Training in progress, step 400

config.json

@@ -1,6 +1,6 @@
 {
-  "_name_or_path": "facebook/wav2vec2-lv-60-espeak-cv-ft",
-  "activation_dropout": 0.0,
+  "_name_or_path": "facebook/wav2vec2-base-960h",
+  "activation_dropout": 0.1,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
@@ -12,9 +12,9 @@
   "attention_dropout": 0.1,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
-  "codevector_dim": 768,
+  "codevector_dim": 256,
   "contrastive_logits_temperature": 0.1,
-  "conv_bias": true,
+  "conv_bias": false,
   "conv_dim": [
     512,
     512,
@@ -45,49 +45,42 @@
   "ctc_loss_reduction": "sum",
   "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": 0.1,
   "feat_quantizer_dropout": 0.0,
-  "final_dropout": 0.0,
+  "final_dropout": 0.1,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout": 0.1,
-  "hidden_size": 1024,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
   "layerdrop": 0.1,
-  "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": 0.075,
-  "mask_time_selection": "static",
+  "mask_time_prob": 0.05,
   "model_type": "wav2vec2",
   "num_adapter_layers": 3,
-  "num_attention_heads": 16,
+  "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,
-  "output_hidden_size": 1024,
+  "output_hidden_size": 768,
   "pad_token_id": 0,
-  "proj_codevector_dim": 768,
+  "proj_codevector_dim": 256,
   "tdnn_dilation": [
     1,
     2,
@@ -112,6 +105,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
   "use_weighted_layer_sum": false,
-  "vocab_size": 392,
+  "vocab_size": 32,
   "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:588566a0dfafd72bafb4f283c2f95c69ea5aaf4a32c513a8bbd848324e09adf7
-size 1263414696
+oid sha256:1fabe1965c716285702c30030261737f96be611387d4346a6a356e84084b0b5c
+size 377611120

preprocessor_config.json

@@ -3,7 +3,7 @@
   "feature_extractor_type": "Wav2Vec2FeatureExtractor",
   "feature_size": 1,
   "padding_side": "right",
-  "padding_value": 0,
-  "return_attention_mask": true,
+  "padding_value": 0.0,
+  "return_attention_mask": false,
   "sampling_rate": 16000
 }

runs/Nov24_20-04-08_70a23f304436/events.out.tfevents.1700856475.70a23f304436.905.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06226d59b114e762595f11543e50d01e3b1d7849f514136d0141817b9e615517
+size 341

runs/Nov24_20-25-14_70a23f304436/events.out.tfevents.1700857631.70a23f304436.905.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a179ff7553d087a324b65a87cf8e6e0fc32c61fa3be611dcb7ca6bdbba94abb0
+size 6213

runs/Nov24_20-31-47_70a23f304436/events.out.tfevents.1700857982.70a23f304436.905.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:315d6518dc935979d404f7a1ddb059be2362cde70a0e8e703ea91bdf583fdc4a
+size 6183

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3214461b60f957150fefd8a20ce955a44eb28e501dee46d30ed3456c368cf7e
+oid sha256:2132510865f69e7cadbb8a443c03f5e4c815e6b8926bcf44b38a29bccda47bc0
 size 4600