Marcos12886
commited on
Commit
•
a007ad9
1
Parent(s):
7630b28
Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +20 -2
- checkpoint-170/config.json +3 -2
- checkpoint-170/model.safetensors +1 -1
- checkpoint-170/optimizer.pt +1 -1
- checkpoint-170/scheduler.pt +1 -1
- checkpoint-170/trainer_state.json +19 -13
- checkpoint-170/training_args.bin +1 -1
- checkpoint-256/config.json +3 -2
- checkpoint-256/model.safetensors +1 -1
- checkpoint-256/optimizer.pt +1 -1
- checkpoint-256/scheduler.pt +1 -1
- checkpoint-256/trainer_state.json +27 -18
- checkpoint-256/training_args.bin +1 -1
- checkpoint-341/config.json +3 -2
- checkpoint-341/model.safetensors +1 -1
- checkpoint-341/optimizer.pt +1 -1
- checkpoint-341/scheduler.pt +1 -1
- checkpoint-341/trainer_state.json +35 -23
- checkpoint-341/training_args.bin +1 -1
- checkpoint-426/config.json +3 -2
- checkpoint-426/model.safetensors +1 -1
- checkpoint-426/optimizer.pt +1 -1
- checkpoint-426/scheduler.pt +1 -1
- checkpoint-426/trainer_state.json +44 -29
- checkpoint-426/training_args.bin +1 -1
- checkpoint-512/config.json +3 -2
- checkpoint-512/model.safetensors +1 -1
- checkpoint-512/optimizer.pt +1 -1
- checkpoint-512/scheduler.pt +1 -1
- checkpoint-512/trainer_state.json +54 -36
- checkpoint-512/training_args.bin +1 -1
- checkpoint-597/config.json +3 -2
- checkpoint-597/model.safetensors +1 -1
- checkpoint-597/optimizer.pt +1 -1
- checkpoint-597/scheduler.pt +1 -1
- checkpoint-597/trainer_state.json +62 -41
- checkpoint-597/training_args.bin +1 -1
- checkpoint-680/config.json +81 -0
- checkpoint-680/model.safetensors +3 -0
- checkpoint-680/optimizer.pt +3 -0
- checkpoint-680/rng_state.pth +3 -0
- checkpoint-680/scheduler.pt +3 -0
- checkpoint-680/trainer_state.json +145 -0
- checkpoint-680/training_args.bin +3 -0
- checkpoint-85/model.safetensors +1 -1
- checkpoint-85/optimizer.pt +1 -1
- checkpoint-85/rng_state.pth +1 -1
- checkpoint-85/scheduler.pt +1 -1
- checkpoint-85/trainer_state.json +13 -13
- checkpoint-85/training_args.bin +1 -1
README.md
CHANGED
@@ -4,6 +4,11 @@ license: apache-2.0
|
|
4 |
base_model: ntu-spml/distilhubert
|
5 |
tags:
|
6 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
7 |
model-index:
|
8 |
- name: distilhubert-finetuned-cry-detector
|
9 |
results: []
|
@@ -15,6 +20,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
# distilhubert-finetuned-cry-detector
|
16 |
|
17 |
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
@@ -42,13 +53,20 @@ The following hyperparameters were used during training:
|
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: cosine
|
44 |
- lr_scheduler_warmup_ratio: 0.001
|
45 |
-
- num_epochs:
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|
50 |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
51 |
-
| No log | 0.9956 | 85 | 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
|
53 |
|
54 |
### Framework versions
|
|
|
4 |
base_model: ntu-spml/distilhubert
|
5 |
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: []
|
|
|
20 |
# distilhubert-finetuned-cry-detector
|
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: 0.0878
|
25 |
+
- Accuracy: 0.9861
|
26 |
+
- Precision: 0.9861
|
27 |
+
- Recall: 0.9861
|
28 |
+
- F1: 0.9861
|
29 |
|
30 |
## Model description
|
31 |
|
|
|
53 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
54 |
- lr_scheduler_type: cosine
|
55 |
- lr_scheduler_warmup_ratio: 0.001
|
56 |
+
- num_epochs: 8
|
57 |
|
58 |
### Training results
|
59 |
|
60 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|
61 |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
62 |
+
| No log | 0.9956 | 85 | 0.1204 | 0.9641 | 0.9641 | 0.9641 | 0.9638 |
|
63 |
+
| No log | 1.9912 | 170 | 0.0847 | 0.9773 | 0.9772 | 0.9773 | 0.9773 |
|
64 |
+
| No log | 2.9985 | 256 | 0.1025 | 0.9766 | 0.9769 | 0.9766 | 0.9766 |
|
65 |
+
| No log | 3.9941 | 341 | 0.0869 | 0.9832 | 0.9835 | 0.9832 | 0.9832 |
|
66 |
+
| No log | 4.9898 | 426 | 0.0746 | 0.9832 | 0.9834 | 0.9832 | 0.9832 |
|
67 |
+
| 0.0538 | 5.9971 | 512 | 0.0870 | 0.9861 | 0.9861 | 0.9861 | 0.9861 |
|
68 |
+
| 0.0538 | 6.9927 | 597 | 0.0890 | 0.9861 | 0.9861 | 0.9861 | 0.9861 |
|
69 |
+
| 0.0538 | 7.9649 | 680 | 0.0878 | 0.9861 | 0.9861 | 0.9861 | 0.9861 |
|
70 |
|
71 |
|
72 |
### Framework versions
|
checkpoint-170/config.json
CHANGED
@@ -45,6 +45,7 @@
|
|
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,
|
@@ -55,8 +56,8 @@
|
|
55 |
"initializer_range": 0.02,
|
56 |
"intermediate_size": 3072,
|
57 |
"label2id": {
|
58 |
-
"crying":
|
59 |
-
"no_crying":
|
60 |
},
|
61 |
"layer_norm_eps": 1e-05,
|
62 |
"layerdrop": 0.0,
|
|
|
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,
|
|
|
56 |
"initializer_range": 0.02,
|
57 |
"intermediate_size": 3072,
|
58 |
"label2id": {
|
59 |
+
"crying": 0,
|
60 |
+
"no_crying": 1
|
61 |
},
|
62 |
"layer_norm_eps": 1e-05,
|
63 |
"layerdrop": 0.0,
|
checkpoint-170/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:ddc4c9cb0876910fe2ac6089e9622d2ec25163c90268babf3b3a68cc1955bbc3
|
3 |
size 94763496
|
checkpoint-170/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:f284ad3b43a12e7fdbaf43673ca92e158c1ab9cbea63e0352b6085f5564ff555
|
3 |
size 189552570
|
checkpoint-170/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 sha256:28ead2442e291cf84a44bd5f670a529388e7aee7f31ec31fec65f8af5dd527ac
|
3 |
size 1064
|
checkpoint-170/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-170",
|
4 |
"epoch": 1.9912152269399708,
|
5 |
"eval_steps": 500,
|
@@ -10,27 +10,33 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.9956076134699854,
|
13 |
-
"eval_accuracy": 0.
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
|
|
|
|
|
|
18 |
"step": 85
|
19 |
},
|
20 |
{
|
21 |
"epoch": 1.9912152269399708,
|
22 |
-
"eval_accuracy": 0.
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
|
|
|
|
|
|
27 |
"step": 170
|
28 |
}
|
29 |
],
|
30 |
"logging_steps": 500,
|
31 |
-
"max_steps":
|
32 |
"num_input_tokens_seen": 0,
|
33 |
-
"num_train_epochs":
|
34 |
"save_steps": 500,
|
35 |
"stateful_callbacks": {
|
36 |
"EarlyStoppingCallback": {
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9772893772893773,
|
3 |
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-170",
|
4 |
"epoch": 1.9912152269399708,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.9956076134699854,
|
13 |
+
"eval_accuracy": 0.9641025641025641,
|
14 |
+
"eval_f1": 0.9637911305761953,
|
15 |
+
"eval_loss": 0.12035853415727615,
|
16 |
+
"eval_precision": 0.9640509308043554,
|
17 |
+
"eval_recall": 0.9641025641025641,
|
18 |
+
"eval_runtime": 6.052,
|
19 |
+
"eval_samples_per_second": 225.545,
|
20 |
+
"eval_steps_per_second": 28.255,
|
21 |
"step": 85
|
22 |
},
|
23 |
{
|
24 |
"epoch": 1.9912152269399708,
|
25 |
+
"eval_accuracy": 0.9772893772893773,
|
26 |
+
"eval_f1": 0.9772624500008753,
|
27 |
+
"eval_loss": 0.08473604917526245,
|
28 |
+
"eval_precision": 0.9772470873644479,
|
29 |
+
"eval_recall": 0.9772893772893773,
|
30 |
+
"eval_runtime": 5.9068,
|
31 |
+
"eval_samples_per_second": 231.09,
|
32 |
+
"eval_steps_per_second": 28.95,
|
33 |
"step": 170
|
34 |
}
|
35 |
],
|
36 |
"logging_steps": 500,
|
37 |
+
"max_steps": 680,
|
38 |
"num_input_tokens_seen": 0,
|
39 |
+
"num_train_epochs": 8,
|
40 |
"save_steps": 500,
|
41 |
"stateful_callbacks": {
|
42 |
"EarlyStoppingCallback": {
|
checkpoint-170/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:cda0bf828ccc04cd6d3fb7933f60f34ca3c8ba14b14579f9e878d688bc739b4a
|
3 |
size 5240
|
checkpoint-256/config.json
CHANGED
@@ -45,6 +45,7 @@
|
|
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,
|
@@ -55,8 +56,8 @@
|
|
55 |
"initializer_range": 0.02,
|
56 |
"intermediate_size": 3072,
|
57 |
"label2id": {
|
58 |
-
"crying":
|
59 |
-
"no_crying":
|
60 |
},
|
61 |
"layer_norm_eps": 1e-05,
|
62 |
"layerdrop": 0.0,
|
|
|
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,
|
|
|
56 |
"initializer_range": 0.02,
|
57 |
"intermediate_size": 3072,
|
58 |
"label2id": {
|
59 |
+
"crying": 0,
|
60 |
+
"no_crying": 1
|
61 |
},
|
62 |
"layer_norm_eps": 1e-05,
|
63 |
"layerdrop": 0.0,
|
checkpoint-256/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 sha256:1e8fcce3d6821b09907a57bf2280fdb73fc79c008d23670c77bd0350d6249146
|
3 |
size 94763496
|
checkpoint-256/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:eb370b3600823d6c126a14d977da564c51a816566b23701954070eb23a1ecf47
|
3 |
size 189552570
|
checkpoint-256/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:b1ef84753a69d0410f7f7d925e2fedd5694b09472e6721f4fe864ef701cb0dd7
|
3 |
size 1064
|
checkpoint-256/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-170",
|
4 |
"epoch": 2.998535871156662,
|
5 |
"eval_steps": 500,
|
@@ -10,36 +10,45 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.9956076134699854,
|
13 |
-
"eval_accuracy": 0.
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
|
|
|
|
|
|
18 |
"step": 85
|
19 |
},
|
20 |
{
|
21 |
"epoch": 1.9912152269399708,
|
22 |
-
"eval_accuracy": 0.
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
|
|
|
|
|
|
27 |
"step": 170
|
28 |
},
|
29 |
{
|
30 |
"epoch": 2.998535871156662,
|
31 |
-
"eval_accuracy": 0.
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
|
|
|
|
|
|
36 |
"step": 256
|
37 |
}
|
38 |
],
|
39 |
"logging_steps": 500,
|
40 |
-
"max_steps":
|
41 |
"num_input_tokens_seen": 0,
|
42 |
-
"num_train_epochs":
|
43 |
"save_steps": 500,
|
44 |
"stateful_callbacks": {
|
45 |
"EarlyStoppingCallback": {
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9772893772893773,
|
3 |
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-170",
|
4 |
"epoch": 2.998535871156662,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.9956076134699854,
|
13 |
+
"eval_accuracy": 0.9641025641025641,
|
14 |
+
"eval_f1": 0.9637911305761953,
|
15 |
+
"eval_loss": 0.12035853415727615,
|
16 |
+
"eval_precision": 0.9640509308043554,
|
17 |
+
"eval_recall": 0.9641025641025641,
|
18 |
+
"eval_runtime": 6.052,
|
19 |
+
"eval_samples_per_second": 225.545,
|
20 |
+
"eval_steps_per_second": 28.255,
|
21 |
"step": 85
|
22 |
},
|
23 |
{
|
24 |
"epoch": 1.9912152269399708,
|
25 |
+
"eval_accuracy": 0.9772893772893773,
|
26 |
+
"eval_f1": 0.9772624500008753,
|
27 |
+
"eval_loss": 0.08473604917526245,
|
28 |
+
"eval_precision": 0.9772470873644479,
|
29 |
+
"eval_recall": 0.9772893772893773,
|
30 |
+
"eval_runtime": 5.9068,
|
31 |
+
"eval_samples_per_second": 231.09,
|
32 |
+
"eval_steps_per_second": 28.95,
|
33 |
"step": 170
|
34 |
},
|
35 |
{
|
36 |
"epoch": 2.998535871156662,
|
37 |
+
"eval_accuracy": 0.9765567765567765,
|
38 |
+
"eval_f1": 0.9766464967450174,
|
39 |
+
"eval_loss": 0.10245847702026367,
|
40 |
+
"eval_precision": 0.9768621127754256,
|
41 |
+
"eval_recall": 0.9765567765567765,
|
42 |
+
"eval_runtime": 5.8911,
|
43 |
+
"eval_samples_per_second": 231.706,
|
44 |
+
"eval_steps_per_second": 29.027,
|
45 |
"step": 256
|
46 |
}
|
47 |
],
|
48 |
"logging_steps": 500,
|
49 |
+
"max_steps": 680,
|
50 |
"num_input_tokens_seen": 0,
|
51 |
+
"num_train_epochs": 8,
|
52 |
"save_steps": 500,
|
53 |
"stateful_callbacks": {
|
54 |
"EarlyStoppingCallback": {
|
checkpoint-256/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:cda0bf828ccc04cd6d3fb7933f60f34ca3c8ba14b14579f9e878d688bc739b4a
|
3 |
size 5240
|
checkpoint-341/config.json
CHANGED
@@ -45,6 +45,7 @@
|
|
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,
|
@@ -55,8 +56,8 @@
|
|
55 |
"initializer_range": 0.02,
|
56 |
"intermediate_size": 3072,
|
57 |
"label2id": {
|
58 |
-
"crying":
|
59 |
-
"no_crying":
|
60 |
},
|
61 |
"layer_norm_eps": 1e-05,
|
62 |
"layerdrop": 0.0,
|
|
|
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,
|
|
|
56 |
"initializer_range": 0.02,
|
57 |
"intermediate_size": 3072,
|
58 |
"label2id": {
|
59 |
+
"crying": 0,
|
60 |
+
"no_crying": 1
|
61 |
},
|
62 |
"layer_norm_eps": 1e-05,
|
63 |
"layerdrop": 0.0,
|
checkpoint-341/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 sha256:083f40b77a3962067064a68eb072696b4bf2222ce7f9bdab915843b0aab6cf86
|
3 |
size 94763496
|
checkpoint-341/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:f581f41271d1b7b3e94ec5316e0b37c75a3ad264185a441b84016451887b8ec4
|
3 |
size 189552570
|
checkpoint-341/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:d5073b7c775ebf0fc889f5dba154fdfe2dbb913e0f115f2091d61c7aad83715e
|
3 |
size 1064
|
checkpoint-341/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-341",
|
4 |
"epoch": 3.994143484626647,
|
5 |
"eval_steps": 500,
|
@@ -10,45 +10,57 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.9956076134699854,
|
13 |
-
"eval_accuracy": 0.
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
|
|
|
|
|
|
18 |
"step": 85
|
19 |
},
|
20 |
{
|
21 |
"epoch": 1.9912152269399708,
|
22 |
-
"eval_accuracy": 0.
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
|
|
|
|
|
|
27 |
"step": 170
|
28 |
},
|
29 |
{
|
30 |
"epoch": 2.998535871156662,
|
31 |
-
"eval_accuracy": 0.
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
|
|
|
|
|
|
36 |
"step": 256
|
37 |
},
|
38 |
{
|
39 |
"epoch": 3.994143484626647,
|
40 |
-
"eval_accuracy": 0.
|
41 |
-
"
|
42 |
-
"
|
43 |
-
"
|
44 |
-
"
|
|
|
|
|
|
|
45 |
"step": 341
|
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": {
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9831501831501831,
|
3 |
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-341",
|
4 |
"epoch": 3.994143484626647,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.9956076134699854,
|
13 |
+
"eval_accuracy": 0.9641025641025641,
|
14 |
+
"eval_f1": 0.9637911305761953,
|
15 |
+
"eval_loss": 0.12035853415727615,
|
16 |
+
"eval_precision": 0.9640509308043554,
|
17 |
+
"eval_recall": 0.9641025641025641,
|
18 |
+
"eval_runtime": 6.052,
|
19 |
+
"eval_samples_per_second": 225.545,
|
20 |
+
"eval_steps_per_second": 28.255,
|
21 |
"step": 85
|
22 |
},
|
23 |
{
|
24 |
"epoch": 1.9912152269399708,
|
25 |
+
"eval_accuracy": 0.9772893772893773,
|
26 |
+
"eval_f1": 0.9772624500008753,
|
27 |
+
"eval_loss": 0.08473604917526245,
|
28 |
+
"eval_precision": 0.9772470873644479,
|
29 |
+
"eval_recall": 0.9772893772893773,
|
30 |
+
"eval_runtime": 5.9068,
|
31 |
+
"eval_samples_per_second": 231.09,
|
32 |
+
"eval_steps_per_second": 28.95,
|
33 |
"step": 170
|
34 |
},
|
35 |
{
|
36 |
"epoch": 2.998535871156662,
|
37 |
+
"eval_accuracy": 0.9765567765567765,
|
38 |
+
"eval_f1": 0.9766464967450174,
|
39 |
+
"eval_loss": 0.10245847702026367,
|
40 |
+
"eval_precision": 0.9768621127754256,
|
41 |
+
"eval_recall": 0.9765567765567765,
|
42 |
+
"eval_runtime": 5.8911,
|
43 |
+
"eval_samples_per_second": 231.706,
|
44 |
+
"eval_steps_per_second": 29.027,
|
45 |
"step": 256
|
46 |
},
|
47 |
{
|
48 |
"epoch": 3.994143484626647,
|
49 |
+
"eval_accuracy": 0.9831501831501831,
|
50 |
+
"eval_f1": 0.9832333934847322,
|
51 |
+
"eval_loss": 0.08685966581106186,
|
52 |
+
"eval_precision": 0.9835305336122597,
|
53 |
+
"eval_recall": 0.9831501831501831,
|
54 |
+
"eval_runtime": 5.9568,
|
55 |
+
"eval_samples_per_second": 229.152,
|
56 |
+
"eval_steps_per_second": 28.707,
|
57 |
"step": 341
|
58 |
}
|
59 |
],
|
60 |
"logging_steps": 500,
|
61 |
+
"max_steps": 680,
|
62 |
"num_input_tokens_seen": 0,
|
63 |
+
"num_train_epochs": 8,
|
64 |
"save_steps": 500,
|
65 |
"stateful_callbacks": {
|
66 |
"EarlyStoppingCallback": {
|
checkpoint-341/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:cda0bf828ccc04cd6d3fb7933f60f34ca3c8ba14b14579f9e878d688bc739b4a
|
3 |
size 5240
|
checkpoint-426/config.json
CHANGED
@@ -45,6 +45,7 @@
|
|
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,
|
@@ -55,8 +56,8 @@
|
|
55 |
"initializer_range": 0.02,
|
56 |
"intermediate_size": 3072,
|
57 |
"label2id": {
|
58 |
-
"crying":
|
59 |
-
"no_crying":
|
60 |
},
|
61 |
"layer_norm_eps": 1e-05,
|
62 |
"layerdrop": 0.0,
|
|
|
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,
|
|
|
56 |
"initializer_range": 0.02,
|
57 |
"intermediate_size": 3072,
|
58 |
"label2id": {
|
59 |
+
"crying": 0,
|
60 |
+
"no_crying": 1
|
61 |
},
|
62 |
"layer_norm_eps": 1e-05,
|
63 |
"layerdrop": 0.0,
|
checkpoint-426/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 sha256:1a9d6d392a4f841e92110c90f40ef7219881d17b11f11a64bad39c27cbe0178e
|
3 |
size 94763496
|
checkpoint-426/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:fcfe6fb7847bde58aeb36b9a7bc45200d4352f754fb3595c33126144f17addf2
|
3 |
size 189552570
|
checkpoint-426/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:d56f52cf1fd1013d5989e211cbbbf97096f52d89af5defd532d0d8a25d4724f7
|
3 |
size 1064
|
checkpoint-426/trainer_state.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-
|
4 |
"epoch": 4.989751098096632,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 426,
|
@@ -10,54 +10,69 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.9956076134699854,
|
13 |
-
"eval_accuracy": 0.
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
|
|
|
|
|
|
18 |
"step": 85
|
19 |
},
|
20 |
{
|
21 |
"epoch": 1.9912152269399708,
|
22 |
-
"eval_accuracy": 0.
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
|
|
|
|
|
|
27 |
"step": 170
|
28 |
},
|
29 |
{
|
30 |
"epoch": 2.998535871156662,
|
31 |
-
"eval_accuracy": 0.
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
|
|
|
|
|
|
36 |
"step": 256
|
37 |
},
|
38 |
{
|
39 |
"epoch": 3.994143484626647,
|
40 |
-
"eval_accuracy": 0.
|
41 |
-
"
|
42 |
-
"
|
43 |
-
"
|
44 |
-
"
|
|
|
|
|
|
|
45 |
"step": 341
|
46 |
},
|
47 |
{
|
48 |
"epoch": 4.989751098096632,
|
49 |
-
"eval_accuracy": 0.
|
50 |
-
"
|
51 |
-
"
|
52 |
-
"
|
53 |
-
"
|
|
|
|
|
|
|
54 |
"step": 426
|
55 |
}
|
56 |
],
|
57 |
"logging_steps": 500,
|
58 |
-
"max_steps":
|
59 |
"num_input_tokens_seen": 0,
|
60 |
-
"num_train_epochs":
|
61 |
"save_steps": 500,
|
62 |
"stateful_callbacks": {
|
63 |
"EarlyStoppingCallback": {
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9831501831501831,
|
3 |
+
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-341",
|
4 |
"epoch": 4.989751098096632,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 426,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.9956076134699854,
|
13 |
+
"eval_accuracy": 0.9641025641025641,
|
14 |
+
"eval_f1": 0.9637911305761953,
|
15 |
+
"eval_loss": 0.12035853415727615,
|
16 |
+
"eval_precision": 0.9640509308043554,
|
17 |
+
"eval_recall": 0.9641025641025641,
|
18 |
+
"eval_runtime": 6.052,
|
19 |
+
"eval_samples_per_second": 225.545,
|
20 |
+
"eval_steps_per_second": 28.255,
|
21 |
"step": 85
|
22 |
},
|
23 |
{
|
24 |
"epoch": 1.9912152269399708,
|
25 |
+
"eval_accuracy": 0.9772893772893773,
|
26 |
+
"eval_f1": 0.9772624500008753,
|
27 |
+
"eval_loss": 0.08473604917526245,
|
28 |
+
"eval_precision": 0.9772470873644479,
|
29 |
+
"eval_recall": 0.9772893772893773,
|
30 |
+
"eval_runtime": 5.9068,
|
31 |
+
"eval_samples_per_second": 231.09,
|
32 |
+
"eval_steps_per_second": 28.95,
|
33 |
"step": 170
|
34 |
},
|
35 |
{
|
36 |
"epoch": 2.998535871156662,
|
37 |
+
"eval_accuracy": 0.9765567765567765,
|
38 |
+
"eval_f1": 0.9766464967450174,
|
39 |
+
"eval_loss": 0.10245847702026367,
|
40 |
+
"eval_precision": 0.9768621127754256,
|
41 |
+
"eval_recall": 0.9765567765567765,
|
42 |
+
"eval_runtime": 5.8911,
|
43 |
+
"eval_samples_per_second": 231.706,
|
44 |
+
"eval_steps_per_second": 29.027,
|
45 |
"step": 256
|
46 |
},
|
47 |
{
|
48 |
"epoch": 3.994143484626647,
|
49 |
+
"eval_accuracy": 0.9831501831501831,
|
50 |
+
"eval_f1": 0.9832333934847322,
|
51 |
+
"eval_loss": 0.08685966581106186,
|
52 |
+
"eval_precision": 0.9835305336122597,
|
53 |
+
"eval_recall": 0.9831501831501831,
|
54 |
+
"eval_runtime": 5.9568,
|
55 |
+
"eval_samples_per_second": 229.152,
|
56 |
+
"eval_steps_per_second": 28.707,
|
57 |
"step": 341
|
58 |
},
|
59 |
{
|
60 |
"epoch": 4.989751098096632,
|
61 |
+
"eval_accuracy": 0.9831501831501831,
|
62 |
+
"eval_f1": 0.983208365019189,
|
63 |
+
"eval_loss": 0.07458490133285522,
|
64 |
+
"eval_precision": 0.9833696765629429,
|
65 |
+
"eval_recall": 0.9831501831501831,
|
66 |
+
"eval_runtime": 5.9419,
|
67 |
+
"eval_samples_per_second": 229.726,
|
68 |
+
"eval_steps_per_second": 28.779,
|
69 |
"step": 426
|
70 |
}
|
71 |
],
|
72 |
"logging_steps": 500,
|
73 |
+
"max_steps": 680,
|
74 |
"num_input_tokens_seen": 0,
|
75 |
+
"num_train_epochs": 8,
|
76 |
"save_steps": 500,
|
77 |
"stateful_callbacks": {
|
78 |
"EarlyStoppingCallback": {
|
checkpoint-426/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:cda0bf828ccc04cd6d3fb7933f60f34ca3c8ba14b14579f9e878d688bc739b4a
|
3 |
size 5240
|
checkpoint-512/config.json
CHANGED
@@ -45,6 +45,7 @@
|
|
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,
|
@@ -55,8 +56,8 @@
|
|
55 |
"initializer_range": 0.02,
|
56 |
"intermediate_size": 3072,
|
57 |
"label2id": {
|
58 |
-
"crying":
|
59 |
-
"no_crying":
|
60 |
},
|
61 |
"layer_norm_eps": 1e-05,
|
62 |
"layerdrop": 0.0,
|
|
|
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,
|
|
|
56 |
"initializer_range": 0.02,
|
57 |
"intermediate_size": 3072,
|
58 |
"label2id": {
|
59 |
+
"crying": 0,
|
60 |
+
"no_crying": 1
|
61 |
},
|
62 |
"layer_norm_eps": 1e-05,
|
63 |
"layerdrop": 0.0,
|
checkpoint-512/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:dbc5b2463f7b10d6accd90a38663b1fe5924ce417d20bd4c4b022491ab407a53
|
3 |
size 94763496
|
checkpoint-512/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 sha256:00ec41f63df75118d702c2384056a8cc4b5a13080b78a48bdd542ffc79dc1c02
|
3 |
size 189552570
|
checkpoint-512/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:bcc97a747eb11a8dc86d1d122f7b8fac6f5b54e0a4e11d9bd187896e44dca8fe
|
3 |
size 1064
|
checkpoint-512/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-512",
|
4 |
"epoch": 5.997071742313324,
|
5 |
"eval_steps": 500,
|
@@ -10,70 +10,88 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.9956076134699854,
|
13 |
-
"eval_accuracy": 0.
