Training in progress, epoch 1

.gitignore

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

config.json

@@ -0,0 +1,100 @@
+{
+  "_name_or_path": "facebook/hubert-base-ls960",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "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,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "blues",
+    "1": "classical",
+    "2": "country",
+    "3": "disco",
+    "4": "hiphop",
+    "5": "jazz",
+    "6": "metal",
+    "7": "pop",
+    "8": "reggae",
+    "9": "rock"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "blues": "0",
+    "classical": "1",
+    "country": "2",
+    "disco": "3",
+    "hiphop": "4",
+    "jazz": "5",
+    "metal": "6",
+    "pop": "7",
+    "reggae": "8",
+    "rock": "9"
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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_prob": 0.05,
+  "model_type": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

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:bb892fbf2cc9bf29c59bf6839df2620b06688de38b5bb2c0b5cc05be63328831
+size 378358249

runs/Mar13_11-38-44_thestallion/events.out.tfevents.1710347933.thestallion.118733.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6229cfdff4b32dd37bc081d0317526e86329204d69af4d36c0abf2d83aeb59
+size 5705

runs/Mar13_11-46-17_thestallion/events.out.tfevents.1710348382.thestallion.118733.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ada88d9e3f8961b61e7d63a71f839d85a941a665c1c4b2b9ed704e5fa2ae6db9
+size 5397

runs/Mar13_11-46-46_thestallion/events.out.tfevents.1710348413.thestallion.134296.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca8c5e512ae2323edc12340c4499b0262ea0edea73bb0b397b5610c6bbacb434
+size 12710

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d051d7fd6f0b80ba39ecb5d425622f08f8254c2924d16e0abc824cd2131844a8
+size 4027