Marcos12886
commited on
Commit
•
eb22acc
1
Parent(s):
9487b76
Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +25 -25
- checkpoint-500/config.json +77 -0
- checkpoint-500/model.safetensors +3 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/trainer_state.json +222 -0
- checkpoint-500/training_args.bin +3 -0
- checkpoint-600/config.json +77 -0
- checkpoint-600/model.safetensors +3 -0
- checkpoint-600/optimizer.pt +3 -0
- checkpoint-600/rng_state.pth +3 -0
- checkpoint-600/scheduler.pt +3 -0
- checkpoint-600/trainer_state.json +258 -0
- checkpoint-600/training_args.bin +3 -0
- checkpoint-700/config.json +77 -0
- checkpoint-700/model.safetensors +3 -0
- checkpoint-700/optimizer.pt +3 -0
- checkpoint-700/rng_state.pth +3 -0
- checkpoint-700/scheduler.pt +3 -0
- checkpoint-700/trainer_state.json +294 -0
- checkpoint-700/training_args.bin +3 -0
- checkpoint-800/config.json +77 -0
- checkpoint-800/model.safetensors +3 -0
- checkpoint-800/optimizer.pt +3 -0
- checkpoint-800/rng_state.pth +3 -0
- checkpoint-800/scheduler.pt +3 -0
- checkpoint-800/trainer_state.json +330 -0
- checkpoint-800/training_args.bin +3 -0
- checkpoint-860/config.json +77 -0
- checkpoint-860/model.safetensors +3 -0
- checkpoint-860/optimizer.pt +3 -0
- checkpoint-860/rng_state.pth +3 -0
- checkpoint-860/scheduler.pt +3 -0
- checkpoint-860/trainer_state.json +337 -0
- checkpoint-860/training_args.bin +3 -0
- model.safetensors +1 -1
- runs/Sep11_15-20-39_ubumarcos/events.out.tfevents.1726060840.ubumarcos +3 -0
- runs/Sep11_15-21-14_ubumarcos/events.out.tfevents.1726060876.ubumarcos +3 -0
- runs/Sep11_15-25-59_ubumarcos/events.out.tfevents.1726061160.ubumarcos +3 -0
- runs/Sep11_15-25-59_ubumarcos/events.out.tfevents.1726061977.ubumarcos +3 -0
- runs/Sep11_15-42-12_ubumarcos/events.out.tfevents.1726062133.ubumarcos +3 -0
- runs/Sep11_15-50-04_ubumarcos/events.out.tfevents.1726062605.ubumarcos +3 -0
- runs/Sep11_15-50-31_ubumarcos/events.out.tfevents.1726062632.ubumarcos +3 -0
- runs/Sep11_15-50-57_ubumarcos/events.out.tfevents.1726062658.ubumarcos +3 -0
- runs/Sep11_15-51-52_ubumarcos/events.out.tfevents.1726062713.ubumarcos +3 -0
- runs/Sep11_15-52-20_ubumarcos/events.out.tfevents.1726062741.ubumarcos +3 -0
- runs/Sep11_15-52-43_ubumarcos/events.out.tfevents.1726062764.ubumarcos +3 -0
- runs/Sep11_15-54-06_ubumarcos/events.out.tfevents.1726062847.ubumarcos +3 -0
- runs/Sep11_15-54-19_ubumarcos/events.out.tfevents.1726062860.ubumarcos +3 -0
README.md
CHANGED
@@ -6,9 +6,9 @@ tags:
|
|
6 |
- generated_from_trainer
|
7 |
metrics:
|
8 |
- accuracy
|
|
|
9 |
- precision
|
10 |
- recall
|
11 |
-
- f1
|
12 |
model-index:
|
13 |
- name: distilhubert-finetuned-cry-detector
|
14 |
results: []
|
@@ -21,11 +21,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
21 |
|
22 |
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on an unknown dataset.
|
23 |
It achieves the following results on the evaluation set:
|
24 |
-
- Loss: 0.
|
25 |
-
- Accuracy: 0.
|
26 |
-
-
|
27 |
-
-
|
28 |
-
-
|
|
|
29 |
|
30 |
## Model description
|
31 |
|
@@ -45,30 +46,29 @@ More information needed
|
|
45 |
|
46 |
The following hyperparameters were used during training:
|
47 |
- learning_rate: 3e-05
|
48 |
-
- train_batch_size:
|
49 |
-
- eval_batch_size:
|
50 |
- seed: 123
|
51 |
-
- gradient_accumulation_steps:
|
52 |
-
- total_train_batch_size:
|
53 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
54 |
-
- lr_scheduler_type:
|
55 |
-
- lr_scheduler_warmup_ratio: 0.
|
56 |
-
- num_epochs:
|
|
|
57 |
|
58 |
### Training results
|
59 |
|
60 |
-
| Training Loss | Epoch
|
61 |
-
|
62 |
-
|
|
63 |
-
|
|
64 |
-
|
|
65 |
-
|
|
66 |
-
|
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.0779 | 8.9956 | 768 | 0.0337 | 0.9912 | 0.9912 | 0.9912 | 0.9912 |
|
71 |
-
| 0.0779 | 9.9561 | 850 | 0.0338 | 0.9912 | 0.9912 | 0.9912 | 0.9912 |
|
72 |
|
73 |
|
74 |
### Framework versions
|
|
|
6 |
- generated_from_trainer
|
7 |
metrics:
|
8 |
- accuracy
|
9 |
+
- f1
|
10 |
- precision
|
11 |
- recall
|
|
|
12 |
model-index:
|
13 |
- name: distilhubert-finetuned-cry-detector
|
14 |
results: []
|
|
|
21 |
|
22 |
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on an unknown dataset.
|
23 |
It achieves the following results on the evaluation set:
|
24 |
+
- Loss: 0.2255
|
25 |
+
- Accuracy: 0.9883
|
26 |
+
- F1: 0.9883
|
27 |
+
- Precision: 0.9883
|
28 |
+
- Recall: 0.9883
|
29 |
+
- Confusion Matrix: [[960, 10], [6, 389]]
|
30 |
|
31 |
## Model description
|
32 |
|
|
|
46 |
|
47 |
The following hyperparameters were used during training:
|
48 |
- learning_rate: 3e-05
|
49 |
+
- train_batch_size: 64
|
50 |
+
- eval_batch_size: 64
|
51 |
- seed: 123
|
52 |
+
- gradient_accumulation_steps: 2
|
53 |
+
- total_train_batch_size: 128
|
54 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
55 |
+
- lr_scheduler_type: cosine_with_restarts
|
56 |
+
- lr_scheduler_warmup_ratio: 0.1
|
57 |
+
- num_epochs: 20
|
58 |
+
- label_smoothing_factor: 0.1
|
59 |
|
60 |
### Training results
|
61 |
|
62 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Confusion Matrix |
|
63 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:----------------------:|
|
64 |
+
| 0.3124 | 2.3256 | 100 | 0.2739 | 0.9641 | 0.9640 | 0.9640 | 0.9641 | [[948, 22], [27, 368]] |
|
65 |
+
| 0.2337 | 4.6512 | 200 | 0.2385 | 0.9736 | 0.9737 | 0.9737 | 0.9736 | [[950, 20], [16, 379]] |
|
66 |
+
| 0.2064 | 6.9767 | 300 | 0.2295 | 0.9832 | 0.9832 | 0.9832 | 0.9832 | [[958, 12], [11, 384]] |
|
67 |
+
| 0.2023 | 9.3023 | 400 | 0.2277 | 0.9868 | 0.9869 | 0.9870 | 0.9868 | [[957, 13], [5, 390]] |
|
68 |
+
| 0.2003 | 11.6279 | 500 | 0.2254 | 0.9875 | 0.9876 | 0.9876 | 0.9875 | [[960, 10], [7, 388]] |
|
69 |
+
| 0.2002 | 13.9535 | 600 | 0.2259 | 0.9875 | 0.9876 | 0.9876 | 0.9875 | [[959, 11], [6, 389]] |
|
70 |
+
| 0.1994 | 16.2791 | 700 | 0.2255 | 0.9883 | 0.9883 | 0.9883 | 0.9883 | [[960, 10], [6, 389]] |
|
71 |
+
| 0.1997 | 18.6047 | 800 | 0.2254 | 0.9883 | 0.9883 | 0.9883 | 0.9883 | [[960, 10], [6, 389]] |
|
|
|
|
|
72 |
|
73 |
|
74 |
### Framework versions
|
checkpoint-500/config.json
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"finetuning_task": "audio-classification",
|
49 |
+
"hidden_act": "gelu",
|
50 |
+
"hidden_dropout": 0.1,
|
51 |
+
"hidden_size": 768,
|
52 |
+
"id2label": {
|
53 |
+
"0": "crying",
|
54 |
+
"1": "no_crying"
|
55 |
+
},
|
56 |
+
"initializer_range": 0.02,
|
57 |
+
"intermediate_size": 3072,
|
58 |
+
"layer_norm_eps": 1e-05,
|
59 |
+
"layerdrop": 0.0,
|
60 |
+
"mask_feature_length": 10,
|
61 |
+
"mask_feature_min_masks": 0,
|
62 |
+
"mask_feature_prob": 0.0,
|
63 |
+
"mask_time_length": 10,
|
64 |
+
"mask_time_min_masks": 2,
|
65 |
+
"mask_time_prob": 0.05,
|
66 |
+
"model_type": "hubert",
|
67 |
+
"num_attention_heads": 12,
|
68 |
+
"num_conv_pos_embedding_groups": 16,
|
69 |
+
"num_conv_pos_embeddings": 128,
|
70 |
+
"num_feat_extract_layers": 7,
|
71 |
+
"num_hidden_layers": 2,
|
72 |
+
"pad_token_id": 0,
|
73 |
+
"torch_dtype": "float32",
|
74 |
+
"transformers_version": "4.44.2",
|
75 |
+
"use_weighted_layer_sum": false,
|
76 |
+
"vocab_size": 32
|
77 |
+
}
|
checkpoint-500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2041eca5fb53efe367a7173ea2f8134639376a8725d1d5e4b703cc5c51091e4d
|
3 |
+
size 94763496
|
checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2841bddb32715286bfd37dc809b01547440737cf55fe0e6e2a35570191638266