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
|
|
|
|
|
|
18 |
"step": 85
|
19 |
},
|
20 |
{
|
21 |
"epoch": 1.9912152269399708,
|
22 |
-
"eval_accuracy": 0.
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
|
|
|
|
|
|
27 |
"step": 170
|
28 |
},
|
29 |
{
|
30 |
"epoch": 2.998535871156662,
|
31 |
-
"eval_accuracy": 0.
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
|
|
|
|
|
|
36 |
"step": 256
|
37 |
},
|
38 |
{
|
39 |
"epoch": 3.994143484626647,
|
40 |
-
"eval_accuracy": 0.
|
41 |
-
"
|
42 |
-
"
|
43 |
-
"
|
44 |
-
"
|
|
|
|
|
|
|
45 |
"step": 341
|
46 |
},
|
47 |
{
|
48 |
"epoch": 4.989751098096632,
|
49 |
-
"eval_accuracy": 0.
|
50 |
-
"
|
51 |
-
"
|
52 |
-
"
|
53 |
-
"
|
|
|
|
|
|
|
54 |
"step": 426
|
55 |
},
|
56 |
{
|
57 |
"epoch": 5.856515373352855,
|
58 |
-
"grad_norm": 0.
|
59 |
-
"learning_rate":
|
60 |
-
"loss": 0.
|
61 |
"step": 500
|
62 |
},
|
63 |
{
|
64 |
"epoch": 5.997071742313324,
|
65 |
-
"eval_accuracy": 0.
|
66 |
-
"
|
67 |
-
"
|
68 |
-
"
|
69 |
-
"
|
|
|
|
|
|
|
70 |
"step": 512
|
71 |
}
|
72 |
],
|
73 |
"logging_steps": 500,
|
74 |
-
"max_steps":
|
75 |
"num_input_tokens_seen": 0,
|
76 |
-
"num_train_epochs":
|
77 |
"save_steps": 500,
|
78 |
"stateful_callbacks": {
|
79 |
"EarlyStoppingCallback": {
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9860805860805861,
|
3 |
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-512",
|
4 |
"epoch": 5.997071742313324,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.9956076134699854,
|
13 |
+
"eval_accuracy": 0.9641025641025641,
|
14 |
+
"eval_f1": 0.9637911305761953,
|
15 |
+
"eval_loss": 0.12035853415727615,
|
16 |
+
"eval_precision": 0.9640509308043554,
|
17 |
+
"eval_recall": 0.9641025641025641,
|
18 |
+
"eval_runtime": 6.052,
|
19 |
+
"eval_samples_per_second": 225.545,
|
20 |
+
"eval_steps_per_second": 28.255,
|
21 |
"step": 85
|
22 |
},
|
23 |
{
|
24 |
"epoch": 1.9912152269399708,
|
25 |
+
"eval_accuracy": 0.9772893772893773,
|
26 |
+
"eval_f1": 0.9772624500008753,
|
27 |
+
"eval_loss": 0.08473604917526245,
|
28 |
+
"eval_precision": 0.9772470873644479,
|
29 |
+
"eval_recall": 0.9772893772893773,
|
30 |
+
"eval_runtime": 5.9068,
|
31 |
+
"eval_samples_per_second": 231.09,
|
32 |
+
"eval_steps_per_second": 28.95,
|
33 |
"step": 170
|
34 |
},
|
35 |
{
|
36 |
"epoch": 2.998535871156662,
|
37 |
+
"eval_accuracy": 0.9765567765567765,
|
38 |
+
"eval_f1": 0.9766464967450174,
|
39 |
+
"eval_loss": 0.10245847702026367,
|
40 |
+
"eval_precision": 0.9768621127754256,
|
41 |
+
"eval_recall": 0.9765567765567765,
|
42 |
+
"eval_runtime": 5.8911,
|
43 |
+
"eval_samples_per_second": 231.706,
|
44 |
+
"eval_steps_per_second": 29.027,
|
45 |
"step": 256
|
46 |
},
|
47 |
{
|
48 |
"epoch": 3.994143484626647,
|
49 |
+
"eval_accuracy": 0.9831501831501831,
|
50 |
+
"eval_f1": 0.9832333934847322,
|
51 |
+
"eval_loss": 0.08685966581106186,
|
52 |
+
"eval_precision": 0.9835305336122597,
|
53 |
+
"eval_recall": 0.9831501831501831,
|
54 |
+
"eval_runtime": 5.9568,
|
55 |
+
"eval_samples_per_second": 229.152,
|
56 |
+
"eval_steps_per_second": 28.707,
|
57 |
"step": 341
|
58 |
},
|
59 |
{
|
60 |
"epoch": 4.989751098096632,
|
61 |
+
"eval_accuracy": 0.9831501831501831,
|
62 |
+
"eval_f1": 0.983208365019189,
|
63 |
+
"eval_loss": 0.07458490133285522,
|
64 |
+
"eval_precision": 0.9833696765629429,
|
65 |
+
"eval_recall": 0.9831501831501831,
|
66 |
+
"eval_runtime": 5.9419,
|
67 |
+
"eval_samples_per_second": 229.726,
|
68 |
+
"eval_steps_per_second": 28.779,
|
69 |
"step": 426
|
70 |
},
|
71 |
{
|
72 |
"epoch": 5.856515373352855,
|
73 |
+
"grad_norm": 0.01886621303856373,
|
74 |
+
"learning_rate": 1.6360497736760383e-05,
|
75 |
+
"loss": 0.0538,
|
76 |
"step": 500
|
77 |
},
|
78 |
{
|
79 |
"epoch": 5.997071742313324,
|
80 |
+
"eval_accuracy": 0.9860805860805861,
|
81 |
+
"eval_f1": 0.9860860332682386,
|
82 |
+
"eval_loss": 0.08699370175600052,
|
83 |
+
"eval_precision": 0.9860927746075414,
|
84 |
+
"eval_recall": 0.9860805860805861,
|
85 |
+
"eval_runtime": 5.9399,
|
86 |
+
"eval_samples_per_second": 229.803,
|
87 |
+
"eval_steps_per_second": 28.789,
|
88 |
"step": 512
|
89 |
}
|
90 |
],
|
91 |
"logging_steps": 500,
|
92 |
+
"max_steps": 680,
|
93 |
"num_input_tokens_seen": 0,
|
94 |
+
"num_train_epochs": 8,
|
95 |
"save_steps": 500,
|
96 |
"stateful_callbacks": {
|
97 |
"EarlyStoppingCallback": {
|
checkpoint-512/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:cda0bf828ccc04cd6d3fb7933f60f34ca3c8ba14b14579f9e878d688bc739b4a
|
3 |
size 5240
|
checkpoint-597/config.json
CHANGED
@@ -45,6 +45,7 @@
|
|
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,
|
@@ -55,8 +56,8 @@
|
|
55 |
"initializer_range": 0.02,
|
56 |
"intermediate_size": 3072,
|
57 |
"label2id": {
|
58 |
-
"crying":
|
59 |
-
"no_crying":
|
60 |
},
|
61 |
"layer_norm_eps": 1e-05,
|
62 |
"layerdrop": 0.0,
|
|
|
