Training in progress, step 272

.gitignore

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

config.json

@@ -0,0 +1,214 @@
+{
+  "_name_or_path": "bayartsogt/wav2vec2-base-mn-pretrain-42h",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "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": 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,
+  "id2label": {
+    "0": "teg",
+    "1": "neg",
+    "2": "hoyor",
+    "3": "gurav",
+    "4": "dorov",
+    "5": "tav",
+    "6": "zurgaa",
+    "7": "doloo",
+    "8": "naim",
+    "9": "yos",
+    "10": "yes",
+    "11": "no",
+    "12": "up",
+    "13": "down",
+    "14": "left",
+    "15": "right",
+    "16": "on",
+    "17": "off",
+    "18": "stop",
+    "19": "go",
+    "20": "zero",
+    "21": "one",
+    "22": "two",
+    "23": "three",
+    "24": "four",
+    "25": "five",
+    "26": "six",
+    "27": "seven",
+    "28": "eight",
+    "29": "nine",
+    "30": "bed",
+    "31": "bird",
+    "32": "cat",
+    "33": "dog",
+    "34": "happy",
+    "35": "house",
+    "36": "marvin",
+    "37": "sheila",
+    "38": "tree",
+    "39": "wow",
+    "40": "backward",
+    "41": "forward",
+    "42": "follow",
+    "43": "learn",
+    "44": "visual",
+    "45": "_silence_"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "_silence_": 45,
+    "backward": 40,
+    "bed": 30,
+    "bird": 31,
+    "cat": 32,
+    "dog": 33,
+    "doloo": 7,
+    "dorov": 4,
+    "down": 13,
+    "eight": 28,
+    "five": 25,
+    "follow": 42,
+    "forward": 41,
+    "four": 24,
+    "go": 19,
+    "gurav": 3,
+    "happy": 34,
+    "house": 35,
+    "hoyor": 2,
+    "learn": 43,
+    "left": 14,
+    "marvin": 36,
+    "naim": 8,
+    "neg": 1,
+    "nine": 29,
+    "no": 11,
+    "off": 17,
+    "on": 16,
+    "one": 21,
+    "right": 15,
+    "seven": 27,
+    "sheila": 37,
+    "six": 26,
+    "stop": 18,
+    "tav": 5,
+    "teg": 0,
+    "three": 23,
+    "tree": 38,
+    "two": 22,
+    "up": 12,
+    "visual": 44,
+    "wow": 39,
+    "yes": 10,
+    "yos": 9,
+    "zero": 20,
+    "zurgaa": 6
+  },
+  "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": "4.30.2",
+  "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": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d79968947259d1560321b880d4d255f2121812ed21b8dd5b13971aba42dfca30
+size 378395625

runs/Aug11_18-35-51_3964b69a31b0/events.out.tfevents.1691778984.3964b69a31b0.29.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed62fc73be3223195fb1fbb42812cae7d7e160c15066e2396224e24190fe1785
+size 12156

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2d63feabcdd4fe27f251fb33dcff5122c6a724a12d27079176ba42e7a938231
+size 4027