ketong3906
commited on
Commit
•
91ad94b
1
Parent(s):
8224e30
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +77 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Jul27_05-53-39_e0020b26d920/1690437236.1499271/events.out.tfevents.1690437236.e0020b26d920.2569.1 +3 -0
- runs/Jul27_05-53-39_e0020b26d920/events.out.tfevents.1690437236.e0020b26d920.2569.0 +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"adapters": {
|
4 |
+
"adapters": {
|
5 |
+
"imdb": "9076f36a74755ac4"
|
6 |
+
},
|
7 |
+
"config_map": {
|
8 |
+
"9076f36a74755ac4": {
|
9 |
+
"adapter_residual_before_ln": false,
|
10 |
+
"cross_adapter": false,
|
11 |
+
"factorized_phm_W": true,
|
12 |
+
"factorized_phm_rule": false,
|
13 |
+
"hypercomplex_nonlinearity": "glorot-uniform",
|
14 |
+
"init_weights": "bert",
|
15 |
+
"inv_adapter": null,
|
16 |
+
"inv_adapter_reduction_factor": null,
|
17 |
+
"is_parallel": false,
|
18 |
+
"learn_phm": true,
|
19 |
+
"leave_out": [],
|
20 |
+
"ln_after": false,
|
21 |
+
"ln_before": false,
|
22 |
+
"mh_adapter": false,
|
23 |
+
"non_linearity": "relu",
|
24 |
+
"original_ln_after": true,
|
25 |
+
"original_ln_before": true,
|
26 |
+
"output_adapter": true,
|
27 |
+
"phm_bias": true,
|
28 |
+
"phm_c_init": "normal",
|
29 |
+
"phm_dim": 4,
|
30 |
+
"phm_init_range": 0.0001,
|
31 |
+
"phm_layer": false,
|
32 |
+
"phm_rank": 1,
|
33 |
+
"reduction_factor": 16,
|
34 |
+
"residual_before_ln": true,
|
35 |
+
"scaling": 1.0,
|
36 |
+
"shared_W_phm": false,
|
37 |
+
"shared_phm_rule": true,
|
38 |
+
"use_gating": false
|
39 |
+
}
|
40 |
+
},
|
41 |
+
"fusion_config_map": {},
|
42 |
+
"fusions": {}
|
43 |
+
},
|
44 |
+
"architectures": [
|
45 |
+
"RobertaForSequenceClassification"
|
46 |
+
],
|
47 |
+
"attention_probs_dropout_prob": 0.1,
|
48 |
+
"bos_token_id": 0,
|
49 |
+
"classifier_dropout": null,
|
50 |
+
"eos_token_id": 2,
|
51 |
+
"hidden_act": "gelu",
|
52 |
+
"hidden_dropout_prob": 0.1,
|
53 |
+
"hidden_size": 768,
|
54 |
+
"id2label": {
|
55 |
+
"0": "NEGATIVE",
|
56 |
+
"1": "POSITIVE"
|
57 |
+
},
|
58 |
+
"initializer_range": 0.02,
|
59 |
+
"intermediate_size": 3072,
|
60 |
+
"label2id": {
|
61 |
+
"NEGATIVE": 0,
|
62 |
+
"POSITIVE": 1
|
63 |
+
},
|
64 |
+
"layer_norm_eps": 1e-05,
|
65 |
+
"max_position_embeddings": 514,
|
66 |
+
"model_type": "roberta",
|
67 |
+
"num_attention_heads": 12,
|
68 |
+
"num_hidden_layers": 12,
|
69 |
+
"pad_token_id": 1,
|
70 |
+
"position_embedding_type": "absolute",
|
71 |
+
"problem_type": "single_label_classification",
|
72 |
+
"torch_dtype": "float32",
|
73 |
+
"transformers_version": "4.26.1",
|
74 |
+
"type_vocab_size": 1,
|
75 |
+
"use_cache": true,
|
76 |
+
"vocab_size": 50265
|
77 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da745849942fc6a941f7024b7ed623cadeaa1fc86130ab88dcdd5871b64d2726
|
3 |
+
size 502257461
|
runs/Jul27_05-53-39_e0020b26d920/1690437236.1499271/events.out.tfevents.1690437236.e0020b26d920.2569.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5845781bf902a56161bcd86bff38615d22aa1ff58ac02ac95ad21d06e273ed5d
|
3 |
+
size 5787
|
runs/Jul27_05-53-39_e0020b26d920/events.out.tfevents.1690437236.e0020b26d920.2569.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e26c4912c10c0f1086285c533665d9316de076ae290a025f4717c62d3a0dd1c4
|
3 |
+
size 5523
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"errors": "replace",
|
7 |
+
"mask_token": "<mask>",
|
8 |
+
"model_max_length": 512,
|
9 |
+
"name_or_path": "roberta-base",
|
10 |
+
"pad_token": "<pad>",
|
11 |
+
"sep_token": "</s>",
|
12 |
+
"special_tokens_map_file": null,
|
13 |
+
"tokenizer_class": "RobertaTokenizer",
|
14 |
+
"trim_offsets": true,
|
15 |
+
"unk_token": "<unk>"
|
16 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef983b170ba0e71db0ce70d95852767bc691664e6c77387303f6a8a5025c4041
|
3 |
+
size 3515
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|