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,
|
|
|
56 |
"initializer_range": 0.02,
|
57 |
"intermediate_size": 3072,
|
58 |
"label2id": {
|
59 |
+
"crying": 0,
|
60 |
+
"no_crying": 1
|
61 |
},
|
62 |
"layer_norm_eps": 1e-05,
|
63 |
"layerdrop": 0.0,
|
checkpoint-597/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:a064606432f81dfcabef436b3a7746c96408c18ddc57930d2e91972b830e997f
|
3 |
size 94763496
|
checkpoint-597/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 sha256:84091c5d2d0db5e72458d1db7aef4f39da72483fa57f4cd28ecc4085a3dfd425
|
3 |
size 189552570
|
checkpoint-597/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:fbae7c9f313f104f989b156afed3a79758bf4cf1949ca702f760fa941bede2bf
|
3 |
size 1064
|
checkpoint-597/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-512",
|
4 |
"epoch": 6.992679355783309,
|
5 |
"eval_steps": 500,
|
@@ -10,79 +10,100 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.9956076134699854,
|
13 |
-
"eval_accuracy": 0.
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
|
|
|
|
|
|
18 |
"step": 85
|
19 |
},
|
20 |
{
|
21 |
"epoch": 1.9912152269399708,
|
22 |
-
"eval_accuracy": 0.
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
|
|
|
|
|
|
27 |
"step": 170
|
28 |
},
|
29 |
{
|
30 |
"epoch": 2.998535871156662,
|
31 |
-
"eval_accuracy": 0.
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
|
|
|
|
|
|
36 |
"step": 256
|
37 |
},
|
38 |
{
|
39 |
"epoch": 3.994143484626647,
|
40 |
-
"eval_accuracy": 0.
|
41 |
-
"
|
42 |
-
"
|
43 |
-
"
|
44 |
-
"
|
|
|
|
|
|
|
45 |
"step": 341
|
46 |
},
|
47 |
{
|
48 |
"epoch": 4.989751098096632,
|
49 |
-
"eval_accuracy": 0.
|
50 |
-
"
|
51 |
-
"
|
52 |
-
"
|
53 |
-
"
|
|
|
|
|
|
|
54 |
"step": 426
|
55 |
},
|
56 |
{
|
57 |
"epoch": 5.856515373352855,
|
58 |
-
"grad_norm": 0.
|
59 |
-
"learning_rate":
|
60 |
-
"loss": 0.
|
61 |
"step": 500
|
62 |
},
|
63 |
{
|
64 |
"epoch": 5.997071742313324,
|
65 |
-
"eval_accuracy": 0.
|
66 |
-
"
|
67 |
-
"
|
68 |
-
"
|
69 |
-
"
|
|
|
|
|
|
|
70 |
"step": 512
|
71 |
},
|
72 |
{
|
73 |
"epoch": 6.992679355783309,
|
74 |
-
"eval_accuracy": 0.
|
75 |
-
"
|
76 |
-
"
|
77 |
-
"
|
78 |
-
"
|
|
|
|
|
|
|
79 |
"step": 597
|
80 |
}
|
81 |
],
|
82 |
"logging_steps": 500,
|
83 |
-
"max_steps":
|
84 |
"num_input_tokens_seen": 0,
|
85 |
-
"num_train_epochs":
|
86 |
"save_steps": 500,
|
87 |
"stateful_callbacks": {
|
88 |
"EarlyStoppingCallback": {
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9860805860805861,
|
3 |
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-512",
|
4 |
"epoch": 6.992679355783309,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.9956076134699854,
|
13 |
+
"eval_accuracy": 0.9641025641025641,
|
14 |
+
"eval_f1": 0.9637911305761953,
|
15 |
+
"eval_loss": 0.12035853415727615,
|
16 |
+
"eval_precision": 0.9640509308043554,
|
17 |
+
"eval_recall": 0.9641025641025641,
|
18 |
+
"eval_runtime": 6.052,
|
19 |
+
"eval_samples_per_second": 225.545,
|
20 |
+
"eval_steps_per_second": 28.255,
|
21 |
"step": 85
|
22 |
},
|
23 |
{
|
24 |
"epoch": 1.9912152269399708,
|
25 |
+
"eval_accuracy": 0.9772893772893773,
|
26 |
+
"eval_f1": 0.9772624500008753,
|
27 |
+
"eval_loss": 0.08473604917526245,
|
28 |
+
"eval_precision": 0.9772470873644479,
|
29 |
+
"eval_recall": 0.9772893772893773,
|
30 |
+
"eval_runtime": 5.9068,
|
31 |
+
"eval_samples_per_second": 231.09,
|
32 |
+
"eval_steps_per_second": 28.95,
|
33 |
"step": 170
|
34 |
},
|
35 |
{
|
36 |
"epoch": 2.998535871156662,
|
37 |
+
"eval_accuracy": 0.9765567765567765,
|
38 |
+
"eval_f1": 0.9766464967450174,
|
39 |
+
"eval_loss": 0.10245847702026367,
|
40 |
+
"eval_precision": 0.9768621127754256,
|
41 |
+
"eval_recall": 0.9765567765567765,
|
42 |
+
"eval_runtime": 5.8911,
|
43 |
+
"eval_samples_per_second": 231.706,
|
44 |
+
"eval_steps_per_second": 29.027,
|
45 |
"step": 256
|
46 |
},
|
47 |
{
|
48 |
"epoch": 3.994143484626647,
|
49 |
+
"eval_accuracy": 0.9831501831501831,
|
50 |
+
"eval_f1": 0.9832333934847322,
|
51 |
+
"eval_loss": 0.08685966581106186,
|
52 |
+
"eval_precision": 0.9835305336122597,
|
53 |
+
"eval_recall": 0.9831501831501831,
|
54 |
+
"eval_runtime": 5.9568,
|
55 |
+
"eval_samples_per_second": 229.152,
|
56 |
+
"eval_steps_per_second": 28.707,
|
57 |
"step": 341
|
58 |
},
|
59 |
{
|
60 |
"epoch": 4.989751098096632,
|
61 |
+
"eval_accuracy": 0.9831501831501831,
|
62 |
+
"eval_f1": 0.983208365019189,
|
63 |
+
"eval_loss": 0.07458490133285522,
|
64 |
+
"eval_precision": 0.9833696765629429,
|
65 |
+
"eval_recall": 0.9831501831501831,
|
66 |
+
"eval_runtime": 5.9419,
|
67 |
+
"eval_samples_per_second": 229.726,
|
68 |
+
"eval_steps_per_second": 28.779,
|
69 |
"step": 426
|
70 |
},
|
71 |
{
|
72 |
"epoch": 5.856515373352855,
|
73 |
+
"grad_norm": 0.01886621303856373,
|
74 |
+
"learning_rate": 1.6360497736760383e-05,
|
75 |
+
"loss": 0.0538,
|
76 |
"step": 500
|
77 |
},
|
78 |
{
