niharikavats2397 commited on
Commit
aed24fc
·
1 Parent(s): 7032a4e

Model save

Browse files
Files changed (5) hide show
  1. README.md +48 -0
  2. config.json +115 -0
  3. generation_config.json +5 -0
  4. model.safetensors +3 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: bert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: all
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # all
15
+
16
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 0.0008
36
+ - train_batch_size: 16
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - num_epochs: 10
42
+
43
+ ### Framework versions
44
+
45
+ - Transformers 4.35.2
46
+ - Pytorch 2.1.0+cu118
47
+ - Datasets 2.15.0
48
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "adapters": {
4
+ "adapters": {
5
+ "ner": "e15331acc3f0a5c0"
6
+ },
7
+ "config_map": {
8
+ "e15331acc3f0a5c0": {
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": 2,
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
+ "BertAdapterModel"
46
+ ],
47
+ "attention_probs_dropout_prob": 0.1,
48
+ "classifier_dropout": null,
49
+ "custom_heads": {},
50
+ "gradient_checkpointing": false,
51
+ "hidden_act": "gelu",
52
+ "hidden_dropout_prob": 0.1,
53
+ "hidden_size": 768,
54
+ "id2label": {
55
+ "0": "O",
56
+ "1": "B-test",
57
+ "2": "I-test",
58
+ "3": "B-problem",
59
+ "4": "I-problem",
60
+ "5": "B-treatment",
61
+ "6": "I-treatment"
62
+ },
63
+ "initializer_range": 0.02,
64
+ "intermediate_size": 3072,
65
+ "label2id": {
66
+ "B-problem": 3,
67
+ "B-test": 1,
68
+ "B-treatment": 5,
69
+ "I-problem": 4,
70
+ "I-test": 2,
71
+ "I-treatment": 6,
72
+ "O": 0
73
+ },
74
+ "layer_norm_eps": 1e-12,
75
+ "max_position_embeddings": 512,
76
+ "model_type": "bert",
77
+ "num_attention_heads": 12,
78
+ "num_hidden_layers": 12,
79
+ "pad_token_id": 0,
80
+ "position_embedding_type": "absolute",
81
+ "prediction_heads": {
82
+ "default": {
83
+ "activation_function": "gelu",
84
+ "bias": true,
85
+ "embedding_size": 768,
86
+ "head_type": "masked_lm",
87
+ "label2id": null,
88
+ "layer_norm": true,
89
+ "layers": 2,
90
+ "shift_labels": false,
91
+ "vocab_size": 30522
92
+ },
93
+ "ner": {
94
+ "activation_function": "tanh",
95
+ "dropout_prob": null,
96
+ "head_type": "tagging",
97
+ "label2id": {
98
+ "B-problem": 3,
99
+ "B-test": 1,
100
+ "B-treatment": 5,
101
+ "I-problem": 4,
102
+ "I-test": 2,
103
+ "I-treatment": 6,
104
+ "O": 0
105
+ },
106
+ "layers": 1,
107
+ "num_labels": 7
108
+ }
109
+ },
110
+ "torch_dtype": "float32",
111
+ "transformers_version": "4.35.2",
112
+ "type_vocab_size": 2,
113
+ "use_cache": true,
114
+ "vocab_size": 30522
115
+ }
generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.35.2"
5
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deb0d97a3ff79230ca79fb1a3c3969b89df0dd99710905ef5f87b2958710a0c9
3
+ size 468838228
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e83baaf7b7beefc9b4a61dcb3d0f20379c9e9a460d1675b482027d13202a602
3
+ size 4536