Hugging Face's logo

cloud0day3
/
finbert-ft-v3

Text Classification
Safetensors
Finnish
bert
classification
news
Model card Files
xet
Community
cloud0day3 commited on
Commit
7bbf28f
·
verified ·
1 Parent(s): ff3386c

Upload 24 files

Browse files
Files changed (24) hide show
  1. checkpoint-115/config.json +36 -0
  2. checkpoint-115/model.safetensors +3 -0
  3. checkpoint-115/optimizer.pt +3 -0
  4. checkpoint-115/rng_state.pth +3 -0
  5. checkpoint-115/scaler.pt +3 -0
  6. checkpoint-115/scheduler.pt +3 -0
  7. checkpoint-115/special_tokens_map.json +37 -0
  8. checkpoint-115/tokenizer.json +0 -0
  9. checkpoint-115/tokenizer_config.json +63 -0
  10. checkpoint-115/trainer_state.json +94 -0
  11. checkpoint-115/training_args.bin +3 -0
  12. checkpoint-115/vocab.txt +0 -0
  13. checkpoint-92/config.json +36 -0
  14. checkpoint-92/model.safetensors +3 -0
  15. checkpoint-92/optimizer.pt +3 -0
  16. checkpoint-92/rng_state.pth +3 -0
  17. checkpoint-92/scaler.pt +3 -0
  18. checkpoint-92/scheduler.pt +3 -0
  19. checkpoint-92/special_tokens_map.json +37 -0
  20. checkpoint-92/tokenizer.json +0 -0
  21. checkpoint-92/tokenizer_config.json +63 -0
  22. checkpoint-92/trainer_state.json +82 -0
  23. checkpoint-92/training_args.bin +3 -0
  24. checkpoint-92/vocab.txt +0 -0
checkpoint-115/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "Not Relevant",
12
+ "1": "Least Relevant",
13
+ "2": "Highly Relevant",
14
+ "3": "Most Relevant"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "Highly Relevant": 2,
20
+ "Least Relevant": 1,
21
+ "Most Relevant": 3,
22
+ "Not Relevant": 0
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.52.4",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 50105
36
+ }
checkpoint-115/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:082fdf615c3687cacd65cc1bf9f6f73edcb2d6452090af25e0cdafbec77008cb
3
+ size 498123784
checkpoint-115/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5870ac7a8429c1e4efbf2c2131a50cf78c5218211218ab59dcf0d938241a7d58
3
+ size 656071115
checkpoint-115/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbde9b269d9890e1fb251553d79ea64e6196f935e7504f8eabd85fab74a6e80e
3
+ size 14645
checkpoint-115/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:633945fb6cc3db303cd79f4626a6e2e40e32113e2a7900cf8e9981d60d46687d
3
+ size 1383
checkpoint-115/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:381354e71949a90e1debaad7c572c71ed4a63903d3e4bb0b3c9d1643de633a52
3
+ size 1465
checkpoint-115/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
+ }
checkpoint-115/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-115/tokenizer_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "101": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "102": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "103": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "104": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "max_length": 64,
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": "[SEP]",
56
+ "stride": 0,
57
+ "strip_accents": null,
58
+ "tokenize_chinese_chars": true,
59
+ "tokenizer_class": "BertTokenizer",
60
+ "truncation_side": "right",
61
+ "truncation_strategy": "longest_first",
62
+ "unk_token": "[UNK]"
63
+ }
checkpoint-115/trainer_state.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 23,
3
+ "best_metric": 0.8660714285714286,
4
+ "best_model_checkpoint": ".\\finbert-ft-v3\\checkpoint-23",
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 115,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.8666666666666667,
15
+ "eval_f1": 0.8660714285714286,
16
+ "eval_loss": 0.4121950566768646,
17
+ "eval_precision": 0.9,
18
+ "eval_recall": 0.875,
19
+ "eval_runtime": 0.0699,
20
+ "eval_samples_per_second": 214.66,
21
+ "eval_steps_per_second": 28.621,
22
+ "step": 23
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "eval_accuracy": 0.7333333333333333,
27
+ "eval_f1": 0.7222222222222221,
28
+ "eval_loss": 0.6659547090530396,
29
+ "eval_precision": 0.825,
30
+ "eval_recall": 0.75,
31
+ "eval_runtime": 0.0495,
32
+ "eval_samples_per_second": 302.768,
33
+ "eval_steps_per_second": 40.369,
34
+ "step": 46
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_accuracy": 0.7333333333333333,
39
+ "eval_f1": 0.7222222222222221,
40
+ "eval_loss": 1.1926629543304443,
41
+ "eval_precision": 0.825,
42
+ "eval_recall": 0.75,
43
+ "eval_runtime": 0.0478,
44
+ "eval_samples_per_second": 314.102,
45
+ "eval_steps_per_second": 41.88,
46
+ "step": 69
47
+ },
48
+ {
49
+ "epoch": 4.0,
50
+ "eval_accuracy": 0.8,
51
+ "eval_f1": 0.7777777777777777,
52
+ "eval_loss": 0.7819080352783203,
53
+ "eval_precision": 0.8166666666666667,
54
+ "eval_recall": 0.7916666666666666,
55
+ "eval_runtime": 0.0488,
56
+ "eval_samples_per_second": 307.139,
57
+ "eval_steps_per_second": 40.952,
58
+ "step": 92
59
+ },
60
+ {
61
+ "epoch": 5.0,
62
+ "eval_accuracy": 0.8666666666666667,
63
+ "eval_f1": 0.8531746031746031,
64
+ "eval_loss": 0.918350875377655,
65
+ "eval_precision": 0.8875,
66
+ "eval_recall": 0.875,
67
+ "eval_runtime": 0.0534,
68
+ "eval_samples_per_second": 280.969,