|
3 |
+
size 189552570
|
checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:edf8e41f94dcf5fdfbe835965b81bc88cbb914f7ffde871d0d81b52f38954873
|
3 |
+
size 14308
|
checkpoint-500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3642500630a8e812e7a47cae4b5478d99e83284cbb8a78eda0b69e2f157e5321
|
3 |
+
size 1064
|
checkpoint-500/trainer_state.json
ADDED
@@ -0,0 +1,222 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9875597008648797,
|
3 |
+
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-500",
|
4 |
+
"epoch": 11.627906976744185,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.1627906976744187,
|
13 |
+
"grad_norm": 0.9607858657836914,
|
14 |
+
"learning_rate": 1.744186046511628e-05,
|
15 |
+
"loss": 0.6124,
|
16 |
+
"step": 50
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 2.3255813953488373,
|
20 |
+
"grad_norm": 2.0142862796783447,
|
21 |
+
"learning_rate": 2.997578868976474e-05,
|
22 |
+
"loss": 0.3124,
|
23 |
+
"step": 100
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.3255813953488373,
|
27 |
+
"eval_accuracy": 0.9641025641025641,
|
28 |
+
"eval_confusion_matrix": [
|
29 |
+
[
|
30 |
+
948,
|
31 |
+
22
|
32 |
+
],
|
33 |
+
[
|
34 |
+
27,
|
35 |
+
368
|
36 |
+
]
|
37 |
+
],
|
38 |
+
"eval_f1": 0.9640343817214121,
|
39 |
+
"eval_loss": 0.2739163041114807,
|
40 |
+
"eval_precision": 0.9639973701512163,
|
41 |
+
"eval_recall": 0.9641025641025641,
|
42 |
+
"eval_runtime": 3.48,
|
43 |
+
"eval_samples_per_second": 392.238,
|
44 |
+
"eval_steps_per_second": 6.322,
|
45 |
+
"step": 100
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 3.488372093023256,
|
49 |
+
"grad_norm": 1.6254416704177856,
|
50 |
+
"learning_rate": 2.9496736466239833e-05,
|
51 |
+
"loss": 0.2509,
|
52 |
+
"step": 150
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 4.651162790697675,
|
56 |
+
"grad_norm": 1.0478523969650269,
|
57 |
+
"learning_rate": 2.8422656841613377e-05,
|
58 |
+
"loss": 0.2337,
|
59 |
+
"step": 200
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.651162790697675,
|
63 |
+
"eval_accuracy": 0.9736263736263736,
|
64 |
+
"eval_confusion_matrix": [
|
65 |
+
[
|
66 |
+
950,
|
67 |
+
20
|
68 |
+
],
|
69 |
+
[
|
70 |
+
16,
|
71 |
+
379
|
72 |
+
]
|
73 |
+
],
|
74 |
+
"eval_f1": 0.9736655604528286,
|
75 |
+
"eval_loss": 0.23845618963241577,
|
76 |
+
"eval_precision": 0.9737247242968067,
|
77 |
+
"eval_recall": 0.9736263736263736,
|
78 |
+
"eval_runtime": 3.3782,
|
79 |
+
"eval_samples_per_second": 404.066,
|
80 |
+
"eval_steps_per_second": 6.512,
|
81 |
+
"step": 200
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 5.813953488372093,
|
85 |
+
"grad_norm": 0.19202682375907898,
|
86 |
+
"learning_rate": 2.679763606999547e-05,
|
87 |
+
"loss": 0.213,
|
88 |
+
"step": 250
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 6.976744186046512,
|
92 |
+
"grad_norm": 3.5125396251678467,
|
93 |
+
"learning_rate": 2.4688374121322346e-05,
|
94 |
+
"loss": 0.2064,
|
95 |
+
"step": 300
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 6.976744186046512,
|
99 |
+
"eval_accuracy": 0.9831501831501831,
|
100 |
+
"eval_confusion_matrix": [
|
101 |
+
[
|
102 |
+
958,
|
103 |
+
12
|
104 |
+
],
|
105 |
+
[
|
106 |
+
11,
|
107 |
+
384
|
108 |
+
]
|
109 |
+
],
|
110 |
+
"eval_f1": 0.9831564891330211,
|
111 |
+
"eval_loss": 0.2294875830411911,
|
112 |
+
"eval_precision": 0.983164066755398,
|
113 |
+
"eval_recall": 0.9831501831501831,
|
114 |
+
"eval_runtime": 3.421,
|
115 |
+
"eval_samples_per_second": 399.01,
|
116 |
+
"eval_steps_per_second": 6.431,
|
117 |
+
"step": 300
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 8.13953488372093,
|
121 |
+
"grad_norm": 0.06433115154504776,
|
122 |
+
"learning_rate": 2.218144694035814e-05,
|
123 |
+
"loss": 0.2044,
|
124 |
+
"step": 350
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 9.30232558139535,
|
128 |
+
"grad_norm": 0.1391066163778305,
|
129 |
+
"learning_rate": 1.9379752884171956e-05,
|
130 |
+
"loss": 0.2023,
|
131 |
+
"step": 400
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 9.30232558139535,
|
135 |
+
"eval_accuracy": 0.9868131868131869,
|
136 |
+
"eval_confusion_matrix": [
|
137 |
+
[
|
138 |
+
957,
|
139 |
+
13
|
140 |
+
],
|
141 |
+
[
|
142 |
+
5,
|
143 |
+
390
|
144 |
+
]
|
145 |
+
],
|
146 |
+
"eval_f1": 0.9868519842367506,
|
147 |
+
"eval_loss": 0.22771421074867249,
|
148 |
+
"eval_precision": 0.986971783497838,
|
149 |
+
"eval_recall": 0.9868131868131869,
|
150 |
+
"eval_runtime": 3.414,
|
151 |
+
"eval_samples_per_second": 399.822,
|
152 |
+
"eval_steps_per_second": 6.444,
|
153 |
+
"step": 400
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 10.465116279069768,
|
157 |
+
"grad_norm": 0.03317234292626381,
|
158 |
+
"learning_rate": 1.6398289196234188e-05,
|
159 |
+
"loss": 0.201,
|
160 |
+
"step": 450
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 11.627906976744185,
|
164 |
+
"grad_norm": 0.0141974575817585,
|
165 |
+
"learning_rate": 1.3359431874331888e-05,
|
166 |
+
"loss": 0.2003,
|
167 |
+
"step": 500
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 11.627906976744185,
|
171 |
+
"eval_accuracy": 0.9875457875457876,
|
172 |
+
"eval_confusion_matrix": [
|
173 |
+
[
|
174 |
+
960,
|
175 |
+
10
|
176 |
+
],
|
177 |
+
[
|
178 |
+
7,
|
179 |
+
388
|
180 |
+
]
|
181 |
+
],
|
182 |
+
"eval_f1": 0.9875597008648797,
|
183 |
+
"eval_loss": 0.22541972994804382,
|
184 |
+
"eval_precision": 0.9875850990732533,
|
185 |
+
"eval_recall": 0.9875457875457876,
|
186 |
+
"eval_runtime": 3.4267,
|
187 |
+
"eval_samples_per_second": 398.347,
|
188 |
+
"eval_steps_per_second": 6.42,
|
189 |
+
"step": 500
|
190 |
+
}
|
191 |
+
],
|
192 |
+
"logging_steps": 50,
|
193 |
+
"max_steps": 860,
|
194 |
+
"num_input_tokens_seen": 0,
|
195 |
+
"num_train_epochs": 20,
|
196 |
+
"save_steps": 100,
|
197 |
+
"stateful_callbacks": {
|
198 |
+
"EarlyStoppingCallback": {
|
199 |
+
"args": {
|
200 |
+
"early_stopping_patience": 5,
|
201 |
+
"early_stopping_threshold": 0.001
|
202 |
+
},
|
203 |
+
"attributes": {
|
204 |
+
"early_stopping_patience_counter": 0
|
205 |
+
}
|
206 |
+
},
|
207 |
+
"TrainerControl": {
|
208 |
+
"args": {
|
209 |
+
"should_epoch_stop": false,
|
210 |
+
"should_evaluate": false,
|
211 |
+
"should_log": false,
|
212 |
+
"should_save": true,
|
213 |
+
"should_training_stop": false
|
214 |
+
},
|
215 |
+
"attributes": {}
|
216 |
+
}
|
217 |
+
},
|
218 |
+
"total_flos": 1.44446640051456e+17,
|
219 |
+
"train_batch_size": 64,
|
220 |
+
"trial_name": null,
|
221 |
+
"trial_params": null
|
222 |
+
}
|
checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3d89420c209e2631922a2e295cec92826140b0b4b3a85040e4f26fe755df93c
|
3 |
+
size 5240
|
checkpoint-600/config.json
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"finetuning_task": "audio-classification",
|
49 |
+
"hidden_act": "gelu",
|
50 |
+
"hidden_dropout": 0.1,
|
51 |
+
"hidden_size": 768,
|
52 |
+
"id2label": {
|
53 |
+
"0": "crying",
|
54 |
+
"1": "no_crying"
|
55 |
+
},
|
56 |
+
"initializer_range": 0.02,
|
57 |
+
"intermediate_size": 3072,
|
58 |
+
"layer_norm_eps": 1e-05,
|
59 |
+
"layerdrop": 0.0,
|
60 |
+
"mask_feature_length": 10,
|
61 |
+
"mask_feature_min_masks": 0,
|
62 |
+
"mask_feature_prob": 0.0,
|
63 |
+
"mask_time_length": 10,
|
64 |
+
"mask_time_min_masks": 2,
|
65 |
+
