kurosekurose
commited on
Commit
•
3ef8d29
1
Parent(s):
863f5f5
Arousal Only Train
Browse files- README.md +64 -0
- config.json +129 -0
- model.safetensors +3 -0
- preprocessor_config.json +9 -0
- runs/Feb05_15-44-26_003d5e2f2917/events.out.tfevents.1707147872.003d5e2f2917.857.0 +3 -0
- trainer_state.json +45 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/wav2vec2-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: Arousal-wav2vec2-base-EMOPIA
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# Arousal-wav2vec2-base-EMOPIA
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.6919
|
21 |
+
- Accuracy: 0.4085
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 1e-06
|
41 |
+
- train_batch_size: 1
|
42 |
+
- eval_batch_size: 1
|
43 |
+
- seed: 42
|
44 |
+
- gradient_accumulation_steps: 3
|
45 |
+
- total_train_batch_size: 3
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- lr_scheduler_warmup_steps: 1000
|
49 |
+
- num_epochs: 1
|
50 |
+
- mixed_precision_training: Native AMP
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
55 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
56 |
+
| 0.7075 | 1.0 | 269 | 0.6919 | 0.4085 |
|
57 |
+
|
58 |
+
|
59 |
+
### Framework versions
|
60 |
+
|
61 |
+
- Transformers 4.37.2
|
62 |
+
- Pytorch 2.1.0+cu121
|
63 |
+
- Datasets 2.16.1
|
64 |
+
- Tokenizers 0.15.1
|
config.json
ADDED
@@ -0,0 +1,129 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"adapter_attn_dim": null,
|
5 |
+
"adapter_kernel_size": 3,
|
6 |
+
"adapter_stride": 2,
|
7 |
+
"add_adapter": false,
|
8 |
+
"apply_spec_augment": true,
|
9 |
+
"architectures": [
|
10 |
+
"Wav2Vec2ForSpeechClassification"
|
11 |
+
],
|
12 |
+
"attention_dropout": 0.1,
|
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,
|
21 |
+
512,
|
22 |
+
512,
|
23 |
+
512,
|
24 |
+
512,
|
25 |
+
512
|
26 |
+
],
|
27 |
+
"conv_kernel": [
|
28 |
+
10,
|
29 |
+
3,
|
30 |
+
3,
|
31 |
+
3,
|
32 |
+
3,
|
33 |
+
2,
|
34 |
+
2
|
35 |
+
],
|
36 |
+
"conv_stride": [
|
37 |
+
5,
|
38 |
+
2,
|
39 |
+
2,
|
40 |
+
2,
|
41 |
+
2,
|
42 |
+
2,
|
43 |
+
2
|
44 |
+
],
|
45 |
+
"ctc_loss_reduction": "sum",
|
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": 0.1,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.0,
|
55 |
+
"finetuning_task": "facebook/wav2vec2-base",
|
56 |
+
"freeze_feat_extract_train": true,
|
57 |
+
"hidden_act": "gelu",
|
58 |
+
"hidden_dropout": 0.1,
|
59 |
+
"hidden_size": 768,
|
60 |
+
"id2label": {
|
61 |
+
"0": "HA",
|
62 |
+
"1": "LA"
|
63 |
+
},
|
64 |
+
"initializer_range": 0.02,
|
65 |
+
"intermediate_size": 3072,
|
66 |
+
"label2id": {
|
67 |
+
"HA": 0,
|
68 |
+
"LA": 1
|
69 |
+
},
|
70 |
+
"layer_norm_eps": 1e-05,
|
71 |
+
"layerdrop": 0.0,
|
72 |
+
"mask_channel_length": 10,
|
73 |
+
"mask_channel_min_space": 1,
|
74 |
+
"mask_channel_other": 0.0,
|
75 |
+
"mask_channel_prob": 0.0,
|
76 |
+
"mask_channel_selection": "static",
|
77 |
+
"mask_feature_length": 10,
|
78 |
+
"mask_feature_min_masks": 0,
|
79 |
+
"mask_feature_prob": 0.0,
|
80 |
+
"mask_time_length": 10,
|
81 |
+
"mask_time_min_masks": 2,
|
82 |
+
"mask_time_min_space": 1,
|
83 |
+
"mask_time_other": 0.0,
|
84 |
+
"mask_time_prob": 0.05,
