Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +80 -0
- pytorch_model.bin +3 -0
- runs/Jun02_10-41-55_f4a43aec5193/1654166644.3540096/events.out.tfevents.1654166644.f4a43aec5193.71.1 +3 -0
- runs/Jun02_10-41-55_f4a43aec5193/events.out.tfevents.1654166644.f4a43aec5193.71.0 +3 -0
- runs/Jun02_11-05-30_f4a43aec5193/1654167958.272989/events.out.tfevents.1654167958.f4a43aec5193.71.3 +3 -0
- runs/Jun02_11-05-30_f4a43aec5193/events.out.tfevents.1654167958.f4a43aec5193.71.2 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"adapters": {
|
5 |
+
"adapters": {
|
6 |
+
"mam_adapter": "6e29731ca7c632cd"
|
7 |
+
},
|
8 |
+
"config_map": {
|
9 |
+
"6e29731ca7c632cd": {
|
10 |
+
"architecture": "union",
|
11 |
+
"configs": [
|
12 |
+
{
|
13 |
+
"architecture": "prefix_tuning",
|
14 |
+
"bottleneck_size": 800,
|
15 |
+
"cross_prefix": true,
|
16 |
+
"dropout": 0.0,
|
17 |
+
"encoder_prefix": true,
|
18 |
+
"flat": false,
|
19 |
+
"leave_out": [],
|
20 |
+
"non_linearity": "tanh",
|
21 |
+
"prefix_length": 30
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"adapter_residual_before_ln": false,
|
25 |
+
"cross_adapter": false,
|
26 |
+
"factorized_phm_W": true,
|
27 |
+
"factorized_phm_rule": false,
|
28 |
+
"hypercomplex_nonlinearity": "glorot-uniform",
|
29 |
+
"init_weights": "mam_adapter",
|
30 |
+
"inv_adapter": null,
|
31 |
+
"inv_adapter_reduction_factor": null,
|
32 |
+
"is_parallel": true,
|
33 |
+
"learn_phm": true,
|
34 |
+
"leave_out": [],
|
35 |
+
"ln_after": false,
|
36 |
+
"ln_before": false,
|
37 |
+
"mh_adapter": false,
|
38 |
+
"non_linearity": "relu",
|
39 |
+
"original_ln_after": true,
|
40 |
+
"original_ln_before": false,
|
41 |
+
"output_adapter": true,
|
42 |
+
"phm_bias": true,
|
43 |
+
"phm_c_init": "normal",
|
44 |
+
"phm_dim": 4,
|
45 |
+
"phm_init_range": 0.0001,
|
46 |
+
"phm_layer": false,
|
47 |
+
"phm_rank": 1,
|
48 |
+
"reduction_factor": 2,
|
49 |
+
"residual_before_ln": true,
|
50 |
+
"scaling": 4.0,
|
51 |
+
"shared_W_phm": false,
|
52 |
+
"shared_phm_rule": true
|
53 |
+
}
|
54 |
+
]
|
55 |
+
}
|
56 |
+
},
|
57 |
+
"fusion_config_map": {},
|
58 |
+
"fusions": {}
|
59 |
+
},
|
60 |
+
"architectures": [
|
61 |
+
"DistilBertForQuestionAnswering"
|
62 |
+
],
|
63 |
+
"attention_dropout": 0.1,
|
64 |
+
"dim": 768,
|
65 |
+
"dropout": 0.1,
|
66 |
+
"hidden_dim": 3072,
|
67 |
+
"initializer_range": 0.02,
|
68 |
+
"max_position_embeddings": 512,
|
69 |
+
"model_type": "distilbert",
|
70 |
+
"n_heads": 12,
|
71 |
+
"n_layers": 6,
|
72 |
+
"pad_token_id": 0,
|
73 |
+
"qa_dropout": 0.1,
|
74 |
+
"seq_classif_dropout": 0.2,
|
75 |
+
"sinusoidal_pos_embds": false,
|
76 |
+
"tie_weights_": true,
|
77 |
+
"torch_dtype": "float32",
|
78 |
+
"transformers_version": "4.17.0",
|
79 |
+
"vocab_size": 30522
|
80 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1b3b57ce1546f0f5d0b0e98c7ae41744317f2f7b88e6d297e181d19ed93019f
|
3 |
+
size 311796155
|
runs/Jun02_10-41-55_f4a43aec5193/1654166644.3540096/events.out.tfevents.1654166644.f4a43aec5193.71.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfefa8995fc82dd4dd62d00504d2d461f1c74d465d2784ab1bb72abe760d22e2
|
3 |
+
size 4826
|
runs/Jun02_10-41-55_f4a43aec5193/events.out.tfevents.1654166644.f4a43aec5193.71.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:972454a7671451cd0db1bb35e080b4f24d8402b71b8d64170b0ed21151dae8e4
|
3 |
+
size 4916
|
runs/Jun02_11-05-30_f4a43aec5193/1654167958.272989/events.out.tfevents.1654167958.f4a43aec5193.71.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a244896489cedece670b64d58d2b70dc7842c8c553e82b3e0cce1fff557bf62
|
3 |
+
size 4826
|
runs/Jun02_11-05-30_f4a43aec5193/events.out.tfevents.1654167958.f4a43aec5193.71.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a519a2eb4b58e1b9242930b2c9623b1ef0487d198a4d217a463b670cbb0cabee
|
3 |
+
size 5073
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ad3006a09687f4f577279359befd1b2e31d06b2b4cf1e8fae37daf5151fd479
|
3 |
+
size 3055
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|