"mask_time_prob": 0.05,
|
66 |
+
"model_type": "hubert",
|
67 |
+
"num_attention_heads": 12,
|
68 |
+
"num_conv_pos_embedding_groups": 16,
|
69 |
+
"num_conv_pos_embeddings": 128,
|
70 |
+
"num_feat_extract_layers": 7,
|
71 |
+
"num_hidden_layers": 2,
|
72 |
+
"pad_token_id": 0,
|
73 |
+
"torch_dtype": "float32",
|
74 |
+
"transformers_version": "4.44.2",
|
75 |
+
"use_weighted_layer_sum": false,
|
76 |
+
"vocab_size": 32
|
77 |
+
}
|
checkpoint-600/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c21555c55a0eb1aec9860b56c83a094ef848ce0579ddca6d5a2738b99a6f806
|
3 |
+
size 94763496
|
checkpoint-600/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7548a3259806672f97717e12300878518dfc2ef8dabff02eac23f755b765bc77
|
3 |
+
size 189552570
|
checkpoint-600/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:651bc52340f775bf5ca0ad060e768c602fb2b8b78ae4dc9f9e330238fb6e4131
|
3 |
+
size 14308
|
checkpoint-600/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbb0226b5a39dda6cf123353e8e8fb3f8a8e30903e4332b33f1dd1a021acd14c
|
3 |
+
size 1064
|
checkpoint-600/trainer_state.json
ADDED
@@ -0,0 +1,258 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9875688610221299,
|
3 |
+
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-600",
|
4 |
+
"epoch": 13.953488372093023,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 600,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.1627906976744187,
|
13 |
+
"grad_norm": 0.9607858657836914,
|
14 |
+
"learning_rate": 1.744186046511628e-05,
|
15 |
+
"loss": 0.6124,
|
16 |
+
"step": 50
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 2.3255813953488373,
|
20 |
+
"grad_norm": 2.0142862796783447,
|
21 |
+
"learning_rate": 2.997578868976474e-05,
|
22 |
+
"loss": 0.3124,
|
23 |
+
"step": 100
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.3255813953488373,
|
27 |
+
"eval_accuracy": 0.9641025641025641,
|
28 |
+
"eval_confusion_matrix": [
|
29 |
+
[
|
30 |
+
948,
|
31 |
+
22
|
32 |
+
],
|
33 |
+
[
|
34 |
+
27,
|
35 |
+
368
|
36 |
+
]
|
37 |
+
],
|
38 |
+
"eval_f1": 0.9640343817214121,
|
39 |
+
"eval_loss": 0.2739163041114807,
|
40 |
+
"eval_precision": 0.9639973701512163,
|
41 |
+
"eval_recall": 0.9641025641025641,
|
42 |
+
"eval_runtime": 3.48,
|
43 |
+
"eval_samples_per_second": 392.238,
|
44 |
+
"eval_steps_per_second": 6.322,
|
45 |
+
"step": 100
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 3.488372093023256,
|
49 |
+
"grad_norm": 1.6254416704177856,
|
50 |
+
"learning_rate": 2.9496736466239833e-05,
|
51 |
+
"loss": 0.2509,
|
52 |
+
"step": 150
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 4.651162790697675,
|
56 |
+
"grad_norm": 1.0478523969650269,
|
57 |
+
"learning_rate": 2.8422656841613377e-05,
|
58 |
+
"loss": 0.2337,
|
59 |
+
"step": 200
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.651162790697675,
|
63 |
+
"eval_accuracy": 0.9736263736263736,
|
64 |
+
"eval_confusion_matrix": [
|
65 |
+
[
|
66 |
+
950,
|
67 |
+
20
|
68 |
+
],
|
69 |
+
[
|
70 |
+
16,
|
71 |
+
379
|
72 |
+
]
|
73 |
+
],
|
74 |
+
"eval_f1": 0.9736655604528286,
|
75 |
+
"eval_loss": 0.23845618963241577,
|
76 |
+
"eval_precision": 0.9737247242968067,
|
77 |
+
"eval_recall": 0.9736263736263736,
|
78 |
+
"eval_runtime": 3.3782,
|
79 |
+
"eval_samples_per_second": 404.066,
|
80 |
+
"eval_steps_per_second": 6.512,
|
81 |
+
"step": 200
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 5.813953488372093,
|
85 |
+
"grad_norm": 0.19202682375907898,
|
86 |
+
"learning_rate": 2.679763606999547e-05,
|
87 |
+
"loss": 0.213,
|
88 |
+
"step": 250
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 6.976744186046512,
|
92 |
+
"grad_norm": 3.5125396251678467,
|
93 |
+
"learning_rate": 2.4688374121322346e-05,
|
94 |
+
"loss": 0.2064,
|
95 |
+
"step": 300
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 6.976744186046512,
|
99 |
+
"eval_accuracy": 0.9831501831501831,
|
100 |
+
"eval_confusion_matrix": [
|
101 |
+
[
|
102 |
+
958,
|
103 |
+
12
|
104 |
+
],
|
105 |
+
[
|
106 |
+
11,
|
107 |
+
384
|
108 |
+
]
|
109 |
+
],
|
110 |
+
"eval_f1": 0.9831564891330211,
|
111 |
+
"eval_loss": 0.2294875830411911,
|
112 |
+
"eval_precision": 0.983164066755398,
|
113 |
+
"eval_recall": 0.9831501831501831,
|
114 |
+
"eval_runtime": 3.421,
|
115 |
+
"eval_samples_per_second": 399.01,
|
116 |
+
"eval_steps_per_second": 6.431,
|
117 |
+
"step": 300
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 8.13953488372093,
|
121 |
+
"grad_norm": 0.06433115154504776,
|
122 |
+
"learning_rate": 2.218144694035814e-05,
|
123 |
+
"loss": 0.2044,
|
124 |
+
"step": 350
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 9.30232558139535,
|
128 |
+
"grad_norm": 0.1391066163778305,
|
129 |
+
"learning_rate": 1.9379752884171956e-05,
|
130 |
+
"loss": 0.2023,
|
131 |
+
"step": 400
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 9.30232558139535,
|
135 |
+
"eval_accuracy": 0.9868131868131869,
|
136 |
+
"eval_confusion_matrix": [
|
137 |
+
[
|
138 |
+
957,
|
139 |
+
13
|
140 |
+
],
|
141 |
+
[
|
142 |
+
5,
|
143 |
+
390
|
144 |
+
]
|
145 |
+
],
|
146 |
+
"eval_f1": 0.9868519842367506,
|
147 |
+
"eval_loss": 0.22771421074867249,
|
148 |
+
"eval_precision": 0.986971783497838,
|
149 |
+
"eval_recall": 0.9868131868131869,
|
150 |
+
"eval_runtime": 3.414,
|
151 |
+
"eval_samples_per_second": 399.822,
|
152 |
+
"eval_steps_per_second": 6.444,
|
153 |
+
"step": 400
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 10.465116279069768,
|
157 |
+
"grad_norm": 0.03317234292626381,
|
158 |
+
"learning_rate": 1.6398289196234188e-05,
|
159 |
+
"loss": 0.201,
|
160 |
+
"step": 450
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 11.627906976744185,
|
164 |
+
"grad_norm": 0.0141974575817585,
|
165 |
+
"learning_rate": 1.3359431874331888e-05,
|
166 |
+
"loss": 0.2003,
|
167 |
+
"step": 500
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 11.627906976744185,
|
171 |
+
"eval_accuracy": 0.9875457875457876,
|
172 |
+
"eval_confusion_matrix": [
|
173 |
+
[
|
174 |
+
960,
|
175 |
+
10
|
176 |
+
],
|
177 |
+
[
|
178 |
+
7,
|
179 |
+
388
|
180 |
+
]
|
181 |
+
],
|
182 |
+
"eval_f1": 0.9875597008648797,
|
183 |
+
"eval_loss": 0.22541972994804382,
|
184 |
+
"eval_precision": 0.9875850990732533,
|
185 |
+
"eval_recall": 0.9875457875457876,
|
186 |
+
"eval_runtime": 3.4267,
|
187 |
+
"eval_samples_per_second": 398.347,
|
188 |
+
"eval_steps_per_second": 6.42,
|
189 |
+
"step": 500
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 12.790697674418604,
|
193 |
+
"grad_norm": 0.020028484985232353,
|
194 |
+
"learning_rate": 1.0387912673007252e-05,
|
195 |
+
"loss": 0.2005,
|
196 |
+
"step": 550
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 13.953488372093023,
|
200 |
+
"grad_norm": 0.013127407990396023,
|
201 |
+
"learning_rate": 7.605699412521431e-06,
|
202 |
+
"loss": 0.2002,
|
203 |
+
"step": 600
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 13.953488372093023,
|
207 |
+
"eval_accuracy": 0.9875457875457876,
|
208 |
+
"eval_confusion_matrix": [
|
209 |
+
[
|
210 |
+
959,
|
211 |
+
11
|
212 |
+
],
|
213 |
+
[
|
214 |
+
6,
|
215 |
+
389
|
216 |
+
]
|
217 |
+
],
|
218 |
+
"eval_f1": 0.9875688610221299,
|
219 |
+
"eval_loss": 0.2259330302476883,
|
220 |
+
"eval_precision": 0.9876237449942113,
|
221 |
+
"eval_recall": 0.9875457875457876,
|
222 |
+
"eval_runtime": 3.3216,
|
223 |
+
"eval_samples_per_second": 410.95,
|
224 |
+
"eval_steps_per_second": 6.623,
|
225 |
+
"step": 600
|
226 |
+
}
|
227 |
+
],
|
228 |
+
"logging_steps": 50,
|
229 |
+
"max_steps": 860,
|
230 |
+
"num_input_tokens_seen": 0,
|
231 |
+
"num_train_epochs": 20,
|
232 |
+
"save_steps": 100,
|
233 |
+
"stateful_callbacks": {
|
234 |
+
"EarlyStoppingCallback": {
|
235 |
+
"args": {
|
236 |
+
"early_stopping_patience": 5,
|
237 |
+
"early_stopping_threshold": 0.001
|
238 |
+
},
|
239 |
+
"attributes": {
|
240 |
+
"early_stopping_patience_counter": 0
|
241 |
+
}
|
242 |
+
},
|
243 |
+
"TrainerControl": {
|
244 |
+
"args": {
|
245 |
+
"should_epoch_stop": false,
|
246 |
+
"should_evaluate": false,
|
247 |
+
"should_log": false,
|
248 |
+
"should_save": true,
|
249 |
+
"should_training_stop": false
|
250 |
+
},
|
251 |
+
"attributes": {}
|
252 |
+
}
|
253 |
+
},
|
254 |
+
"total_flos": 1.73355980821248e+17,
|
255 |
+
"train_batch_size": 64,
|
256 |
+
"trial_name": null,
|
257 |
+
"trial_params": null
|
258 |
+
}
|
checkpoint-600/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3d89420c209e2631922a2e295cec92826140b0b4b3a85040e4f26fe755df93c
|
3 |
+
size 5240
|
checkpoint-700/config.json
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"finetuning_task": "audio-classification",
|
49 |
+
"hidden_act": "gelu",
|
50 |
+
"hidden_dropout": 0.1,
|
51 |
+
"hidden_size": 768,
|
52 |
+
"id2label": {
|
53 |
+
"0": "crying",
|
54 |
+
"1": "no_crying"
|
55 |
+
},
|
56 |
+
"initializer_range": 0.02,
|
57 |
+
"intermediate_size": 3072,
|
58 |
+
"layer_norm_eps": 1e-05,
|
59 |
+
"layerdrop": 0.0,
|
60 |
+
"mask_feature_length": 10,
|
61 |
+
"mask_feature_min_masks": 0,
|
62 |
+
"mask_feature_prob": 0.0,
|
63 |
+
"mask_time_length": 10,
|
64 |
+
"mask_time_min_masks": 2,
|
65 |
+
"mask_time_prob": 0.05,
|
66 |
+
"model_type": "hubert",
|
67 |
+
"num_attention_heads": 12,
|
68 |
+
"num_conv_pos_embedding_groups": 16,
|
69 |
+
"num_conv_pos_embeddings": 128,
|
70 |
+
"num_feat_extract_layers": 7,
|
71 |
+
"num_hidden_layers": 2,
|
72 |
+
"pad_token_id": 0,
|
73 |
+
"torch_dtype": "float32",
|
74 |
+
"transformers_version": "4.44.2",
|
75 |
+
"use_weighted_layer_sum": false,
|
76 |
+
"vocab_size": 32
|
77 |
+
}
|
checkpoint-700/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc9d6a3efaa15139c296f80cc6ffb6fb613e832c8d723e4e3b6b9262917a4d3c
|
3 |
+
size 94763496
|
checkpoint-700/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98e2c90128a1e2ea359948ddde461ddbd528fd38eb7b3d98c943f471de53b0fd
|
3 |
+
size 189552570
|
checkpoint-700/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b58dca5fb1b7169134a579fbefe18f63835f88838b2ef059378fcdd3c9cecd5f
|
3 |
+
size 14308
|
checkpoint-700/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9763cc72a9be84b93ee3f8307b04709caa68b45aea1c765c4087e9b0f2cec06b
|
3 |
+
size 1064
|
checkpoint-700/trainer_state.json
ADDED
@@ -0,0 +1,294 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9882958046457017,
|
3 |
+
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-700",
|
4 |
+
"epoch": 16.27906976744186,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 700,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.1627906976744187,
|
13 |
+
"grad_norm": 0.9607858657836914,
|
14 |
+
"learning_rate": 1.744186046511628e-05,
|
15 |
+
"loss": 0.6124,
|
16 |
+
"step": 50
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 2.3255813953488373,
|
20 |
+
"grad_norm": 2.0142862796783447,
|
21 |
+
"learning_rate": 2.997578868976474e-05,
|
22 |
+
"loss": 0.3124,
|
23 |
+
"step": 100
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.3255813953488373,
|
27 |
+
"eval_accuracy": 0.9641025641025641,
|
28 |
+
"eval_confusion_matrix": [
|
29 |
+
[
|
30 |
+
948,
|
31 |
+
22
|
32 |
+
],
|
33 |
+
[
|
34 |
+
27,
|
35 |
+
368
|
36 |
+
]
|
37 |
+
],
|
38 |
+
"eval_f1": 0.9640343817214121,
|
39 |
+
"eval_loss": 0.2739163041114807,
|
40 |
+
"eval_precision": 0.9639973701512163,
|
41 |
+
"eval_recall": 0.9641025641025641,
|
42 |
+
"eval_runtime": 3.48,
|
43 |
+
"eval_samples_per_second": 392.238,
|
44 |
+
"eval_steps_per_second": 6.322,
|
45 |
+
"step": 100
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 3.488372093023256,
|
49 |
+
"grad_norm": 1.6254416704177856,
|
50 |
+
"learning_rate": 2.9496736466239833e-05,
|
51 |
+
"loss": 0.2509,
|
52 |
+
"step": 150
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 4.651162790697675,
|
56 |
+
"grad_norm": 1.0478523969650269,
|
57 |
+
"learning_rate": 2.8422656841613377e-05,
|
58 |
+
"loss": 0.2337,
|
59 |
+
"step": 200
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.651162790697675,
|
63 |
+
"eval_accuracy": 0.9736263736263736,
|
64 |
+
"eval_confusion_matrix": [
|
65 |
+
[
|
66 |
+
950,
|
67 |
+
20
|
68 |
+
],
|
69 |
+
[
|
70 |
+
16,
|
71 |
+
379
|
72 |
+
]
|
73 |
+
],
|
74 |
+
"eval_f1": 0.9736655604528286,
|
75 |
+
"eval_loss": 0.23845618963241577,
|
76 |
+
"eval_precision": 0.9737247242968067,
|
77 |
+
"eval_recall": 0.9736263736263736,
|
78 |
+
"eval_runtime": 3.3782,
|
79 |
+
"eval_samples_per_second": 404.066,
|
80 |
+
"eval_steps_per_second": 6.512,
|
81 |
+
"step": 200
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 5.813953488372093,
|
85 |
+
"grad_norm": 0.19202682375907898,
|
86 |
+
"learning_rate": 2.679763606999547e-05,
|
87 |
+
"loss": 0.213,
|
88 |
+
"step": 250
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 6.976744186046512,
|
92 |
+
"grad_norm": 3.5125396251678467,
|
93 |
+
"learning_rate": 2.4688374121322346e-05,
|
94 |
+
"loss": 0.2064,
|
95 |
+
"step": 300
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 6.976744186046512,
|
99 |
+
"eval_accuracy": 0.9831501831501831,
|
100 |
+
"eval_confusion_matrix": [
|
101 |
+
[
|
102 |
+
958,
|
103 |
+
12
|
104 |
+
],
|
105 |
+
[
|
106 |
+
11,
|
107 |
+
384
|
108 |
+
]
|
109 |
+
],
|
110 |
+
"eval_f1": 0.9831564891330211,
|
111 |
+
"eval_loss": 0.2294875830411911,
|
112 |
+
"eval_precision": 0.983164066755398,
|
113 |
+
"eval_recall": 0.9831501831501831,
|
114 |
+
"eval_runtime": 3.421,
|
115 |
+
"eval_samples_per_second": 399.01,
|
116 |
+
"eval_steps_per_second": 6.431,
|
117 |
+
"step": 300
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 8.13953488372093,
|
121 |
+
"grad_norm": 0.06433115154504776,
|
122 |
+
"learning_rate": 2.218144694035814e-05,
|
123 |
+
"loss": 0.2044,
|
124 |
+
"step": 350
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 9.30232558139535,
|
128 |
+
"grad_norm": 0.1391066163778305,
|
129 |
+
"learning_rate": 1.9379752884171956e-05,
|
130 |
+
"loss": 0.2023,
|
131 |
+
"step": 400
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 9.30232558139535,
|
135 |
+
"eval_accuracy": 0.9868131868131869,
|
136 |
+
"eval_confusion_matrix": [
|
137 |
+
[
|
138 |
+
957,
|
139 |
+
13
|
140 |
+
],
|
141 |
+
[
|
142 |
+
5,
|
143 |
+
390
|
144 |
+
]
|
145 |
+
],
|
146 |
+
"eval_f1": 0.9868519842367506,
|
147 |
+
"eval_loss": 0.22771421074867249,
|
148 |
+
"eval_precision": 0.986971783497838,
|
149 |
+
"eval_recall": 0.9868131868131869,
|
150 |
+
"eval_runtime": 3.414,
|
151 |
+
"eval_samples_per_second": 399.822,
|
152 |
+
"eval_steps_per_second": 6.444,
|
153 |
+
"step": 400
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 10.465116279069768,
|
157 |
+
"grad_norm": 0.03317234292626381,
|
158 |
+
"learning_rate": 1.6398289196234188e-05,
|
159 |
+
"loss": 0.201,
