Training in progress, epoch 0

config.json

@@ -1,6 +1,6 @@
 {
-  "_name_or_path": "facebook/wav2vec2-base",
-  "activation_dropout": 0.0,
+  "_name_or_path": "nguyenvulebinh/wav2vec2-base-vietnamese-250h",
+  "activation_dropout": 0.1,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
@@ -42,19 +42,20 @@
     2,
     2
   ],
-  "ctc_loss_reduction": "sum",
+  "ctc_loss_reduction": "mean",
   "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": 0.1,
   "feat_quantizer_dropout": 0.0,
-  "final_dropout": 0.0,
-  "freeze_feat_extract_train": true,
+  "final_dropout": 0.1,
   "hidden_act": "gelu",
   "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
     "0": "ngang",
@@ -75,24 +76,14 @@
     "sac": 1
   },
   "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,
@@ -103,7 +94,7 @@
   "num_hidden_layers": 12,
   "num_negatives": 100,
   "output_hidden_size": 768,
-  "pad_token_id": 0,
+  "pad_token_id": 109,
   "proj_codevector_dim": 256,
   "tdnn_dilation": [
     1,
@@ -129,6 +120,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.31.0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 32,
+  "vocab_size": 110,
   "xvector_output_dim": 512
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a908b699426c17ece3c7200f9a27ed9f3671727a83b5b7714cdaa202142fad3
+oid sha256:e1e0d62feb56f9e82317ac8b56a25e960029df39be054f8afd44f9b5b750e2e5
 size 378354537

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:668b2e01eadad0202c49fb12b24606827e25baa7a1a0c6ceae2c1c5b4e90dd27
+oid sha256:cc1d1eb7ba186b12a0cd47765395233617259d6f2a3846476fabadd718c55461
 size 3963