dvssr commited on
Commit
e86b626
1 Parent(s): c8e8258

Model save

Browse files
README.md ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: mse30/bart-base-finetuned-pubmed
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: unipelt
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
+ # unipelt
15
+
16
+ This model is a fine-tuned version of [mse30/bart-base-finetuned-pubmed](https://huggingface.co/mse30/bart-base-finetuned-pubmed) 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: 2e-05
36
+ - train_batch_size: 4
37
+ - eval_batch_size: 4
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - num_epochs: 1.0
42
+
43
+ ### Training results
44
+
45
+
46
+
47
+ ### Framework versions
48
+
49
+ - Transformers 4.36.2
50
+ - Pytorch 2.1.2
51
+ - Datasets 2.1.0
52
+ - Tokenizers 0.15.1
config.json ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mse30/bart-base-finetuned-pubmed",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "adapters": {
6
+ "adapters": {
7
+ "adapter1": "847a59cd9f1cbf0e",
8
+ "adapter2": "847a59cd9f1cbf0e",
9
+ "adapter3": "847a59cd9f1cbf0e",
10
+ "lora": "f0eb7ef74e7bf400",
11
+ "pft": "cd16fc398a753123"
12
+ },
13
+ "config_map": {
14
+ "847a59cd9f1cbf0e": {
15
+ "adapter_residual_before_ln": false,
16
+ "cross_adapter": false,
17
+ "factorized_phm_W": true,
18
+ "factorized_phm_rule": false,
19
+ "hypercomplex_nonlinearity": "glorot-uniform",
20
+ "init_weights": "bert",
21
+ "inv_adapter": null,
22
+ "inv_adapter_reduction_factor": null,
23
+ "is_parallel": false,
24
+ "learn_phm": true,
25
+ "leave_out": [],
26
+ "ln_after": false,
27
+ "ln_before": false,
28
+ "mh_adapter": false,
29
+ "non_linearity": "relu",
30
+ "original_ln_after": true,
31
+ "original_ln_before": true,
32
+ "output_adapter": true,
33
+ "phm_bias": true,
34
+ "phm_c_init": "normal",
35
+ "phm_dim": 4,
36
+ "phm_init_range": 0.0001,
37
+ "phm_layer": false,
38
+ "phm_rank": 1,
39
+ "reduction_factor": 16,
40
+ "residual_before_ln": true,
41
+ "scaling": 1.0,
42
+ "shared_W_phm": false,
43
+ "shared_phm_rule": true,
44
+ "use_gating": true
45
+ },
46
+ "cd16fc398a753123": {
47
+ "architecture": "prefix_tuning",
48
+ "bottleneck_size": 512,
49
+ "cross_prefix": true,
50
+ "dropout": 0.0,
51
+ "encoder_prefix": true,
52
+ "flat": false,
53
+ "leave_out": [],
54
+ "non_linearity": "tanh",
55
+ "prefix_length": 10,
56
+ "shared_gating": true,
57
+ "use_gating": true
58
+ },
59
+ "f0eb7ef74e7bf400": {
60
+ "alpha": 8,
61
+ "architecture": "lora",
62
+ "attn_matrices": [
63
+ "q",
64
+ "v"
65
+ ],
66
+ "composition_mode": "add",
67
+ "dropout": 0.0,
68
+ "init_weights": "lora",
69
+ "intermediate_lora": false,
70
+ "leave_out": [],
71
+ "output_lora": false,
72
+ "r": 8,
73
+ "selfattn_lora": true,
74
+ "use_gating": true
75
+ }
76
+ },
77
+ "fusion_config_map": {},
78
+ "fusions": {
79
+ "adapter1,adapter2,adapter3": "dynamic"
80
+ }
81
+ },
82
+ "add_bias_logits": false,
83
+ "add_final_layer_norm": false,
84
+ "architectures": [
85
+ "BartForConditionalGeneration"
86
+ ],
87
+ "attention_dropout": 0.1,
88
+ "bos_token_id": 0,
89
+ "classif_dropout": 0.1,
90
+ "classifier_dropout": 0.0,
91
+ "d_model": 768,
92
+ "decoder_attention_heads": 12,
93
+ "decoder_ffn_dim": 3072,
94
+ "decoder_layerdrop": 0.0,
95
+ "decoder_layers": 6,
96
+ "decoder_start_token_id": 2,
97
+ "dropout": 0.1,
98
+ "early_stopping": true,
99
+ "encoder_attention_heads": 12,
100
+ "encoder_ffn_dim": 3072,
101
+ "encoder_layerdrop": 0.0,
102
+ "encoder_layers": 6,
103
+ "eos_token_id": 2,
104
+ "forced_eos_token_id": 2,
105
+ "gradient_checkpointing": false,
106
+ "id2label": {
107
+ "0": "LABEL_0",
108
+ "1": "LABEL_1",
109
+ "2": "LABEL_2"
110
+ },
111
+ "init_std": 0.02,
112
+ "is_encoder_decoder": true,
113
+ "label2id": {
114
+ "LABEL_0": 0,
115
+ "LABEL_1": 1,
116
+ "LABEL_2": 2
117
+ },
118
+ "max_position_embeddings": 1024,
119
+ "model_type": "bart",
120
+ "no_repeat_ngram_size": 3,
121
+ "normalize_before": false,
122
+ "normalize_embedding": true,
123
+ "num_beams": 4,
124
+ "num_hidden_layers": 6,
125
+ "pad_token_id": 1,
126
+ "scale_embedding": false,
127
+ "task_specific_params": {
128
+ "summarization": {
129
+ "length_penalty": 1.0,
130
+ "max_length": 128,
131
+ "min_length": 12,
132
+ "num_beams": 4
133
+ },
134
+ "summarization_cnn": {
135
+ "length_penalty": 2.0,
136
+ "max_length": 142,
137
+ "min_length": 56,
138
+ "num_beams": 4
139
+ },
140
+ "summarization_xsum": {
141
+ "length_penalty": 1.0,
142
+ "max_length": 62,
143
+ "min_length": 11,
144
+ "num_beams": 6
145
+ }
146
+ },
147
+ "torch_dtype": "float32",
148
+ "transformers_version": "4.36.2",
149
+ "use_cache": true,
150
+ "vocab_size": 50265
151
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "forced_eos_token_id": 2,
8
+ "no_repeat_ngram_size": 3,
9
+ "num_beams": 4,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.36.2"
12
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:835266b2f76e264782ee6ea1f8b7ac764a1a8a9c724a0286639b85573ea4f0c8
3
+ size 717319732
runs/Mar16_02-33-15_13e96b604141/events.out.tfevents.1710556408.13e96b604141.98.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b30b6f3fe4c1e00f21ba2a04e50a47470514d05ac9f2f1aa326c2d5d008066c
3
+ size 5459
runs/Mar16_02-56-35_13e96b604141/events.out.tfevents.1710557800.13e96b604141.143.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f0c28a341da441f1e4797bc7cd0c6310fd0e2d40330e1f5c1c7fef7b87a91d5
3
+ size 5459
runs/Mar16_02-59-16_13e96b604141/events.out.tfevents.1710557960.13e96b604141.184.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb8ed28ceb15b8fe172f5255d0365c3cbf5e58b2b40f1d87bbc9a306b402afc8
3
+ size 5807
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 1024,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "BartTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbd23e226c108f719499b283c2090d68f527e6d0a4fd022590c063eade4541b0
3
+ size 4792
vocab.json ADDED
The diff for this file is too large to render. See raw diff