|
79 |
"epoch": 5.997071742313324,
|
80 |
+
"eval_accuracy": 0.9860805860805861,
|
81 |
+
"eval_f1": 0.9860860332682386,
|
82 |
+
"eval_loss": 0.08699370175600052,
|
83 |
+
"eval_precision": 0.9860927746075414,
|
84 |
+
"eval_recall": 0.9860805860805861,
|
85 |
+
"eval_runtime": 5.9399,
|
86 |
+
"eval_samples_per_second": 229.803,
|
87 |
+
"eval_steps_per_second": 28.789,
|
88 |
"step": 512
|
89 |
},
|
90 |
{
|
91 |
"epoch": 6.992679355783309,
|
92 |
+
"eval_accuracy": 0.9860805860805861,
|
93 |
+
"eval_f1": 0.9860860332682386,
|
94 |
+
"eval_loss": 0.08903729915618896,
|
95 |
+
"eval_precision": 0.9860927746075414,
|
96 |
+
"eval_recall": 0.9860805860805861,
|
97 |
+
"eval_runtime": 5.9207,
|
98 |
+
"eval_samples_per_second": 230.546,
|
99 |
+
"eval_steps_per_second": 28.882,
|
100 |
"step": 597
|
101 |
}
|
102 |
],
|
103 |
"logging_steps": 500,
|
104 |
+
"max_steps": 680,
|
105 |
"num_input_tokens_seen": 0,
|
106 |
+
"num_train_epochs": 8,
|
107 |
"save_steps": 500,
|
108 |
"stateful_callbacks": {
|
109 |
"EarlyStoppingCallback": {
|
checkpoint-597/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:cda0bf828ccc04cd6d3fb7933f60f34ca3c8ba14b14579f9e878d688bc739b4a
|
3 |
size 5240
|
checkpoint-680/config.json
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"label2id": {
|
59 |
+
"crying": 0,
|
60 |
+
"no_crying": 1
|
61 |
+
},
|
62 |
+
"layer_norm_eps": 1e-05,
|
63 |
+
"layerdrop": 0.0,
|
64 |
+
"mask_feature_length": 10,
|
65 |
+
"mask_feature_min_masks": 0,
|
66 |
+
"mask_feature_prob": 0.0,
|
67 |
+
"mask_time_length": 10,
|
68 |
+
"mask_time_min_masks": 2,
|
69 |
+
"mask_time_prob": 0.05,
|
70 |
+
"model_type": "hubert",
|
71 |
+
"num_attention_heads": 12,
|
72 |
+
"num_conv_pos_embedding_groups": 16,
|
73 |
+
"num_conv_pos_embeddings": 128,
|
74 |
+
"num_feat_extract_layers": 7,
|
75 |
+
"num_hidden_layers": 2,
|
76 |
+
"pad_token_id": 0,
|
77 |
+
"torch_dtype": "float32",
|
78 |
+
"transformers_version": "4.44.2",
|
79 |
+
"use_weighted_layer_sum": false,
|
80 |
+
"vocab_size": 32
|
81 |
+
}
|
checkpoint-680/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44cc698d409540f6e674563ba636b09a358b51b95c971805d7140c78f749221d
|
3 |
+
size 94763496
|
checkpoint-680/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64ee67cfbe8e68b976d9e8b9d28361fe29aabb080922e8ca1dfc46687eee0bf5
|
3 |
+
size 189552570
|
checkpoint-680/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89fd3252e5fe944df77172e7776b58570ce1e9687a28e4844bb5682e98356731
|
3 |
+
size 14308
|
checkpoint-680/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba3c5930117a39fdd2c8cd1183dafd9e8a9fe0628798a35edc18e6f58251dd0e
|
3 |
+
size 1064
|
checkpoint-680/trainer_state.json
ADDED
@@ -0,0 +1,145 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9860805860805861,
|
3 |
+
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-512",
|
4 |
+
"epoch": 7.964860907759883,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 680,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.9956076134699854,
|
13 |
+
"eval_accuracy": 0.9641025641025641,
|
14 |
+
"eval_f1": 0.9637911305761953,
|
15 |
+
"eval_loss": 0.12035853415727615,
|
16 |
+
"eval_precision": 0.9640509308043554,
|
17 |
+
"eval_recall": 0.9641025641025641,
|
18 |
+
"eval_runtime": 6.052,
|
19 |
+
"eval_samples_per_second": 225.545,
|
20 |
+
"eval_steps_per_second": 28.255,
|
21 |
+
"step": 85
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 1.9912152269399708,
|
25 |
+
"eval_accuracy": 0.9772893772893773,
|
26 |
+
"eval_f1": 0.9772624500008753,
|
27 |
+
"eval_loss": 0.08473604917526245,
|
28 |
+
"eval_precision": 0.9772470873644479,
|
29 |
+
"eval_recall": 0.9772893772893773,
|
30 |
+
"eval_runtime": 5.9068,
|
31 |
+
"eval_samples_per_second": 231.09,
|
32 |
+
"eval_steps_per_second": 28.95,
|
33 |
+
"step": 170
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 2.998535871156662,
|
37 |
+
"eval_accuracy": 0.9765567765567765,
|
38 |
+
"eval_f1": 0.9766464967450174,
|
39 |
+
"eval_loss": 0.10245847702026367,
|
40 |
+
"eval_precision": 0.9768621127754256,
|
41 |
+
"eval_recall": 0.9765567765567765,
|
42 |
+
"eval_runtime": 5.8911,
|
43 |
+
"eval_samples_per_second": 231.706,
|
44 |
+
"eval_steps_per_second": 29.027,
|
45 |
+
"step": 256
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 3.994143484626647,
|
49 |
+
"eval_accuracy": 0.9831501831501831,
|
50 |
+
"eval_f1": 0.9832333934847322,
|
51 |
+
"eval_loss": 0.08685966581106186,
|
52 |
+
"eval_precision": 0.9835305336122597,
|
53 |
+
"eval_recall": 0.9831501831501831,
|
54 |
+
"eval_runtime": 5.9568,
|
55 |
+
"eval_samples_per_second": 229.152,
|
56 |
+
"eval_steps_per_second": 28.707,
|
57 |
+
"step": 341
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 4.989751098096632,
|
61 |
+
"eval_accuracy": 0.9831501831501831,
|
62 |
+
"eval_f1": 0.983208365019189,
|
63 |
+