|
85 |
+
"mask_time_selection": "static",
|
86 |
+
"model_type": "wav2vec2",
|
87 |
+
"no_mask_channel_overlap": false,
|
88 |
+
"no_mask_time_overlap": false,
|
89 |
+
"num_adapter_layers": 3,
|
90 |
+
"num_attention_heads": 12,
|
91 |
+
"num_codevector_groups": 2,
|
92 |
+
"num_codevectors_per_group": 320,
|
93 |
+
"num_conv_pos_embedding_groups": 16,
|
94 |
+
"num_conv_pos_embeddings": 128,
|
95 |
+
"num_feat_extract_layers": 7,
|
96 |
+
"num_hidden_layers": 12,
|
97 |
+
"num_negatives": 100,
|
98 |
+
"output_hidden_size": 768,
|
99 |
+
"pad_token_id": 0,
|
100 |
+
"pooling_mode": "mean",
|
101 |
+
"problem_type": "single_label_classification",
|
102 |
+
"proj_codevector_dim": 256,
|
103 |
+
"tdnn_dilation": [
|
104 |
+
1,
|
105 |
+
2,
|
106 |
+
3,
|
107 |
+
1,
|
108 |
+
1
|
109 |
+
],
|
110 |
+
"tdnn_dim": [
|
111 |
+
512,
|
112 |
+
512,
|
113 |
+
512,
|
114 |
+
512,
|
115 |
+
1500
|
116 |
+
],
|
117 |
+
"tdnn_kernel": [
|
118 |
+
5,
|
119 |
+
3,
|
120 |
+
3,
|
121 |
+
1,
|
122 |
+
1
|
123 |
+
],
|
124 |
+
"torch_dtype": "float32",
|
125 |
+
"transformers_version": "4.37.2",
|
126 |
+
"use_weighted_layer_sum": false,
|
127 |
+
"vocab_size": 32,
|
128 |
+
"xvector_output_dim": 512
|
129 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc59436a776ace60768d1997d9f14a66e8039c52c9791feb588528148780a5ea
|
3 |
+
size 379881432
|
preprocessor_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0.0,
|
7 |
+
"return_attention_mask": false,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
runs/Feb05_15-44-26_003d5e2f2917/events.out.tfevents.1707147872.003d5e2f2917.857.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5111720bd3bb88dd4495eaa19f06987630ee3d106cebe29348713d588ae201c
|
3 |
+
size 13661
|
trainer_state.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6918669939041138,
|
3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/AI_development/Musicbot/train_model/Arousal-wav2vec2-base-EMOPIA/checkpoint-269",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 269,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"learning_rate": 2.69e-07,
|
14 |
+
"loss": 0.7075,
|
15 |
+
"step": 269
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"eval_accuracy": 0.4084506928920746,
|
20 |
+
"eval_loss": 0.6918669939041138,
|
21 |
+
"eval_runtime": 39.6785,
|
22 |
+
"eval_samples_per_second": 1.789,
|
23 |
+
"eval_steps_per_second": 1.789,
|
24 |
+
"step": 269
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 1.0,
|
28 |
+
"step": 269,
|
29 |
+
"total_flos": 4.48797597870528e+17,
|
30 |
+
"train_loss": 0.7074856102245005,
|
31 |
+
"train_runtime": 1028.8672,
|
32 |
+
"train_samples_per_second": 0.784,
|
33 |
+
"train_steps_per_second": 0.261
|
34 |
+
}
|
35 |
+
],
|
36 |
+
"logging_steps": 33,
|
37 |
+
"max_steps": 269,
|
38 |
+
"num_input_tokens_seen": 0,
|
39 |
+
"num_train_epochs": 1,
|
40 |
+
"save_steps": 500,
|
41 |
+
"total_flos": 4.48797597870528e+17,
|
42 |
+
"train_batch_size": 1,
|
43 |
+
"trial_name": null,
|
44 |
+
"trial_params": null
|
45 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0b5954fe455b5a7f9d3d4dffa43e6dcfa1ecc8d79884821e3cc8163631dd071
|
3 |
+
size 4856
|