Marcos12886
commited on
Commit
•
ee61ac2
1
Parent(s):
119c958
Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +45 -3
- checkpoint-102/config.json +80 -0
- checkpoint-102/model.safetensors +3 -0
- checkpoint-102/optimizer.pt +3 -0
- checkpoint-102/preprocessor_config.json +9 -0
- checkpoint-102/rng_state.pth +3 -0
- checkpoint-102/scheduler.pt +3 -0
- checkpoint-102/trainer_state.json +138 -0
- checkpoint-102/training_args.bin +3 -0
- checkpoint-114/config.json +80 -0
- checkpoint-114/model.safetensors +3 -0
- checkpoint-114/optimizer.pt +3 -0
- checkpoint-114/preprocessor_config.json +9 -0
- checkpoint-114/rng_state.pth +3 -0
- checkpoint-114/scheduler.pt +3 -0
- checkpoint-114/trainer_state.json +150 -0
- checkpoint-114/training_args.bin +3 -0
- checkpoint-12/model.safetensors +1 -1
- checkpoint-12/optimizer.pt +1 -1
- checkpoint-12/rng_state.pth +1 -1
- checkpoint-12/scheduler.pt +1 -1
- checkpoint-12/trainer_state.json +13 -13
- checkpoint-12/training_args.bin +1 -1
- checkpoint-120/config.json +80 -0
- checkpoint-120/model.safetensors +3 -0
- checkpoint-120/optimizer.pt +3 -0
- checkpoint-120/preprocessor_config.json +9 -0
- checkpoint-120/rng_state.pth +3 -0
- checkpoint-120/scheduler.pt +3 -0
- checkpoint-120/trainer_state.json +162 -0
- checkpoint-120/training_args.bin +3 -0
- checkpoint-25/model.safetensors +1 -1
- checkpoint-25/optimizer.pt +1 -1
- checkpoint-25/rng_state.pth +2 -2
- checkpoint-25/scheduler.pt +1 -1
- checkpoint-25/trainer_state.json +20 -20
- checkpoint-25/training_args.bin +1 -1
- checkpoint-38/model.safetensors +1 -1
- checkpoint-38/optimizer.pt +1 -1
- checkpoint-38/rng_state.pth +2 -2
- checkpoint-38/scheduler.pt +1 -1
- checkpoint-38/trainer_state.json +28 -28
- checkpoint-38/training_args.bin +1 -1
- checkpoint-51/model.safetensors +1 -1
- checkpoint-51/optimizer.pt +1 -1
- checkpoint-51/rng_state.pth +2 -2
- checkpoint-51/scheduler.pt +1 -1
- checkpoint-51/trainer_state.json +36 -36
- checkpoint-51/training_args.bin +1 -1
- checkpoint-63/model.safetensors +1 -1
README.md
CHANGED
@@ -6,9 +6,36 @@ tags:
|
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
8 |
- audiofolder
|
|
|
|
|
|
|
|
|
|
|
9 |
model-index:
|
10 |
- name: distilhubert-finetuned-cry-detector
|
11 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
---
|
13 |
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -17,6 +44,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
# distilhubert-finetuned-cry-detector
|
18 |
|
19 |
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -44,13 +77,22 @@ The following hyperparameters were used during training:
|
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: cosine
|
46 |
- lr_scheduler_warmup_ratio: 0.001
|
47 |
-
- num_epochs:
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
52 |
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
53 |
-
| No log | 0.9412 | 12 | 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
|
55 |
|
56 |
### Framework versions
|
|
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
8 |
- audiofolder
|
9 |
+
metrics:
|
10 |
+
- accuracy
|
11 |
+
- f1
|
12 |
+
- precision
|
13 |
+
- recall
|
14 |
model-index:
|
15 |
- name: distilhubert-finetuned-cry-detector
|
16 |
+
results:
|
17 |
+
- task:
|
18 |
+
name: Audio Classification
|
19 |
+
type: audio-classification
|
20 |
+
dataset:
|
21 |
+
name: audiofolder
|
22 |
+
type: audiofolder
|
23 |
+
config: default
|
24 |
+
split: train
|
25 |
+
args: default
|
26 |
+
metrics:
|
27 |
+
- name: Accuracy
|
28 |
+
type: accuracy
|
29 |
+
value: 0.9852941176470589
|
30 |
+
- name: F1
|
31 |
+
type: f1
|
32 |
+
value: 0.9853150765112866
|
33 |
+
- name: Precision
|
34 |
+
type: precision
|
35 |
+
value: 0.9853868369053048
|
36 |
+
- name: Recall
|
37 |
+
type: recall
|
38 |
+
value: 0.9852941176470589
|
39 |
---
|
40 |
|
41 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
44 |
# distilhubert-finetuned-cry-detector
|
45 |
|
46 |
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
|
47 |
+
It achieves the following results on the evaluation set:
|
48 |
+
- Loss: 0.0332
|
49 |
+
- Accuracy: 0.9853
|
50 |
+
- F1: 0.9853
|
51 |
+
- Precision: 0.9854
|
52 |
+
- Recall: 0.9853
|
53 |
|
54 |
## Model description
|
55 |
|
|
|
77 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
78 |
- lr_scheduler_type: cosine
|
79 |
- lr_scheduler_warmup_ratio: 0.001
|
80 |
+
- num_epochs: 10
|
81 |
|
82 |
### Training results
|
83 |
|
84 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
85 |
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
86 |
+
| No log | 0.9412 | 12 | 0.1931 | 0.9363 | 0.9365 | 0.9372 | 0.9363 |
|
87 |
+
| No log | 1.9608 | 25 | 0.0950 | 0.9706 | 0.9704 | 0.9710 | 0.9706 |
|
88 |
+
