Aline Rodrigues
commited on
Commit
·
310873e
1
Parent(s):
3ed4dc6
Training in progress, epoch 1
Browse files- config.json +8 -16
- pytorch_model.bin +2 -2
config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"_name_or_path": "/content/model_fase2_aug",
|
3 |
-
"activation_dropout": 0.
|
4 |
"adapter_kernel_size": 3,
|
5 |
"adapter_stride": 2,
|
6 |
"add_adapter": false,
|
@@ -11,7 +11,7 @@
|
|
11 |
"attention_dropout": 0.1,
|
12 |
"bos_token_id": 1,
|
13 |
"classifier_proj_size": 256,
|
14 |
-
"codevector_dim":
|
15 |
"contrastive_logits_temperature": 0.1,
|
16 |
"conv_bias": true,
|
17 |
"conv_dim": [
|
@@ -51,28 +51,20 @@
|
|
51 |
"feat_extract_norm": "layer",
|
52 |
"feat_proj_dropout": 0.1,
|
53 |
"feat_quantizer_dropout": 0.0,
|
54 |
-
"final_dropout": 0.
|
55 |
"hidden_act": "gelu",
|
56 |
"hidden_dropout": 0.1,
|
57 |
-
"hidden_size":
|
58 |
"initializer_range": 0.02,
|
59 |
-
"intermediate_size":
|
60 |
"layer_norm_eps": 1e-05,
|
61 |
"layerdrop": 0.07,
|
62 |
-
"mask_channel_length": 10,
|
63 |
-
"mask_channel_min_space": 1,
|
64 |
-
"mask_channel_other": 0.0,
|
65 |
-
"mask_channel_prob": 0.0,
|
66 |
-
"mask_channel_selection": "static",
|
67 |
"mask_feature_length": 10,
|
68 |
"mask_feature_min_masks": 0,
|
69 |
"mask_feature_prob": 0.0,
|
70 |
"mask_time_length": 10,
|
71 |
"mask_time_min_masks": 2,
|
72 |
-
"mask_time_min_space": 1,
|
73 |
-
"mask_time_other": 0.0,
|
74 |
"mask_time_prob": 0.1,
|
75 |
-
"mask_time_selection": "static",
|
76 |
"model_type": "wav2vec2",
|
77 |
"num_adapter_layers": 3,
|
78 |
"num_attention_heads": 16,
|
@@ -81,11 +73,11 @@
|
|
81 |
"num_conv_pos_embedding_groups": 16,
|
82 |
"num_conv_pos_embeddings": 128,
|
83 |
"num_feat_extract_layers": 7,
|
84 |
-
"num_hidden_layers":
|
85 |
"num_negatives": 100,
|
86 |
-
"output_hidden_size":
|
87 |
"pad_token_id": 45,
|
88 |
-
"proj_codevector_dim":
|
89 |
"tdnn_dilation": [
|
90 |
1,
|
91 |
2,
|
|
|
1 |
{
|
2 |
"_name_or_path": "/content/model_fase2_aug",
|
3 |
+
"activation_dropout": 0.05,
|
4 |
"adapter_kernel_size": 3,
|
5 |
"adapter_stride": 2,
|
6 |
"add_adapter": false,
|
|
|
11 |
"attention_dropout": 0.1,
|
12 |
"bos_token_id": 1,
|
13 |
"classifier_proj_size": 256,
|
14 |
+
"codevector_dim": 1024,
|
15 |
"contrastive_logits_temperature": 0.1,
|
16 |
"conv_bias": true,
|
17 |
"conv_dim": [
|
|
|
51 |
"feat_extract_norm": "layer",
|
52 |
"feat_proj_dropout": 0.1,
|
53 |
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.05,
|
55 |
"hidden_act": "gelu",
|
56 |
"hidden_dropout": 0.1,
|
57 |
+
"hidden_size": 1280,
|
58 |
"initializer_range": 0.02,
|
59 |
+
"intermediate_size": 5120,
|
60 |
"layer_norm_eps": 1e-05,
|
61 |
"layerdrop": 0.07,
|
|
|
|
|
|
|
|
|
|
|
62 |
"mask_feature_length": 10,
|
63 |
"mask_feature_min_masks": 0,
|
64 |
"mask_feature_prob": 0.0,
|
65 |
"mask_time_length": 10,
|
66 |
"mask_time_min_masks": 2,
|
|
|
|
|
67 |
"mask_time_prob": 0.1,
|
|
|
68 |
"model_type": "wav2vec2",
|
69 |
"num_adapter_layers": 3,
|
70 |
"num_attention_heads": 16,
|
|
|
73 |
"num_conv_pos_embedding_groups": 16,
|
74 |
"num_conv_pos_embeddings": 128,
|
75 |
"num_feat_extract_layers": 7,
|
76 |
+
"num_hidden_layers": 48,
|
77 |
"num_negatives": 100,
|
78 |
+
"output_hidden_size": 1280,
|
79 |
"pad_token_id": 45,
|
80 |
+
"proj_codevector_dim": 1024,
|
81 |
"tdnn_dilation": [
|
82 |
1,
|
83 |
2,
|
pytorch_model.bin
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 sha256:46b00334f80b8f0239c60bf4e72770fea7bc68ffe4786405e253e14a334cd24e
|
3 |
+
size 3850506538
|