Training in progress, step 200

config.json

@@ -1,13 +1,19 @@
 {
-  "_name_or_path": "hiba2/hybird_hubert_transformer40",
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
   "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
   "apply_spec_augment": true,
   "architectures": [
-    "HubertForCTC"
+    "Wav2Vec2ForCTC"
   ],
-  "attention_dropout": 0.0,
+  "attention_dropout": 0.1,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
   "conv_bias": true,
   "conv_dim": [
     512,
@@ -37,23 +43,24 @@
     2
   ],
   "ctc_loss_reduction": "mean",
-  "ctc_zero_infinity": true,
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
   "do_stable_layer_norm": true,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
   "feat_extract_dropout": 0.0,
   "feat_extract_norm": "layer",
   "feat_proj_dropout": 0.0,
-  "feat_proj_layer_norm": true,
+  "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.0,
+  "hidden_dropout": 0.1,
   "hidden_size": 1024,
   "initializer_range": 0.02,
   "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
+  "layerdrop": 0.1,
   "mask_channel_length": 10,
   "mask_channel_min_space": 1,
   "mask_channel_other": 0.0,
@@ -68,16 +75,43 @@
   "mask_time_other": 0.0,
   "mask_time_prob": 0.05,
   "mask_time_selection": "static",
-  "model_type": "hubert",
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
   "num_attention_heads": 16,
+  "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": 24,
-  "pad_token_id": 109,
-  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 104,
+  "proj_codevector_dim": 768,
+  "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": "4.45.0.dev0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 112
+  "vocab_size": 107,
+  "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db7a016164732d45ea060a16b4a76e03b73be1b1f2e6cb80d2db9d85601cc0d8
-size 1262265848
+oid sha256:95a2631f93bb19b8d71ca557831d84493cc97a326a4bc4babf49615a2347b013
+size 1262246180

runs/Sep18_22-40-40_3e3dee49a124/events.out.tfevents.1726699732.3e3dee49a124.1102.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd8fc946106bb6168fb6124b19ef968716fd870e6ae8e83c32307516c446d677
-size 11361
+oid sha256:36bf3d20fd477068e1fd59a530a4d9d029bee05c7e7ced176306e36d21a14d1e
+size 11890

runs/Sep18_22-40-40_3e3dee49a124/events.out.tfevents.1726704060.3e3dee49a124.1102.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6a14584f93fc786857043b7e967e4c0e38f23090f4f5a02b8505f433446d359
+size 7659