PabloAccuosto commited on
Commit
92af824
·
verified ·
1 Parent(s): 6e991c1

Upload 8 files

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
classification_report.txt ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ precision recall f1-score support
2
+
3
+ business_rnd_innovation 0.938 0.833 0.882 18
4
+ fellowships_scholarships 0.886 0.912 0.899 34
5
+ institutional_funding 0.750 0.600 0.667 5
6
+ networking_collaborative 0.773 0.850 0.810 20
7
+ other_research_funding 1.000 0.455 0.625 11
8
+ out_of_scope 0.812 0.867 0.839 30
9
+ project_grants_public 0.864 0.895 0.879 114
10
+ research_infrastructure 0.714 0.714 0.714 14
11
+
12
+ accuracy 0.850 246
13
+ macro avg 0.842 0.766 0.789 246
14
+ weighted avg 0.854 0.850 0.846 246
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
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": 1024,
12
+ "id2label": {
13
+ "0": "business_rnd_innovation",
14
+ "1": "fellowships_scholarships",
15
+ "2": "institutional_funding",
16
+ "3": "networking_collaborative",
17
+ "4": "other_research_funding",
18
+ "5": "out_of_scope",
19
+ "6": "project_grants_public",
20
+ "7": "research_infrastructure"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 4096,
24
+ "label2id": {
25
+ "business_rnd_innovation": 0,
26
+ "fellowships_scholarships": 1,
27
+ "institutional_funding": 2,
28
+ "networking_collaborative": 3,
29
+ "other_research_funding": 4,
30
+ "out_of_scope": 5,
31
+ "project_grants_public": 6,
32
+ "research_infrastructure": 7
33
+ },
34
+ "layer_norm_eps": 1e-05,
35
+ "max_position_embeddings": 514,
36
+ "model_type": "xlm-roberta",
37
+ "num_attention_heads": 16,
38
+ "num_hidden_layers": 24,
39
+ "output_past": true,
40
+ "pad_token_id": 1,
41
+ "position_embedding_type": "absolute",
42
+ "problem_type": "single_label_classification",
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.51.3",
45
+ "type_vocab_size": 1,
46
+ "use_cache": true,
47
+ "vocab_size": 250002
48
+ }
label_mappings.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"label_list": ["business_rnd_innovation", "fellowships_scholarships", "institutional_funding", "networking_collaborative", "other_research_funding", "out_of_scope", "project_grants_public", "research_infrastructure"], "label2id": {"business_rnd_innovation": 0, "fellowships_scholarships": 1, "institutional_funding": 2, "networking_collaborative": 3, "other_research_funding": 4, "out_of_scope": 5, "project_grants_public": 6, "research_infrastructure": 7}, "id2label": {"0": "business_rnd_innovation", "1": "fellowships_scholarships", "2": "institutional_funding", "3": "networking_collaborative", "4": "other_research_funding", "5": "out_of_scope", "6": "project_grants_public", "7": "research_infrastructure"}}
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14b03dd7a3c9cbd5eea56fbfd522aa323778ae71abbdd963d48150b451a3c02d
3
+ size 2239643272
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
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
3
+ size 17082999
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 512,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f729fffea91b416e475974b584fec16bbaf82c82209e0a48e3a4e9e8e3245979
3
+ size 5841