Commit
•
a348421
1
Parent(s):
cc8a9e2
End of training
Browse files- README.md +80 -80
- config.json +80 -80
- model.safetensors +1 -1
- preprocessor_config.json +9 -9
- runs/Aug21_16-08-57_3ae7262d22ce/events.out.tfevents.1724256552.3ae7262d22ce.245.1 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,80 +1,80 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
base_model: ntu-spml/distilhubert
|
| 4 |
-
tags:
|
| 5 |
-
- generated_from_trainer
|
| 6 |
-
datasets:
|
| 7 |
-
- audiofolder
|
| 8 |
-
metrics:
|
| 9 |
-
- accuracy
|
| 10 |
-
model-index:
|
| 11 |
-
- name: distilhubert-finetuned-cry-detector
|
| 12 |
-
results:
|
| 13 |
-
- task:
|
| 14 |
-
name: Audio Classification
|
| 15 |
-
type: audio-classification
|
| 16 |
-
dataset:
|
| 17 |
-
name: audiofolder
|
| 18 |
-
type: audiofolder
|
| 19 |
-
config: default
|
| 20 |
-
split: train
|
| 21 |
-
args: default
|
| 22 |
-
metrics:
|
| 23 |
-
- name: Accuracy
|
| 24 |
-
type: accuracy
|
| 25 |
-
value: 0.9786096256684492
|
| 26 |
-
---
|
| 27 |
-
|
| 28 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
-
|
| 31 |
-
# distilhubert-finetuned-cry-detector
|
| 32 |
-
|
| 33 |
-
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
|
| 34 |
-
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.9786
|
| 37 |
-
|
| 38 |
-
## Model description
|
| 39 |
-
|
| 40 |
-
More information needed
|
| 41 |
-
|
| 42 |
-
## Intended uses & limitations
|
| 43 |
-
|
| 44 |
-
More information needed
|
| 45 |
-
|
| 46 |
-
## Training and evaluation data
|
| 47 |
-
|
| 48 |
-
More information needed
|
| 49 |
-
|
| 50 |
-
## Training procedure
|
| 51 |
-
|
| 52 |
-
### Training hyperparameters
|
| 53 |
-
|
| 54 |
-
The following hyperparameters were used during training:
|
| 55 |
-
- learning_rate: 0.0001
|
| 56 |
-
- train_batch_size: 8
|
| 57 |
-
- eval_batch_size: 8
|
| 58 |
-
- seed: 123
|
| 59 |
-
- gradient_accumulation_steps: 8
|
| 60 |
-
- total_train_batch_size: 64
|
| 61 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
-
- lr_scheduler_type: cosine
|
| 63 |
-
- num_epochs: 4
|
| 64 |
-
|
| 65 |
-
### Training results
|
| 66 |
-
|
| 67 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 68 |
-
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
| 69 |
-
| No log | 0.9362 | 11 | 0.
|
| 70 |
-
| No log | 1.9574 | 23 | 0.
|
| 71 |
-
| No log | 2.9787 | 35 | 0.
|
| 72 |
-
| No log | 3.7447 | 44 | 0.
|
| 73 |
-
|
| 74 |
-
|
| 75 |
-
### Framework versions
|
| 76 |
-
|
| 77 |
-
- Transformers 4.
|
| 78 |
-
- Pytorch 2.