|
160 |
+
"step": 450
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 11.627906976744185,
|
164 |
+
"grad_norm": 0.0141974575817585,
|
165 |
+
"learning_rate": 1.3359431874331888e-05,
|
166 |
+
"loss": 0.2003,
|
167 |
+
"step": 500
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 11.627906976744185,
|
171 |
+
"eval_accuracy": 0.9875457875457876,
|
172 |
+
"eval_confusion_matrix": [
|
173 |
+
[
|
174 |
+
960,
|
175 |
+
10
|
176 |
+
],
|
177 |
+
[
|
178 |
+
7,
|
179 |
+
388
|
180 |
+
]
|
181 |
+
],
|
182 |
+
"eval_f1": 0.9875597008648797,
|
183 |
+
"eval_loss": 0.22541972994804382,
|
184 |
+
"eval_precision": 0.9875850990732533,
|
185 |
+
"eval_recall": 0.9875457875457876,
|
186 |
+
"eval_runtime": 3.4267,
|
187 |
+
"eval_samples_per_second": 398.347,
|
188 |
+
"eval_steps_per_second": 6.42,
|
189 |
+
"step": 500
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 12.790697674418604,
|
193 |
+
"grad_norm": 0.020028484985232353,
|
194 |
+
"learning_rate": 1.0387912673007252e-05,
|
195 |
+
"loss": 0.2005,
|
196 |
+
"step": 550
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 13.953488372093023,
|
200 |
+
"grad_norm": 0.013127407990396023,
|
201 |
+
"learning_rate": 7.605699412521431e-06,
|
202 |
+
"loss": 0.2002,
|
203 |
+
"step": 600
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 13.953488372093023,
|
207 |
+
"eval_accuracy": 0.9875457875457876,
|
208 |
+
"eval_confusion_matrix": [
|
209 |
+
[
|
210 |
+
959,
|
211 |
+
11
|
212 |
+
],
|
213 |
+
[
|
214 |
+
6,
|
215 |
+
389
|
216 |
+
]
|
217 |
+
],
|
218 |
+
"eval_f1": 0.9875688610221299,
|
219 |
+
"eval_loss": 0.2259330302476883,
|
220 |
+
"eval_precision": 0.9876237449942113,
|
221 |
+
"eval_recall": 0.9875457875457876,
|
222 |
+
"eval_runtime": 3.3216,
|
223 |
+
"eval_samples_per_second": 410.95,
|
224 |
+
"eval_steps_per_second": 6.623,
|
225 |
+
"step": 600
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 15.116279069767442,
|
229 |
+
"grad_norm": 0.016032038256525993,
|
230 |
+
"learning_rate": 5.126989735188782e-06,
|
231 |
+
"loss": 0.2012,
|
232 |
+
"step": 650
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 16.27906976744186,
|
236 |
+
"grad_norm": 0.012081542983651161,
|
237 |
+
"learning_rate": 3.0535237934100274e-06,
|
238 |
+
"loss": 0.1994,
|
239 |
+
"step": 700
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 16.27906976744186,
|
243 |
+
"eval_accuracy": 0.9882783882783883,
|
244 |
+
"eval_confusion_matrix": [
|
245 |
+
[
|
246 |
+
960,
|
247 |
+
10
|
248 |
+
],
|
249 |
+
[
|
250 |
+
6,
|
251 |
+
389
|
252 |
+
]
|
253 |
+
],
|
254 |
+
"eval_f1": 0.9882958046457017,
|
255 |
+
"eval_loss": 0.22554340958595276,
|
256 |
+
"eval_precision": 0.9883336307004172,
|
257 |
+
"eval_recall": 0.9882783882783883,
|
258 |
+
"eval_runtime": 3.3839,
|
259 |
+
"eval_samples_per_second": 403.383,
|
260 |
+
"eval_steps_per_second": 6.501,
|
261 |
+
"step": 700
|
262 |
+
}
|
263 |
+
],
|
264 |
+
"logging_steps": 50,
|
265 |
+
"max_steps": 860,
|
266 |
+
"num_input_tokens_seen": 0,
|
267 |
+
"num_train_epochs": 20,
|
268 |
+
"save_steps": 100,
|
269 |
+
"stateful_callbacks": {
|
270 |
+
"EarlyStoppingCallback": {
|
271 |
+
"args": {
|
272 |
+
"early_stopping_patience": 5,
|
273 |
+
"early_stopping_threshold": 0.001
|
274 |
+
},
|
275 |
+
"attributes": {
|
276 |
+
"early_stopping_patience_counter": 0
|
277 |
+
}
|
278 |
+
},
|
279 |
+
"TrainerControl": {
|
280 |
+
"args": {
|
281 |
+
"should_epoch_stop": false,
|
282 |
+
"should_evaluate": false,
|
283 |
+
"should_log": false,
|
284 |
+
"should_save": true,
|
285 |
+
"should_training_stop": false
|
286 |
+
},
|
287 |
+
"attributes": {}
|
288 |
+
}
|
289 |
+
},
|
290 |
+
"total_flos": 2.02165257793536e+17,
|
291 |
+
"train_batch_size": 64,
|
292 |
+
"trial_name": null,
|
293 |
+
"trial_params": null
|
294 |
+
}
|
checkpoint-700/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3d89420c209e2631922a2e295cec92826140b0b4b3a85040e4f26fe755df93c
|
3 |
+
size 5240
|
checkpoint-800/config.json
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"finetuning_task": "audio-classification",
|
49 |
+
"hidden_act": "gelu",
|
50 |
+
"hidden_dropout": 0.1,
|
51 |
+
"hidden_size": 768,
|
52 |
+
"id2label": {
|
53 |
+
"0": "crying",
|
54 |
+
"1": "no_crying"
|
55 |
+
},
|
56 |
+
"initializer_range": 0.02,
|
57 |
+
"intermediate_size": 3072,
|
58 |
+
"layer_norm_eps": 1e-05,
|
59 |
+
"layerdrop": 0.0,
|
60 |
+
"mask_feature_length": 10,
|
61 |
+
"mask_feature_min_masks": 0,
|
62 |
+
"mask_feature_prob": 0.0,
|
63 |
+
"mask_time_length": 10,
|
64 |
+
"mask_time_min_masks": 2,
|
65 |
+
"mask_time_prob": 0.05,
|
66 |
+
"model_type": "hubert",
|
67 |
+
"num_attention_heads": 12,
|
68 |
+
"num_conv_pos_embedding_groups": 16,
|
69 |
+
"num_conv_pos_embeddings": 128,
|
70 |
+
"num_feat_extract_layers": 7,
|
71 |
+
"num_hidden_layers": 2,
|
72 |
+
"pad_token_id": 0,
|
73 |
+
"torch_dtype": "float32",
|
74 |
+
"transformers_version": "4.44.2",
|
75 |
+
"use_weighted_layer_sum": false,
|
76 |
+
"vocab_size": 32
|
77 |
+
}
|
checkpoint-800/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ca2c8b3045e83eee0dd3997a0d466b85f518369f3117e39e4afe419a6cab06b
|
3 |
+
size 94763496
|
checkpoint-800/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48fe4b3c8426713ecb377f192fbe2278ecf2710151ea3b3a8d8e5710d4c0dd32
|
3 |
+
size 189552570
|
checkpoint-800/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b21d10b3ec1e745fe106985b1f76b00d319efb8e992b1ee18f7aa51bf01b984
|
3 |
+
size 14308
|
checkpoint-800/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e085557df30c0fd508f88a56be4593075bb2341a5f76662bf774b850aa237abb
|
3 |
+
size 1064
|
checkpoint-800/trainer_state.json
ADDED
@@ -0,0 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9882958046457017,
|
3 |
+
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-700",
|
4 |
+
"epoch": 18.6046511627907,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 800,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.1627906976744187,
|
13 |
+
"grad_norm": 0.9607858657836914,
|
14 |
+
"learning_rate": 1.744186046511628e-05,
|
15 |
+
"loss": 0.6124,
|
16 |
+
"step": 50
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 2.3255813953488373,
|
20 |
+
"grad_norm": 2.0142862796783447,
|
21 |
+
"learning_rate": 2.997578868976474e-05,
|
22 |
+
"loss": 0.3124,
|
23 |
+
"step": 100
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.3255813953488373,
|
27 |
+
"eval_accuracy": 0.9641025641025641,
|
28 |
+
"eval_confusion_matrix": [
|
29 |
+
[
|
30 |
+
948,
|
31 |
+
22
|
32 |
+
],
|
33 |
+
[
|
34 |
+
27,
|
35 |
+
368
|
36 |
+
]
|
37 |
+
],
|
38 |
+
"eval_f1": 0.9640343817214121,
|
39 |
+
"eval_loss": 0.2739163041114807,
|
40 |
+
"eval_precision": 0.9639973701512163,
|
41 |
+
"eval_recall": 0.9641025641025641,
|
42 |
+
"eval_runtime": 3.48,
|
43 |
+
"eval_samples_per_second": 392.238,
|
44 |
+
"eval_steps_per_second": 6.322,
|
45 |
+
"step": 100
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 3.488372093023256,
|
49 |
+
"grad_norm": 1.6254416704177856,
|
50 |
+
"learning_rate": 2.9496736466239833e-05,
|
51 |
+
"loss": 0.2509,
|
52 |
+
"step": 150
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 4.651162790697675,
|
56 |
+
"grad_norm": 1.0478523969650269,
|
57 |
+
"learning_rate": 2.8422656841613377e-05,
|
58 |
+
"loss": 0.2337,
|
59 |
+
"step": 200
