Cath25 commited on
Commit
e0c8b36
·
verified ·
1 Parent(s): 86dd073

Training complete

Browse files
README.md CHANGED
@@ -1,6 +1,7 @@
1
  ---
2
  library_name: transformers
3
- base_model: cardiffnlp/twitter-roberta-base
 
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -15,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # tweet-classifier
17
 
18
- This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base](https://huggingface.co/cardiffnlp/twitter-roberta-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.4290
21
- - Accuracy: 0.8926
22
 
23
  ## Model description
24
 
@@ -49,9 +50,9 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
- | 0.4808 | 1.0 | 1062 | 0.5176 | 0.8547 |
53
- | 0.3479 | 2.0 | 2124 | 0.4521 | 0.8737 |
54
- | 0.0921 | 3.0 | 3186 | 0.4290 | 0.8926 |
55
 
56
 
57
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
+ license: apache-2.0
4
+ base_model: distilbert/distilroberta-base
5
  tags:
6
  - generated_from_trainer
7
  metrics:
 
16
 
17
  # tweet-classifier
18
 
19
+ This model is a fine-tuned version of [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.1510
22
+ - Accuracy: 0.941
23
 
24
  ## Model description
25
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 0.2876 | 1.0 | 1000 | 0.1812 | 0.9325 |
54
+ | 0.1441 | 2.0 | 2000 | 0.1583 | 0.9355 |
55
+ | 0.1227 | 3.0 | 3000 | 0.1510 | 0.941 |
56
 
57
 
58
  ### Framework versions
config.json CHANGED
@@ -6,61 +6,32 @@
6
  "bos_token_id": 0,
7
  "classifier_dropout": null,
8
  "eos_token_id": 2,
9
- "gradient_checkpointing": false,
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
13
  "id2label": {
14
- "0": "label_1",
15
- "1": "label_2",
16
- "2": "label_3",
17
- "3": "label_4",
18
- "4": "label_5",
19
- "5": "label_6",
20
- "6": "label_7",
21
- "7": "label_8",
22
- "8": "label_9",
23
- "9": "label_10",
24
- "10": "label_11",
25
- "11": "label_12",
26
- "12": "label_13",
27
- "13": "label_14",
28
- "14": "label_15",
29
- "15": "label_16",
30
- "16": "label_17",
31
- "17": "label_18",
32
- "18": "label_19",
33
- "19": "label_20"
34
  },
35
  "initializer_range": 0.02,
36
  "intermediate_size": 3072,
37
  "label2id": {
38
- "label_1": 0,
39
- "label_10": 9,
40
- "label_11": 10,
41
- "label_12": 11,
42
- "label_13": 12,
43
- "label_14": 13,
44
- "label_15": 14,
45
- "label_16": 15,
46
- "label_17": 16,
47
- "label_18": 17,
48
- "label_19": 18,
49
- "label_2": 1,
50
- "label_20": 19,
51
- "label_3": 2,
52
- "label_4": 3,
53
- "label_5": 4,
54
- "label_6": 5,
55
- "label_7": 6,
56
- "label_8": 7,
57
- "label_9": 8
58
  },
59
  "layer_norm_eps": 1e-05,
60
  "max_position_embeddings": 514,
61
  "model_type": "roberta",
62
  "num_attention_heads": 12,
63
- "num_hidden_layers": 12,
64
  "pad_token_id": 1,
65
  "position_embedding_type": "absolute",
66
  "problem_type": "single_label_classification",
 
6
  "bos_token_id": 0,
7
  "classifier_dropout": null,
8
  "eos_token_id": 2,
 
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 768,
12
  "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  },
20
  "initializer_range": 0.02,
21
  "intermediate_size": 3072,
22
  "label2id": {
23
+ "LABEL_0": 0,
24
+ "LABEL_1": 1,
25
+ "LABEL_2": 2,
26
+ "LABEL_3": 3,
27
+ "LABEL_4": 4,
28
+ "LABEL_5": 5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  },
30
  "layer_norm_eps": 1e-05,
31
  "max_position_embeddings": 514,
32
  "model_type": "roberta",
33
  "num_attention_heads": 12,
34
+ "num_hidden_layers": 6,
35
  "pad_token_id": 1,
36
  "position_embedding_type": "absolute",
37
  "problem_type": "single_label_classification",
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9245f04b70f05606f4a31644f35339b2364bf00043929269504a9693a08359d
3
- size 498668192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:381b6eedb4b048fd9de7ffe40f8af854de463c5b43948fa8fc01b6068730c6c8
3
+ size 328504584
runs/Apr03_13-02-02_ed66a94a5026/events.out.tfevents.1743685326.ed66a94a5026.1783.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98e5c7b389f3a5c57da4e86679651cf5e609148e7843d952a8df3fa9de9a78f2
3
+ size 69968
runs/Apr03_13-02-02_ed66a94a5026/events.out.tfevents.1743685532.ed66a94a5026.1783.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a05ada88227f4c0c93841ba9b876f19df23714d5025591eeecc9aff7d64d3be
3
+ size 411
special_tokens_map.json CHANGED
@@ -1,25 +1,7 @@
1
  {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "cls_token": {
10
- "content": "<s>",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "eos_token": {
17
- "content": "</s>",
18
- "lstrip": false,
19
- "normalized": true,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
  "mask_token": {
24
  "content": "<mask>",
25
  "lstrip": true,
@@ -27,25 +9,7 @@
27
  "rstrip": false,
28
  "single_word": false
29
  },
30
- "pad_token": {
31
- "content": "<pad>",
32
- "lstrip": false,
33
- "normalized": true,
34
- "rstrip": false,
35
- "single_word": false
36
- },
37
- "sep_token": {
38
- "content": "</s>",
39
- "lstrip": false,
40
- "normalized": true,
41
- "rstrip": false,
42
- "single_word": false
43
- },
44
- "unk_token": {
45
- "content": "<unk>",
46
- "lstrip": false,
47
- "normalized": true,
48
- "rstrip": false,
49
- "single_word": false
50
- }
51
  }
 
1
  {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "mask_token": {
6
  "content": "<mask>",
7
  "lstrip": true,
 
9
  "rstrip": false,
10
  "single_word": false
11
  },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  }
tokenizer_config.json CHANGED
@@ -49,7 +49,7 @@
49
  "errors": "replace",
50
  "extra_special_tokens": {},
51
  "mask_token": "<mask>",
52
- "model_max_length": 1000000000000000019884624838656,
53
  "pad_token": "<pad>",
54
  "sep_token": "</s>",
55
  "tokenizer_class": "RobertaTokenizer",
 
49
  "errors": "replace",
50
  "extra_special_tokens": {},
51
  "mask_token": "<mask>",
52
+ "model_max_length": 512,
53
  "pad_token": "<pad>",
54
  "sep_token": "</s>",
55
  "tokenizer_class": "RobertaTokenizer",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38dfe502f793fd79abfed36999a2f692b8fb7254faba43555edb4b406cd61c8a
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6994dee4b5a40364ab008180ccccf9fdad27aade12f682ff07eeba1271ab5eb
3
  size 5368