| No log | 2.9804 | 38 | 0.0611 | 0.9804 | 0.9804 | 0.9804 | 0.9804 |
|
89 |
+
| No log | 4.0 | 51 | 0.0492 | 0.9853 | 0.9853 | 0.9853 | 0.9853 |
|
90 |
+
| No log | 4.9412 | 63 | 0.0588 | 0.9804 | 0.9805 | 0.9814 | 0.9804 |
|
91 |
+
| No log | 5.9608 | 76 | 0.0368 | 0.9853 | 0.9853 | 0.9854 | 0.9853 |
|
92 |
+
| No log | 6.9804 | 89 | 0.0382 | 0.9902 | 0.9902 | 0.9903 | 0.9902 |
|
93 |
+
| No log | 8.0 | 102 | 0.0318 | 0.9951 | 0.9951 | 0.9951 | 0.9951 |
|
94 |
+
| No log | 8.9412 | 114 | 0.0331 | 0.9853 | 0.9853 | 0.9854 | 0.9853 |
|
95 |
+
| No log | 9.4118 | 120 | 0.0332 | 0.9853 | 0.9853 | 0.9854 | 0.9853 |
|
96 |
|
97 |
|
98 |
### Framework versions
|
checkpoint-102/config.json
ADDED
@@ -0,0 +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": "4.44.2",
|
78 |
+
"use_weighted_layer_sum": false,
|
79 |
+
"vocab_size": 32
|
80 |
+
}
|
checkpoint-102/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:098c90d2cba195ac20033090c5954f7ef596abcdeebba724cb1365151033b05e
|
3 |
+
size 94763496
|
checkpoint-102/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6038d1ad5c694fa39b163e31b2ae8b290c47bf72179e6f7edebc2516088a6742
|
3 |
+
size 189552570
|
checkpoint-102/preprocessor_config.json
ADDED
@@ -0,0 +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 |
+
}
|
checkpoint-102/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e516bd48eedd1efdcdab1bc63eb245ee5f25372c9b0345efbc5ed2cd8b1b542
|
3 |
+
size 14308
|
checkpoint-102/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b0f7d0de8839ca69a8acf7eae5d4a6ab5235d97ffbdfee2586222c3a1d5f473
|
3 |
+
size 1064
|
checkpoint-102/trainer_state.json
ADDED
@@ -0,0 +1,138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9950980392156863,
|
3 |
+
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-102",
|
4 |
+
"epoch": 8.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 102,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.9411764705882353,
|
13 |
+
"eval_accuracy": 0.9362745098039216,
|
14 |
+
"eval_f1": 0.9365356058160116,
|
15 |
+
"eval_loss": 0.19313116371631622,
|
16 |
+
"eval_precision": 0.9372234219385678,
|
17 |
+
"eval_recall": 0.9362745098039216,
|
18 |
+
"eval_runtime": 3.0986,
|
19 |
+
"eval_samples_per_second": 65.836,
|
20 |
+
"eval_steps_per_second": 8.391,
|
21 |
+
"step": 12
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 1.9607843137254903,
|
25 |
+
"eval_accuracy": 0.9705882352941176,
|
26 |
+
"eval_f1": 0.9704025549613785,
|
27 |
+
"eval_loss": 0.09495726972818375,
|
28 |
+
"eval_precision": 0.971039759187257,
|
29 |
+
"eval_recall": 0.9705882352941176,
|
30 |
+
"eval_runtime": 3.1171,
|
31 |
+
"eval_samples_per_second": 65.446,
|
32 |
+
"eval_steps_per_second": 8.341,
|
33 |
+
"step": 25
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 2.980392156862745,
|
37 |
+
"eval_accuracy": 0.9803921568627451,
|
38 |
+
"eval_f1": 0.9803921568627451,
|
39 |
+
"eval_loss": 0.06114682927727699,
|
40 |
+
"eval_precision": 0.9803921568627451,
|
41 |
+
"eval_recall": 0.9803921568627451,
|
42 |
+
"eval_runtime": 3.2163,
|
43 |
+
"eval_samples_per_second": 63.428,
|
44 |
+
"eval_steps_per_second": 8.084,
|
45 |
+
"step": 38
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 4.0,
|
49 |
+
"eval_accuracy": 0.9852941176470589,
|
50 |
+
"eval_f1": 0.9852722698274712,
|
51 |
+
"eval_loss": 0.049169763922691345,
|
52 |
+
"eval_precision": 0.9853018065952722,
|
53 |
+
"eval_recall": 0.9852941176470589,
|
54 |
+
"eval_runtime": 3.1223,
|
55 |
+
"eval_samples_per_second": 65.336,
|
56 |
+
"eval_steps_per_second": 8.327,
|
57 |
+
"step": 51
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 4.9411764705882355,
|
61 |
+
"eval_accuracy": 0.9803921568627451,
|
62 |
+
"eval_f1": 0.9804969685242518,
|
63 |
+
"eval_loss": 0.05879249796271324,
|
64 |
+
"eval_precision": 0.9813976872800402,
|
65 |
+
"eval_recall": 0.9803921568627451,
|
66 |
+
"eval_runtime": 3.1449,
|
67 |
+
"eval_samples_per_second": 64.868,
|
68 |
+
"eval_steps_per_second": 8.267,
|
69 |
+
"step": 63
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 5.96078431372549,
|
73 |
+
"eval_accuracy": 0.9852941176470589,
|
74 |
+
"eval_f1": 0.9853150765112866,
|
75 |
+
"eval_loss": 0.03680075705051422,
|
76 |
+
"eval_precision": 0.9853868369053048,
|
77 |
+
"eval_recall": 0.9852941176470589,
|
78 |
+
"eval_runtime": 3.1698,
|
79 |
+
"eval_samples_per_second": 64.358,
|
80 |
+
"eval_steps_per_second": 8.203,
|
81 |
+
"step": 76
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 6.980392156862745,
|
85 |
+
"eval_accuracy": 0.9901960784313726,
|
86 |
+
"eval_f1": 0.9901663478316141,
|
87 |
+
"eval_loss": 0.0382298119366169,
|
88 |
+
"eval_precision": 0.9903446226975638,
|
89 |
+
"eval_recall": 0.9901960784313726,
