Training in progress, step 50
Browse files- config.json +11 -11
- model.safetensors +2 -2
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_attn_dim": null,
|
5 |
"adapter_kernel_size": 3,
|
@@ -12,7 +12,7 @@
|
|
12 |
"attention_dropout": 0.0,
|
13 |
"bos_token_id": 1,
|
14 |
"classifier_proj_size": 256,
|
15 |
-
"codevector_dim":
|
16 |
"contrastive_logits_temperature": 0.1,
|
17 |
"conv_bias": true,
|
18 |
"conv_dim": [
|
@@ -56,17 +56,17 @@
|
|
56 |
"gradient_checkpointing": false,
|
57 |
"hidden_act": "gelu",
|
58 |
"hidden_dropout": 0.0,
|
59 |
-
"hidden_size":
|
60 |
"initializer_range": 0.02,
|
61 |
-
"intermediate_size":
|
62 |
"layer_norm_eps": 1e-05,
|
63 |
-
"layerdrop": 0.
|
64 |
"mask_feature_length": 10,
|
65 |
"mask_feature_min_masks": 0,
|
66 |
"mask_feature_prob": 0.0,
|
67 |
"mask_time_length": 10,
|
68 |
"mask_time_min_masks": 2,
|
69 |
-
"mask_time_prob": 0.
|
70 |
"model_type": "wav2vec2",
|
71 |
"num_adapter_layers": 3,
|
72 |
"num_attention_heads": 16,
|
@@ -75,11 +75,11 @@
|
|
75 |
"num_conv_pos_embedding_groups": 16,
|
76 |
"num_conv_pos_embeddings": 128,
|
77 |
"num_feat_extract_layers": 7,
|
78 |
-
"num_hidden_layers":
|
79 |
"num_negatives": 100,
|
80 |
-
"output_hidden_size":
|
81 |
-
"pad_token_id":
|
82 |
-
"proj_codevector_dim":
|
83 |
"tdnn_dilation": [
|
84 |
1,
|
85 |
2,
|
@@ -104,6 +104,6 @@
|
|
104 |
"torch_dtype": "float32",
|
105 |
"transformers_version": "4.40.2",
|
106 |
"use_weighted_layer_sum": false,
|
107 |
-
"vocab_size":
|
108 |
"xvector_output_dim": 512
|
109 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-xls-r-1b",
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_attn_dim": null,
|
5 |
"adapter_kernel_size": 3,
|
|
|
12 |
"attention_dropout": 0.0,
|
13 |
"bos_token_id": 1,
|
14 |
"classifier_proj_size": 256,
|
15 |
+
"codevector_dim": 1024,
|
16 |
"contrastive_logits_temperature": 0.1,
|
17 |
"conv_bias": true,
|
18 |
"conv_dim": [
|
|
|
56 |
"gradient_checkpointing": false,
|
57 |
"hidden_act": "gelu",
|
58 |
"hidden_dropout": 0.0,
|
59 |
+
"hidden_size": 1280,
|
60 |
"initializer_range": 0.02,
|
61 |
+
"intermediate_size": 5120,
|
62 |
"layer_norm_eps": 1e-05,
|
63 |
+
"layerdrop": 0.0,
|
64 |
"mask_feature_length": 10,
|
65 |
"mask_feature_min_masks": 0,
|
66 |
"mask_feature_prob": 0.0,
|
67 |
"mask_time_length": 10,
|
68 |
"mask_time_min_masks": 2,
|
69 |
+
"mask_time_prob": 0.05,
|
70 |
"model_type": "wav2vec2",
|
71 |
"num_adapter_layers": 3,
|
72 |
"num_attention_heads": 16,
|
|
|
75 |
"num_conv_pos_embedding_groups": 16,
|
76 |
"num_conv_pos_embeddings": 128,
|
77 |
"num_feat_extract_layers": 7,
|
78 |
+
"num_hidden_layers": 48,
|
79 |
"num_negatives": 100,
|
80 |
+
"output_hidden_size": 1280,
|
81 |
+
"pad_token_id": 113,
|
82 |
+
"proj_codevector_dim": 1024,
|
83 |
"tdnn_dilation": [
|
84 |
1,
|
85 |
2,
|
|
|
104 |
"torch_dtype": "float32",
|
105 |
"transformers_version": "4.40.2",
|
106 |
"use_weighted_layer_sum": false,
|
107 |
+
"vocab_size": 116,
|
108 |
"xvector_output_dim": 512
|
109 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6538754a81944c6a4f97561dd9553b27dad6c300584be6456c10324c6e6d7697
|
3 |
+
size 3850685384
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:235157fb4a76d2528b38c85f26b206b572718d3994ea59298007647ea9ea38e2
|
3 |
size 4984
|