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.651162790697675,
|
63 |
+
"eval_accuracy": 0.9736263736263736,
|
64 |
+
"eval_confusion_matrix": [
|
65 |
+
[
|
66 |
+
950,
|
67 |
+
20
|
68 |
+
],
|
69 |
+
[
|
70 |
+
16,
|
71 |
+
379
|
72 |
+
]
|
73 |
+
],
|
74 |
+
"eval_f1": 0.9736655604528286,
|
75 |
+
"eval_loss": 0.23845618963241577,
|
76 |
+
"eval_precision": 0.9737247242968067,
|
77 |
+
"eval_recall": 0.9736263736263736,
|
78 |
+
"eval_runtime": 3.3782,
|
79 |
+
"eval_samples_per_second": 404.066,
|
80 |
+
"eval_steps_per_second": 6.512,
|
81 |
+
"step": 200
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 5.813953488372093,
|
85 |
+
"grad_norm": 0.19202682375907898,
|
86 |
+
"learning_rate": 2.679763606999547e-05,
|
87 |
+
"loss": 0.213,
|
88 |
+
"step": 250
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 6.976744186046512,
|
92 |
+
"grad_norm": 3.5125396251678467,
|
93 |
+
"learning_rate": 2.4688374121322346e-05,
|
94 |
+
"loss": 0.2064,
|
95 |
+
"step": 300
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 6.976744186046512,
|
99 |
+
"eval_accuracy": 0.9831501831501831,
|
100 |
+
"eval_confusion_matrix": [
|
101 |
+
[
|
102 |
+
958,
|
103 |
+
12
|
104 |
+
],
|
105 |
+
[
|
106 |
+
11,
|
107 |
+
384
|
108 |
+
]
|
109 |
+
],
|
110 |
+
"eval_f1": 0.9831564891330211,
|
111 |
+
"eval_loss": 0.2294875830411911,
|
112 |
+
"eval_precision": 0.983164066755398,
|
113 |
+
"eval_recall": 0.9831501831501831,
|
114 |
+
"eval_runtime": 3.421,
|
115 |
+
"eval_samples_per_second": 399.01,
|
116 |
+
"eval_steps_per_second": 6.431,
|
117 |
+
"step": 300
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 8.13953488372093,
|
121 |
+
"grad_norm": 0.06433115154504776,
|
122 |
+
"learning_rate": 2.218144694035814e-05,
|
123 |
+
"loss": 0.2044,
|
124 |
+
"step": 350
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 9.30232558139535,
|
128 |
+
"grad_norm": 0.1391066163778305,
|
129 |
+
"learning_rate": 1.9379752884171956e-05,
|
130 |
+
"loss": 0.2023,
|
131 |
+
"step": 400
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 9.30232558139535,
|
135 |
+
"eval_accuracy": 0.9868131868131869,
|
136 |
+
"eval_confusion_matrix": [
|
137 |
+
[
|
138 |
+
957,
|
139 |
+
13
|
140 |
+
],
|
141 |
+
[
|
142 |
+
5,
|
143 |
+
390
|
144 |
+
]
|
145 |
+
],
|
146 |
+
"eval_f1": 0.9868519842367506,
|
147 |
+
"eval_loss": 0.22771421074867249,
|
148 |
+
"eval_precision": 0.986971783497838,
|
149 |
+
"eval_recall": 0.9868131868131869,
|
150 |
+
"eval_runtime": 3.414,
|
151 |
+
"eval_samples_per_second": 399.822,
|
152 |
+
"eval_steps_per_second": 6.444,
|
153 |
+
"step": 400
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 10.465116279069768,
|
157 |
+
"grad_norm": 0.03317234292626381,
|
158 |
+
"learning_rate": 1.6398289196234188e-05,
|
159 |
+
"loss": 0.201,
|
160 |
+
"step": 450
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 11.627906976744185,
|
164 |
+
"grad_norm": 0.0141974575817585,
|
165 |
+
"learning_rate": 1.3359431874331888e-05,
|
166 |
+
"loss": 0.2003,
|
167 |
+
"step": 500
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 11.627906976744185,
|
171 |
+
"eval_accuracy": 0.9875457875457876,
|
172 |
+
"eval_confusion_matrix": [
|
173 |
+
[
|
174 |
+
960,
|
175 |
+
10
|
176 |
+
],
|
177 |
+
[
|
178 |
+
7,
|
179 |
+
388
|
180 |
+
]
|
181 |
+
],
|
182 |
+
"eval_f1": 0.9875597008648797,
|
183 |
+
"eval_loss": 0.22541972994804382,
|
184 |
+
"eval_precision": 0.9875850990732533,
|
185 |
+
"eval_recall": 0.9875457875457876,
|
186 |
+
"eval_runtime": 3.4267,
|
187 |
+
"eval_samples_per_second": 398.347,
|
188 |
+
"eval_steps_per_second": 6.42,
|
189 |
+
"step": 500
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 12.790697674418604,
|
193 |
+
"grad_norm": 0.020028484985232353,
|
194 |
+
"learning_rate": 1.0387912673007252e-05,
|
195 |
+
"loss": 0.2005,
|
196 |
+
"step": 550
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 13.953488372093023,
|
200 |
+
"grad_norm": 0.013127407990396023,
|
201 |
+
"learning_rate": 7.605699412521431e-06,
|
202 |
+
"loss": 0.2002,
|
203 |
+
"step": 600
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 13.953488372093023,
|
207 |
+
"eval_accuracy": 0.9875457875457876,
|
208 |
+
"eval_confusion_matrix": [
|
209 |
+
[
|
210 |
+
959,
|
211 |
+
11
|
212 |
+
],
|
213 |
+
[
|
214 |
+
6,
|
215 |
+
389
|
216 |
+
]
|
217 |
+
],
|
218 |
+
"eval_f1": 0.9875688610221299,
|
219 |
+
"eval_loss": 0.2259330302476883,
|
220 |
+
"eval_precision": 0.9876237449942113,
|
221 |
+
"eval_recall": 0.9875457875457876,
|
222 |
+
"eval_runtime": 3.3216,
|
223 |
+
"eval_samples_per_second": 410.95,
|
224 |
+
"eval_steps_per_second": 6.623,
|
225 |
+
"step": 600
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 15.116279069767442,
|
229 |
+
"grad_norm": 0.016032038256525993,
|
230 |
+
"learning_rate": 5.126989735188782e-06,
|
231 |
+
"loss": 0.2012,
|
232 |
+
"step": 650
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 16.27906976744186,
|
236 |
+
"grad_norm": 0.012081542983651161,
|
237 |
+
"learning_rate": 3.0535237934100274e-06,
|
238 |
+
"loss": 0.1994,
|
239 |
+
"step": 700
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 16.27906976744186,
|
243 |
+
"eval_accuracy": 0.9882783882783883,
|
244 |
+
"eval_confusion_matrix": [
|
245 |
+
[
|
246 |
+
960,
|
247 |
+
10
|
248 |
+
],
|
249 |
+
[
|
250 |
+
6,
|
251 |
+
389
|
252 |
+
]
|
253 |
+
],
|
254 |
+
"eval_f1": 0.9882958046457017,
|
255 |
+
"eval_loss": 0.22554340958595276,
|
256 |
+
"eval_precision": 0.9883336307004172,
|
257 |
+
"eval_recall": 0.9882783882783883,
|
258 |
+
"eval_runtime": 3.3839,
|
259 |
+
"eval_samples_per_second": 403.383,
|
260 |
+
"eval_steps_per_second": 6.501,
|
261 |
+
"step": 700
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 17.441860465116278,
|
265 |
+
"grad_norm": 0.015530905686318874,
|
266 |
+
"learning_rate": 1.470408262986479e-06,
|
267 |
+
"loss": 0.2008,
|
268 |
+
"step": 750
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 18.6046511627907,
|
272 |
+
"grad_norm": 0.03649911284446716,
|
273 |
+
"learning_rate": 4.4262308763892087e-07,
|
274 |
+
"loss": 0.1997,
|
275 |
+
"step": 800
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 18.6046511627907,
|
279 |
+
"eval_accuracy": 0.9882783882783883,
|
280 |
+
"eval_confusion_matrix": [
|
281 |
+
[
|
282 |
+
960,
|
283 |
+
10
|
284 |
+
],
|
285 |
+
[
|
286 |
+
6,
|
287 |
+
389
|
288 |
+
]
|
289 |
+
],
|
290 |
+
"eval_f1": 0.9882958046457017,
|
291 |
+
"eval_loss": 0.22540099918842316,
|
292 |
+
"eval_precision": 0.9883336307004172,
|
293 |
+
"eval_recall": 0.9882783882783883,
|
294 |
+
"eval_runtime": 3.38,
|
295 |
+
"eval_samples_per_second": 403.852,
|
296 |
+
"eval_steps_per_second": 6.509,
|
297 |
+
"step": 800
|
298 |
+
}
|
299 |
+
],
|
300 |
+
"logging_steps": 50,
|
301 |
+
"max_steps": 860,
|
302 |
+
"num_input_tokens_seen": 0,
|
303 |
+
"num_train_epochs": 20,
|
304 |
+
"save_steps": 100,
|
305 |
+
"stateful_callbacks": {
|
306 |
+
"EarlyStoppingCallback": {
|
307 |
+
"args": {
|
308 |
+
"early_stopping_patience": 5,
|
309 |
+
"early_stopping_threshold": 0.001
|
310 |
+
},
|
311 |
+
"attributes": {
|
312 |
+
"early_stopping_patience_counter": 0
|
313 |
+
}
|
314 |
+
},
|
315 |
+
"TrainerControl": {
|
316 |
+
"args": {
|
317 |
+
"should_epoch_stop": false,
|
318 |
+
"should_evaluate": false,
|
319 |
+
"should_log": false,
