Training in progress, epoch 0

config.json

@@ -1,13 +1,19 @@
 {
-  "_name_or_path": "ntu-spml/distilhubert",
-  "activation_dropout": 0.1,
-  "apply_spec_augment": false,
+  "_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": false,
+  "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,
@@ -64,21 +72,59 @@
   },
   "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,
-  "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": 2,
+  "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": "4.38.1",
   "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:aec7ed1beeb937916d25a88936f61427066d2542b9891a93880b10979623c9ac
-size 94765560
+oid sha256:9c854dbd39936d8411dd320a685808690cf8086c42556fe79b1cb181a053d2d2
+size 378304424

preprocessor_config.json

@@ -1,9 +1,9 @@
 {
-  "do_normalize": false,
+  "do_normalize": true,
   "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/Feb29_08-22-01_voice-ai-transformer/events.out.tfevents.1709194926.voice-ai-transformer.1807516.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b65040dc06cf046682eb8e0546ba2ea50a168163c389f1e6d37a20dc0ea8575c
+size 6758

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c256601f90d19614335b4e541755e33a91df2ff1dcef7a838fe3877398e461c5
+oid sha256:58e18cb8c5e03b6d494d015bc384937b13748e9503ddf1c56e6e6242ebfcf95f
 size 4920