Hugging Face's logo

SuperSl6
/
saudi-eou-model-final

Safetensors
bert
Model card Files
xet
Community
SuperSl6 commited on
Commit
74f6c2b
·
verified ·
1 Parent(s): 6a1623d

Upload folder using huggingface_hub

Browse files
Files changed (15) hide show
  1. checkpoint-468/config.json +35 -0
  2. checkpoint-468/model.safetensors +3 -0
  3. checkpoint-468/optimizer.pt +3 -0
  4. checkpoint-468/rng_state.pth +3 -0
  5. checkpoint-468/scheduler.pt +3 -0
  6. checkpoint-468/special_tokens_map.json +51 -0
  7. checkpoint-468/tokenizer.json +0 -0
  8. checkpoint-468/tokenizer_config.json +58 -0
  9. checkpoint-468/trainer_state.json +64 -0
  10. checkpoint-468/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-468/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-468/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf6db6269e6bfc854aeca0f70a95b12405bd588b07e4407755710ddf907f24ec
3
+ size 574595072
checkpoint-468/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59150cb180c27e634bd26ba1d88b41ac080666c0037494a93b434944cf34ec47
3
+ size 1149314443
checkpoint-468/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ad6002cdad966a05959034fcd3c9ad0b548b53f86de6ba140bc2e437585bfbe
3
+ size 14645
checkpoint-468/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82f72c82a29670228815eefb56ee909c1fdcbb348e750e940daa41b382769e9b
3
+ size 1465
checkpoint-468/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-468/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-468/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-468/trainer_state.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 468,
3
+ "best_metric": 0.7780678851174935,
4
+ "best_model_checkpoint": "./final_saudi_eou_model/checkpoint-468",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 468,
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": 0.7821670428893905,
15
+ "eval_f1": 0.7450462351387054,
16
+ "eval_loss": 0.44109082221984863,
17
+ "eval_runtime": 1.4755,
18
+ "eval_samples_per_second": 600.495,
19
+ "eval_steps_per_second": 18.977,
20
+ "step": 156
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.8036117381489842,
25
+ "eval_f1": 0.7698412698412699,
26
+ "eval_loss": 0.4332410395145416,
27
+ "eval_runtime": 1.4672,
28
+ "eval_samples_per_second": 603.892,
29
+ "eval_steps_per_second": 19.085,
30
+ "step": 312
31
+ },
32
+ {
33
+ "epoch": 3.0,
34
+ "eval_accuracy": 0.8081264108352144,
35
+ "eval_f1": 0.7780678851174935,
36
+ "eval_loss": 0.4599204957485199,
37
+ "eval_runtime": 1.4526,
38
+ "eval_samples_per_second": 609.937,
39
+ "eval_steps_per_second": 19.276,
40
+ "step": 468
41
+ }
42
+ ],
43
+ "logging_steps": 500,
44
+ "max_steps": 468,
45
+ "num_input_tokens_seen": 0,
46
+ "num_train_epochs": 3,
47
+ "save_steps": 500,
48
+ "stateful_callbacks": {
49
+ "TrainerControl": {
50
+ "args": {
51
+ "should_epoch_stop": false,
52
+ "should_evaluate": false,
53
+ "should_log": false,
54
+ "should_save": true,
55
+ "should_training_stop": true
56
+ },
57
+ "attributes": {}
58
+ }
59
+ },
60
+ "total_flos": 490965229301760.0,
61
+ "train_batch_size": 32,
62
+ "trial_name": null,
63
+ "trial_params": null
64
+ }
checkpoint-468/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4a69358dc3f9d77df0870ef8dbef5c7e4406cc886e45b138f9e52fe0708217e
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:cf6db6269e6bfc854aeca0f70a95b12405bd588b07e4407755710ddf907f24ec
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
+ }