Hugging Face's logo

SuperSl6
/
saudi-eou-model-v1

Safetensors
bert
Model card Files
xet
Community
SuperSl6 commited on
Commit
9e47d9f
·
verified ·
1 Parent(s): 7334afc

Upload folder using huggingface_hub

Browse files
Files changed (15) hide show
  1. checkpoint-808/config.json +35 -0
  2. checkpoint-808/model.safetensors +3 -0
  3. checkpoint-808/optimizer.pt +3 -0
  4. checkpoint-808/rng_state.pth +3 -0
  5. checkpoint-808/scheduler.pt +3 -0
  6. checkpoint-808/special_tokens_map.json +51 -0
  7. checkpoint-808/tokenizer.json +0 -0
  8. checkpoint-808/tokenizer_config.json +58 -0
  9. checkpoint-808/trainer_state.json +81 -0
  10. checkpoint-808/training_args.bin +3 -0
  11. config.json +35 -0
  12. model.safetensors +3 -0
  13. special_tokens_map.json +51 -0
  14. tokenizer.json +0 -0
  15. tokenizer_config.json +58 -0
checkpoint-808/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 2,
7
+ "classifier_dropout": null,
8
+ "dtype": "float32",
9
+ "eos_token_id": 3,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "INCOMPLETE",
15
+ "1": "COMPLETE"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "COMPLETE": 1,
21
+ "INCOMPLETE": 0
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "transformers_version": "4.57.3",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 75000
35
+ }
checkpoint-808/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2524c8b1e0c6eaf41b6dcc547c2526c2cdfe3d1aa84b7f16fb886df50521ddb1
3
+ size 574595072
checkpoint-808/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:384a9fb242b9d1fd5439081f81cd1f34e09c1b78c3049084e9a743bdd93ea642
3
+ size 1149314443
checkpoint-808/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd8536890139b1076111967d68aa6b5346ab80ed46fe42c8edb89686fb3bde83
3
+ size 14645
checkpoint-808/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdb2e4b4ce70673702b093cf6ac00d458232bb7d8b74559cbbef43102bf96a68
3
+ size 1465
checkpoint-808/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
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": "[SEP]",
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-808/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-808/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": true,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "keep_accents": false,
51
+ "mask_token": "[MASK]",
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "remove_space": true,
55
+ "sep_token": "[SEP]",
56
+ "tokenizer_class": "AlbertTokenizerFast",
57
+ "unk_token": "<unk>"
58
+ }
checkpoint-808/trainer_state.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 808,
3
+ "best_metric": 0.9076923076923077,
4
+ "best_model_checkpoint": "./final_saudi_eou_model_SAUDIBERT_v2/checkpoint-808",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 808,
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": 0.8363636363636363,
15
+ "eval_f1": 0.8517110266159695,
16
+ "eval_loss": 0.3720616102218628,
17
+ "eval_runtime": 0.7344,
18
+ "eval_samples_per_second": 973.57,
19
+ "eval_steps_per_second": 31.318,
20
+ "step": 202
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.8783216783216783,
25
+ "eval_f1": 0.8897338403041825,
26
+ "eval_loss": 0.30772021412849426,
27
+ "eval_runtime": 0.7079,
28
+ "eval_samples_per_second": 1010.016,
29
+ "eval_steps_per_second": 32.49,
30
+ "step": 404
31
+ },
32
+ {
33
+ "epoch": 2.4752475247524752,
34
+ "grad_norm": 8.218647003173828,
35
+ "learning_rate": 6.541284403669725e-06,
36
+ "loss": 0.3929,
37
+ "step": 500
38
+ },
39
+ {
40
+ "epoch": 3.0,
41
+ "eval_accuracy": 0.8937062937062937,
42
+ "eval_f1": 0.9015544041450777,
43
+ "eval_loss": 0.27716031670570374,
44
+ "eval_runtime": 0.7099,
45
+ "eval_samples_per_second": 1007.217,
46
+ "eval_steps_per_second": 32.4,
47
+ "step": 606
48
+ },
49
+ {
50
+ "epoch": 4.0,
51
+ "eval_accuracy": 0.9076923076923077,
52
+ "eval_f1": 0.9136125654450262,
53
+ "eval_loss": 0.296909362077713,
54
+ "eval_runtime": 0.7755,
55
+ "eval_samples_per_second": 921.993,
56
+ "eval_steps_per_second": 29.659,
57
+ "step": 808
58
+ }
59
+ ],
60
+ "logging_steps": 500,
61
+ "max_steps": 1212,
62
+ "num_input_tokens_seen": 0,
63
+ "num_train_epochs": 6,
64
+ "save_steps": 500,
65
+ "stateful_callbacks": {
66
+ "TrainerControl": {
67
+ "args": {
68
+ "should_epoch_stop": false,
69
+ "should_evaluate": false,
70
+ "should_log": false,
71
+ "should_save": true,
72
+ "should_training_stop": false
73
+ },
74
+ "attributes": {}
75
+ }
76
+ },
77
+ "total_flos": 846559820620800.0,
78
+ "train_batch_size": 32,
79
+ "trial_name": null,
80
+ "trial_params": null
81
+ }
checkpoint-808/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faf77515d06f560834a45d72f01409471397ce26a56b8b580eb851dbe41908b0
3
+ size 5841
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 2,
7
+ "classifier_dropout": null,
8
+ "dtype": "float32",
9
+ "eos_token_id": 3,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "INCOMPLETE",
15
+ "1": "COMPLETE"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "COMPLETE": 1,
21
+ "INCOMPLETE": 0
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "transformers_version": "4.57.3",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 75000
35
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2524c8b1e0c6eaf41b6dcc547c2526c2cdfe3d1aa84b7f16fb886df50521ddb1
3
+ size 574595072
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
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": "[SEP]",
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
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": true,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "keep_accents": false,
51
+ "mask_token": "[MASK]",
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "remove_space": true,
55
+ "sep_token": "[SEP]",
56
+ "tokenizer_class": "AlbertTokenizerFast",
57
+ "unk_token": "<unk>"
58
+ }