|
320 |
+
"should_save": true,
|
321 |
+
"should_training_stop": false
|
322 |
+
},
|
323 |
+
"attributes": {}
|
324 |
+
}
|
325 |
+
},
|
326 |
+
"total_flos": 2.31074598563328e+17,
|
327 |
+
"train_batch_size": 64,
|
328 |
+
"trial_name": null,
|
329 |
+
"trial_params": null
|
330 |
+
}
|
checkpoint-800/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3d89420c209e2631922a2e295cec92826140b0b4b3a85040e4f26fe755df93c
|
3 |
+
size 5240
|
checkpoint-860/config.json
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"finetuning_task": "audio-classification",
|
49 |
+
"hidden_act": "gelu",
|
50 |
+
"hidden_dropout": 0.1,
|
51 |
+
"hidden_size": 768,
|
52 |
+
"id2label": {
|
53 |
+
"0": "crying",
|
54 |
+
"1": "no_crying"
|
55 |
+
},
|
56 |
+
"initializer_range": 0.02,
|
57 |
+
"intermediate_size": 3072,
|
58 |
+
"layer_norm_eps": 1e-05,
|
59 |
+
"layerdrop": 0.0,
|
60 |
+
"mask_feature_length": 10,
|
61 |
+
"mask_feature_min_masks": 0,
|
62 |
+
"mask_feature_prob": 0.0,
|
63 |
+
"mask_time_length": 10,
|
64 |
+
"mask_time_min_masks": 2,
|
65 |
+
"mask_time_prob": 0.05,
|
66 |
+
"model_type": "hubert",
|
67 |
+
"num_attention_heads": 12,
|
68 |
+
"num_conv_pos_embedding_groups": 16,
|
69 |
+
"num_conv_pos_embeddings": 128,
|
70 |
+
"num_feat_extract_layers": 7,
|
71 |
+
"num_hidden_layers": 2,
|
72 |
+
"pad_token_id": 0,
|
73 |
+
"torch_dtype": "float32",
|
74 |
+
"transformers_version": "4.44.2",
|
75 |
+
"use_weighted_layer_sum": false,
|
76 |
+
"vocab_size": 32
|
77 |
+
}
|
checkpoint-860/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39d7ea4d47fbee3393f5e749620e0b4a578cea2449907bfe0372d868b5f4b30a
|
3 |
+
size 94763496
|
checkpoint-860/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1bfa4331625c52dd28223fd3b2cba322b7836ef0875a75d29701a3fd08df747a
|
3 |
+
size 189552570
|
checkpoint-860/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea8e1549744101389fee1cb4923c7729bf266144965aa751df09dad62532a0fd
|
3 |
+
size 14308
|
checkpoint-860/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3305b0d94ed5c5807ba878e31359e591ea9ddd9f01e4c81eb836abb2e249bfab
|
3 |
+
size 1064
|
checkpoint-860/trainer_state.json
ADDED
@@ -0,0 +1,337 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9882958046457017,
|
3 |
+
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-700",
|
4 |
+
"epoch": 20.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 860,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.1627906976744187,
|
13 |
+
"grad_norm": 0.9607858657836914,
|
14 |
+
"learning_rate": 1.744186046511628e-05,
|
15 |
+
"loss": 0.6124,
|
16 |
+
"step": 50
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 2.3255813953488373,
|
20 |
+
"grad_norm": 2.0142862796783447,
|
21 |
+
"learning_rate": 2.997578868976474e-05,
|
22 |
+
"loss": 0.3124,
|
23 |
+
"step": 100
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.3255813953488373,
|
27 |
+
"eval_accuracy": 0.9641025641025641,
|
28 |
+
"eval_confusion_matrix": [
|
29 |
+
[
|
30 |
+
948,
|
31 |
+
22
|
32 |
+
],
|
33 |
+
[
|
34 |
+
27,
|
35 |
+
368
|
36 |
+
]
|
37 |
+
],
|
38 |
+
"eval_f1": 0.9640343817214121,
|
39 |
+
"eval_loss": 0.2739163041114807,
|
40 |
+
"eval_precision": 0.9639973701512163,
|
41 |
+
"eval_recall": 0.9641025641025641,
|
42 |
+
"eval_runtime": 3.48,
|
43 |
+
"eval_samples_per_second": 392.238,
|
44 |
+
"eval_steps_per_second": 6.322,
|
45 |
+
"step": 100
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 3.488372093023256,
|
49 |
+
"grad_norm": 1.6254416704177856,
|
50 |
+
"learning_rate": 2.9496736466239833e-05,
|
51 |
+
"loss": 0.2509,
|
52 |
+
"step": 150
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 4.651162790697675,
|
56 |
+
"grad_norm": 1.0478523969650269,
|
57 |
+
"learning_rate": 2.8422656841613377e-05,
|
58 |
+
"loss": 0.2337,
|
59 |
+
"step": 200
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.651162790697675,
|
63 |
+
"eval_accuracy": 0.9736263736263736,
|
64 |
+
"eval_confusion_matrix": [
|
65 |
+
[
|
66 |
+
950,
|
67 |
+
20
|
68 |
+
],
|
69 |
+
[
|
70 |
+
16,
|
71 |
+
379
|
72 |
+
]
|
73 |
+
],
|
74 |
+
"eval_f1": 0.9736655604528286,
|
75 |
+
"eval_loss": 0.23845618963241577,
|
76 |
+
"eval_precision": 0.9737247242968067,
|
77 |
+
"eval_recall": 0.9736263736263736,
|
78 |
+
"eval_runtime": 3.3782,
|
79 |
+
"eval_samples_per_second": 404.066,
|
80 |
+
"eval_steps_per_second": 6.512,
|
81 |
+
"step": 200
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 5.813953488372093,
|
85 |
+
"grad_norm": 0.19202682375907898,
|
86 |
+
"learning_rate": 2.679763606999547e-05,
|
87 |
+
"loss": 0.213,
|
88 |
+
"step": 250
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 6.976744186046512,
|
92 |
+
"grad_norm": 3.5125396251678467,
|
93 |
+
"learning_rate": 2.4688374121322346e-05,
|
94 |
+
"loss": 0.2064,
|
95 |
+
"step": 300
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 6.976744186046512,
|
99 |
+
"eval_accuracy": 0.9831501831501831,
|
100 |
+
"eval_confusion_matrix": [
|
101 |
+
[
|
102 |
+
958,
|
103 |
+
12
|
104 |
+
],
|
105 |
+
[
|
106 |
+
11,
|
107 |
+
384
|
108 |
+
]
|
109 |
+
],
|
110 |
+
"eval_f1": 0.9831564891330211,
|
111 |
+
"eval_loss": 0.2294875830411911,
|
112 |
+
"eval_precision": 0.983164066755398,
|
113 |
+
"eval_recall": 0.9831501831501831,
|
114 |
+
"eval_runtime": 3.421,
|
115 |
+
"eval_samples_per_second": 399.01,
|
116 |
+
"eval_steps_per_second": 6.431,
|
117 |
+
"step": 300
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 8.13953488372093,
|
121 |
+
"grad_norm": 0.06433115154504776,
|
122 |
+
"learning_rate": 2.218144694035814e-05,
|
123 |
+
"loss": 0.2044,
|
124 |
+
"step": 350
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 9.30232558139535,
|
128 |
+
"grad_norm": 0.1391066163778305,
|
129 |
+
"learning_rate": 1.9379752884171956e-05,
|
130 |
+
"loss": 0.2023,
|
131 |
+
"step": 400
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 9.30232558139535,
|
135 |
+
"eval_accuracy": 0.9868131868131869,
|
136 |
+
"eval_confusion_matrix": [
|
137 |
+
[
|
138 |
+
957,
|
139 |
+
13
|
140 |
+
],
|
141 |
+
[
|
142 |
+
5,
|
143 |
+
390
|
144 |
+
]
|
145 |
+
],
|
146 |
+
"eval_f1": 0.9868519842367506,
|
147 |
+
"eval_loss": 0.22771421074867249,
|
148 |
+
"eval_precision": 0.986971783497838,
|
149 |
+
"eval_recall": 0.9868131868131869,
|
150 |
+
"eval_runtime": 3.414,
|
151 |
+
"eval_samples_per_second": 399.822,
|
152 |
+
"eval_steps_per_second": 6.444,
|
153 |
+
"step": 400
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 10.465116279069768,
|
157 |
+
"grad_norm": 0.03317234292626381,
|
158 |
+
"learning_rate": 1.6398289196234188e-05,
|
159 |
+
"loss": 0.201,
|
160 |
+
"step": 450
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 11.627906976744185,
|
164 |
+
"grad_norm": 0.0141974575817585,
|
165 |
+
"learning_rate": 1.3359431874331888e-05,
|
166 |
+
"loss": 0.2003,
|
167 |
+
"step": 500
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 11.627906976744185,
|
171 |
+
"eval_accuracy": 0.9875457875457876,
|
172 |
+
"eval_confusion_matrix": [
|
173 |
+
[
|
174 |
+
960,
|
175 |
+
10
|
176 |
+
],
|
177 |
+
[
|
178 |
+
7,
|
179 |
+
388
|
180 |
+
]
|
181 |
+
],
|
182 |
+
"eval_f1": 0.9875597008648797,
|
183 |
+
"eval_loss": 0.22541972994804382,
|
184 |
+
"eval_precision": 0.9875850990732533,
|
185 |
+
"eval_recall": 0.9875457875457876,
|
186 |
+
"eval_runtime": 3.4267,