|
90 |
+
"eval_runtime": 3.1376,
|
91 |
+
"eval_samples_per_second": 65.019,
|
92 |
+
"eval_steps_per_second": 8.287,
|
93 |
+
"step": 89
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 8.0,
|
97 |
+
"eval_accuracy": 0.9950980392156863,
|
98 |
+
"eval_f1": 0.995090756609157,
|
99 |
+
"eval_loss": 0.03175761550664902,
|
100 |
+
"eval_precision": 0.995135458763658,
|
101 |
+
"eval_recall": 0.9950980392156863,
|
102 |
+
"eval_runtime": 2.949,
|
103 |
+
"eval_samples_per_second": 69.175,
|
104 |
+
"eval_steps_per_second": 8.816,
|
105 |
+
"step": 102
|
106 |
+
}
|
107 |
+
],
|
108 |
+
"logging_steps": 500,
|
109 |
+
"max_steps": 120,
|
110 |
+
"num_input_tokens_seen": 0,
|
111 |
+
"num_train_epochs": 10,
|
112 |
+
"save_steps": 500,
|
113 |
+
"stateful_callbacks": {
|
114 |
+
"EarlyStoppingCallback": {
|
115 |
+
"args": {
|
116 |
+
"early_stopping_patience": 3,
|
117 |
+
"early_stopping_threshold": 0.0
|
118 |
+
},
|
119 |
+
"attributes": {
|
120 |
+
"early_stopping_patience_counter": 0
|
121 |
+
}
|
122 |
+
},
|
123 |
+
"TrainerControl": {
|
124 |
+
"args": {
|
125 |
+
"should_epoch_stop": false,
|
126 |
+
"should_evaluate": false,
|
127 |
+
"should_log": false,
|
128 |
+
"should_save": true,
|
129 |
+
"should_training_stop": false
|
130 |
+
},
|
131 |
+
"attributes": {}
|
132 |
+
}
|
133 |
+
},
|
134 |
+
"total_flos": 1.052064945063383e+17,
|
135 |
+
"train_batch_size": 8,
|
136 |
+
"trial_name": null,
|
137 |
+
"trial_params": null
|
138 |
+
}
|
checkpoint-102/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b77b2a33ca88330b7909aacab81332695e9c9dcf797e7a7757ca31ffcde6f31
|
3 |
+
size 5240
|
checkpoint-114/config.json
ADDED
@@ -0,0 +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": "4.44.2",
|
78 |
+
"use_weighted_layer_sum": false,
|
79 |
+
"vocab_size": 32
|
80 |
+
}
|
checkpoint-114/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b910bf6b8ec6e19d58a4b52c50de712e949fcdaeece42948112d2e5d95e8f47c
|
3 |
+
size 94763496
|
checkpoint-114/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85b95917e0620b5556323a8c02ab048666c97ab19fb25f8fa5f1554c0bfc225f
|
3 |
+
size 189552570
|
checkpoint-114/preprocessor_config.json
ADDED
@@ -0,0 +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 |
+
}
|
checkpoint-114/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:636081736c072d4bb3052b5541d861668c6c103f9a3ad62f001239e9a3a36fb1
|
3 |
+
size 14308
|
checkpoint-114/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fde2346e00a3c4644832268d0eaddcd20d8548145016394246c018bb8a28ba1
|
3 |
+
size 1064
|
checkpoint-114/trainer_state.json
ADDED
@@ -0,0 +1,150 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9950980392156863,
|
3 |
+
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-102",
|
4 |
+
"epoch": 8.941176470588236,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 114,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.9411764705882353,
|
13 |
+
"eval_accuracy": 0.9362745098039216,
|
14 |
+
"eval_f1": 0.9365356058160116,
|
15 |
+
"eval_loss": 0.19313116371631622,
|
16 |
+
"eval_precision": 0.9372234219385678,
|
17 |
+
"eval_recall": 0.9362745098039216,
|
18 |
+
"eval_runtime": 3.0986,
|
19 |
+
"eval_samples_per_second": 65.836,
|
20 |
+
"eval_steps_per_second": 8.391,
|
21 |
+
"step": 12
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 1.9607843137254903,
|
25 |
+
"eval_accuracy": 0.9705882352941176,
|
26 |
+
"eval_f1": 0.9704025549613785,
|
27 |
+
"eval_loss": 0.09495726972818375,
|
28 |
+
"eval_precision": 0.971039759187257,
|
29 |
+
"eval_recall": 0.9705882352941176,
|
30 |
+
"eval_runtime": 3.1171,
|
31 |
+
"eval_samples_per_second": 65.446,
|
32 |
+
"eval_steps_per_second": 8.341,
|
33 |
+
"step": 25
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 2.980392156862745,
|
37 |
+
"eval_accuracy": 0.9803921568627451,
|
38 |
+
"eval_f1": 0.9803921568627451,
|
39 |
+
"eval_loss": 0.06114682927727699,
|
40 |
+
"eval_precision": 0.9803921568627451,
|
41 |
+
"eval_recall": 0.9803921568627451,
|
42 |
+
"eval_runtime": 3.2163,
|
43 |
+
"eval_samples_per_second": 63.428,
|
44 |
+
"eval_steps_per_second": 8.084,
|
45 |
+
"step": 38
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 4.0,
|
49 |
+
"eval_accuracy": 0.9852941176470589,
|
50 |
+
"eval_f1": 0.9852722698274712,
|
51 |
+
"eval_loss": 0.049169763922691345,
|
52 |
+
"eval_precision": 0.9853018065952722,
|
53 |
+
"eval_recall": 0.9852941176470589,
|
54 |
+
"eval_runtime": 3.1223,
|
55 |
+
"eval_samples_per_second": 65.336,
|
56 |
+
"eval_steps_per_second": 8.327,
|
57 |
+
"step": 51
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 4.9411764705882355,
|
61 |
+
"eval_accuracy": 0.9803921568627451,
|
62 |
+
"eval_f1": 0.9804969685242518,
|
63 |
+
"eval_loss": 0.05879249796271324,
|
64 |
+
"eval_precision": 0.9813976872800402,
|
65 |
+
"eval_recall": 0.9803921568627451,
|
66 |
+
"eval_runtime": 3.1449,
|
67 |
+
"eval_samples_per_second": 64.868,
|
68 |
+
"eval_steps_per_second": 8.267,
|
69 |
+
"step": 63
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 5.96078431372549,
|
73 |
+
"eval_accuracy": 0.9852941176470589,
|
74 |
+
"eval_f1": 0.9853150765112866,
|
75 |
+
"eval_loss": 0.03680075705051422,
|
76 |
+
"eval_precision": 0.9853868369053048,
|
77 |
+
"eval_recall": 0.9852941176470589,
|
78 |
+
"eval_runtime": 3.1698,
|
79 |
+
"eval_samples_per_second": 64.358,
|
80 |
+
"eval_steps_per_second": 8.203,
|
81 |
+
"step": 76
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 6.980392156862745,
|
85 |
+
"eval_accuracy": 0.9901960784313726,
|
86 |
+
"eval_f1": 0.9901663478316141,
|
87 |
+
"eval_loss": 0.0382298119366169,
|
88 |
+
"eval_precision": 0.9903446226975638,
|
89 |
+
"eval_recall": 0.9901960784313726,
|
90 |
+
"eval_runtime": 3.1376,
|
91 |
+
"eval_samples_per_second": 65.019,
|
92 |
+
"eval_steps_per_second": 8.287,
|
93 |
+
"step": 89
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 8.0,
|
97 |
+
"eval_accuracy": 0.9950980392156863,
|
98 |
+
"eval_f1": 0.995090756609157,
|
99 |
+
"eval_loss": 0.03175761550664902,
|
100 |
+
"eval_precision": 0.995135458763658,
|
101 |
+
"eval_recall": 0.9950980392156863,
|
102 |
+
"eval_runtime": 2.949,
|
103 |
+
"eval_samples_per_second": 69.175,
|
104 |
+
"eval_steps_per_second": 8.816,
|
105 |
+
"step": 102
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 8.941176470588236,
|
109 |
+
"eval_accuracy": 0.9852941176470589,
|
110 |
+
"eval_f1": 0.9853150765112866,
|
111 |
+
"eval_loss": 0.033123087137937546,
|
112 |
+
"eval_precision": 0.9853868369053048,
|
113 |
+
"eval_recall": 0.9852941176470589,
|
114 |
+
"eval_runtime": 2.9458,
|
115 |
+
"eval_samples_per_second": 69.251,
|
116 |
+
"eval_steps_per_second": 8.826,
|
117 |
+
"step": 114
|
118 |
+
}
|
119 |
+
],
|
120 |
+
"logging_steps": 500,
|
121 |
+
"max_steps": 120,
|
122 |
+
"num_input_tokens_seen": 0,
|
123 |
+
"num_train_epochs": 10,
|
124 |
+
"save_steps": 500,
|
125 |
+
"stateful_callbacks": {
|
126 |
+
"EarlyStoppingCallback": {
|
127 |
+
"args": {
|
128 |
+
"early_stopping_patience": 3,
|
129 |
+
"early_stopping_threshold": 0.0
|
130 |
+
},
|
131 |
+
"attributes": {
|
132 |
+
"early_stopping_patience_counter": 0
|
133 |
+
}
|
134 |
+
},
|
135 |
+
"TrainerControl": {
|
136 |
+
"args": {
|
137 |
+
"should_epoch_stop": false,
|
138 |
+
"should_evaluate": false,
|
139 |
+
"should_log": false,
|
140 |
+
"should_save": true,
|
141 |
+
"should_training_stop": false
|
142 |
+
},
|
143 |
+
"attributes": {}
|
144 |
+
}
|
145 |
+
},
|
146 |
+
"total_flos": 1.1834894644418458e+17,
|
147 |
+
"train_batch_size": 8,
|
148 |
+
"trial_name": null,
|
149 |
+
"trial_params": null
|
150 |
+
}
|
checkpoint-114/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b77b2a33ca88330b7909aacab81332695e9c9dcf797e7a7757ca31ffcde6f31
|
3 |
+
size 5240
|
checkpoint-12/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 sha256:7ac774d14fe5167fbe1adddc20941f151440dc32f43d6762bbe9d60a26726e8e
|
3 |
size 94763496
|
checkpoint-12/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 189552570
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56315b610ef113026417660dc64000a73d31bcdf367d4ade81935feefcbbb425
|
3 |
size 189552570
|
checkpoint-12/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14308
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:caebb0abc1e3f29ed8c6d6714ac9331ab5a6b59efbd9b310598bb00f5bca4c19
|
3 |
size 14308
|
checkpoint-12/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ca0321d043e24273cc9815784db5e90a317cada9c48cd156d448ab1591d936c
|
3 |
size 1064
|
checkpoint-12/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-12",
|
4 |
"epoch": 0.9411764705882353,
|
5 |
"eval_steps": 500,
|
@@ -10,21 +10,21 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.9411764705882353,
|
13 |
-
"eval_accuracy": 0.
|
14 |
-
"eval_f1": 0.
|
15 |
-
"eval_loss": 0.
|
16 |
-
"eval_precision": 0.
|
17 |
-
"eval_recall": 0.
|
18 |
-
"eval_runtime": 3.
|
19 |
-
"eval_samples_per_second":
|
20 |
-
"eval_steps_per_second": 8.
|
21 |
"step": 12
|
22 |
}
|
23 |
],
|
24 |
"logging_steps": 500,
|
25 |
-
"max_steps":
|
26 |
"num_input_tokens_seen": 0,
|
27 |
-
"num_train_epochs":
|
28 |
"save_steps": 500,
|
29 |
"stateful_callbacks": {
|
30 |
"EarlyStoppingCallback": {
|
@@ -42,12 +42,12 @@
|
|
42 |
"should_evaluate": false,
|
43 |
"should_log": false,
|
44 |
"should_save": true,
|
45 |
-
"should_training_stop":
|
46 |
},
|
47 |
"attributes": {}
|
48 |
}
|
49 |
},
|
50 |
-
"total_flos": 1.
|
51 |
"train_batch_size": 8,
|
52 |
"trial_name": null,
|
53 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9362745098039216,
|
3 |
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-12",
|
4 |
"epoch": 0.9411764705882353,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.9411764705882353,
|
13 |
+
"eval_accuracy": 0.9362745098039216,
|
14 |
+
"eval_f1": 0.9365356058160116,
|
15 |
+
"eval_loss": 0.19313116371631622,
|
16 |
+
"eval_precision": 0.9372234219385678,
|
17 |
+
"eval_recall": 0.9362745098039216,
|
18 |
+
"eval_runtime": 3.0986,
|
19 |
+
"eval_samples_per_second": 65.836,
|
20 |
+
"eval_steps_per_second": 8.391,
|
21 |
"step": 12
|
22 |
}
|
23 |
],
|
24 |
"logging_steps": 500,
|
25 |
+
"max_steps": 120,
|
26 |
"num_input_tokens_seen": 0,
|
27 |
+
"num_train_epochs": 10,
|
28 |
"save_steps": 500,
|
29 |
"stateful_callbacks": {
|
30 |
"EarlyStoppingCallback": {
|
|
|
42 |
"should_evaluate": false,
|
43 |
"should_log": false,
|
44 |
"should_save": true,
|
45 |
+
"should_training_stop": false
|
46 |
},
|
47 |
"attributes": {}
|
48 |
}
|
49 |
},
|
50 |
+
"total_flos": 1.315729776671232e+16,
|
51 |
"train_batch_size": 8,
|
52 |
"trial_name": null,
|
53 |
"trial_params": null
|
checkpoint-12/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b77b2a33ca88330b7909aacab81332695e9c9dcf797e7a7757ca31ffcde6f31
|
3 |
size 5240
|
checkpoint-120/config.json
ADDED
@@ -0,0 +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": "4.44.2",
|
78 |
+
"use_weighted_layer_sum": false,
|
79 |
+
"vocab_size": 32
|
80 |
+
}
|
checkpoint-120/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3258e17c3151e1d9899b5ecaa38ee7208137f2c975f17a7f66834494fb6f1ddb
|
3 |
+
size 94763496
|
checkpoint-120/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d67e947c82c7eff62fe82e2161b429d0f674dcb710ae9e066c9aaeaa53719096
|
3 |
+
size 189552570
|
checkpoint-120/preprocessor_config.json
ADDED
@@ -0,0 +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 |
+
}
|
checkpoint-120/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:286671099adfaa4371e8fead24d8a5f622004012b7f075f68979922946bd3511
|
3 |
+
size 14308
|
checkpoint-120/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2409fb1c3fd1c2de2c63b5459c49a97abc9a50084af4337cc5090c00ef975a6
|
3 |
+
size 1064
|
checkpoint-120/trainer_state.json
ADDED
@@ -0,0 +1,162 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9950980392156863,
|
3 |
+
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-102",
|
4 |
+
"epoch": 9.411764705882353,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 120,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.9411764705882353,
|
13 |
+
"eval_accuracy": 0.9362745098039216,
|
14 |
+
"eval_f1": 0.9365356058160116,
|
15 |
+
"eval_loss": 0.19313116371631622,
|
16 |
+
"eval_precision": 0.9372234219385678,
|
17 |
+
"eval_recall": 0.9362745098039216,
|
18 |
+
"eval_runtime": 3.0986,
|
19 |
+
"eval_samples_per_second": 65.836,
|
20 |
+
"eval_steps_per_second": 8.391,
|
21 |
+
"step": 12
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 1.9607843137254903,
|
25 |
+
"eval_accuracy": 0.9705882352941176,
|
26 |
+
"eval_f1": 0.9704025549613785,
|
27 |
+
"eval_loss": 0.09495726972818375,
|
28 |
+
"eval_precision": 0.971039759187257,
|
29 |
+
"eval_recall": 0.9705882352941176,
|
30 |
+
"eval_runtime": 3.1171,
|
31 |
+
"eval_samples_per_second": 65.446,
|
32 |
+
"eval_steps_per_second": 8.341,
|
33 |
+
"step": 25
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 2.980392156862745,
|
37 |
+
"eval_accuracy": 0.9803921568627451,
|
38 |
+
"eval_f1": 0.9803921568627451,
|
39 |
+
"eval_loss": 0.06114682927727699,
|
40 |
+
"eval_precision": 0.9803921568627451,
|
41 |
+
"eval_recall": 0.9803921568627451,
|
42 |
+
"eval_runtime": 3.2163,
|
43 |
+
"eval_samples_per_second": 63.428,
|
44 |
+
"eval_steps_per_second": 8.084,
|
45 |
+
"step": 38
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 4.0,
|
49 |
+
"eval_accuracy": 0.9852941176470589,
|
50 |
+
"eval_f1": 0.9852722698274712,
|
51 |
+
"eval_loss": 0.049169763922691345,
|
52 |
+
"eval_precision": 0.9853018065952722,
|
53 |
+
"eval_recall": 0.9852941176470589,
|
54 |
+
"eval_runtime": 3.1223,
|
55 |
+
"eval_samples_per_second": 65.336,
|
56 |
+
"eval_steps_per_second": 8.327,
|
57 |
+
"step": 51
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 4.9411764705882355,
|
61 |
+
"eval_accuracy": 0.9803921568627451,
|
62 |
+
"eval_f1": 0.9804969685242518,
|
63 |
+
"eval_loss": 0.05879249796271324,
|
64 |
+
"eval_precision": 0.9813976872800402,
|
65 |
+
"eval_recall": 0.9803921568627451,
|
66 |
+
"eval_runtime": 3.1449,
|
67 |
+
"eval_samples_per_second": 64.868,
|
68 |
+
"eval_steps_per_second": 8.267,
|
69 |
+
"step": 63
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 5.96078431372549,
|
73 |
+
"eval_accuracy": 0.9852941176470589,
|
74 |
+
"eval_f1": 0.9853150765112866,
|
75 |
+
"eval_loss": 0.03680075705051422,
|
76 |
+
"eval_precision": 0.9853868369053048,
|
77 |
+
"eval_recall": 0.9852941176470589,
|
78 |
+
"eval_runtime": 3.1698,
|
79 |
+
"eval_samples_per_second": 64.358,
|
80 |
+
"eval_steps_per_second": 8.203,
|
81 |
+
"step": 76
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 6.980392156862745,
|
85 |
+
"eval_accuracy": 0.9901960784313726,
|
86 |
+
"eval_f1": 0.9901663478316141,
|
87 |
+
"eval_loss": 0.0382298119366169,
|
88 |
+
"eval_precision": 0.9903446226975638,
|
89 |
+
"eval_recall": 0.9901960784313726,
|
90 |
+
"eval_runtime": 3.1376,
|
91 |
+
"eval_samples_per_second": 65.019,
|
92 |
+
"eval_steps_per_second": 8.287,
|
93 |
+
"step": 89
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 8.0,
|
97 |
+
"eval_accuracy": 0.9950980392156863,
|
98 |
+
"eval_f1": 0.995090756609157,
|
99 |
+
"eval_loss": 0.03175761550664902,
|
100 |
+
"eval_precision": 0.995135458763658,
|
101 |
+
"eval_recall": 0.9950980392156863,
|
102 |
+
"eval_runtime": 2.949,
|
103 |
+
"eval_samples_per_second": 69.175,
|
104 |
+
"eval_steps_per_second": 8.816,
|
105 |
+
"step": 102
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 8.941176470588236,
|
109 |
+
"eval_accuracy": 0.9852941176470589,
|
110 |
+
"eval_f1": 0.9853150765112866,
|
111 |
+
"eval_loss": 0.033123087137937546,
|
112 |
+
"eval_precision": 0.9853868369053048,
|
113 |
+
"eval_recall": 0.9852941176470589,
|
114 |
+
"eval_runtime": 2.9458,
|
115 |
+
"eval_samples_per_second": 69.251,
|
116 |
+
"eval_steps_per_second": 8.826,
|
117 |
+
"step": 114
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 9.411764705882353,
|
121 |
+
"eval_accuracy": 0.9852941176470589,
|
122 |
+
"eval_f1": 0.9853150765112866,
|
123 |
+
"eval_loss": 0.033173661679029465,
|
124 |
+
"eval_precision": 0.9853868369053048,
|
125 |
+
"eval_recall": 0.9852941176470589,
|
126 |
+
"eval_runtime": 2.9666,
|
127 |
+
"eval_samples_per_second": 68.766,
|
128 |
+
"eval_steps_per_second": 8.764,
|
129 |
+
"step": 120
|
130 |
+
}
|
131 |
+
],
|
132 |
+
"logging_steps": 500,
|
133 |
+
"max_steps": 120,
|
134 |
+
"num_input_tokens_seen": 0,
|
135 |
+
"num_train_epochs": 10,
|
136 |
+
"save_steps": 500,
|
137 |
+
"stateful_callbacks": {
|
138 |
+
"EarlyStoppingCallback": {
|
139 |
+
"args": {
|
140 |
+
"early_stopping_patience": 3,
|
141 |
+
"early_stopping_threshold": 0.0
|
142 |
+
},
|
143 |
+
"attributes": {
|
144 |
+
"early_stopping_patience_counter": 0
|
145 |
+
}
|
146 |
+
},
|
147 |
+
"TrainerControl": {
|
148 |
+
"args": {
|
149 |
+
"should_epoch_stop": false,
|
150 |
+
"should_evaluate": false,
|
151 |
+
"should_log": false,
|
152 |
+
"should_save": true,
|
153 |
+
"should_training_stop": true
|
154 |
+
},
|
155 |
+
"attributes": {}
|
156 |
+
}
|
157 |
+
},
|
158 |
+
"total_flos": 1.237670053721906e+17,
|
159 |
+
"train_batch_size": 8,
|
160 |
+
"trial_name": null,
|
161 |
+
"trial_params": null
|
162 |
+
}
|
checkpoint-120/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b77b2a33ca88330b7909aacab81332695e9c9dcf797e7a7757ca31ffcde6f31
|
3 |
+
size 5240
|
checkpoint-25/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:da1949ab9da06d9f94ddb053df98c408f27159d75669cf1d2eb4e1cc47323344
|
3 |
size 94763496
|
checkpoint-25/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 189552570
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64fe5dbcc580831e63b26cf1b5d7e9409f5b456d1141636612d7fca115a01a87
|
3 |
size 189552570
|
checkpoint-25/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:272c079a133d684090b7a24b10497f4bd703dbf9ecfecafe1a788c62b4404ce6
|
3 |
+
size 14308
|
checkpoint-25/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6633f18d367676ea03844228fc7112a6a9464032824bb5f9f17a85ee888f12e8
|
3 |
size 1064
|
checkpoint-25/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-25",
|
4 |
"epoch": 1.9607843137254903,
|
5 |
"eval_steps": 500,
|
@@ -10,33 +10,33 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.9411764705882353,
|
13 |
-
"eval_accuracy": 0.
|
14 |
-
"eval_f1": 0.
|
15 |
-
"eval_loss": 0.
|
16 |
-
"eval_precision": 0.
|
17 |
-
"eval_recall": 0.
|
18 |
-
"eval_runtime":
|
19 |
-
"eval_samples_per_second":
|
20 |
-
"eval_steps_per_second": 8.
|
21 |
"step": 12
|
22 |
},
|
23 |
{
|
24 |
"epoch": 1.9607843137254903,
|
25 |
-
"eval_accuracy": 0.
|
26 |
-
"eval_f1": 0.
|
27 |
-
"eval_loss": 0.
|
28 |
-
"eval_precision": 0.
|
29 |
-
"eval_recall": 0.
|
30 |
-
"eval_runtime":
|
31 |
-
"eval_samples_per_second":
|
32 |
-
"eval_steps_per_second": 8.
|
33 |
"step": 25
|
34 |
}
|
35 |
],
|
36 |
"logging_steps": 500,
|
37 |
-
"max_steps":
|
38 |
"num_input_tokens_seen": 0,
|
39 |
-
"num_train_epochs":
|
40 |
"save_steps": 500,
|
41 |
"stateful_callbacks": {
|
42 |
"EarlyStoppingCallback": {
|
@@ -59,7 +59,7 @@
|
|
59 |
"attributes": {}
|
60 |
}
|
61 |
},
|
62 |
-
"total_flos": 2.
|
63 |
"train_batch_size": 8,
|
64 |
"trial_name": null,
|
65 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9705882352941176,
|
3 |
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-25",
|
4 |
"epoch": 1.9607843137254903,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.9411764705882353,
|
13 |
+
"eval_accuracy": 0.9362745098039216,
|
14 |
+
"eval_f1": 0.9365356058160116,
|
15 |
+
"eval_loss": 0.19313116371631622,
|
16 |
+
"eval_precision": 0.9372234219385678,
|
17 |
+
"eval_recall": 0.9362745098039216,
|
18 |
+
"eval_runtime": 3.0986,
|
19 |
+
"eval_samples_per_second": 65.836,
|
20 |
+
"eval_steps_per_second": 8.391,
|
21 |
"step": 12
|
22 |
},
|
23 |
{
|
24 |
"epoch": 1.9607843137254903,
|
25 |
+
"eval_accuracy": 0.9705882352941176,
|
26 |
+
"eval_f1": 0.9704025549613785,
|
27 |
+
"eval_loss": 0.09495726972818375,
|
28 |
+
"eval_precision": 0.971039759187257,
|
29 |
+
"eval_recall": 0.9705882352941176,
|
30 |
+
"eval_runtime": 3.1171,
|
31 |
+
"eval_samples_per_second": 65.446,
|
32 |
+
"eval_steps_per_second": 8.341,
|
33 |
"step": 25
|
34 |
}
|
35 |
],
|
36 |
"logging_steps": 500,
|
37 |
+
"max_steps": 120,
|
38 |
"num_input_tokens_seen": 0,
|
39 |
+
"num_train_epochs": 10,
|
40 |
"save_steps": 500,
|
41 |
"stateful_callbacks": {
|
42 |
"EarlyStoppingCallback": {
|
|
|
59 |
"attributes": {}
|
60 |
}
|
61 |
},
|
62 |
+
"total_flos": 2.630848254506803e+16,
|
63 |
"train_batch_size": 8,
|
64 |
"trial_name": null,
|
65 |
"trial_params": null
|
checkpoint-25/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b77b2a33ca88330b7909aacab81332695e9c9dcf797e7a7757ca31ffcde6f31
|
3 |
size 5240
|
checkpoint-38/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:d8bc28d8ebd1dbdd73656a784624c72928eb10e21d9e6acdce2e1d312d787010
|
3 |
size 94763496
|
checkpoint-38/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 189552570
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ee1b6c4df5d7a5ef50f7350cb964bab9875222b057b8eb71768826fceb9156f
|
3 |
size 189552570
|
checkpoint-38/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d19f57e20f91b35ae6289880b02cdfa14033ed6b20b4d1730bfb179a9264102
|
3 |
+
size 14308
|
checkpoint-38/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5df84074f7631c8ca35330b9e20d4190996409e954261c1b476ad0fabe74b93b
|
3 |
size 1064
|
checkpoint-38/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-38",
|
4 |
"epoch": 2.980392156862745,
|
5 |
"eval_steps": 500,
|
@@ -10,45 +10,45 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.9411764705882353,
|
13 |
-
"eval_accuracy": 0.
