RogerB commited on
Commit
2b828a5
1 Parent(s): 7334b96

End of training

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: RogerB/afro-xlmr-large-kinte-domain-kinte-task
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - f1
8
+ model-index:
9
+ - name: afro-xlmr-large-kinte-domain-kinte-task-unkin-sent3
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # afro-xlmr-large-kinte-domain-kinte-task-unkin-sent3
17
+
18
+ This model is a fine-tuned version of [RogerB/afro-xlmr-large-kinte-domain-kinte-task](https://huggingface.co/RogerB/afro-xlmr-large-kinte-domain-kinte-task) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.9052
21
+ - F1: 0.6940
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-06
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 4
43
+ - seed: 10000000
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 3
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | F1 |
51
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
52
+ | 0.8886 | 1.0 | 1013 | 0.6276 | 0.7466 |
53
+ | 0.706 | 2.0 | 2026 | 0.5056 | 0.8074 |
54
+ | 0.6116 | 3.0 | 3039 | 0.4733 | 0.8313 |
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - Transformers 4.34.0
60
+ - Pytorch 2.0.1+cu118
61
+ - Datasets 2.14.5
62
+ - Tokenizers 0.14.1
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<mask>": 250001,
4
+ "<pad>": 1,
5
+ "<s>": 0,
6
+ "<unk>": 3
7
+ }
config.json CHANGED
@@ -11,16 +11,16 @@
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 1024,
13
  "id2label": {
14
- "0": "LABEL_0",
15
- "1": "LABEL_1",
16
- "2": "LABEL_2"
17
  },
18
  "initializer_range": 0.02,
19
  "intermediate_size": 4096,
20
  "label2id": {
21
- "LABEL_0": 0,
22
- "LABEL_1": 1,
23
- "LABEL_2": 2
24
  },
25
  "layer_norm_eps": 1e-05,
26
  "max_position_embeddings": 514,
 
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 1024,
13
  "id2label": {
14
+ "0": "positive",
15
+ "1": "neutral",
16
+ "2": "negative"
17
  },
18
  "initializer_range": 0.02,
19
  "intermediate_size": 4096,
20
  "label2id": {
21
+ "negative": 2,
22
+ "neutral": 1,
23
+ "positive": 0
24
  },
25
  "layer_norm_eps": 1e-05,
26
  "max_position_embeddings": 514,
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>",
4
+ "<pad>",
5
+ "</s>",
6
+ "<unk>",
7
+ "<mask>"
8
+ ],
9
+ "bos_token": "<s>",
10
+ "cls_token": "<s>",
11
+ "eos_token": "</s>",
12
+ "mask_token": "<mask>",
13
+ "pad_token": "<pad>",
14
+ "sep_token": "</s>",
15
+ "unk_token": "<unk>"
16
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58793ef39055f8a0cc52fd1ab1fb8c242714bdd2042e9e3039a158dc35b29d17
3
+ size 17082951
tokenizer_config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
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
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [
45
+ "<s>",
46
+ "<pad>",
47
+ "</s>",
48
+ "<unk>",
49
+ "<mask>"
50
+ ],
51
+ "bos_token": "<s>",
52
+ "clean_up_tokenization_spaces": true,
53
+ "cls_token": "<s>",
54
+ "eos_token": "</s>",
55
+ "mask_token": "<mask>",
56
+ "model_max_length": 512,
57
+ "pad_token": "<pad>",
58
+ "sep_token": "</s>",
59
+ "tokenizer_class": "XLMRobertaTokenizer",
60
+ "unk_token": "<unk>"
61
+ }