+mizani==0.11.1
+ml-dtypes==0.2.0
+mlcrate==0.2.0
+mlens==0.2.3
+mlxtend==0.23.1
+mne==1.6.1
+mnist==0.2.2
+momepy==0.7.0
+more-itertools==10.2.0
+mpld3==0.5.10
+mpmath==1.3.0
+msgpack==1.0.7
+multidict==6.0.4
+multimethod==1.10
+multipledispatch==1.0.0
+multiprocess==0.70.16
+munkres==1.1.4
+murmurhash==1.0.10
+mypy-extensions==1.0.0
+namex==0.0.8
+nb-conda-kernels==2.3.1
+nb_conda==2.2.1
+nbclassic==1.0.0
+nbclient==0.5.13
+nbconvert==6.4.5
+nbdime==3.2.0
+nbformat==5.9.2
+ndindex==1.8
+nest-asyncio==1.5.8
+networkx==3.2.1
+nibabel==5.2.1
+nilearn==0.10.4
+ninja==1.11.1.1
+nltk==3.2.4
+nose==1.3.7
+notebook==6.5.4
+notebook==6.5.6
+notebook_executor==0.2
+notebook_shim==0.2.3
+numba==0.58.1
+numba==0.59.1
+numexpr==2.10.0
+numpy==1.26.4
+nvidia-ml-py==11.495.46
+nvtx==0.2.10
+oauth2client==4.1.3
+oauthlib==3.2.2
+objsize==0.6.1
+odfpy==1.4.1
+olefile==0.47
+onnx==1.16.0
+opencensus-context==0.1.3
+opencensus==0.11.4
+opencv-contrib-python==4.9.0.80
+opencv-python-headless==4.9.0.80
+opencv-python==4.9.0.80
+openpyxl==3.1.2
+openslide-python==1.3.1
+opentelemetry-api==1.22.0
+opentelemetry-exporter-otlp-proto-common==1.22.0
+opentelemetry-exporter-otlp-proto-grpc==1.22.0
+opentelemetry-exporter-otlp-proto-http==1.22.0
+opentelemetry-exporter-otlp==1.22.0
+opentelemetry-proto==1.22.0
+opentelemetry-sdk==1.22.0
+opentelemetry-semantic-conventions==0.43b0
+opt-einsum==3.3.0
+optax==0.2.2
+optree==0.11.0
+optuna==3.6.1
+orbax-checkpoint==0.5.9
+ordered-set==4.1.0
+orjson==3.9.10
+ortools==9.4.1874
+osmnx==1.9.2
+overrides==7.4.0
+packaging==21.3
+pandas-datareader==0.10.0
+pandas-profiling==3.6.6
+pandas-summary==0.2.0
+pandas==2.1.4
+pandas==2.2.2
+pandasql==0.7.3
+pandocfilters==1.5.0
+panel==1.4.1
+papermill==2.5.0
+param==2.1.0
+parso==0.8.3
+partd==1.4.1
+path.py==12.5.0
+path==16.14.0
+pathos==0.3.2
+pathy==0.10.3
+patsy==0.5.6
+pdf2image==1.17.0
+pettingzoo==1.24.0
+pexpect==4.8.0
+pexpect==4.9.0
+phik==0.12.4
+pickleshare==0.7.5
+pillow==10.3.0
+pip==23.3.2
+pkgutil_resolve_name==1.3.10
+platformdirs==4.2.0
+plotly-express==0.4.1
+plotly==5.18.0
+plotnine==0.13.4
+pluggy==1.4.0
+pointpats==2.4.0
+polars==0.20.21
+polyglot==16.7.4
+pooch==1.8.1
+pox==0.3.4
+ppca==0.0.4
+ppft==1.7.6.8
+preprocessing==0.1.13
+preshed==3.0.9
+prettytable==3.9.0
+progressbar2==4.4.2
+prometheus-client==0.19.0
+promise==2.3
+prompt-toolkit==3.0.42
+prompt-toolkit==3.0.43
+prophet==1.1.1
+proto-plus==1.23.0
+protobuf==3.20.3
+protobuf==4.21.12
+psutil==5.9.3
+psutil==5.9.7
+ptyprocess==0.7.0
+pudb==2024.1
+pure-eval==0.2.2
+py-cpuinfo==9.0.0
+py-spy==0.3.14
+py4j==0.10.9.7
+pyLDAvis==3.4.1
+pyOpenSSL==23.3.0
+pyaml==23.12.0
+pyarrow-hotfix==0.6
+pyarrow==15.0.2
+pyasn1-modules==0.3.0
+pyasn1==0.5.1
+pybind11==2.12.0
+pyclipper==1.3.0.post5
+pycodestyle==2.11.1
+pycosat==0.6.6
+pycparser==2.21
+pycryptodome==3.20.0
+pyct==0.5.0
+pycuda==2024.1
+pydantic==2.5.3
+pydantic==2.7.0
+pydantic_core==2.14.6
+pydantic_core==2.18.1
+pydegensac==0.1.2
+pydicom==2.4.4
+pydocstyle==6.3.0
+pydot==1.4.2
+pydub==0.25.1
+pyemd==1.0.0
+pyerfa==2.0.1.4
+pyexcel-io==0.6.6
+pyexcel-ods==0.6.0
+pyflakes==3.2.0
+pygltflib==1.16.2
+pykalman==0.9.7
+pylibraft==23.8.0
+pylint==3.1.0
+pymc3==3.11.4
+pymongo==3.13.0
+pynndescent==0.5.12
+pynvml==11.4.1
+pynvrtc==9.2
+pyparsing==3.1.1
+pyparsing==3.1.2
+pypdf==4.2.0
+pyproj==3.6.1
+pysal==24.1
+pyshp==2.3.1
+pytesseract==0.3.10
+pytest==8.1.1
+python-bidi==0.4.2
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.0
+python-json-logger==2.0.7
+python-louvain==0.16
+python-lsp-jsonrpc==1.1.2
+python-lsp-server==1.11.0
+python-slugify==8.0.4
+python-utils==3.8.2
+pythreejs==2.4.2
+pytoolconfig==1.3.1
+pytools==2024.1.1
+pytorch-ignite==0.5.0.post2
+pytorch-lightning==2.2.2
+pytz==2023.3.post1
+pytz==2024.1
+pyu2f==0.1.5
+pyviz_comms==3.0.2
+pyzmq==24.0.1
+pyzmq==25.1.2
+qgrid==1.3.1
+qtconsole==5.5.1
+quantecon==0.7.2
+qudida==0.0.4
+raft-dask==23.8.0
+rapidfuzz==3.9.1
+rasterio==1.3.10
+rasterstats==0.19.0
+ray-cpp==2.9.0
+ray==2.9.0
+referencing==0.32.1
+regex==2023.12.25
+requests-oauthlib==1.3.1
+requests-toolbelt==0.10.1
+requests==2.31.0
+retrying==1.3.3
+retrying==1.3.4
+rfc3339-validator==0.1.4
+rfc3986-validator==0.1.1
+rgf-python==3.12.0
+rich-click==1.7.4
+rich==13.7.0
+rich==13.7.1
+rmm==23.8.0
+rope==1.13.0
+rpds-py==0.16.2
+rsa==4.9
+ruamel-yaml-conda==0.15.100
+ruamel.yaml.clib==0.2.7
+ruamel.yaml==0.17.40
+s2sphere==0.2.5
+s3fs==2024.2.0
+s3transfer==0.6.2
+safetensors==0.4.3
+scattertext==0.1.19
+scikit-image==0.22.0
+scikit-learn-intelex==2024.3.0
+scikit-learn==1.2.2
+scikit-multilearn==0.2.0
+scikit-optimize==0.10.1
+scikit-plot==0.3.7
+scikit-surprise==1.1.3
+scipy==1.11.4
+scipy==1.13.0
+seaborn==0.12.2
+segment_anything==1.0
+segregation==2.5
+semver==3.0.2
+sentencepiece==0.2.0
+sentry-sdk==1.45.0
+setproctitle==1.3.3
+setuptools-git==1.2
+setuptools-scm==8.0.4
+setuptools==69.0.3
+shap==0.44.1
+shapely==2.0.4
+shellingham==1.5.4
+simpervisor==1.0.0
+simplejson==3.19.2
+six==1.16.0
+sklearn-pandas==2.2.0
+slicer==0.0.7
+smart-open==6.4.0
+smmap==5.0.1
+sniffio==1.3.0
+snowballstemmer==2.2.0
+snuggs==1.4.7
+sortedcontainers==2.4.0
+soundfile==0.12.1
+soupsieve==2.5
+soxr==0.3.7
+spacy-legacy==3.0.12
+spacy-loggers==1.0.5
+spacy==3.7.3
+spaghetti==1.7.5.post1
+spectral==0.23.1
+spglm==1.1.0
+sphinx-rtd-theme==0.2.4
+spint==1.0.7
+splot==1.1.5.post1
+spopt==0.6.0
+spreg==1.4.2
+spvcm==0.3.0
+sqlparse==0.4.4
+squarify==0.4.3
+srsly==2.4.8
+stable-baselines3==2.1.0
+stack-data==0.6.2
+stack-data==0.6.3
+stanio==0.5.0
+starlette==0.32.0.post1
+statsmodels==0.14.1
+stemming==1.0.1
+stop-words==2018.7.23
+stopit==1.1.2
+stumpy==1.12.0
+sympy==1.12
+tables==3.9.2
+tabulate==0.9.0
+tangled-up-in-unicode==0.2.0
+tbb==2021.12.0
+tblib==3.0.0
+tenacity==8.2.3
+tensorboard-data-server==0.7.2
+tensorboard-plugin-profile==2.15.0
+tensorboard==2.15.1
+tensorboardX==2.6.2.2
+tensorflow-cloud==0.1.16
+tensorflow-datasets==4.9.4
+tensorflow-decision-forests==1.8.1
+tensorflow-estimator==2.15.0
+tensorflow-hub==0.16.1
+tensorflow-io-gcs-filesystem==0.35.0
+tensorflow-io==0.35.0
+tensorflow-metadata==0.14.0
+tensorflow-probability==0.23.0
+tensorflow-serving-api==2.14.1
+tensorflow-text==2.15.0
+tensorflow-transform==0.14.0
+tensorflow==2.15.0
+tensorstore==0.1.56
+termcolor==2.4.0
+terminado==0.18.0
+testpath==0.6.0
+text-unidecode==1.3
+textblob==0.18.0.post0
+texttable==1.7.0
+tf_keras==2.15.1
+tfp-nightly==0.24.0.dev0
+thinc==8.2.2
+threadpoolctl==3.2.0
+tifffile==2023.12.9
+timm==0.9.16
+tinycss2==1.2.1
+tobler==0.11.2
+tokenizers==0.15.2
+toml==0.10.2
+tomli==2.0.1
+tomlkit==0.12.4
+toolz==0.12.1
+torch==2.1.2
+torchaudio==2.1.2
+torchdata==0.7.1
+torchinfo==1.8.0
+torchmetrics==1.3.2
+torchtext==0.16.2
+torchvision==0.16.2
+tornado==6.3.3
+tqdm==4.66.1
+traceml==1.0.8
+traitlets==5.9.0
+traittypes==0.2.1
+transformers==4.39.3
+treelite-runtime==3.2.0
+treelite==3.2.0
+truststore==0.8.0
+trx-python==0.2.9
+tsfresh==0.20.2
+typeguard==4.1.5
+typer==0.9.0
+typer==0.9.4
+types-python-dateutil==2.8.19.20240106
+typing-inspect==0.9.0
+typing-utils==0.1.0
+typing_extensions==4.9.0
+tzdata==2023.4
+uc-micro-py==1.0.3
+ucx-py==0.33.0
+ujson==5.9.0
+umap-learn==0.5.6
+unicodedata2==15.1.0
+update-checker==0.18.0
+uri-template==1.3.0
+uritemplate==3.0.1
+urllib3==1.26.18
+urllib3==2.1.0
+urwid==2.6.10
+urwid_readline==0.14
+uvicorn==0.25.0
+uvloop==0.19.0
+vaex-astro==0.9.3
+vaex-core==4.17.1
+vaex-hdf5==0.14.1
+vaex-jupyter==0.8.2
+vaex-ml==0.18.3
+vaex-server==0.9.0
+vaex-viz==0.5.4
+vaex==4.17.0
+vec_noise==1.1.4
+vecstack==0.4.0
+virtualenv==20.21.0
+visions==0.7.5
+vowpalwabbit==9.9.0
+vtk==9.3.0
+wandb==0.16.6
+wasabi==1.1.2
+watchfiles==0.21.0
+wavio==0.0.8
+wcwidth==0.2.13
+weasel==0.3.4
+webcolors==1.13
+webencodings==0.5.1
+websocket-client==1.7.0
+websockets==12.0
+wfdb==4.1.2
+whatthepatch==1.0.5
+wheel==0.42.0
+widgetsnbextension==3.6.6
+witwidget==1.8.1
+woodwork==0.30.0
+wordcloud==1.9.3
+wordsegment==1.3.1
+wrapt==1.14.1
+xarray-einstats==0.7.0
+xarray==2024.3.0
+xgboost==2.0.3
+xvfbwrapper==0.2.9
+xxhash==3.4.1
+xyzservices==2024.4.0
+y-py==0.6.2
+yapf==0.40.2
+yarl==1.9.3
+yarl==1.9.4
+ydata-profiling==4.6.4
+yellowbrick==1.5
+ypy-websocket==0.8.4
+zict==3.0.0
+zipp==3.17.0
+zstandard==0.22.0

wandb/run-20240524_202737-n1w0kmmv/files/wandb-metadata.json

@@ -0,0 +1,62 @@
+{
+    "os": "Linux-5.15.133+-x86_64-with-glibc2.31",
+    "python": "3.10.13",
+    "heartbeatAt": "2024-05-24T20:27:38.540904",
+    "startedAt": "2024-05-24T20:27:37.415317",
+    "docker": null,
+    "cuda": null,
+    "args": [],
+    "state": "running",
+    "program": "kaggle.ipynb",
+    "codePathLocal": null,
+    "root": "/kaggle/working",
+    "host": "890e8b3ca76b",
+    "username": "root",
+    "executable": "/opt/conda/bin/python3.10",
+    "cpu_count": 2,
+    "cpu_count_logical": 4,
+    "cpu_freq": {
+        "current": 2000.17,
+        "min": 0.0,
+        "max": 0.0
+    },
+    "cpu_freq_per_core": [
+        {
+            "current": 2000.17,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2000.17,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2000.17,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2000.17,
+            "min": 0.0,
+            "max": 0.0
+        }
+    ],
+    "disk": {
+        "/": {
+            "total": 8062.387607574463,
+            "used": 5599.177722930908
+        }
+    },
+    "gpu": "Tesla P100-PCIE-16GB",
+    "gpu_count": 1,
+    "gpu_devices": [
+        {
+            "name": "Tesla P100-PCIE-16GB",
+            "memory_total": 17179869184
+        }
+    ],
+    "memory": {
+        "total": 31.357559204101562
+    }
+}

wandb/run-20240524_202737-n1w0kmmv/files/wandb-summary.json

@@ -0,0 +1 @@
+{"train/loss": 8079.875, "train/grad_norm": NaN, "train/learning_rate": 3.6e-06, "train/epoch": 11.36, "train/global_step": 500, "_timestamp": 1716584600.8230615, "_runtime": 2143.3996374607086, "_step": 1, "eval/loss": NaN, "eval/wer": 0.9984338292873923, "eval/runtime": 10.1243, "eval/samples_per_second": 19.754, "eval/steps_per_second": 2.469}

wandb/run-20240524_202737-n1w0kmmv/logs/debug.log

@@ -0,0 +1,217 @@
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_setup.py:_flush():76] Current SDK version is 0.16.6
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_setup.py:_flush():76] Configure stats pid to 34
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_setup.py:_flush():76] Loading settings from /root/.config/wandb/settings
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_setup.py:_flush():76] Loading settings from /kaggle/working/wandb/settings
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program': '<python with no main file>'}
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_setup.py:_flush():76] Applying login settings: {}
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_setup.py:_flush():76] Applying login settings: {'api_key': '***REDACTED***'}
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_init.py:_log_setup():521] Logging user logs to /kaggle/working/wandb/run-20240524_202737-n1w0kmmv/logs/debug.log
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_init.py:_log_setup():522] Logging internal logs to /kaggle/working/wandb/run-20240524_202737-n1w0kmmv/logs/debug-internal.log
+2024-05-24 20:27:37,417 INFO    MainThread:34 [wandb_init.py:_jupyter_setup():467] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x785a802b9120>
+2024-05-24 20:27:37,418 INFO    MainThread:34 [wandb_init.py:init():561] calling init triggers
+2024-05-24 20:27:37,418 INFO    MainThread:34 [wandb_init.py:init():568] wandb.init called with sweep_config: {}
+config: {}
+2024-05-24 20:27:37,418 INFO    MainThread:34 [wandb_init.py:init():611] starting backend
+2024-05-24 20:27:37,418 INFO    MainThread:34 [wandb_init.py:init():615] setting up manager
+2024-05-24 20:27:37,420 INFO    MainThread:34 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-05-24 20:27:37,423 INFO    MainThread:34 [wandb_init.py:init():623] backend started and connected
+2024-05-24 20:27:37,434 INFO    MainThread:34 [wandb_run.py:_label_probe_notebook():1299] probe notebook
+2024-05-24 20:27:38,191 INFO    MainThread:34 [wandb_init.py:init():715] updated telemetry
+2024-05-24 20:27:38,195 INFO    MainThread:34 [wandb_init.py:init():748] communicating run to backend with 90.0 second timeout
+2024-05-24 20:27:38,448 INFO    MainThread:34 [wandb_run.py:_on_init():2357] communicating current version
+2024-05-24 20:27:38,512 INFO    MainThread:34 [wandb_run.py:_on_init():2366] got version response upgrade_message: "wandb version 0.17.0 is available!  To upgrade, please run:\n $ pip install wandb --upgrade"
+
+2024-05-24 20:27:38,514 INFO    MainThread:34 [wandb_init.py:init():799] starting run threads in backend
+2024-05-24 20:27:54,627 INFO    MainThread:34 [wandb_run.py:_console_start():2335] atexit reg
+2024-05-24 20:27:54,628 INFO    MainThread:34 [wandb_run.py:_redirect():2190] redirect: wrap_raw
+2024-05-24 20:27:54,628 INFO    MainThread:34 [wandb_run.py:_redirect():2255] Wrapping output streams.
+2024-05-24 20:27:54,629 INFO    MainThread:34 [wandb_run.py:_redirect():2280] Redirects installed.
+2024-05-24 20:27:54,630 INFO    MainThread:34 [wandb_init.py:init():842] run started, returning control to user process
+2024-05-24 20:27:54,637 INFO    MainThread:34 [wandb_run.py:_config_callback():1347] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['Wav2Vec2ForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 0, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/wav2vec2-base', 'transformers_version': '4.39.3', 'freeze_feat_extract_train': True, 'mask_channel_length': 10, 'mask_channel_min_space': 1, 'mask_channel_other': 0.0, 'mask_channel_prob': 0.0, 'mask_channel_selection': 'static', 'mask_time_min_space': 1, 'mask_time_other': 0.0, 'mask_time_selection': 'static', 'model_type': 'wav2vec2', 'no_mask_channel_overlap': False, 'no_mask_time_overlap': False, 'num_feat_extract_layers': 7, 'hidden_size': 768, 'feat_extract_norm': 'group', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': False, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 12, 'intermediate_size': 3072, 'hidden_act': 'gelu', 'num_attention_heads': 12, 'hidden_dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'feat_proj_dropout': 0.1, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 32, 'do_stable_layer_norm': False, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.05, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 256, 'proj_codevector_dim': 256, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'sum', 'ctc_zero_infinity': False, 'add_adapter': False, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 768, 'adapter_attn_dim': None, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 32, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0001, 'weight_decay': 0.005, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 30, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/May24_20-24-49_890e8b3ca76b', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 2, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': True, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
+2024-05-24 20:28:04,489 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:28:04,489 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:28:58,368 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:28:59,625 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:28:59,625 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:29:08,949 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:29:08,951 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:29:08,951 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:29:12,141 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:29:16,856 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:29:16,857 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:29:20,764 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:29:24,478 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:29:24,478 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:29:30,221 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:30:45,072 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:30:45,072 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:30:58,707 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:30:58,709 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:30:58,710 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:31:02,188 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:31:02,613 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:31:02,613 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:31:04,725 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:31:04,727 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:31:04,727 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:31:07,065 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:31:07,298 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:31:07,298 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:31:10,187 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:31:10,193 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:31:10,193 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:31:12,404 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:31:50,143 INFO    MainThread:34 [wandb_run.py:_config_callback():1347] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['Wav2Vec2ForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 0, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/wav2vec2-base', 'transformers_version': '4.39.3', 'freeze_feat_extract_train': True, 'mask_channel_length': 10, 'mask_channel_min_space': 1, 'mask_channel_other': 0.0, 'mask_channel_prob': 0.0, 'mask_channel_selection': 'static', 'mask_time_min_space': 1, 'mask_time_other': 0.0, 'mask_time_selection': 'static', 'model_type': 'wav2vec2', 'no_mask_channel_overlap': False, 'no_mask_time_overlap': False, 'num_feat_extract_layers': 7, 'hidden_size': 768, 'feat_extract_norm': 'group', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': False, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 12, 'intermediate_size': 3072, 'hidden_act': 'gelu', 'num_attention_heads': 12, 'hidden_dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'feat_proj_dropout': 0.1, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 32, 'do_stable_layer_norm': False, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.05, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 256, 'proj_codevector_dim': 256, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'sum', 'ctc_zero_infinity': False, 'add_adapter': False, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 768, 'adapter_attn_dim': None, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 32, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0001, 'weight_decay': 0.005, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 30, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/May24_20-31-07_890e8b3ca76b', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 2, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': True, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
+2024-05-24 20:31:58,626 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:31:58,626 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:34:06,571 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:34:06,717 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:34:06,717 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:34:10,001 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:34:46,464 INFO    MainThread:34 [wandb_run.py:_config_callback():1347] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['Wav2Vec2ForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 0, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/wav2vec2-base', 'transformers_version': '4.39.3', 'freeze_feat_extract_train': True, 'mask_channel_length': 10, 'mask_channel_min_space': 1, 'mask_channel_other': 0.0, 'mask_channel_prob': 0.0, 'mask_channel_selection': 'static', 'mask_time_min_space': 1, 'mask_time_other': 0.0, 'mask_time_selection': 'static', 'model_type': 'wav2vec2', 'no_mask_channel_overlap': False, 'no_mask_time_overlap': False, 'num_feat_extract_layers': 7, 'hidden_size': 768, 'feat_extract_norm': 'group', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': False, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 12, 'intermediate_size': 3072, 'hidden_act': 'gelu', 'num_attention_heads': 12, 'hidden_dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'feat_proj_dropout': 0.1, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 32, 'do_stable_layer_norm': False, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.05, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 256, 'proj_codevector_dim': 256, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'sum', 'ctc_zero_infinity': False, 'add_adapter': False, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 768, 'adapter_attn_dim': None, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 64, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0001, 'weight_decay': 0.005, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 30, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/May24_20-34-06_890e8b3ca76b', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 2, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': True, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