|
187 |
+
"eval_samples_per_second": 398.347,
|
188 |
+
"eval_steps_per_second": 6.42,
|
189 |
+
"step": 500
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 12.790697674418604,
|
193 |
+
"grad_norm": 0.020028484985232353,
|
194 |
+
"learning_rate": 1.0387912673007252e-05,
|
195 |
+
"loss": 0.2005,
|
196 |
+
"step": 550
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 13.953488372093023,
|
200 |
+
"grad_norm": 0.013127407990396023,
|
201 |
+
"learning_rate": 7.605699412521431e-06,
|
202 |
+
"loss": 0.2002,
|
203 |
+
"step": 600
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 13.953488372093023,
|
207 |
+
"eval_accuracy": 0.9875457875457876,
|
208 |
+
"eval_confusion_matrix": [
|
209 |
+
[
|
210 |
+
959,
|
211 |
+
11
|
212 |
+
],
|
213 |
+
[
|
214 |
+
6,
|
215 |
+
389
|
216 |
+
]
|
217 |
+
],
|
218 |
+
"eval_f1": 0.9875688610221299,
|
219 |
+
"eval_loss": 0.2259330302476883,
|
220 |
+
"eval_precision": 0.9876237449942113,
|
221 |
+
"eval_recall": 0.9875457875457876,
|
222 |
+
"eval_runtime": 3.3216,
|
223 |
+
"eval_samples_per_second": 410.95,
|
224 |
+
"eval_steps_per_second": 6.623,
|
225 |
+
"step": 600
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 15.116279069767442,
|
229 |
+
"grad_norm": 0.016032038256525993,
|
230 |
+
"learning_rate": 5.126989735188782e-06,
|
231 |
+
"loss": 0.2012,
|
232 |
+
"step": 650
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 16.27906976744186,
|
236 |
+
"grad_norm": 0.012081542983651161,
|
237 |
+
"learning_rate": 3.0535237934100274e-06,
|
238 |
+
"loss": 0.1994,
|
239 |
+
"step": 700
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 16.27906976744186,
|
243 |
+
"eval_accuracy": 0.9882783882783883,
|
244 |
+
"eval_confusion_matrix": [
|
245 |
+
[
|
246 |
+
960,
|
247 |
+
10
|
248 |
+
],
|
249 |
+
[
|
250 |
+
6,
|
251 |
+
389
|
252 |
+
]
|
253 |
+
],
|
254 |
+
"eval_f1": 0.9882958046457017,
|
255 |
+
"eval_loss": 0.22554340958595276,
|
256 |
+
"eval_precision": 0.9883336307004172,
|
257 |
+
"eval_recall": 0.9882783882783883,
|
258 |
+
"eval_runtime": 3.3839,
|
259 |
+
"eval_samples_per_second": 403.383,
|
260 |
+
"eval_steps_per_second": 6.501,
|
261 |
+
"step": 700
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 17.441860465116278,
|
265 |
+
"grad_norm": 0.015530905686318874,
|
266 |
+
"learning_rate": 1.470408262986479e-06,
|
267 |
+
"loss": 0.2008,
|
268 |
+
"step": 750
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 18.6046511627907,
|
272 |
+
"grad_norm": 0.03649911284446716,
|
273 |
+
"learning_rate": 4.4262308763892087e-07,
|
274 |
+
"loss": 0.1997,
|
275 |
+
"step": 800
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 18.6046511627907,
|
279 |
+
"eval_accuracy": 0.9882783882783883,
|
280 |
+
"eval_confusion_matrix": [
|
281 |
+
[
|
282 |
+
960,
|
283 |
+
10
|
284 |
+
],
|
285 |
+
[
|
286 |
+
6,
|
287 |
+
389
|
288 |
+
]
|
289 |
+
],
|
290 |
+
"eval_f1": 0.9882958046457017,
|
291 |
+
"eval_loss": 0.22540099918842316,
|
292 |
+
"eval_precision": 0.9883336307004172,
|
293 |
+
"eval_recall": 0.9882783882783883,
|
294 |
+
"eval_runtime": 3.38,
|
295 |
+
"eval_samples_per_second": 403.852,
|
296 |
+
"eval_steps_per_second": 6.509,
|
297 |
+
"step": 800
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 19.767441860465116,
|
301 |
+
"grad_norm": 0.17561723291873932,
|
302 |
+
"learning_rate": 1.2354337535766536e-08,
|
303 |
+
"loss": 0.2008,
|
304 |
+
"step": 850
|
305 |
+
}
|
306 |
+
],
|
307 |
+
"logging_steps": 50,
|
308 |
+
"max_steps": 860,
|
309 |
+
"num_input_tokens_seen": 0,
|
310 |
+
"num_train_epochs": 20,
|
311 |
+
"save_steps": 100,
|
312 |
+
"stateful_callbacks": {
|
313 |
+
"EarlyStoppingCallback": {
|
314 |
+
"args": {
|
315 |
+
"early_stopping_patience": 5,
|
316 |
+
"early_stopping_threshold": 0.001
|
317 |
+
},
|
318 |
+
"attributes": {
|
319 |
+
"early_stopping_patience_counter": 0
|
320 |
+
}
|
321 |
+
},
|
322 |
+
"TrainerControl": {
|
323 |
+
"args": {
|
324 |
+
"should_epoch_stop": false,
|
325 |
+
"should_evaluate": false,
|
326 |
+
"should_log": false,
|
327 |
+
"should_save": true,
|
328 |
+
"should_training_stop": true
|
329 |
+
},
|
330 |
+
"attributes": {}
|
331 |
+
}
|
332 |
+
},
|
333 |
+
"total_flos": 2.483401519872e+17,
|
334 |
+
"train_batch_size": 64,
|
335 |
+
"trial_name": null,
|
336 |
+
"trial_params": null
|
337 |
+
}
|
checkpoint-860/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3d89420c209e2631922a2e295cec92826140b0b4b3a85040e4f26fe755df93c
|
3 |
+
size 5240
|
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:dc9d6a3efaa15139c296f80cc6ffb6fb613e832c8d723e4e3b6b9262917a4d3c
|
3 |
size 94763496
|
runs/Sep11_15-20-39_ubumarcos/events.out.tfevents.1726060840.ubumarcos
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3457d6d32eee966361cd1a5e55bfc41aea0b8448b79e8dc0419ad9f56364d56
|
3 |
+
size 5795
|
runs/Sep11_15-21-14_ubumarcos/events.out.tfevents.1726060876.ubumarcos
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2677a6a2bf7d8a64d0c79c173ee4f873dd3a521604a432950bae62def6d8e06e
|
3 |
+
size 7184
|
runs/Sep11_15-25-59_ubumarcos/events.out.tfevents.1726061160.ubumarcos
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8dbe9a7696e2700e9ae245d9bd2b3e8f9ce8e4c4724beed7069fcf4b8827c826
|
3 |
+
size 10773
|
runs/Sep11_15-25-59_ubumarcos/events.out.tfevents.1726061977.ubumarcos
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea600bf545d3d4626fd88b275f082cd15a4449c22b38bdc432c40f465a710247
|
3 |
+
size 503
|
runs/Sep11_15-42-12_ubumarcos/events.out.tfevents.1726062133.ubumarcos
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4204743a7822eb72e21292b34c8728a7257c7e6624882cef2790dc8e48c7dee0
|
3 |
+
size 7647
|
runs/Sep11_15-50-04_ubumarcos/events.out.tfevents.1726062605.ubumarcos
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae11e51efaad3daa9c0afdc2f11dbd3f7305426132549ec41a4a4a274c18c988
|
3 |
+
size 5806
|
runs/Sep11_15-50-31_ubumarcos/events.out.tfevents.1726062632.ubumarcos
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc9e10b14d9386a106cfe9f147897a38340fa2232ba11190681651623aa3eb1a
|
3 |
+
size 5804
|
runs/Sep11_15-50-57_ubumarcos/events.out.tfevents.1726062658.ubumarcos
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e350751289634829a9fd460749053434acd1af6a93ed53f32d40ba013fa2170
|
3 |
+
size 5806
|
runs/Sep11_15-51-52_ubumarcos/events.out.tfevents.1726062713.ubumarcos
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d152b790394ef1654f41e83eee46f69ad24e2c6949b44a7d10b165f8445e42a7
|
3 |
+
size 5807
|
runs/Sep11_15-52-20_ubumarcos/events.out.tfevents.1726062741.ubumarcos
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54b53922a640a17f8f76424c75f29092341a456c1ab191c88af0a378c2b04c97
|
3 |
+
size 5806
|
runs/Sep11_15-52-43_ubumarcos/events.out.tfevents.1726062764.ubumarcos
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:948a1e01a387f8ee74909d6ff171610a41577bf81caef495d41daecdf546b406
|
3 |
+
size 5807
|
runs/Sep11_15-54-06_ubumarcos/events.out.tfevents.1726062847.ubumarcos
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:012e4be1fb2dcb0201aad7f28222fcb79340b9cf0fc188a95c1eb9d0e43a8b33
|
3 |
+
size 5807
|
runs/Sep11_15-54-19_ubumarcos/events.out.tfevents.1726062860.ubumarcos
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17d408531ac1a90d9d340e9886c50d5d601dc05adbeb15f7553e3e20fbb324ee
|
3 |
+
size 5806
|