Training in progress, step 200
Browse files- config.json +5 -5
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
config.json
CHANGED
@@ -9,7 +9,7 @@
|
|
9 |
"architectures": [
|
10 |
"Wav2Vec2ForCTC"
|
11 |
],
|
12 |
-
"attention_dropout": 0.
|
13 |
"bos_token_id": 1,
|
14 |
"classifier_proj_size": 256,
|
15 |
"codevector_dim": 768,
|
@@ -50,23 +50,23 @@
|
|
50 |
"feat_extract_activation": "gelu",
|
51 |
"feat_extract_dropout": 0.0,
|
52 |
"feat_extract_norm": "layer",
|
53 |
-
"feat_proj_dropout": 0.
|
54 |
"feat_quantizer_dropout": 0.0,
|
55 |
"final_dropout": 0.0,
|
56 |
"gradient_checkpointing": false,
|
57 |
"hidden_act": "gelu",
|
58 |
-
"hidden_dropout": 0.
|
59 |
"hidden_size": 1024,
|
60 |
"initializer_range": 0.02,
|
61 |
"intermediate_size": 4096,
|
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,
|
|
|
9 |
"architectures": [
|
10 |
"Wav2Vec2ForCTC"
|
11 |
],
|
12 |
+
"attention_dropout": 0.05,
|
13 |
"bos_token_id": 1,
|
14 |
"classifier_proj_size": 256,
|
15 |
"codevector_dim": 768,
|
|
|
50 |
"feat_extract_activation": "gelu",
|
51 |
"feat_extract_dropout": 0.0,
|
52 |
"feat_extract_norm": "layer",
|
53 |
+
"feat_proj_dropout": 0.05,
|
54 |
"feat_quantizer_dropout": 0.0,
|
55 |
"final_dropout": 0.0,
|
56 |
"gradient_checkpointing": false,
|
57 |
"hidden_act": "gelu",
|
58 |
+
"hidden_dropout": 0.05,
|
59 |
"hidden_size": 1024,
|
60 |
"initializer_range": 0.02,
|
61 |
"intermediate_size": 4096,
|
62 |
"layer_norm_eps": 1e-05,
|
63 |
+
"layerdrop": 0.05,
|
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,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262078125
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6021091032b663ccf6c2034ba01cf47996f8676a59b5ce854a4d17e7619a622
|
3 |
size 1262078125
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4091
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5cba54ba04b80d4a4eec349edb1fc078e4c7d1f9d17a9f1dc86fc159f3c83d6
|
3 |
size 4091
|