69
+ "eval_steps_per_second": 37.463,
70
+ "step": 115
71
+ }
72
+ ],
73
+ "logging_steps": 500,
74
+ "max_steps": 138,
75
+ "num_input_tokens_seen": 0,
76
+ "num_train_epochs": 6,
77
+ "save_steps": 500,
78
+ "stateful_callbacks": {
79
+ "TrainerControl": {
80
+ "args": {
81
+ "should_epoch_stop": false,
82
+ "should_evaluate": false,
83
+ "should_log": false,
84
+ "should_save": true,
85
+ "should_training_stop": false
86
+ },
87
+ "attributes": {}
88
+ }
89
+ },
90
+ "total_flos": 29929419985920.0,
91
+ "train_batch_size": 8,
92
+ "trial_name": null,
93
+ "trial_params": null
94
+ }
checkpoint-115/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a36d0132994a1bd7a59fe4db5a5c2981fe4747425b913034796fac386de924e
3
+ size 5649
checkpoint-115/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-92/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "Not Relevant",
12
+ "1": "Least Relevant",
13
+ "2": "Highly Relevant",
14
+ "3": "Most Relevant"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "Highly Relevant": 2,
20
+ "Least Relevant": 1,
21
+ "Most Relevant": 3,
22
+ "Not Relevant": 0
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.52.4",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 50105
36
+ }
checkpoint-92/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b6ab5d7035e8b39cc8c46ba687664d25e39fa5ab8c1a975cafdeb50baba289e
3
+ size 498123784
checkpoint-92/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f45e3c239ef631b93571b8f2c0ea5252546e543cd45dca4e905f92c16d89bc6f
3
+ size 656071115
checkpoint-92/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2dfe3cb85418cb1ce63b87645778fdb559ae6fed3c45bb64dd00941577cb464
3
+ size 14645
checkpoint-92/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:831f9fc92e4734ff04638f1bfaf4d876c6dbe5a816807b40707fd72a42816c8a
3
+ size 1383
checkpoint-92/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:202c7a28ff33d3223c6057afb0fcffcba76969da1e4b2017076225a7f6312094
3
+ size 1465
checkpoint-92/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
+ }
checkpoint-92/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-92/tokenizer_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "101": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "102": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "103": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "104": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "max_length": 64,
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": "[SEP]",
56
+ "stride": 0,
57
+ "strip_accents": null,
58
+ "tokenize_chinese_chars": true,
59
+ "tokenizer_class": "BertTokenizer",
60
+ "truncation_side": "right",
61
+ "truncation_strategy": "longest_first",
62
+ "unk_token": "[UNK]"
63
+ }
checkpoint-92/trainer_state.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 23,
3
+ "best_metric": 0.8660714285714286,
4
+ "best_model_checkpoint": ".\\finbert-ft-v3\\checkpoint-23",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 92,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.8666666666666667,
15
+ "eval_f1": 0.8660714285714286,
16
+ "eval_loss": 0.4121950566768646,
17
+ "eval_precision": 0.9,
18
+ "eval_recall": 0.875,
19
+ "eval_runtime": 0.0699,
20
+ "eval_samples_per_second": 214.66,
21
+ "eval_steps_per_second": 28.621,
22
+ "step": 23
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "eval_accuracy": 0.7333333333333333,
27
+ "eval_f1": 0.7222222222222221,
28
+ "eval_loss": 0.6659547090530396,
29
+ "eval_precision": 0.825,
30
+ "eval_recall": 0.75,
31
+ "eval_runtime": 0.0495,
32
+ "eval_samples_per_second": 302.768,
33
+ "eval_steps_per_second": 40.369,
34
+ "step": 46
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_accuracy": 0.7333333333333333,
39
+ "eval_f1": 0.7222222222222221,
40
+ "eval_loss": 1.1926629543304443,
41
+ "eval_precision": 0.825,
42
+ "eval_recall": 0.75,
43
+ "eval_runtime": 0.0478,
44
+ "eval_samples_per_second": 314.102,
45
+ "eval_steps_per_second": 41.88,
46
+ "step": 69
47
+ },
48
+ {
49
+ "epoch": 4.0,
50
+ "eval_accuracy": 0.8,
51
+ "eval_f1": 0.7777777777777777,
52
+ "eval_loss": 0.7819080352783203,
53
+ "eval_precision": 0.8166666666666667,
54
+ "eval_recall": 0.7916666666666666,
55
+ "eval_runtime": 0.0488,
56
+ "eval_samples_per_second": 307.139,
57
+ "eval_steps_per_second": 40.952,
58
+ "step": 92
59
+ }
60
+ ],
61
+ "logging_steps": 500,
62
+ "max_steps": 138,
63
+ "num_input_tokens_seen": 0,
64
+ "num_train_epochs": 6,
65
+ "save_steps": 500,
66
+ "stateful_callbacks": {
67
+ "TrainerControl": {
68
+ "args": {
69
+ "should_epoch_stop": false,
70
+ "should_evaluate": false,
71
+ "should_log": false,
72
+ "should_save": true,
73
+ "should_training_stop": false
74
+ },
75
+ "attributes": {}
76
+ }
77
+ },
78
+ "total_flos": 23943535988736.0,
79
+ "train_batch_size": 8,
80
+ "trial_name": null,
81
+ "trial_params": null
82
+ }
checkpoint-92/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a36d0132994a1bd7a59fe4db5a5c2981fe4747425b913034796fac386de924e
3
+ size 5649
checkpoint-92/vocab.txt ADDED
The diff for this file is too large to render. See raw diff