|
14 |
-
"eval_f1": 0.
|
15 |
-
"eval_loss": 0.
|
16 |
-
"eval_precision": 0.
|
17 |
-
"eval_recall": 0.
|
18 |
-
"eval_runtime":
|
19 |
-
"eval_samples_per_second":
|
20 |
-
"eval_steps_per_second": 8.
|
21 |
"step": 12
|
22 |
},
|
23 |
{
|
24 |
"epoch": 1.9607843137254903,
|
25 |
-
"eval_accuracy": 0.
|
26 |
-
"eval_f1": 0.
|
27 |
-
"eval_loss": 0.
|
28 |
-
"eval_precision": 0.
|
29 |
-
"eval_recall": 0.
|
30 |
-
"eval_runtime":
|
31 |
-
"eval_samples_per_second":
|
32 |
-
"eval_steps_per_second": 8.
|
33 |
"step": 25
|
34 |
},
|
35 |
{
|
36 |
"epoch": 2.980392156862745,
|
37 |
-
"eval_accuracy": 0.
|
38 |
-
"eval_f1": 0.
|
39 |
-
"eval_loss": 0.
|
40 |
-
"eval_precision": 0.
|
41 |
-
"eval_recall": 0.
|
42 |
-
"eval_runtime":
|
43 |
-
"eval_samples_per_second":
|
44 |
-
"eval_steps_per_second": 8.
|
45 |
"step": 38
|
46 |
}
|
47 |
],
|
48 |
"logging_steps": 500,
|
49 |
-
"max_steps":
|
50 |
"num_input_tokens_seen": 0,
|
51 |
-
"num_train_epochs":
|
52 |
"save_steps": 500,
|
53 |
"stateful_callbacks": {
|
54 |
"EarlyStoppingCallback": {
|
@@ -71,7 +71,7 @@
|
|
71 |
"attributes": {}
|
72 |
}
|
73 |
},
|
74 |
-
"total_flos": 3.
|
75 |
"train_batch_size": 8,
|
76 |
"trial_name": null,
|
77 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9803921568627451,
|
3 |
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-38",
|
4 |
"epoch": 2.980392156862745,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.9411764705882353,
|
13 |
+
"eval_accuracy": 0.9362745098039216,
|
14 |
+
"eval_f1": 0.9365356058160116,
|
15 |
+
"eval_loss": 0.19313116371631622,
|
16 |
+
"eval_precision": 0.9372234219385678,
|
17 |
+
"eval_recall": 0.9362745098039216,
|
18 |
+
"eval_runtime": 3.0986,
|
19 |
+
"eval_samples_per_second": 65.836,
|
20 |
+
"eval_steps_per_second": 8.391,
|
21 |
"step": 12
|
22 |
},
|
23 |
{
|
24 |
"epoch": 1.9607843137254903,
|
25 |
+
"eval_accuracy": 0.9705882352941176,
|
26 |
+
"eval_f1": 0.9704025549613785,
|
27 |
+
"eval_loss": 0.09495726972818375,
|
28 |
+
"eval_precision": 0.971039759187257,
|
29 |
+
"eval_recall": 0.9705882352941176,
|
30 |
+
"eval_runtime": 3.1171,
|
31 |
+
"eval_samples_per_second": 65.446,
|
32 |
+
"eval_steps_per_second": 8.341,
|
33 |
"step": 25
|
34 |
},
|
35 |
{
|
36 |
"epoch": 2.980392156862745,
|
37 |
+
"eval_accuracy": 0.9803921568627451,
|
38 |
+
"eval_f1": 0.9803921568627451,
|
39 |
+
"eval_loss": 0.06114682927727699,
|
40 |
+
"eval_precision": 0.9803921568627451,
|
41 |
+
"eval_recall": 0.9803921568627451,
|
42 |
+
"eval_runtime": 3.2163,
|
43 |
+
"eval_samples_per_second": 63.428,
|
44 |
+
"eval_steps_per_second": 8.084,
|
45 |
"step": 38
|
46 |
}
|
47 |
],
|
48 |
"logging_steps": 500,
|
49 |
+
"max_steps": 120,
|
50 |
"num_input_tokens_seen": 0,
|
51 |
+
"num_train_epochs": 10,
|
52 |
"save_steps": 500,
|
53 |
"stateful_callbacks": {
|
54 |
"EarlyStoppingCallback": {
|
|
|
71 |
"attributes": {}
|
72 |
}
|
73 |
},
|
74 |
+
"total_flos": 3.946056334924685e+16,
|
75 |
"train_batch_size": 8,
|
76 |
"trial_name": null,
|
77 |
"trial_params": null
|
checkpoint-38/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b77b2a33ca88330b7909aacab81332695e9c9dcf797e7a7757ca31ffcde6f31
|
3 |
size 5240
|
checkpoint-51/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 sha256:072781416d7434132c8e1b73276d4503dca0b1b8db503afa1a8ba07bc69b3ae9
|
3 |
size 94763496
|
checkpoint-51/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 189552570
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da71c2ca09d32a4c673ba10e3259d6198c7a2fbaa9004a4a0eaa7d9cc8d8fecb
|
3 |
size 189552570
|
checkpoint-51/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdc415b22b0f41c29b31b3bf40c83a0c3865a35793ba92c48d3d575e69ed5279
|
3 |
+
size 14308
|
checkpoint-51/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99f2e94f9942cdbd4528ad8ed9baf4498c04d7503c2ef6dab9521dfcb4021a49
|
3 |
size 1064
|
checkpoint-51/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-51",
|
4 |
"epoch": 4.0,
|
5 |
"eval_steps": 500,
|
@@ -10,57 +10,57 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.9411764705882353,
|
13 |
-
"eval_accuracy": 0.
