Hugging Face's logo

SIRIS-Lab
/
slovenia-s5-classifier-seven-cats

Safetensors
xlm-roberta
Model card Files Community
PabloAccuosto commited on
Commit
f223209
·
verified ·
1 Parent(s): a4f7ced

Upload folder using huggingface_hub

Browse files
Files changed (20) hide show
  1. .gitattributes +2 -0
  2. checkpoint-1035/config.json +47 -0
  3. checkpoint-1035/model.safetensors +3 -0
  4. checkpoint-1035/optimizer.pt +3 -0
  5. checkpoint-1035/rng_state.pth +3 -0
  6. checkpoint-1035/scheduler.pt +3 -0
  7. checkpoint-1035/sentencepiece.bpe.model +3 -0
  8. checkpoint-1035/special_tokens_map.json +51 -0
  9. checkpoint-1035/tokenizer.json +3 -0
  10. checkpoint-1035/tokenizer_config.json +61 -0
  11. checkpoint-1035/trainer_state.json +59 -0
  12. checkpoint-1035/training_args.bin +3 -0
  13. config.json +47 -0
  14. model.safetensors +3 -0
  15. sentencepiece.bpe.model +3 -0
  16. special_tokens_map.json +51 -0
  17. tokenizer.json +3 -0
  18. tokenizer_config.json +61 -0
  19. training_args.bin +3 -0
  20. training_metrics.tsv +5 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
+ checkpoint-1035/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-1035/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../models/model_gemma",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "circular_economy",
15
+ "1": "factories_future",
16
+ "2": "health_medicine",
17
+ "3": "ict",
18
+ "4": "mobility",
19
+ "5": "smart_buildings",
20
+ "6": "smart_cities"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 4096,
24
+ "label2id": {
25
+ "circular_economy": "0",
26
+ "factories_future": "1",
27
+ "health_medicine": "2",
28
+ "ict": "3",
29
+ "mobility": "4",
30
+ "smart_buildings": "5",
31
+ "smart_cities": "6"
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "max_position_embeddings": 514,
35
+ "model_type": "xlm-roberta",
36
+ "num_attention_heads": 16,
37
+ "num_hidden_layers": 24,
38
+ "output_past": true,
39
+ "pad_token_id": 1,
40
+ "position_embedding_type": "absolute",
41
+ "problem_type": "multi_label_classification",
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.46.2",
44
+ "type_vocab_size": 1,
45
+ "use_cache": true,
46
+ "vocab_size": 250002
47
+ }
checkpoint-1035/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d52563a231a7ae7a6b1d124044006b3c050cea2942fc02e11c1e94efdccaed4d
3
+ size 2239639172
checkpoint-1035/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1db4f2fdc7d927654342092bcf03cba453d689cd6fa1018c61638451bfea0970
3
+ size 8458514
checkpoint-1035/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cae715cda2f91e5ba83e6187de0ba45d474c4fc5ea1b1a1aef51dcc310adf8ba
3
+ size 14244
checkpoint-1035/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c55d450a02b9967d4aa54e376bffdd947bf7abbde2c2bf1abb42f82de62339d4
3
+ size 1064
checkpoint-1035/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
checkpoint-1035/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
+ }
checkpoint-1035/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
3
+ size 17082999
checkpoint-1035/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
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "max_length": 512,
50
+ "model_max_length": 512,
51
+ "pad_to_multiple_of": null,
52
+ "pad_token": "<pad>",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
+ "sep_token": "</s>",
56
+ "stride": 0,
57
+ "tokenizer_class": "XLMRobertaTokenizer",
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
+ "unk_token": "<unk>"
61
+ }
checkpoint-1035/trainer_state.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9771112865035517,
3
+ "best_model_checkpoint": "../models/slovenia-s5-classifier-seven-cats/checkpoint-1035",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1035,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.4830917874396135,
