ashishpatel26 commited on
Commit
f679fc1
1 Parent(s): 4e83ad3

ashishpatel26/span-marker-bert-base-fewnerd-coarse-super

Browse files
README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: ''
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - few-nerd
7
+ model-index:
8
+ - name: span-marker-bert-base-fewnerd-coarse-super
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # span-marker-bert-base-fewnerd-coarse-super
16
+
17
+ This model is a fine-tuned version of [](https://huggingface.co/) on the few-nerd dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.0191
20
+ - Overall Precision: 0.7817
21
+ - Overall Recall: 0.7683
22
+ - Overall F1: 0.7749
23
+ - Overall Accuracy: 0.9394
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 5e-05
43
+ - train_batch_size: 4
44
+ - eval_batch_size: 4
45
+ - seed: 42
46
+ - gradient_accumulation_steps: 2
47
+ - total_train_batch_size: 8
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: linear
50
+ - lr_scheduler_warmup_ratio: 0.1
51
+ - num_epochs: 1
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
56
+ |:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:|
57
+ | 0.0393 | 0.16 | 200 | 0.0348 | 0.7084 | 0.6377 | 0.6712 | 0.9082 |
58
+ | 0.0311 | 0.33 | 400 | 0.0233 | 0.7744 | 0.6994 | 0.7350 | 0.9225 |
59
+ | 0.0242 | 0.49 | 600 | 0.0214 | 0.7725 | 0.7293 | 0.7503 | 0.9323 |
60
+ | 0.0238 | 0.65 | 800 | 0.0204 | 0.7744 | 0.7663 | 0.7703 | 0.9359 |
61
+ | 0.0212 | 0.81 | 1000 | 0.0193 | 0.7878 | 0.7617 | 0.7746 | 0.9379 |
62
+ | 0.0181 | 0.98 | 1200 | 0.0190 | 0.7830 | 0.7671 | 0.7750 | 0.9391 |
63
+
64
+
65
+ ### Framework versions
66
+
67
+ - Transformers 4.32.1
68
+ - Pytorch 2.0.1+cu118
69
+ - Datasets 2.14.4
70
+ - Tokenizers 0.13.3
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<end>": 28997,
3
+ "<start>": 28996
4
+ }
config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SpanMarkerModel"
4
+ ],
5
+ "encoder": {
6
+ "_name_or_path": "bert-base-cased",
7
+ "add_cross_attention": false,
8
+ "architectures": [
9
+ "BertForMaskedLM"
10
+ ],
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": null,
13
+ "begin_suppress_tokens": null,
14
+ "bos_token_id": null,
15
+ "chunk_size_feed_forward": 0,
16
+ "classifier_dropout": null,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "encoder_no_repeat_ngram_size": 0,
23
+ "eos_token_id": null,
24
+ "exponential_decay_length_penalty": null,
25
+ "finetuning_task": null,
26
+ "forced_bos_token_id": null,
27
+ "forced_eos_token_id": null,
28
+ "gradient_checkpointing": false,
29
+ "hidden_act": "gelu",
30
+ "hidden_dropout_prob": 0.1,
31
+ "hidden_size": 768,
32
+ "id2label": {
33
+ "0": "O",
34
+ "1": "art",
35
+ "2": "building",
36
+ "3": "event",
37
+ "4": "location",
38
+ "5": "organization",
39
+ "6": "other",
40
+ "7": "person",
41
+ "8": "product"
42
+ },
43
+ "initializer_range": 0.02,
44
+ "intermediate_size": 3072,
45
+ "is_decoder": false,
46
+ "is_encoder_decoder": false,
47
+ "label2id": {
48
+ "O": 0,
49
+ "art": 1,
50
+ "building": 2,
51
+ "event": 3,
52
+ "location": 4,
53
+ "organization": 5,
54
+ "other": 6,
55
+ "person": 7,
56
+ "product": 8
57
+ },
58
+ "layer_norm_eps": 1e-12,
59
+ "length_penalty": 1.0,
60
+ "max_length": 20,
61
+ "max_position_embeddings": 512,
62
+ "min_length": 0,
63
+ "model_type": "bert",
64
+ "no_repeat_ngram_size": 0,
65
+ "num_attention_heads": 12,
66
+ "num_beam_groups": 1,
67
+ "num_beams": 1,
68
+ "num_hidden_layers": 12,
69
+ "num_return_sequences": 1,
70
+ "output_attentions": false,
71
+ "output_hidden_states": false,
72
+ "output_scores": false,
73
+ "pad_token_id": 0,
74
+ "position_embedding_type": "absolute",
75
+ "prefix": null,
76
+ "problem_type": null,
77
+ "pruned_heads": {},
78
+ "remove_invalid_values": false,
79
+ "repetition_penalty": 1.0,
80
+ "return_dict": true,
81
+ "return_dict_in_generate": false,
82
+ "sep_token_id": null,
83
+ "suppress_tokens": null,
84
+ "task_specific_params": null,
85
+ "temperature": 1.0,
86
+ "tf_legacy_loss": false,
87
+ "tie_encoder_decoder": false,
88
+ "tie_word_embeddings": true,
89
+ "tokenizer_class": null,
90
+ "top_k": 50,
91
+ "top_p": 1.0,
92
+ "torch_dtype": null,
93
+ "torchscript": false,
94
+ "transformers_version": "4.32.1",
95
+ "type_vocab_size": 2,
96
+ "typical_p": 1.0,
97
+ "use_bfloat16": false,
98
+ "use_cache": true,
99
+ "vocab_size": 28998
100
+ },
101
+ "entity_max_length": 8,
102
+ "marker_max_length": 128,
103
+ "max_next_context": null,
104
+ "max_prev_context": null,
105
+ "model_max_length": 256,
106
+ "model_max_length_default": 512,
107
+ "model_type": "span-marker",
108
+ "span_marker_version": "1.3.0",
109
+ "torch_dtype": "float32",
110
+ "trained_with_document_context": false,
111
+ "transformers_version": "4.32.1",
112
+ "vocab_size": 28998
113
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfd5c0de7229e20656754f7897d12042a4764103766b4afe854188c28c878750
3
+ size 433371505
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": false,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 256,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:661a4b70bb40184e29d4e53532079ff7084025a0ee7a7e5e3d8cd0c22ba43f87
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff