Training in progress, step 50

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,325 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "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": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "finetuning_task": "audio-classification",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Afrikaans",
+    "1": "Amharic",
+    "2": "Arabic",
+    "3": "Assamese",
+    "4": "Asturian",
+    "5": "Azerbaijani",
+    "6": "Belarusian",
+    "7": "Bulgarian",
+    "8": "Bengali",
+    "9": "Bosnian",
+    "10": "Catalan",
+    "11": "Cebuano",
+    "12": "Sorani-Kurdish",
+    "13": "Mandarin Chinese",
+    "14": "Czech",
+    "15": "Welsh",
+    "16": "Danish",
+    "17": "German",
+    "18": "Greek",
+    "19": "English",
+    "20": "Spanish",
+    "21": "Estonian",
+    "22": "Persian",
+    "23": "Fula",
+    "24": "Finnish",
+    "25": "Filipino",
+    "26": "French",
+    "27": "Irish",
+    "28": "Galician",
+    "29": "Gujarati",
+    "30": "Hausa",
+    "31": "Hebrew",
+    "32": "Hindi",
+    "33": "Croatian",
+    "34": "Hungarian",
+    "35": "Armenian",
+    "36": "Indonesian",
+    "37": "Igbo",
+    "38": "Icelandic",
+    "39": "Italian",
+    "40": "Japanese",
+    "41": "Javanese",
+    "42": "Georgian",
+    "43": "Kamba",
+    "44": "Kabuverdianu",
+    "45": "Kazakh",
+    "46": "Khmer",
+    "47": "Kannada",
+    "48": "Korean",
+    "49": "Kyrgyz",
+    "50": "Luxembourgish",
+    "51": "Ganda",
+    "52": "Lingala",
+    "53": "Lao",
+    "54": "Lithuanian",
+    "55": "Luo",
+    "56": "Latvian",
+    "57": "Maori",
+    "58": "Macedonian",
+    "59": "Malayalam",
+    "60": "Mongolian",
+    "61": "Marathi",
+    "62": "Malay",
+    "63": "Maltese",
+    "64": "Burmese",
+    "65": "Norwegian",
+    "66": "Nepali",
+    "67": "Dutch",
+    "68": "Northern-Sotho",
+    "69": "Nyanja",
+    "70": "Occitan",
+    "71": "Oromo",
+    "72": "Oriya",
+    "73": "Punjabi",
+    "74": "Polish",
+    "75": "Pashto",
+    "76": "Portuguese",
+    "77": "Romanian",
+    "78": "Russian",
+    "79": "Sindhi",
+    "80": "Slovak",
+    "81": "Slovenian",
+    "82": "Shona",
+    "83": "Somali",
+    "84": "Serbian",
+    "85": "Swedish",
+    "86": "Swahili",
+    "87": "Tamil",
+    "88": "Telugu",
+    "89": "Tajik",
+    "90": "Thai",
+    "91": "Turkish",
+    "92": "Ukrainian",
+    "93": "Umbundu",
+    "94": "Urdu",
+    "95": "Uzbek",
+    "96": "Vietnamese",
+    "97": "Wolof",
+    "98": "Xhosa",
+    "99": "Yoruba",
+    "100": "Cantonese Chinese",
+    "101": "Zulu"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "Afrikaans": 0,
+    "Amharic": 1,
+    "Arabic": 2,
+    "Armenian": 35,
+    "Assamese": 3,
+    "Asturian": 4,
+    "Azerbaijani": 5,
+    "Belarusian": 6,
+    "Bengali": 8,
+    "Bosnian": 9,
+    "Bulgarian": 7,
+    "Burmese": 64,
+    "Cantonese Chinese": 100,
+    "Catalan": 10,
+    "Cebuano": 11,
+    "Croatian": 33,
+    "Czech": 14,
+    "Danish": 16,
+    "Dutch": 67,
+    "English": 19,
+    "Estonian": 21,
+    "Filipino": 25,
+    "Finnish": 24,
+    "French": 26,
+    "Fula": 23,
+    "Galician": 28,
+    "Ganda": 51,
+    "Georgian": 42,
+    "German": 17,
+    "Greek": 18,
+    "Gujarati": 29,
+    "Hausa": 30,
+    "Hebrew": 31,
+    "Hindi": 32,
+    "Hungarian": 34,
+    "Icelandic": 38,
+    "Igbo": 37,
+    "Indonesian": 36,
+    "Irish": 27,
+    "Italian": 39,
+    "Japanese": 40,
+    "Javanese": 41,
+    "Kabuverdianu": 44,
+    "Kamba": 43,
+    "Kannada": 47,
+    "Kazakh": 45,
+    "Khmer": 46,
+    "Korean": 48,
+    "Kyrgyz": 49,
+    "Lao": 53,
+    "Latvian": 56,
+    "Lingala": 52,
+    "Lithuanian": 54,
+    "Luo": 55,
+    "Luxembourgish": 50,
+    "Macedonian": 58,
+    "Malay": 62,
+    "Malayalam": 59,
+    "Maltese": 63,
+    "Mandarin Chinese": 13,
+    "Maori": 57,
+    "Marathi": 61,
+    "Mongolian": 60,
+    "Nepali": 66,
+    "Northern-Sotho": 68,
+    "Norwegian": 65,
+    "Nyanja": 69,
+    "Occitan": 70,
+    "Oriya": 72,
+    "Oromo": 71,
+    "Pashto": 75,
+    "Persian": 22,
+    "Polish": 74,
+    "Portuguese": 76,
+    "Punjabi": 73,
+    "Romanian": 77,
+    "Russian": 78,
+    "Serbian": 84,
+    "Shona": 82,
+    "Sindhi": 79,
+    "Slovak": 80,
+    "Slovenian": 81,
+    "Somali": 83,
+    "Sorani-Kurdish": 12,
+    "Spanish": 20,
+    "Swahili": 86,
+    "Swedish": 85,
+    "Tajik": 89,
+    "Tamil": 87,
+    "Telugu": 88,
+    "Thai": 90,
+    "Turkish": 91,
+    "Ukrainian": 92,
+    "Umbundu": 93,
+    "Urdu": 94,
+    "Uzbek": 95,
+    "Vietnamese": 96,
+    "Welsh": 15,
+    "Wolof": 97,
+    "Xhosa": 98,
+    "Yoruba": 99,
+    "Zulu": 101
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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": 0.075,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "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": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 768,
+  "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": "4.27.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

preprocessor_config.json

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

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7c3fa369184f0abc415fa689f114d8b2ab28ebe8a268b8e0d54f22cb9570f79
+size 1263056949

runs/Feb14_08-52-09_sanchit-t4-fleurs/1676364755.1343477/events.out.tfevents.1676364755.sanchit-t4-fleurs.22843.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03dbd767e7a489cb4bdb8987be7819b06ef4d1dbaad03f61063893d8cbcfe702
+size 5787

runs/Feb14_08-52-09_sanchit-t4-fleurs/events.out.tfevents.1676364755.sanchit-t4-fleurs.22843.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bdfe219194b90e4c8767dc96c72007c4dea92c66a472e245308322be20edf57
+size 10835

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0296f4edb1371079dce6e9092845091c8c0d7b8f17e1fd4cef32baee56d97d4c
+size 3579