13
+ "grad_norm": 0.0846693217754364,
14
+ "learning_rate": 5.1690821256038647e-05,
15
+ "loss": 0.0316,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.966183574879227,
20
+ "grad_norm": 0.034613098949193954,
21
+ "learning_rate": 3.3816425120772947e-06,
22
+ "loss": 0.0076,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_f1_macro": 0.9808089925902543,
28
+ "eval_f1_micro": 0.9825396825396825,
29
+ "eval_loss": 0.027310708537697792,
30
+ "eval_precision": 0.9880287310454908,
31
+ "eval_recall": 0.9771112865035517,
32
+ "eval_runtime": 8.4322,
33
+ "eval_samples_per_second": 107.089,
34
+ "eval_steps_per_second": 6.76,
35
+ "step": 1035
36
+ }
37
+ ],
38
+ "logging_steps": 500,
39
+ "max_steps": 1035,
40
+ "num_input_tokens_seen": 0,
41
+ "num_train_epochs": 1,
42
+ "save_steps": 500,
43
+ "stateful_callbacks": {
44
+ "TrainerControl": {
45
+ "args": {
46
+ "should_epoch_stop": false,
47
+ "should_evaluate": false,
48
+ "should_log": false,
49
+ "should_save": true,
50
+ "should_training_stop": true
51
+ },
52
+ "attributes": {}
53
+ }
54
+ },
55
+ "total_flos": 7716522048675840.0,
56
+ "train_batch_size": 8,
57
+ "trial_name": null,
58
+ "trial_params": null
59
+ }
checkpoint-1035/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:660785574c12cced7fa5ff95d78a473832442abef9325a91794c161322f7c7b8
3
+ size 5304
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../models/model_gemma",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "circular_economy",
15
+ "1": "factories_future",
16
+ "2": "health_medicine",
17
+ "3": "ict",
18
+ "4": "mobility",
19
+ "5": "smart_buildings",
20
+ "6": "smart_cities"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 4096,
24
+ "label2id": {
25
+ "circular_economy": "0",
26
+ "factories_future": "1",
27
+ "health_medicine": "2",
28
+ "ict": "3",
29
+ "mobility": "4",
30
+ "smart_buildings": "5",
31
+ "smart_cities": "6"
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "max_position_embeddings": 514,
35
+ "model_type": "xlm-roberta",
36
+ "num_attention_heads": 16,
37
+ "num_hidden_layers": 24,
38
+ "output_past": true,
39
+ "pad_token_id": 1,
40
+ "position_embedding_type": "absolute",
41
+ "problem_type": "multi_label_classification",
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.46.2",
44
+ "type_vocab_size": 1,
45
+ "use_cache": true,
46
+ "vocab_size": 250002
47
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d52563a231a7ae7a6b1d124044006b3c050cea2942fc02e11c1e94efdccaed4d
3
+ size 2239639172
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 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "max_length": 512,
50
+ "model_max_length": 512,
51
+ "pad_to_multiple_of": null,
52
+ "pad_token": "<pad>",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
+ "sep_token": "</s>",
56
+ "stride": 0,
57
+ "tokenizer_class": "XLMRobertaTokenizer",
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
+ "unk_token": "<unk>"
61
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:660785574c12cced7fa5ff95d78a473832442abef9325a91794c161322f7c7b8
3
+ size 5304
training_metrics.tsv ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ loss grad_norm learning_rate epoch step eval_loss eval_f1_micro eval_f1_macro eval_precision eval_recall eval_runtime eval_samples_per_second eval_steps_per_second train_runtime train_samples_per_second train_steps_per_second total_flos train_loss
2
+ 0.0316 0.0846693217754364 5.1690821256038647e-05 0.4830917874396135 500
3
+ 0.0076 0.034613098949193954 3.3816425120772947e-06 0.966183574879227 1000
4
+ 1.0 1035 0.027310708537697792 0.9825396825396825 0.9808089925902543 0.9880287310454908 0.9771112865035517 8.4322 107.089 6.76
5
+ 1.0 1035 95.2688 86.912 10.864 7716522048675840.0 0.019097913535320817