|
| 79 |
-
- Datasets 2.21.0
|
| 80 |
-
- Tokenizers 0.19.1
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: ntu-spml/distilhubert
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- audiofolder
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: distilhubert-finetuned-cry-detector
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Audio Classification
|
| 15 |
+
type: audio-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: audiofolder
|
| 18 |
+
type: audiofolder
|
| 19 |
+
config: default
|
| 20 |
+
split: train
|
| 21 |
+
args: default
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.9786096256684492
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
+
|
| 31 |
+
# distilhubert-finetuned-cry-detector
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.0732
|
| 36 |
+
- Accuracy: 0.9786
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Intended uses & limitations
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training procedure
|
| 51 |
+
|
| 52 |
+
### Training hyperparameters
|
| 53 |
+
|
| 54 |
+
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 0.0001
|
| 56 |
+
- train_batch_size: 8
|
| 57 |
+
- eval_batch_size: 8
|
| 58 |
+
- seed: 123
|
| 59 |
+
- gradient_accumulation_steps: 8
|
| 60 |
+
- total_train_batch_size: 64
|
| 61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
+
- lr_scheduler_type: cosine
|
| 63 |
+
- num_epochs: 4
|
| 64 |
+
|
| 65 |
+
### Training results
|
| 66 |
+
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 68 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
| 69 |
+
| No log | 0.9362 | 11 | 0.1831 | 0.9358 |
|
| 70 |
+
| No log | 1.9574 | 23 | 0.1361 | 0.9519 |
|
| 71 |
+
| No log | 2.9787 | 35 | 0.0748 | 0.9786 |
|
| 72 |
+
| No log | 3.7447 | 44 | 0.0732 | 0.9786 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- Transformers 4.42.4
|
| 78 |
+
- Pytorch 2.3.1+cu121
|
| 79 |
+
- Datasets 2.21.0
|
| 80 |
+
- Tokenizers 0.19.1
|
config.json
CHANGED
|
@@ -1,80 +1,80 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "ntu-spml/distilhubert",
|
| 3 |
-
"activation_dropout": 0.1,
|
| 4 |
-
"apply_spec_augment": false,
|
| 5 |
-
"architectures": [
|
| 6 |
-
"HubertForSequenceClassification"
|
| 7 |
-
],
|
| 8 |
-
"attention_dropout": 0.1,
|
| 9 |
-
"bos_token_id": 1,
|
| 10 |
-
"classifier_proj_size": 256,
|
| 11 |
-
"conv_bias": false,
|
| 12 |
-
"conv_dim": [
|
| 13 |
-
512,
|
| 14 |
-
512,
|
| 15 |
-
512,
|
| 16 |
-
512,
|
| 17 |
-
512,
|
| 18 |
-
512,
|
| 19 |
-
512
|
| 20 |
-
],
|
| 21 |
-
"conv_kernel": [
|
| 22 |
-
10,
|
| 23 |
-
3,
|
| 24 |
-
3,
|
| 25 |
-
3,
|
| 26 |
-
3,
|
| 27 |
-
2,
|
| 28 |
-
2
|
| 29 |
-
],
|
| 30 |
-
"conv_stride": [
|
| 31 |
-
5,
|
| 32 |
-
2,
|
| 33 |
-
2,
|
| 34 |
-
2,
|
| 35 |
-
2,
|
| 36 |
-
2,
|
| 37 |
-
2
|
| 38 |
-
],
|
| 39 |
-
"ctc_loss_reduction": "sum",
|
| 40 |
-
"ctc_zero_infinity": false,
|
| 41 |
-
"do_stable_layer_norm": false,
|
| 42 |
-
"eos_token_id": 2,
|
| 43 |
-
"feat_extract_activation": "gelu",
|
| 44 |
-
"feat_extract_norm": "group",
|
| 45 |
-
"feat_proj_dropout": 0.0,
|
| 46 |
-
"feat_proj_layer_norm": false,
|
| 47 |
-
"final_dropout": 0.0,
|
| 48 |
-
"hidden_act": "gelu",
|
| 49 |
-
"hidden_dropout": 0.1,
|
| 50 |
-
"hidden_size": 768,
|
| 51 |
-
"id2label": {
|
| 52 |
-
"0": "crying",
|
| 53 |
-
"1": "no_crying"
|
| 54 |
-
},
|
| 55 |
-
"initializer_range": 0.02,
|
| 56 |
-
"intermediate_size": 3072,
|
| 57 |
-
"label2id": {
|
| 58 |
-
"crying": "0",
|
| 59 |
-
"no_crying": "1"
|
| 60 |
-
},
|
| 61 |
-
"layer_norm_eps": 1e-05,
|
| 62 |
-
"layerdrop": 0.0,
|
| 63 |
-
"mask_feature_length": 10,
|
| 64 |
-
"mask_feature_min_masks": 0,
|
| 65 |
-
"mask_feature_prob": 0.0,
|
| 66 |
-
"mask_time_length": 10,
|
| 67 |
-
"mask_time_min_masks": 2,
|
| 68 |
-
"mask_time_prob": 0.05,
|
| 69 |
-
"model_type": "hubert",
|
| 70 |
-
"num_attention_heads": 12,
|
| 71 |
-
"num_conv_pos_embedding_groups": 16,
|
| 72 |
-
"num_conv_pos_embeddings": 128,
|
| 73 |
-
"num_feat_extract_layers": 7,
|
| 74 |
-
"num_hidden_layers": 2,
|
| 75 |
-
"pad_token_id": 0,
|
| 76 |
-
"torch_dtype": "float32",
|
| 77 |
-
"transformers_version": "4.
