Training in progress, epoch 1
Browse files- config.json +4 -4
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
{
|
2 |
"_name_or_path": "sophiaaez/distilhubert_clone",
|
3 |
-
"activation_dropout": 0.
|
4 |
"apply_spec_augment": false,
|
5 |
"architectures": [
|
6 |
"HubertForSequenceClassification"
|
7 |
],
|
8 |
-
"attention_dropout": 0.
|
9 |
"bos_token_id": 1,
|
10 |
"classifier_proj_size": 256,
|
11 |
"conv_bias": false,
|
@@ -44,9 +44,9 @@
|
|
44 |
"feat_extract_norm": "group",
|
45 |
"feat_proj_dropout": 0.0,
|
46 |
"feat_proj_layer_norm": false,
|
47 |
-
"final_dropout": 0.
|
48 |
"hidden_act": "gelu",
|
49 |
-
"hidden_dropout": 0.
|
50 |
"hidden_size": 768,
|
51 |
"id2label": {
|
52 |
"0": "blues",
|
|
|
1 |
{
|
2 |
"_name_or_path": "sophiaaez/distilhubert_clone",
|
3 |
+
"activation_dropout": 0.15,
|
4 |
"apply_spec_augment": false,
|
5 |
"architectures": [
|
6 |
"HubertForSequenceClassification"
|
7 |
],
|
8 |
+
"attention_dropout": 0.15,
|
9 |
"bos_token_id": 1,
|
10 |
"classifier_proj_size": 256,
|
11 |
"conv_bias": false,
|
|
|
44 |
"feat_extract_norm": "group",
|
45 |
"feat_proj_dropout": 0.0,
|
46 |
"feat_proj_layer_norm": false,
|
47 |
+
"final_dropout": 0.05,
|
48 |
"hidden_act": "gelu",
|
49 |
+
"hidden_dropout": 0.15,
|
50 |
"hidden_size": 768,
|
51 |
"id2label": {
|
52 |
"0": "blues",
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 94783376
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fade675c51933b93412635f472e293b52fa8cf3b63d9088f70034212725a06dd
|
3 |
size 94783376
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4091
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6698cb4e63839e3ed019cae3ab5e0156574a72997803ddd2020bf0da9f54eda
|
3 |
size 4091
|