jcrkn commited on
Commit
7b39843
1 Parent(s): 836cc73

Training in progress, step 200

Browse files
Files changed (3) hide show
  1. config.json +5 -5
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
config.json CHANGED
@@ -9,7 +9,7 @@
9
  "architectures": [
10
  "Wav2Vec2ForCTC"
11
  ],
12
- "attention_dropout": 0.5,
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": 0.5,
54
  "feat_quantizer_dropout": 0.0,
55
  "final_dropout": 0.0,
56
  "gradient_checkpointing": false,
57
  "hidden_act": "gelu",
58
- "hidden_dropout": 0.5,
59
  "hidden_size": 1024,
60
  "initializer_range": 0.02,
61
  "intermediate_size": 4096,
62
  "layer_norm_eps": 1e-05,
63
- "layerdrop": 0.5,
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": 0.5,
70
  "model_type": "wav2vec2",
71
  "num_adapter_layers": 3,
72
  "num_attention_heads": 16,
 
9
  "architectures": [
10
  "Wav2Vec2ForCTC"
11
  ],
12
+ "attention_dropout": 0.1,
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": 0.1,
54
  "feat_quantizer_dropout": 0.0,
55
  "final_dropout": 0.0,
56
  "gradient_checkpointing": false,
57
  "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
  "hidden_size": 1024,
60
  "initializer_range": 0.02,
61
  "intermediate_size": 4096,
62
  "layer_norm_eps": 1e-05,
63
+ "layerdrop": 0.1,
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": 0.1,
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 sha256:09cec751d92d427d01a7244e2fdfb94085cbb26e667a6691be535e520820264e
3
  size 1262078125
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e1b72540f9a2e172e39367b0739a029952a34e3d8d3e157557113f229cb3c1f
3
  size 1262078125
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff3b6244d02e10c1622747e21a44c1b78135b779e1584e1fde30188de459e50a
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:744685239522a92f2ec327ea24c8e287231e0f2a45228dd000f71a4c57f07b75
3
  size 4091