Training in progress, step 500

config.json

@@ -1,19 +1,14 @@
 {
-  "_name_or_path": "facebook/wav2vec2-base",
-  "activation_dropout": 0.0,
-  "adapter_kernel_size": 3,
-  "adapter_stride": 2,
-  "add_adapter": false,
+  "_name_or_path": "facebook/hubert-large-ls960-ft",
+  "activation_dropout": 0.1,
   "apply_spec_augment": true,
   "architectures": [
-    "Wav2Vec2ForCTC"
+    "HubertForCTC"
   ],
   "attention_dropout": 0.1,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
-  "codevector_dim": 256,
-  "contrastive_logits_temperature": 0.1,
-  "conv_bias": false,
+  "conv_bias": true,
   "conv_dim": [
     512,
     512,
@@ -44,74 +39,37 @@
   "ctc_loss_reduction": "mean",
   "ctc_zero_infinity": false,
   "diversity_loss_weight": 0.1,
-  "do_stable_layer_norm": false,
+  "do_stable_layer_norm": true,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
-  "feat_extract_norm": "group",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
   "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,
   "hidden_act": "gelu",
   "hidden_dropout": 0.1,
-  "hidden_size": 768,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "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,
-  "num_attention_heads": 12,
-  "num_codevector_groups": 2,
-  "num_codevectors_per_group": 320,
+  "model_type": "hubert",
+  "num_attention_heads": 16,
   "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,
+  "num_hidden_layers": 24,
   "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": "4.15.0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 32,
-  "xvector_output_dim": 512
+  "vocab_size": 32
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7051aaffc713d8249fdeb2e1733b79a42c5e58640e68018e56a4e358e4abc88d
-size 377670039
+oid sha256:a7ffbc95bff5bb9cab9ab34e1cef865fa1eab43ef600ee3bd0927ef70dd3b1eb
+size 1262053361

runs/Dec29_12-57-55_rkmtk2/1640750517.3995166/events.out.tfevents.1640750517.rkmtk2.194273.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab449a474a04ab2b292d0d8a038961f1150e4a5bd6aaf7730a5a11fdba351041
+size 4766

runs/Dec29_12-57-55_rkmtk2/events.out.tfevents.1640750517.rkmtk2.194273.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60d081717be6c07926a013b048300205ac642b61688438f9394078703ae404c9
+size 4634

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9e8409310be2f8f074f76a8a5c224e6c48341cb39e13934ae5cf52a7580324a
+oid sha256:070dd7f9f857e80b5fe27d28815577b2a14535c6256e5acf3d7283c1b44b2ee2
 size 2927