|
14 |
-
"eval_f1": 0.
|
15 |
-
"eval_loss": 0.
|
16 |
-
"eval_precision": 0.
|
17 |
-
"eval_recall": 0.
|
18 |
-
"eval_runtime": 3.
|
19 |
-
"eval_samples_per_second":
|
20 |
-
"eval_steps_per_second": 8.
|
21 |
"step": 12
|
22 |
},
|
23 |
{
|
24 |
"epoch": 1.9607843137254903,
|
25 |
-
"eval_accuracy": 0.
|
26 |
-
"eval_f1": 0.
|
27 |
-
"eval_loss": 0.
|
28 |
-
"eval_precision": 0.
|
29 |
-
"eval_recall": 0.
|
30 |
-
"eval_runtime": 3.
|
31 |
-
"eval_samples_per_second":
|
32 |
-
"eval_steps_per_second": 8.
|
33 |
"step": 25
|
34 |
},
|
35 |
{
|
36 |
"epoch": 2.980392156862745,
|
37 |
-
"eval_accuracy": 0.
|
38 |
-
"eval_f1": 0.
|
39 |
-
"eval_loss": 0.
|
40 |
-
"eval_precision": 0.
|
41 |
-
"eval_recall": 0.
|
42 |
-
"eval_runtime": 3.
|
43 |
-
"eval_samples_per_second":
|
44 |
-
"eval_steps_per_second": 8.
|
45 |
"step": 38
|
46 |
},
|
47 |
{
|
48 |
"epoch": 4.0,
|
49 |
-
"eval_accuracy": 0.
|
50 |
-
"eval_f1": 0.
|
51 |
-
"eval_loss": 0.
|
52 |
-
"eval_precision": 0.
|
53 |
-
"eval_recall": 0.
|
54 |
-
"eval_runtime": 3.
|
55 |
-
"eval_samples_per_second":
|
56 |
-
"eval_steps_per_second": 8.
|
57 |
"step": 51
|
58 |
}
|
59 |
],
|
60 |
"logging_steps": 500,
|
61 |
-
"max_steps":
|
62 |
"num_input_tokens_seen": 0,
|
63 |
-
"num_train_epochs":
|
64 |
"save_steps": 500,
|
65 |
"stateful_callbacks": {
|
66 |
"EarlyStoppingCallback": {
|
@@ -83,7 +83,7 @@
|
|
83 |
"attributes": {}
|
84 |
}
|
85 |
},
|
86 |
-
"total_flos": 5.
|
87 |
"train_batch_size": 8,
|
88 |
"trial_name": null,
|
89 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9852941176470589,
|
3 |
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-51",
|
4 |
"epoch": 4.0,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.9411764705882353,
|
13 |
+
"eval_accuracy": 0.9362745098039216,
|
14 |
+
"eval_f1": 0.9365356058160116,
|
15 |
+
"eval_loss": 0.19313116371631622,
|
16 |
+
"eval_precision": 0.9372234219385678,
|
17 |
+
"eval_recall": 0.9362745098039216,
|
18 |
+
"eval_runtime": 3.0986,
|
19 |
+
"eval_samples_per_second": 65.836,
|
20 |
+
"eval_steps_per_second": 8.391,
|
21 |
"step": 12
|
22 |
},
|
23 |
{
|
24 |
"epoch": 1.9607843137254903,
|
25 |
+
"eval_accuracy": 0.9705882352941176,
|
26 |
+
"eval_f1": 0.9704025549613785,
|
27 |
+
"eval_loss": 0.09495726972818375,
|
28 |
+
"eval_precision": 0.971039759187257,
|
29 |
+
"eval_recall": 0.9705882352941176,
|
30 |
+
"eval_runtime": 3.1171,
|
31 |
+
"eval_samples_per_second": 65.446,
|
32 |
+
"eval_steps_per_second": 8.341,
|
33 |
"step": 25
|
34 |
},
|
35 |
{
|
36 |
"epoch": 2.980392156862745,
|
37 |
+
"eval_accuracy": 0.9803921568627451,
|
38 |
+
"eval_f1": 0.9803921568627451,
|
39 |
+
"eval_loss": 0.06114682927727699,
|
40 |
+
"eval_precision": 0.9803921568627451,
|
41 |
+
"eval_recall": 0.9803921568627451,
|
42 |
+
"eval_runtime": 3.2163,
|
43 |
+
"eval_samples_per_second": 63.428,
|
44 |
+
"eval_steps_per_second": 8.084,
|
45 |
"step": 38
|
46 |
},
|
47 |
{
|
48 |
"epoch": 4.0,
|
49 |
+
"eval_accuracy": 0.9852941176470589,
|
50 |
+
"eval_f1": 0.9852722698274712,
|
51 |
+
"eval_loss": 0.049169763922691345,
|
52 |
+
"eval_precision": 0.9853018065952722,
|
53 |
+
"eval_recall": 0.9852941176470589,
|
54 |
+
"eval_runtime": 3.1223,
|
55 |
+
"eval_samples_per_second": 65.336,
|
56 |
+
"eval_steps_per_second": 8.327,
|
57 |
"step": 51
|
58 |
}
|
59 |
],
|
60 |
"logging_steps": 500,
|
61 |
+
"max_steps": 120,
|
62 |
"num_input_tokens_seen": 0,
|
63 |
+
"num_train_epochs": 10,
|
64 |
"save_steps": 500,
|
65 |
"stateful_callbacks": {
|
66 |
"EarlyStoppingCallback": {
|
|
|
83 |
"attributes": {}
|
84 |
}
|
85 |
},
|
86 |
+
"total_flos": 5.261731531342733e+16,
|
87 |
"train_batch_size": 8,
|
88 |
"trial_name": null,
|
89 |
"trial_params": null
|
checkpoint-51/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b77b2a33ca88330b7909aacab81332695e9c9dcf797e7a7757ca31ffcde6f31
|
3 |
size 5240
|
checkpoint-63/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 sha256:2c1568086524c8dced6705098aa1db3285da46fd4a5391fa6b9d6eb7df4502d4
|
3 |
size 94763496
|