Training in progress, step 20
Browse files- config.json +13 -15
- model.safetensors +2 -2
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"activation_dropout": 0.
|
4 |
"adapter_attn_dim": null,
|
5 |
"adapter_kernel_size": 3,
|
6 |
"adapter_stride": 2,
|
@@ -12,9 +12,9 @@
|
|
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":
|
18 |
"conv_dim": [
|
19 |
512,
|
20 |
512,
|
@@ -45,20 +45,18 @@
|
|
45 |
"ctc_loss_reduction": "mean",
|
46 |
"ctc_zero_infinity": false,
|
47 |
"diversity_loss_weight": 0.1,
|
48 |
-
"do_stable_layer_norm":
|
49 |
"eos_token_id": 2,
|
50 |
"feat_extract_activation": "gelu",
|
51 |
-
"
|
52 |
-
"feat_extract_norm": "layer",
|
53 |
"feat_proj_dropout": 0.0,
|
54 |
"feat_quantizer_dropout": 0.0,
|
55 |
-
"final_dropout": 0.
|
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": 0.0,
|
64 |
"mask_feature_length": 10,
|
@@ -69,17 +67,17 @@
|
|
69 |
"mask_time_prob": 0.05,
|
70 |
"model_type": "wav2vec2",
|
71 |
"num_adapter_layers": 3,
|
72 |
-
"num_attention_heads":
|
73 |
"num_codevector_groups": 2,
|
74 |
"num_codevectors_per_group": 320,
|
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": 49,
|
82 |
-
"proj_codevector_dim":
|
83 |
"tdnn_dilation": [
|
84 |
1,
|
85 |
2,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/content/Untitled Folder",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
"adapter_attn_dim": null,
|
5 |
"adapter_kernel_size": 3,
|
6 |
"adapter_stride": 2,
|
|
|
12 |
"attention_dropout": 0.0,
|
13 |
"bos_token_id": 1,
|
14 |
"classifier_proj_size": 256,
|
15 |
+
"codevector_dim": 256,
|
16 |
"contrastive_logits_temperature": 0.1,
|
17 |
+
"conv_bias": false,
|
18 |
"conv_dim": [
|
19 |
512,
|
20 |
512,
|
|
|
45 |
"ctc_loss_reduction": "mean",
|
46 |
"ctc_zero_infinity": false,
|
47 |
"diversity_loss_weight": 0.1,
|
48 |
+
"do_stable_layer_norm": false,
|
49 |
"eos_token_id": 2,
|
50 |
"feat_extract_activation": "gelu",
|
51 |
+
"feat_extract_norm": "group",
|
|
|
52 |
"feat_proj_dropout": 0.0,
|
53 |
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.1,
|
|
|
55 |
"hidden_act": "gelu",
|
56 |
"hidden_dropout": 0.0,
|
57 |
+
"hidden_size": 768,
|
58 |
"initializer_range": 0.02,
|
59 |
+
"intermediate_size": 3072,
|
60 |
"layer_norm_eps": 1e-05,
|
61 |
"layerdrop": 0.0,
|
62 |
"mask_feature_length": 10,
|
|
|
67 |
"mask_time_prob": 0.05,
|
68 |
"model_type": "wav2vec2",
|
69 |
"num_adapter_layers": 3,
|
70 |
+
"num_attention_heads": 12,
|
71 |
"num_codevector_groups": 2,
|
72 |
"num_codevectors_per_group": 320,
|
73 |
"num_conv_pos_embedding_groups": 16,
|
74 |
"num_conv_pos_embeddings": 128,
|
75 |
"num_feat_extract_layers": 7,
|
76 |
+
"num_hidden_layers": 12,
|
77 |
"num_negatives": 100,
|
78 |
+
"output_hidden_size": 768,
|
79 |
"pad_token_id": 49,
|
80 |
+
"proj_codevector_dim": 256,
|
81 |
"tdnn_dilation": [
|
82 |
1,
|
83 |
2,
|
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 sha256:0664857e0b95a1879ee813fb4b97bca67dab0e6693339a0503c19ec615c8de7b
|
3 |
+
size 377672648
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7528199d7bfbcb5025cc25f997740f040b5bdddadd4b4b58742dace63b346ece
|
3 |
size 5112
|