End of training
Browse files- README.md +55 -1
- config.json +82 -0
- model.safetensors +3 -0
- runs/Jan23_17-03-23_f6f062ea6b90/events.out.tfevents.1706029409.f6f062ea6b90.371.0 +3 -0
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,3 +1,57 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
base_model: ylacombe/w2v-bert-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- common_voice_11_0
|
7 |
+
model-index:
|
8 |
+
- name: w2v-bert-2.0-mongolian-colab-CV16.0
|
9 |
+
results: []
|
10 |
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# w2v-bert-2.0-mongolian-colab-CV16.0
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [ylacombe/w2v-bert-2.0](https://huggingface.co/ylacombe/w2v-bert-2.0) on the common_voice_11_0 dataset.
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 5e-05
|
37 |
+
- train_batch_size: 16
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
40 |
+
- gradient_accumulation_steps: 2
|
41 |
+
- total_train_batch_size: 32
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- lr_scheduler_warmup_steps: 500
|
45 |
+
- num_epochs: 10
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
|
51 |
+
|
52 |
+
### Framework versions
|
53 |
+
|
54 |
+
- Transformers 4.37.0.dev0
|
55 |
+
- Pytorch 2.1.0+cu121
|
56 |
+
- Datasets 2.16.1
|
57 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ylacombe/w2v-bert-2.0",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"adapter_act": "relu",
|
5 |
+
"adapter_kernel_size": 3,
|
6 |
+
"adapter_stride": 2,
|
7 |
+
"add_adapter": true,
|
8 |
+
"apply_spec_augment": false,
|
9 |
+
"architectures": [
|
10 |
+
"Wav2Vec2BertForCTC"
|
11 |
+
],
|
12 |
+
"attention_dropout": 0.0,
|
13 |
+
"bos_token_id": 1,
|
14 |
+
"classifier_proj_size": 768,
|
15 |
+
"codevector_dim": 768,
|
16 |
+
"conformer_conv_dropout": 0.1,
|
17 |
+
"contrastive_logits_temperature": 0.1,
|
18 |
+
"conv_depthwise_kernel_size": 31,
|
19 |
+
"ctc_loss_reduction": "mean",
|
20 |
+
"ctc_zero_infinity": false,
|
21 |
+
"diversity_loss_weight": 0.1,
|
22 |
+
"eos_token_id": 2,
|
23 |
+
"feat_proj_dropout": 0.0,
|
24 |
+
"feat_quantizer_dropout": 0.0,
|
25 |
+
"feature_projection_input_dim": 160,
|
26 |
+
"final_dropout": 0.1,
|
27 |
+
"hidden_act": "swish",
|
28 |
+
"hidden_dropout": 0.0,
|
29 |
+
"hidden_size": 1024,
|
30 |
+
"initializer_range": 0.02,
|
31 |
+
"intermediate_size": 4096,
|
32 |
+
"layer_norm_eps": 1e-05,
|
33 |
+
"layerdrop": 0.0,
|
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": 0.0,
|
41 |
+
"max_source_positions": 5000,
|
42 |
+
"model_type": "wav2vec2-bert",
|
43 |
+
"num_adapter_layers": 1,
|
44 |
+
"num_attention_heads": 16,
|
45 |
+
"num_codevector_groups": 2,
|
46 |
+
"num_codevectors_per_group": 320,
|
47 |
+
"num_hidden_layers": 24,
|
48 |
+
"num_negatives": 100,
|
49 |
+
"output_hidden_size": 1024,
|
50 |
+
"pad_token_id": 10,
|
51 |
+
"position_embeddings_type": "relative_key",
|
52 |
+
"proj_codevector_dim": 768,
|
53 |
+
"right_max_position_embeddings": 8,
|
54 |
+
"rotary_embedding_base": 10000,
|
55 |
+
"tdnn_dilation": [
|
56 |
+
1,
|
57 |
+
2,
|
58 |
+
3,
|
59 |
+
1,
|
60 |
+
1
|
61 |
+
],
|
62 |
+
"tdnn_dim": [
|
63 |
+
512,
|
64 |
+
512,
|
65 |
+
512,
|
66 |
+
512,
|
67 |
+
1500
|
68 |
+
],
|
69 |
+
"tdnn_kernel": [
|
70 |
+
5,
|
71 |
+
3,
|
72 |
+
3,
|
73 |
+
1,
|
74 |
+
1
|
75 |
+
],
|
76 |
+
"torch_dtype": "float32",
|
77 |
+
"transformers_version": "4.37.0.dev0",
|
78 |
+
"use_intermediate_ffn_before_adapter": false,
|
79 |
+
"use_weighted_layer_sum": false,
|
80 |
+
"vocab_size": 13,
|
81 |
+
"xvector_output_dim": 512
|
82 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44ced201be8b3e415cdf123b1cf7fd9b2d9e781614f67f55c08834cc521233b1
|
3 |
+
size 2422867852
|
runs/Jan23_17-03-23_f6f062ea6b90/events.out.tfevents.1706029409.f6f062ea6b90.371.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa8e8eb870446f9c8ceb6471e28e223243dfa99fc53069f24a9d5405aba3605e
|
3 |
+
size 6053
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50e801c4d00c37516629ac230fdb15d4edd256316ccf1c7bd2e02dd0ff4a0660
|
3 |
+
size 4728
|