+2024-05-24 20:34:55,928 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:34:55,929 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:35:26,131 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:35:26,139 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:35:26,139 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:35:32,729 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:35:32,732 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:35:32,732 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:35:34,729 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:35:34,732 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:35:34,733 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:35:47,483 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:35:47,488 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:35:47,488 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:35:56,249 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:35:56,253 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:35:56,253 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:37:20,366 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:37:20,370 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:37:20,370 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:37:28,481 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:37:28,510 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:37:28,511 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:38:00,946 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:38:00,950 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:38:00,950 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:38:04,524 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:38:04,550 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:38:04,550 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:38:12,369 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:38:12,432 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:38:12,432 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:38:16,938 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:38:16,998 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:38:16,998 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:38:21,248 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:38:21,260 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:38:21,260 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:38:22,930 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:38:22,940 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:38:22,940 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:38:37,851 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:38:55,254 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:38:55,254 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:38:58,788 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:38:58,827 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:38:58,827 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:39:00,762 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:40:16,333 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:40:16,334 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:40:21,472 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:40:22,682 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:40:22,682 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:40:28,979 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:40:33,961 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:40:33,961 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:40:36,994 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:40:36,996 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:40:36,997 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:40:42,203 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:40:42,621 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:40:42,621 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:40:44,473 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:40:44,475 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:40:44,475 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:40:48,431 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:40:48,669 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:40:48,669 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:40:50,725 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:40:50,730 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:40:50,730 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:40:52,537 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:41:30,450 INFO    MainThread:34 [wandb_run.py:_config_callback():1347] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['Wav2Vec2ForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 0, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/wav2vec2-base', 'transformers_version': '4.39.3', 'freeze_feat_extract_train': True, 'mask_channel_length': 10, 'mask_channel_min_space': 1, 'mask_channel_other': 0.0, 'mask_channel_prob': 0.0, 'mask_channel_selection': 'static', 'mask_time_min_space': 1, 'mask_time_other': 0.0, 'mask_time_selection': 'static', 'model_type': 'wav2vec2', 'no_mask_channel_overlap': False, 'no_mask_time_overlap': False, 'num_feat_extract_layers': 7, 'hidden_size': 768, 'feat_extract_norm': 'group', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': False, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 12, 'intermediate_size': 3072, 'hidden_act': 'gelu', 'num_attention_heads': 12, 'hidden_dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'feat_proj_dropout': 0.1, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 32, 'do_stable_layer_norm': False, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.05, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 256, 'proj_codevector_dim': 256, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'sum', 'ctc_zero_infinity': False, 'add_adapter': False, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 768, 'adapter_attn_dim': None, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 64, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0001, 'weight_decay': 0.005, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 30, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/May24_20-40-48_890e8b3ca76b', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 2, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': True, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