"eval_loss": 0.07458490133285522,
|
64 |
+
"eval_precision": 0.9833696765629429,
|
65 |
+
"eval_recall": 0.9831501831501831,
|
66 |
+
"eval_runtime": 5.9419,
|
67 |
+
"eval_samples_per_second": 229.726,
|
68 |
+
"eval_steps_per_second": 28.779,
|
69 |
+
"step": 426
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 5.856515373352855,
|
73 |
+
"grad_norm": 0.01886621303856373,
|
74 |
+
"learning_rate": 1.6360497736760383e-05,
|
75 |
+
"loss": 0.0538,
|
76 |
+
"step": 500
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 5.997071742313324,
|
80 |
+
"eval_accuracy": 0.9860805860805861,
|
81 |
+
"eval_f1": 0.9860860332682386,
|
82 |
+
"eval_loss": 0.08699370175600052,
|
83 |
+
"eval_precision": 0.9860927746075414,
|
84 |
+
"eval_recall": 0.9860805860805861,
|
85 |
+
"eval_runtime": 5.9399,
|
86 |
+
"eval_samples_per_second": 229.803,
|
87 |
+
"eval_steps_per_second": 28.789,
|
88 |
+
"step": 512
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 6.992679355783309,
|
92 |
+
"eval_accuracy": 0.9860805860805861,
|
93 |
+
"eval_f1": 0.9860860332682386,
|
94 |
+
"eval_loss": 0.08903729915618896,
|
95 |
+
"eval_precision": 0.9860927746075414,
|
96 |
+
"eval_recall": 0.9860805860805861,
|
97 |
+
"eval_runtime": 5.9207,
|
98 |
+
"eval_samples_per_second": 230.546,
|
99 |
+
"eval_steps_per_second": 28.882,
|
100 |
+
"step": 597
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 7.964860907759883,
|
104 |
+
"eval_accuracy": 0.9860805860805861,
|
105 |
+
"eval_f1": 0.9860860332682386,
|
106 |
+
"eval_loss": 0.08778514713048935,
|
107 |
+
"eval_precision": 0.9860927746075414,
|
108 |
+
"eval_recall": 0.9860805860805861,
|
109 |
+
"eval_runtime": 5.9724,
|
110 |
+
"eval_samples_per_second": 228.552,
|
111 |
+
"eval_steps_per_second": 28.632,
|
112 |
+
"step": 680
|
113 |
+
}
|
114 |
+
],
|
115 |
+
"logging_steps": 500,
|
116 |
+
"max_steps": 680,
|
117 |
+
"num_input_tokens_seen": 0,
|
118 |
+
"num_train_epochs": 8,
|
119 |
+
"save_steps": 500,
|
120 |
+
"stateful_callbacks": {
|
121 |
+
"EarlyStoppingCallback": {
|
122 |
+
"args": {
|
123 |
+
"early_stopping_patience": 3,
|
124 |
+
"early_stopping_threshold": 0.0
|
125 |
+
},
|
126 |
+
"attributes": {
|
127 |
+
"early_stopping_patience_counter": 0
|
128 |
+
}
|
129 |
+
},
|
130 |
+
"TrainerControl": {
|
131 |
+
"args": {
|
132 |
+
"should_epoch_stop": false,
|
133 |
+
"should_evaluate": false,
|
134 |
+
"should_log": false,
|
135 |
+
"should_save": true,
|
136 |
+
"should_training_stop": true
|
137 |
+
},
|
138 |
+
"attributes": {}
|
139 |
+
}
|
140 |
+
},
|
141 |
+
"total_flos": 9.8908515478272e+16,
|
142 |
+
"train_batch_size": 8,
|
143 |
+
"trial_name": null,
|
144 |
+
"trial_params": null
|
145 |
+
}
|
checkpoint-680/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cda0bf828ccc04cd6d3fb7933f60f34ca3c8ba14b14579f9e878d688bc739b4a
|
3 |
+
size 5240
|
checkpoint-85/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:a15277aa4797964b12aaedf5acf9218acf9f11597a299deaf3a64bad8d89176e
|
3 |
size 94763496
|
checkpoint-85/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:f9c4d0328f867e3a4371326367364a334fc34c6ecaba4f27c44bae6d943a3f5e
|
3 |
size 189552570
|
checkpoint-85/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 sha256:74e1c11b94b090a41a3c1ccee3afde4077ab65e935c7dfa8559b5a7860ed3169
|
3 |
size 14308
|
checkpoint-85/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 sha256:1a3200599f03a01d89a474fcdd8a567058cd33b2f50dde928b44d422ff5012f0
|
3 |
size 1064
|
checkpoint-85/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-85",
|
4 |
"epoch": 0.9956076134699854,
|
5 |
"eval_steps": 500,
|
@@ -10,21 +10,21 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.9956076134699854,
|
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":
|
21 |
"step": 85
|
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": 0.9641025641025641,
|
3 |
"best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-85",
|
4 |
"epoch": 0.9956076134699854,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.9956076134699854,
|
13 |
+
"eval_accuracy": 0.9641025641025641,
|
14 |
+
"eval_f1": 0.9637911305761953,
|
15 |
+
"eval_loss": 0.12035853415727615,
|
16 |
+
"eval_precision": 0.9640509308043554,
|
17 |
+
"eval_recall": 0.9641025641025641,
|
18 |
+
"eval_runtime": 6.052,
|
19 |
+
"eval_samples_per_second": 225.545,
|
20 |
+
"eval_steps_per_second": 28.255,
|
21 |
"step": 85
|
22 |
}
|
23 |
],
|
24 |
"logging_steps": 500,
|
25 |
+
"max_steps": 680,
|
26 |
"num_input_tokens_seen": 0,
|
27 |
+
"num_train_epochs": 8,
|
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": 1.241700759936e+16,
|
51 |
"train_batch_size": 8,
|
52 |
"trial_name": null,
|
53 |
"trial_params": null
|
checkpoint-85/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:cda0bf828ccc04cd6d3fb7933f60f34ca3c8ba14b14579f9e878d688bc739b4a
|
3 |
size 5240
|