Training in progress, step 500
Browse files
config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "facebook/hubert-
|
3 |
-
"activation_dropout": 0.
|
4 |
"apply_spec_augment": true,
|
5 |
"architectures": [
|
6 |
"HubertForSequenceClassification"
|
@@ -8,7 +8,7 @@
|
|
8 |
"attention_dropout": 0.1,
|
9 |
"bos_token_id": 1,
|
10 |
"classifier_proj_size": 256,
|
11 |
-
"conv_bias":
|
12 |
"conv_dim": [
|
13 |
512,
|
14 |
512,
|
@@ -38,19 +38,18 @@
|
|
38 |
],
|
39 |
"ctc_loss_reduction": "sum",
|
40 |
"ctc_zero_infinity": false,
|
41 |
-
"do_stable_layer_norm":
|
42 |
"eos_token_id": 2,
|
43 |
"feat_extract_activation": "gelu",
|
44 |
"feat_extract_dropout": 0.0,
|
45 |
-
"feat_extract_norm": "
|
46 |
"feat_proj_dropout": 0.1,
|
47 |
"feat_proj_layer_norm": true,
|
48 |
-
"final_dropout": 0.
|
49 |
"gradient_checkpointing": false,
|
50 |
"hidden_act": "gelu",
|
51 |
"hidden_dropout": 0.1,
|
52 |
-
"
|
53 |
-
"hidden_size": 768,
|
54 |
"id2label": {
|
55 |
"0": "LABEL_0",
|
56 |
"1": "LABEL_1",
|
@@ -138,7 +137,7 @@
|
|
138 |
"83": "LABEL_83"
|
139 |
},
|
140 |
"initializer_range": 0.02,
|
141 |
-
"intermediate_size":
|
142 |
"label2id": {
|
143 |
"LABEL_0": 0,
|
144 |
"LABEL_1": 1,
|
@@ -227,18 +226,26 @@
|
|
227 |
},
|
228 |
"layer_norm_eps": 1e-05,
|
229 |
"layerdrop": 0.1,
|
|
|
|
|
|
|
|
|
|
|
230 |
"mask_feature_length": 10,
|
231 |
"mask_feature_min_masks": 0,
|
232 |
"mask_feature_prob": 0.0,
|
233 |
"mask_time_length": 10,
|
234 |
"mask_time_min_masks": 2,
|
235 |
-
"
|
|
|
|
|
|
|
236 |
"model_type": "hubert",
|
237 |
-
"num_attention_heads":
|
238 |
"num_conv_pos_embedding_groups": 16,
|
239 |
"num_conv_pos_embeddings": 128,
|
240 |
"num_feat_extract_layers": 7,
|
241 |
-
"num_hidden_layers":
|
242 |
"pad_token_id": 0,
|
243 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
244 |
"torch_dtype": "float32",
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "facebook/hubert-large-ll60k",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
"apply_spec_augment": true,
|
5 |
"architectures": [
|
6 |
"HubertForSequenceClassification"
|
|
|
8 |
"attention_dropout": 0.1,
|
9 |
"bos_token_id": 1,
|
10 |
"classifier_proj_size": 256,
|
11 |
+
"conv_bias": true,
|
12 |
"conv_dim": [
|
13 |
512,
|
14 |
512,
|
|
|
38 |
],
|
39 |
"ctc_loss_reduction": "sum",
|
40 |
"ctc_zero_infinity": false,
|
41 |
+
"do_stable_layer_norm": true,
|
42 |
"eos_token_id": 2,
|
43 |
"feat_extract_activation": "gelu",
|
44 |
"feat_extract_dropout": 0.0,
|
45 |
+
"feat_extract_norm": "layer",
|
46 |
"feat_proj_dropout": 0.1,
|
47 |
"feat_proj_layer_norm": true,
|
48 |
+
"final_dropout": 0.0,
|
49 |
"gradient_checkpointing": false,
|
50 |
"hidden_act": "gelu",
|
51 |
"hidden_dropout": 0.1,
|
52 |
+
"hidden_size": 1024,
|
|
|
53 |
"id2label": {
|
54 |
"0": "LABEL_0",
|
55 |
"1": "LABEL_1",
|
|
|
137 |
"83": "LABEL_83"
|
138 |
},
|
139 |
"initializer_range": 0.02,
|
140 |
+
"intermediate_size": 4096,
|
141 |
"label2id": {
|
142 |
"LABEL_0": 0,
|
143 |
"LABEL_1": 1,
|
|
|
226 |
},
|
227 |
"layer_norm_eps": 1e-05,
|
228 |
"layerdrop": 0.1,
|
229 |
+
"mask_channel_length": 10,
|
230 |
+
"mask_channel_min_space": 1,
|
231 |
+
"mask_channel_other": 0.0,
|
232 |
+
"mask_channel_prob": 0.0,
|
233 |
+
"mask_channel_selection": "static",
|
234 |
"mask_feature_length": 10,
|
235 |
"mask_feature_min_masks": 0,
|
236 |
"mask_feature_prob": 0.0,
|
237 |
"mask_time_length": 10,
|
238 |
"mask_time_min_masks": 2,
|
239 |
+
"mask_time_min_space": 1,
|
240 |
+
"mask_time_other": 0.0,
|
241 |
+
"mask_time_prob": 0.075,
|
242 |
+
"mask_time_selection": "static",
|
243 |
"model_type": "hubert",
|
244 |
+
"num_attention_heads": 16,
|
245 |
"num_conv_pos_embedding_groups": 16,
|
246 |
"num_conv_pos_embeddings": 128,
|
247 |
"num_feat_extract_layers": 7,
|
248 |
+
"num_hidden_layers": 24,
|
249 |
"pad_token_id": 0,
|
250 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
251 |
"torch_dtype": "float32",
|
model.safetensors
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:eacf169a553fbf358fa5223cdde17f080c7d175cc87e985a453e53174b39261b
|
3 |
+
size 1262942768
|
runs/Jul23_01-31-58_LAPTOP-1GID9RGH/events.out.tfevents.1721673119.LAPTOP-1GID9RGH.24960.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9f34ba18d83ae76f619dc4b07775b840e937e33d5318f713e807f5f58d21c89
|
3 |
+
size 9297
|
runs/Jul23_01-47-26_LAPTOP-1GID9RGH/events.out.tfevents.1721674047.LAPTOP-1GID9RGH.2264.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6d83ee0e79e35c2b22062388673d56dba90e04f511b24e1bb4bb9c8a87d36cf
|
3 |
+
size 14665
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2267625fb5bb3e6ce0ce3baf60b4073360076dffb219dc39c36a3a38d8778058
|
3 |
size 4984
|