|
| 78 |
-
"use_weighted_layer_sum": false,
|
| 79 |
-
"vocab_size": 32
|
| 80 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ntu-spml/distilhubert",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"apply_spec_augment": false,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"HubertForSequenceClassification"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"classifier_proj_size": 256,
|
| 11 |
+
"conv_bias": false,
|
| 12 |
+
"conv_dim": [
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512,
|
| 16 |
+
512,
|
| 17 |
+
512,
|
| 18 |
+
512,
|
| 19 |
+
512
|
| 20 |
+
],
|
| 21 |
+
"conv_kernel": [
|
| 22 |
+
10,
|
| 23 |
+
3,
|
| 24 |
+
3,
|
| 25 |
+
3,
|
| 26 |
+
3,
|
| 27 |
+
2,
|
| 28 |
+
2
|
| 29 |
+
],
|
| 30 |
+
"conv_stride": [
|
| 31 |
+
5,
|
| 32 |
+
2,
|
| 33 |
+
2,
|
| 34 |
+
2,
|
| 35 |
+
2,
|
| 36 |
+
2,
|
| 37 |
+
2
|
| 38 |
+
],
|
| 39 |
+
"ctc_loss_reduction": "sum",
|
| 40 |
+
"ctc_zero_infinity": false,
|
| 41 |
+
"do_stable_layer_norm": false,
|
| 42 |
+
"eos_token_id": 2,
|
| 43 |
+
"feat_extract_activation": "gelu",
|
| 44 |
+
"feat_extract_norm": "group",
|
| 45 |
+
"feat_proj_dropout": 0.0,
|
| 46 |
+
"feat_proj_layer_norm": false,
|
| 47 |
+
"final_dropout": 0.0,
|
| 48 |
+
"hidden_act": "gelu",
|
| 49 |
+
"hidden_dropout": 0.1,
|
| 50 |
+
"hidden_size": 768,
|
| 51 |
+
"id2label": {
|
| 52 |
+
"0": "crying",
|
| 53 |
+
"1": "no_crying"
|
| 54 |
+
},
|
| 55 |
+
"initializer_range": 0.02,
|
| 56 |
+
"intermediate_size": 3072,
|
| 57 |
+
"label2id": {
|
| 58 |
+
"crying": "0",
|
| 59 |
+
"no_crying": "1"
|
| 60 |
+
},
|
| 61 |
+
"layer_norm_eps": 1e-05,
|
| 62 |
+
"layerdrop": 0.0,
|
| 63 |
+
"mask_feature_length": 10,
|
| 64 |
+
"mask_feature_min_masks": 0,
|
| 65 |
+
"mask_feature_prob": 0.0,
|
| 66 |
+
"mask_time_length": 10,
|
| 67 |
+
"mask_time_min_masks": 2,
|
| 68 |
+
"mask_time_prob": 0.05,
|
| 69 |
+
"model_type": "hubert",
|
| 70 |
+
"num_attention_heads": 12,
|
| 71 |
+
"num_conv_pos_embedding_groups": 16,
|
| 72 |
+
"num_conv_pos_embeddings": 128,
|
| 73 |
+
"num_feat_extract_layers": 7,
|
| 74 |
+
"num_hidden_layers": 2,
|
| 75 |
+
"pad_token_id": 0,
|
| 76 |
+
"torch_dtype": "float32",
|
| 77 |
+
"transformers_version": "4.42.4",
|
| 78 |
+
"use_weighted_layer_sum": false,
|
| 79 |
+
"vocab_size": 32
|
| 80 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 94763496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37fd4a948a69ccbbd999b0b48a7af1b366b82c87b508d35767cdfbf1c2bba96c
|
| 3 |
size 94763496
|
preprocessor_config.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
-
{
|
| 2 |
-
"do_normalize": false,
|
| 3 |
-
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
-
"feature_size": 1,
|
| 5 |
-
"padding_side": "right",
|
| 6 |
-
"padding_value": 0,
|
| 7 |
-
"return_attention_mask": false,
|
| 8 |
-
"sampling_rate": 16000
|
| 9 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": false,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0,
|
| 7 |
+
"return_attention_mask": false,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|
runs/Aug21_16-08-57_3ae7262d22ce/events.out.tfevents.1724256552.3ae7262d22ce.245.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23d3614cc79d7be042a338d827db6546f17b0d5272166ee83d6bc3054481e38c
|
| 3 |
+
size 7406
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbc895582845e04f7b896e904848b260ab962b034fa8d8a0a3cd0d29f8a8cdc1
|
| 3 |
size 5176
|