+2024-05-24 20:41:39,043 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:41:39,044 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:42:26,950 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:42:27,128 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:42:27,128 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:42:29,871 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:43:07,276 INFO    MainThread:34 [wandb_run.py:_config_callback():1347] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['Wav2Vec2ForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 0, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/wav2vec2-base', 'transformers_version': '4.39.3', 'freeze_feat_extract_train': True, 'mask_channel_length': 10, 'mask_channel_min_space': 1, 'mask_channel_other': 0.0, 'mask_channel_prob': 0.0, 'mask_channel_selection': 'static', 'mask_time_min_space': 1, 'mask_time_other': 0.0, 'mask_time_selection': 'static', 'model_type': 'wav2vec2', 'no_mask_channel_overlap': False, 'no_mask_time_overlap': False, 'num_feat_extract_layers': 7, 'hidden_size': 768, 'feat_extract_norm': 'group', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': False, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 12, 'intermediate_size': 3072, 'hidden_act': 'gelu', 'num_attention_heads': 12, 'hidden_dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'feat_proj_dropout': 0.1, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 32, 'do_stable_layer_norm': False, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.05, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 256, 'proj_codevector_dim': 256, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'sum', 'ctc_zero_infinity': False, 'add_adapter': False, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 768, 'adapter_attn_dim': None, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 16, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0001, 'weight_decay': 0.005, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 30, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/May24_20-42-26_890e8b3ca76b', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 2, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': True, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
+2024-05-24 20:43:12,247 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:43:12,247 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:44:08,643 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:44:14,294 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:44:14,295 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:44:39,719 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:44:39,770 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:44:39,770 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:44:43,543 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:46:31,143 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:46:31,143 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:46:49,361 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:46:49,391 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:46:49,391 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:46:52,169 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:46:54,391 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:46:54,391 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:46:58,317 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:46:58,322 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:46:58,322 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:47:06,482 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:47:07,830 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:47:07,830 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:47:10,833 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:47:10,835 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:47:10,839 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:47:14,002 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:48:02,460 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:48:02,460 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:48:05,731 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:48:05,733 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:48:05,734 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:48:08,287 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:48:08,714 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:48:08,714 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:48:10,290 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:48:10,293 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:48:10,294 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:48:13,841 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:48:14,091 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:48:14,092 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:48:16,125 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:48:40,373 INFO    MainThread:34 [wandb_run.py:_config_callback():1347] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['Wav2Vec2ForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 0, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/wav2vec2-base', 'transformers_version': '4.39.3', 'freeze_feat_extract_train': True, 'mask_channel_length': 10, 'mask_channel_min_space': 1, 'mask_channel_other': 0.0, 'mask_channel_prob': 0.0, 'mask_channel_selection': 'static', 'mask_time_min_space': 1, 'mask_time_other': 0.0, 'mask_time_selection': 'static', 'model_type': 'wav2vec2', 'no_mask_channel_overlap': False, 'no_mask_time_overlap': False, 'num_feat_extract_layers': 7, 'hidden_size': 768, 'feat_extract_norm': 'group', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': False, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 12, 'intermediate_size': 3072, 'hidden_act': 'gelu', 'num_attention_heads': 12, 'hidden_dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'feat_proj_dropout': 0.1, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 32, 'do_stable_layer_norm': False, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.05, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 256, 'proj_codevector_dim': 256, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'sum', 'ctc_zero_infinity': False, 'add_adapter': False, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 768, 'adapter_attn_dim': None, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 16, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0001, 'weight_decay': 0.005, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 30, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/May24_20-48-13_890e8b3ca76b', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 2, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': True, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
+2024-05-24 20:48:42,631 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:48:42,632 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:49:00,381 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:49:00,425 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:49:00,425 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:49:03,721 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:49:03,725 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:49:03,726 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:49:08,089 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:49:08,455 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:49:08,456 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:51:52,779 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:51:52,781 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:51:52,781 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:51:56,593 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:52:22,759 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:52:22,759 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:52:49,570 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend
+2024-05-24 20:52:49,572 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-05-24 20:52:49,572 INFO    MainThread:34 [wandb_init.py:_pause_backend():432] pausing backend
+2024-05-24 20:52:52,107 INFO    MainThread:34 [wandb_init.py:_resume_backend():437] resuming backend