Hugging Face's logo

HatemMoushir
/
ArEn-TweetSentiment-BERT-Hatem

Text Classification
TensorBoard
Safetensors
Arabic
English
bert
sentiment-analysis
twitter
arabic
english
multilingual
social-media
bert-base-multilingual-cased
UCI Sentiment Dataset
Egypt
Ain shams university
Hatem Moushir
Model card Files
xet
Metrics Community
HatemMoushir commited on
Commit
2a909c4
·
verified ·
1 Parent(s): 07129fb

Upload folder using huggingface_hub

Browse files
Files changed (23) hide show
  1. checkpoint-113/config.json +31 -0
  2. checkpoint-113/model.safetensors +3 -0
  3. checkpoint-113/optimizer.pt +3 -0
  4. checkpoint-113/rng_state.pth +3 -0
  5. checkpoint-113/scheduler.pt +3 -0
  6. checkpoint-113/special_tokens_map.json +7 -0
  7. checkpoint-113/tokenizer.json +0 -0
  8. checkpoint-113/tokenizer_config.json +56 -0
  9. checkpoint-113/trainer_state.json +60 -0
  10. checkpoint-113/training_args.bin +3 -0
  11. checkpoint-113/vocab.txt +0 -0
  12. checkpoint-226/config.json +31 -0
  13. checkpoint-226/model.safetensors +3 -0
  14. checkpoint-226/optimizer.pt +3 -0
  15. checkpoint-226/rng_state.pth +3 -0
  16. checkpoint-226/scheduler.pt +3 -0
  17. checkpoint-226/special_tokens_map.json +7 -0
  18. checkpoint-226/tokenizer.json +0 -0
  19. checkpoint-226/tokenizer_config.json +56 -0
  20. checkpoint-226/trainer_state.json +86 -0
  21. checkpoint-226/training_args.bin +3 -0
  22. checkpoint-226/vocab.txt +0 -0
  23. runs/Jul18_14-32-06_a3388a082de1/events.out.tfevents.1752849127.a3388a082de1.2378.0 +3 -0
checkpoint-113/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "directionality": "bidi",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "pooler_fc_size": 768,
20
+ "pooler_num_attention_heads": 12,
21
+ "pooler_num_fc_layers": 3,
22
+ "pooler_size_per_head": 128,
23
+ "pooler_type": "first_token_transform",
24
+ "position_embedding_type": "absolute",
25
+ "problem_type": "single_label_classification",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.53.2",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 119547
31
+ }
checkpoint-113/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5044c146312e4ec717fc44883b102a888ec2015e0841e8d966c4f9742d7c1bd1
3
+ size 711443456
checkpoint-113/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cfc6ebe6947b93e1963b8a288c4867d56a91ff7e98cbc67b5a6948ee3d253f6
3
+ size 1423002362
checkpoint-113/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea69c5a30104a25935343f204e7c2954bb036f208c653cd9c98824474d358a17
3
+ size 13990
checkpoint-113/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62d123612937ef65d0d6feed455ac2e5af7a55ea00f20cfb6da53350745f7a4c
3
+ size 1064
checkpoint-113/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
checkpoint-113/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-113/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
checkpoint-113/trainer_state.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 113,
3
+ "best_metric": 0.7536251544952393,
4
+ "best_model_checkpoint": "sentiment_ar_en_model/checkpoint-113",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 113,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.4424778761061947,
14
+ "grad_norm": 3.632207155227661,
15
+ "learning_rate": 3.915929203539823e-05,
16
+ "loss": 0.6712,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.8849557522123894,
21
+ "grad_norm": 7.496383190155029,
22
+ "learning_rate": 2.8097345132743364e-05,
23
+ "loss": 0.6266,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 1.0,
28
+ "eval_accuracy": 0.59,
29
+ "eval_f1": 0.18,
30
+ "eval_loss": 0.7536251544952393,
31
+ "eval_precision": 0.6428571428571429,
32
+ "eval_recall": 0.10465116279069768,
33
+ "eval_runtime": 83.8931,
34
+ "eval_samples_per_second": 2.384,
35
+ "eval_steps_per_second": 0.298,
36
+ "step": 113
37
+ }
38
+ ],
39
+ "logging_steps": 50,
40
+ "max_steps": 226,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 2,
43
+ "save_steps": 500,
44
+ "stateful_callbacks": {
45
+ "TrainerControl": {
46
+ "args": {
47
+ "should_epoch_stop": false,
48
+ "should_evaluate": false,
49
+ "should_log": false,
50
+ "should_save": true,
51
+ "should_training_stop": false
52
+ },
53
+ "attributes": {}
54
+ }
55
+ },
56
+ "total_flos": 118399974912000.0,
57
+ "train_batch_size": 16,
58
+ "trial_name": null,
59
+ "trial_params": null
60
+ }
checkpoint-113/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ab6db1d6d7b5401108e2452dcb02ecb15ee5a21e77dad28c545644c2c391391
3
+ size 5368
checkpoint-113/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-226/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "directionality": "bidi",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "pooler_fc_size": 768,
20
+ "pooler_num_attention_heads": 12,
21
+ "pooler_num_fc_layers": 3,
22
+ "pooler_size_per_head": 128,
23
+ "pooler_type": "first_token_transform",
24
+ "position_embedding_type": "absolute",
25
+ "problem_type": "single_label_classification",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.53.2",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 119547
31
+ }
checkpoint-226/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1185eaf2df5394cd93508c26479ef782d2bc65be8305f3721df121cb1262355
3
+ size 711443456
checkpoint-226/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82d3c34d53e174ea38e48c09b35a249eb5e5b1f85416d2dbd66f1b5b78c2fb89
3
+ size 1423002362
checkpoint-226/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1d675553b63f276ab8abd0f73e98e42f235caa385162ea88b64805e4097f5a3
3
+ size 13990
checkpoint-226/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:821df82aafb4a95fbc1dccebb0267fa9e0cb5cd2562f3a917556a3a9eb0a15a8
3
+ size 1064
checkpoint-226/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
checkpoint-226/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-226/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
checkpoint-226/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 226,
3
+ "best_metric": 0.5943940281867981,
4
+ "best_model_checkpoint": "sentiment_ar_en_model/checkpoint-226",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 226,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.4424778761061947,
14
+ "grad_norm": 3.632207155227661,
15
+ "learning_rate": 3.915929203539823e-05,
16
+ "loss": 0.6712,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.8849557522123894,
21
+ "grad_norm": 7.496383190155029,
22
+ "learning_rate": 2.8097345132743364e-05,
23
+ "loss": 0.6266,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 1.0,
28
+ "eval_accuracy": 0.59,
29
+ "eval_f1": 0.18,
30
+ "eval_loss": 0.7536251544952393,
31
+ "eval_precision": 0.6428571428571429,
32
+ "eval_recall": 0.10465116279069768,
33
+ "eval_runtime": 83.8931,
34
+ "eval_samples_per_second": 2.384,
35
+ "eval_steps_per_second": 0.298,
36
+ "step": 113
37
+ },
38
+ {
39
+ "epoch": 1.3274336283185841,
40
+ "grad_norm": 7.0585832595825195,
41
+ "learning_rate": 1.7035398230088495e-05,
42
+ "loss": 0.537,
43
+ "step": 150
44
+ },
45
+ {
46
+ "epoch": 1.7699115044247788,
47
+ "grad_norm": 6.620525360107422,
48
+ "learning_rate": 5.973451327433629e-06,
49
+ "loss": 0.5127,
50
+ "step": 200
51
+ },
52
+ {
53
+ "epoch": 2.0,
54
+ "eval_accuracy": 0.72,
55
+ "eval_f1": 0.6666666666666666,
56
+ "eval_loss": 0.5943940281867981,
57
+ "eval_precision": 0.6829268292682927,
58
+ "eval_recall": 0.6511627906976745,
59
+ "eval_runtime": 83.6193,
60
+ "eval_samples_per_second": 2.392,
61
+ "eval_steps_per_second": 0.299,
62
+ "step": 226
63
+ }
64
+ ],
65
+ "logging_steps": 50,
66
+ "max_steps": 226,
67
+ "num_input_tokens_seen": 0,
68
+ "num_train_epochs": 2,
69
+ "save_steps": 500,
70
+ "stateful_callbacks": {
71
+ "TrainerControl": {
72
+ "args": {
73
+ "should_epoch_stop": false,
74
+ "should_evaluate": false,
75
+ "should_log": false,
76
+ "should_save": true,
77
+ "should_training_stop": true
78
+ },
79
+ "attributes": {}
80
+ }
81
+ },
82
+ "total_flos": 236799949824000.0,
83
+ "train_batch_size": 16,
84
+ "trial_name": null,
85
+ "trial_params": null
86
+ }
checkpoint-226/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ab6db1d6d7b5401108e2452dcb02ecb15ee5a21e77dad28c545644c2c391391
3
+ size 5368
checkpoint-226/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Jul18_14-32-06_a3388a082de1/events.out.tfevents.1752849127.a3388a082de1.2378.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa696600e81dcb2a8a3c448148040ef4ec3e46e25983ba1a979a6d9eec062e4
3
+ size 7249