hilco commited on
Commit
68c2932
1 Parent(s): a140d24

Finished training.

Browse files
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - parquet
5
+ - text-classification
6
+ datasets:
7
+ - tweet_eval
8
+ metrics:
9
+ - accuracy
10
+ base_model: finiteautomata/betonews-tweetcontext
11
+ model-index:
12
+ - name: finiteautomata_betonews-tweetcontext-finetuned-lora-tweet_eval_emotion
13
+ results:
14
+ - task:
15
+ type: text-classification
16
+ name: Text Classification
17
+ dataset:
18
+ name: tweet_eval
19
+ type: tweet_eval
20
+ config: emotion
21
+ split: validation
22
+ args: emotion
23
+ metrics:
24
+ - type: accuracy
25
+ value: 0.46524064171123
26
+ name: accuracy
27
+ ---
28
+
29
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
+ should probably proofread and complete it, then remove this comment. -->
31
+
32
+ # finiteautomata_betonews-tweetcontext-finetuned-lora-tweet_eval_emotion
33
+
34
+ This model is a fine-tuned version of [finiteautomata/betonews-tweetcontext](https://huggingface.co/finiteautomata/betonews-tweetcontext) on the tweet_eval dataset.
35
+ It achieves the following results on the evaluation set:
36
+ - accuracy: 0.4652
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 0.0004
56
+ - train_batch_size: 32
57
+ - eval_batch_size: 32
58
+ - seed: 42
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - num_epochs: 4
62
+
63
+ ### Training results
64
+
65
+ | accuracy | train_loss | epoch |
66
+ |:--------:|:----------:|:-----:|
67
+ | 0.2273 | None | 0 |
68
+ | 0.4278 | 1.2682 | 0 |
69
+ | 0.4385 | 1.2378 | 1 |
70
+ | 0.4465 | 1.2172 | 2 |
71
+ | 0.4652 | 1.2025 | 3 |
72
+
73
+
74
+ ### Framework versions
75
+
76
+ - PEFT 0.8.2
77
+ - Transformers 4.37.2
78
+ - Pytorch 2.2.0
79
+ - Datasets 2.16.1
80
+ - Tokenizers 0.15.2
adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "finiteautomata/betonews-tweetcontext",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 1,
13
+ "lora_dropout": 0.1,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 1,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "value",
23
+ "query"
24
+ ],
25
+ "task_type": "SEQ_CLS",
26
+ "use_rslora": false
27
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e738d7167eb70a43fc1ec34cc387be71399391d7965c31384afd771cae2ae43d
3
+ size 166552
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "@usuario": 31002,
3
+ "emoji": 31005,
4
+ "hashtag": 31004,
5
+ "url": 31003
6
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[MASK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[PAD]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "3": {
20
+ "content": "[UNK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "4": {
28
+ "content": "[CLS]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "5": {
36
+ "content": "[SEP]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "31002": {
44
+ "content": "@usuario",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "31003": {
52
+ "content": "url",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "31004": {
60
+ "content": "hashtag",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "31005": {
68
+ "content": "emoji",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ }
75
+ },
76
+ "clean_up_tokenization_spaces": true,
77
+ "cls_token": "[CLS]",
78
+ "do_basic_tokenize": true,
79
+ "do_lower_case": false,
80
+ "mask_token": "[MASK]",
81
+ "max_length": 256,
82
+ "model_max_length": 512,
83
+ "never_split": null,
84
+ "pad_to_multiple_of": null,
85
+ "pad_token": "[PAD]",
86
+ "pad_token_type_id": 0,
87
+ "padding_side": "right",
88
+ "sep_token": "[SEP]",
89
+ "stride": 0,
90
+ "strip_accents": false,
91
+ "tokenize_chinese_chars": true,
92
+ "tokenizer_class": "BertTokenizer",
93
+ "truncation_side": "right",
94
+ "truncation_strategy": "longest_first",
95
+ "unk_token": "[UNK]"
96
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff