codingaslu
commited on
Commit
•
4083b4b
1
Parent(s):
abca0e8
Training in progress, step 100
Browse files
config.json
ADDED
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/hubert-large-ls960-ft",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"apply_spec_augment": true,
|
5 |
+
"architectures": [
|
6 |
+
"HubertForSequenceClassification"
|
7 |
+
],
|
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,
|
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 |
+
"diversity_loss_weight": 0.1,
|
42 |
+
"do_stable_layer_norm": true,
|
43 |
+
"eos_token_id": 2,
|
44 |
+
"feat_extract_activation": "gelu",
|
45 |
+
"feat_extract_dropout": 0.0,
|
46 |
+
"feat_extract_norm": "layer",
|
47 |
+
"feat_proj_dropout": 0.1,
|
48 |
+
"feat_proj_layer_norm": true,
|
49 |
+
"final_dropout": 0.1,
|
50 |
+
"gradient_checkpointing": false,
|
51 |
+
"hidden_act": "gelu",
|
52 |
+
"hidden_dropout": 0.1,
|
53 |
+
"hidden_dropout_prob": 0.1,
|
54 |
+
"hidden_size": 1024,
|
55 |
+
"id2label": {
|
56 |
+
"0": "LABEL_0",
|
57 |
+
"1": "LABEL_1",
|
58 |
+
"2": "LABEL_2",
|
59 |
+
"3": "LABEL_3",
|
60 |
+
"4": "LABEL_4",
|
61 |
+
"5": "LABEL_5"
|
62 |
+
},
|
63 |
+
"initializer_range": 0.02,
|
64 |
+
"intermediate_size": 4096,
|
65 |
+
"label2id": {
|
66 |
+
"LABEL_0": 0,
|
67 |
+
"LABEL_1": 1,
|
68 |
+
"LABEL_2": 2,
|
69 |
+
"LABEL_3": 3,
|
70 |
+
"LABEL_4": 4,
|
71 |
+
"LABEL_5": 5
|
72 |
+
},
|
73 |
+
"layer_norm_eps": 1e-05,
|
74 |
+
"layerdrop": 0.1,
|
75 |
+
"mask_feature_length": 10,
|
76 |
+
"mask_feature_min_masks": 0,
|
77 |
+
"mask_feature_prob": 0.0,
|
78 |
+
"mask_time_length": 10,
|
79 |
+
"mask_time_min_masks": 2,
|
80 |
+
"mask_time_prob": 0.05,
|
81 |
+
"model_type": "hubert",
|
82 |
+
"num_attention_heads": 16,
|
83 |
+
"num_conv_pos_embedding_groups": 16,
|
84 |
+
"num_conv_pos_embeddings": 128,
|
85 |
+
"num_feat_extract_layers": 7,
|
86 |
+
"num_hidden_layers": 24,
|
87 |
+
"pad_token_id": 0,
|
88 |
+
"torch_dtype": "float32",
|
89 |
+
"transformers_version": "4.37.2",
|
90 |
+
"use_weighted_layer_sum": false,
|
91 |
+
"vocab_size": 32
|
92 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e081dd5ab6ed006a97ff6a070468f998c4b616bf16be907dd13002f57239429
|
3 |
+
size 1262862576
|
runs/Feb19_15-04-34_1d43b743edf1/events.out.tfevents.1708355074.1d43b743edf1.432.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e591c10022c5217fb3a9242f12043029f053cbe13dc57fdee2adc80b2a9745d7
|
3 |
+
size 21389
|
runs/Feb19_15-17-08_1d43b743edf1/events.out.tfevents.1708355834.1d43b743edf1.432.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ae5f758d4196daafe9da67ff13c12d8cd5aa3b13b03db5e83a856375757e438
|
3 |
+
size 7093
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32951cc799e892507575220813206bfc3123087500c770be6d529bf30d6cf075
|
3 |
+
size 4728
|