Training in progress, step 200
Browse files- config.json +7 -7
- model.safetensors +2 -2
- training_args.bin +1 -1
config.json
CHANGED
@@ -9,7 +9,7 @@
|
|
9 |
"architectures": [
|
10 |
"Wav2Vec2BertForCTC"
|
11 |
],
|
12 |
-
"attention_dropout": 0.
|
13 |
"bos_token_id": 1,
|
14 |
"classifier_proj_size": 768,
|
15 |
"codevector_dim": 768,
|
@@ -20,24 +20,24 @@
|
|
20 |
"ctc_zero_infinity": false,
|
21 |
"diversity_loss_weight": 0.1,
|
22 |
"eos_token_id": 2,
|
23 |
-
"feat_proj_dropout": 0.
|
24 |
"feat_quantizer_dropout": 0.0,
|
25 |
"feature_projection_input_dim": 160,
|
26 |
"final_dropout": 0.1,
|
27 |
"hidden_act": "swish",
|
28 |
-
"hidden_dropout": 0.
|
29 |
"hidden_size": 1024,
|
30 |
"initializer_range": 0.02,
|
31 |
"intermediate_size": 4096,
|
32 |
"layer_norm_eps": 1e-05,
|
33 |
-
"layerdrop": 0.
|
34 |
"left_max_position_embeddings": 64,
|
35 |
"mask_feature_length": 10,
|
36 |
"mask_feature_min_masks": 0,
|
37 |
"mask_feature_prob": 0.0,
|
38 |
"mask_time_length": 10,
|
39 |
"mask_time_min_masks": 2,
|
40 |
-
"mask_time_prob": 0.
|
41 |
"max_source_positions": 5000,
|
42 |
"model_type": "wav2vec2-bert",
|
43 |
"num_adapter_layers": 1,
|
@@ -47,7 +47,7 @@
|
|
47 |
"num_hidden_layers": 24,
|
48 |
"num_negatives": 100,
|
49 |
"output_hidden_size": 1024,
|
50 |
-
"pad_token_id":
|
51 |
"position_embeddings_type": "relative_key",
|
52 |
"proj_codevector_dim": 768,
|
53 |
"right_max_position_embeddings": 8,
|
@@ -77,6 +77,6 @@
|
|
77 |
"transformers_version": "4.37.1",
|
78 |
"use_intermediate_ffn_before_adapter": false,
|
79 |
"use_weighted_layer_sum": false,
|
80 |
-
"vocab_size":
|
81 |
"xvector_output_dim": 512
|
82 |
}
|
|
|
9 |
"architectures": [
|
10 |
"Wav2Vec2BertForCTC"
|
11 |
],
|
12 |
+
"attention_dropout": 0.094,
|
13 |
"bos_token_id": 1,
|
14 |
"classifier_proj_size": 768,
|
15 |
"codevector_dim": 768,
|
|
|
20 |
"ctc_zero_infinity": false,
|
21 |
"diversity_loss_weight": 0.1,
|
22 |
"eos_token_id": 2,
|
23 |
+
"feat_proj_dropout": 0.04,
|
24 |
"feat_quantizer_dropout": 0.0,
|
25 |
"feature_projection_input_dim": 160,
|
26 |
"final_dropout": 0.1,
|
27 |
"hidden_act": "swish",
|
28 |
+
"hidden_dropout": 0.047,
|
29 |
"hidden_size": 1024,
|
30 |
"initializer_range": 0.02,
|
31 |
"intermediate_size": 4096,
|
32 |
"layer_norm_eps": 1e-05,
|
33 |
+
"layerdrop": 0.041,
|
34 |
"left_max_position_embeddings": 64,
|
35 |
"mask_feature_length": 10,
|
36 |
"mask_feature_min_masks": 0,
|
37 |
"mask_feature_prob": 0.0,
|
38 |
"mask_time_length": 10,
|
39 |
"mask_time_min_masks": 2,
|
40 |
+
"mask_time_prob": 0.082,
|
41 |
"max_source_positions": 5000,
|
42 |
"model_type": "wav2vec2-bert",
|
43 |
"num_adapter_layers": 1,
|
|
|
47 |
"num_hidden_layers": 24,
|
48 |
"num_negatives": 100,
|
49 |
"output_hidden_size": 1024,
|
50 |
+
"pad_token_id": 30,
|
51 |
"position_embeddings_type": "relative_key",
|
52 |
"proj_codevector_dim": 768,
|
53 |
"right_max_position_embeddings": 8,
|
|
|
77 |
"transformers_version": "4.37.1",
|
78 |
"use_intermediate_ffn_before_adapter": false,
|
79 |
"use_weighted_layer_sum": false,
|
80 |
+
"vocab_size": 33,
|
81 |
"xvector_output_dim": 512
|
82 |
}
|
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:ead45dfa8c03bd2d10c5c4e3d09f476c9f0a2b8df0751d07566c54ab2fcaf091
|
3 |
+
size 2422954060
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5bb26e778420fd0b07b32eaf2a2743154884f9b6eebf38865474eade984bfbde
|
3 |
size 4728
|