Training in progress, step 100

config.json

@@ -1,16 +1,19 @@
 {
-  "_name_or_path": "CuongLD/wav2vec2-large-xlsr-vietnamese",
+  "_name_or_path": "nguyenvulebinh/wav2vec2-base-vi-vlsp2020",
   "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
   "apply_spec_augment": true,
   "architectures": [
     "Wav2Vec2ForCTC"
   ],
-  "attention_dropout": 0.0,
+  "attention_dropout": 0.05,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
   "codevector_dim": 256,
   "contrastive_logits_temperature": 0.1,
-  "conv_bias": true,
+  "conv_bias": false,
   "conv_dim": [
     512,
     512,
@@ -41,46 +44,65 @@
   "ctc_loss_reduction": "mean",
   "ctc_zero_infinity": false,
   "diversity_loss_weight": 0.1,
-  "do_stable_layer_norm": true,
+  "do_stable_layer_norm": false,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
   "feat_extract_dropout": 0.0,
-  "feat_extract_norm": "layer",
+  "feat_extract_norm": "group",
   "feat_proj_dropout": 0.0,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.0,
-  "hidden_size": 1024,
+  "hidden_dropout": 0.05,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "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_space": 1,
-  "mask_time_other": 0.0,
+  "mask_time_min_masks": 2,
   "mask_time_prob": 0.05,
-  "mask_time_selection": "static",
   "model_type": "wav2vec2",
-  "num_attention_heads": 16,
+  "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": 24,
+  "num_hidden_layers": 12,
   "num_negatives": 100,
-  "pad_token_id": 89,
+  "output_hidden_size": 768,
+  "pad_token_id": 95,
   "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": "4.11.3",
+  "transformers_version": "4.20.0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 92
+  "vocab_size": 98,
+  "xvector_output_dim": 512
 }

preprocessor_config.json

@@ -4,6 +4,7 @@
   "feature_size": 1,
   "padding_side": "right",
   "padding_value": 0.0,
-  "return_attention_mask": true,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "return_attention_mask": false,
   "sampling_rate": 16000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d04e270b7a021a4b0ccbe014ff2499cb1cc802fc02dff495bcf1273773f5672
-size 1262300849
+oid sha256:6f438a114bdc1dc057a606f298bd870f6b9ec7a954c7712eb32f73181472f837
+size 384990573

runs/Jan17_05-57-20_dfa34576fb6a/1673935499.4076784/events.out.tfevents.1673935499.dfa34576fb6a.22.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ed81d74dc323b7017d2c8cf0eb8dbea97cbecd841f52e39cd6b00a6f85bcb1
+size 5323

runs/Jan17_05-57-20_dfa34576fb6a/events.out.tfevents.1673935499.dfa34576fb6a.22.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b7659c875a6c826e39b1116b8d6a2c6fc61115ab8397a329092fd5a61e65bfd
+size 5488

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac1dac58ea4b4a7dafc2e844e7f7f0515a327dbfa8628dd4068416ff55397fee
-size 2799
+oid sha256:83c094825a2dc05c9cc06527ba032c5aec49a72dc58f517badb41d17c72f093e
+size 3247