Training in progress, epoch 1

config.json

@@ -1,13 +1,19 @@
 {
-  "_name_or_path": "TencentGameMate/chinese-hubert-base",
+  "_name_or_path": "facebook/wav2vec2-base-960h",
   "activation_dropout": 0.1,
+  "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,
@@ -38,15 +44,19 @@
   ],
   "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": 0.0,
-  "feat_proj_layer_norm": true,
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.1,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0",
@@ -68,15 +78,43 @@
   "mask_time_length": 10,
   "mask_time_min_masks": 2,
   "mask_time_prob": 0.05,
-  "model_type": "hubert",
+  "model_type": "wav2vec2",
+  "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 sha256:09eae53f786a9f2b6b4388b8e6a1e8f14924856760f7a85f72f82cb4b1a16fea
-size 378302924
+oid sha256:25953404b2e53278ea639ac217bdbe55280c2e17382a8f6fabc64b3a5c317811
+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_19-50-29_WIN-CEJF2NB9KFH/events.out.tfevents.1719402630.WIN-CEJF2NB9KFH.22620.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d582021340cca9ebe1fc388a455b3c4087ed185bc723fd627de5837923def8db
-size 6143
+oid sha256:edc3fab3ac9286f1dfcacd5706829f8f3163684a4cc0f9b37d9ef642074e42b5
+size 16623

runs/Jun26_20-10-34_WIN-CEJF2NB9KFH/events.out.tfevents.1719403834.WIN-CEJF2NB9KFH.90888.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:921ed22ef9423a8041bd77c442276e8fb5de9f88152fff5ed46ba4010c334e4d
+size 6309

runs/Jun26_20-25-17_WIN-CEJF2NB9KFH/events.out.tfevents.1719404718.WIN-CEJF2NB9KFH.103028.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59137a25f699f33c70e3231de7e71e0a8851234990d09ee5a7e9563e3ff30c62
+size 6827

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:855af6a7997f2ff63e34d7c2cfb56ba1a2250807246fba5594465d97bd67bc37
+oid sha256:897260c8505bfa227f769b3a26006d2fc0d2796781ca13e334e5c9f33a3d5510
 size 4539