Training in progress, epoch 0

config.json

@@ -1,19 +1,13 @@
 {
-  "_name_or_path": "facebook/wav2vec2-base",
-  "activation_dropout": 0.0,
-  "adapter_attn_dim": null,
-  "adapter_kernel_size": 3,
-  "adapter_stride": 2,
-  "add_adapter": false,
+  "_name_or_path": "facebook/hubert-base-ls960",
+  "activation_dropout": 0.1,
   "apply_spec_augment": true,
   "architectures": [
-    "Wav2Vec2ForSequenceClassification"
+    "HubertForSequenceClassification"
   ],
   "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,
@@ -44,17 +38,18 @@
   ],
   "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_dropout": 0.0,
   "feat_extract_norm": "group",
   "feat_proj_dropout": 0.1,
-  "feat_quantizer_dropout": 0.0,
-  "final_dropout": 0.0,
-  "freeze_feat_extract_train": true,
+  "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": "abroad",
@@ -91,60 +86,23 @@
     "pay_bill": "13"
   },
   "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",
+  "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_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,
+  "model_type": "hubert",
   "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
-  ],
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.46.2",
   "use_weighted_layer_sum": false,
-  "vocab_size": 32,
-  "xvector_output_dim": 512
+  "vocab_size": 32
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af3a8ba106fce6462688fc9da5b1a7d4bb58e6723b9f6db6a6421c9e5c6c626b
-size 378314704
+oid sha256:539a3300ddc5838035d92646911c754f12850c220be2e84cb57b5716f450daf2
+size 378314288

preprocessor_config.json

@@ -3,7 +3,7 @@
   "feature_extractor_type": "Wav2Vec2FeatureExtractor",
   "feature_size": 1,
   "padding_side": "right",
-  "padding_value": 0.0,
+  "padding_value": 0,
   "return_attention_mask": false,
   "sampling_rate": 16000
 }

runs/Nov21_10-22-43_4ea088996f90/events.out.tfevents.1732184564.4ea088996f90.906.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce9cb6d3ea13edd34f84fc24bbcd7edd6f5bd3641a8b3bad8f96e1022cbc3f04
+size 6996

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2570805406795615320a5ae726ba3c09b01ae6bb37f30351c40d2fabaa845c6d
+oid sha256:91250d33015def1b55b35eaa0c730b2e9aa110ea242b18a8a8cfaaa6d76f4a1c
 size 5304