Training in progress, epoch 1

config.json

@@ -1,13 +1,19 @@
 {
-  "_name_or_path": "TencentGameMate/chinese-hubert-base",
-  "activation_dropout": 0.1,
+  "_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": [
-    "HubertForSequenceClassification"
+    "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,
@@ -38,13 +44,15 @@
   ],
   "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": 0.0,
-  "feat_proj_layer_norm": true,
-  "final_dropout": 0.1,
+  "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,
@@ -61,22 +69,60 @@
     "LABEL_2": 2
   },
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.1,
+  "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,
-  "model_type": "hubert",
+  "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": "4.40.2",
   "use_weighted_layer_sum": false,
-  "vocab_size": 32
+  "vocab_size": 32,
+  "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31ce70957ca20dc5d5dad9711ad3619371cc9f9e39d8516e88a56c8c9426ebcc
-size 378302924
+oid sha256:6e639bab791a1b5ad8b41d7dc9d59d02aa2dfa77c1b0e7e6cd16f748795157a3
+size 378303340

preprocessor_config.json

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

runs/Jun26_17-38-26_WIN-CEJF2NB9KFH/events.out.tfevents.1719394706.WIN-CEJF2NB9KFH.85300.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fa660591aba462f5c2a80cbcef8c810ddca03d5d387c5234b99cbd0445e9d52
-size 6143
+oid sha256:4bab15b26b88a1633a77a88540355bd2b494c697afed12e6f243e8b713d0ba0b
+size 13953

runs/Jun26_17-53-35_WIN-CEJF2NB9KFH/events.out.tfevents.1719395616.WIN-CEJF2NB9KFH.91860.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e01fd182e53b2f861a79c60d045350fa1cd366b032e8b1fd6a4c5427d0b0870
+size 14894

runs/Jun26_19-08-23_WIN-CEJF2NB9KFH/events.out.tfevents.1719400104.WIN-CEJF2NB9KFH.37732.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ddd750d1a331dd184e49b258932dae1fbf204beab283d21310c1c032fcb9715
+size 7083

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16d09aeeac4d6ba704bfef04a5c6b9793695e70fc996fec39517e0fe89a7fc3d
+oid sha256:e520fa03092f74f79776e945f260abbc663c6fe792e530708e14eb35d1af337c
 size 4539