salsarra commited on
Commit
01aa670
1 Parent(s): 0623e3e

Upload 13 files

Browse files
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ metrics:
5
+ - accuracy
6
+ model-index:
7
+ - name: ConfliBERT-Arabic-multilingual-uncased
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # ConfliBERT-Arabic-multilingual-uncased
15
+
16
+ This model is a fine-tuned version of [../models/bert-base-multilingual-uncased](https://huggingface.co/../models/bert-base-multilingual-uncased) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.4586
19
+ - Accuracy: 0.8897
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
+ - train_batch_size: 32
40
+ - eval_batch_size: 32
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - training_steps: 944187
45
+
46
+ ### Training results
47
+
48
+
49
+
50
+ ### Framework versions
51
+
52
+ - Transformers 4.26.0
53
+ - Pytorch 1.13.0.dev20220616
54
+ - Datasets 2.8.0
55
+ - Tokenizers 0.13.2
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.39,
3
+ "eval_accuracy": 0.8897356664039185,
4
+ "eval_loss": 0.45863792300224304,
5
+ "eval_runtime": 4431.9499,
6
+ "eval_samples": 662729,
7
+ "eval_samples_per_second": 149.534,
8
+ "eval_steps_per_second": 4.673,
9
+ "perplexity": 1.5819178230194426,
10
+ "train_loss": 0.6286116640401175,
11
+ "train_runtime": 410211.7129,
12
+ "train_samples": 12666977,
13
+ "train_samples_per_second": 73.655,
14
+ "train_steps_per_second": 2.302
15
+ }
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../models/bert-base-multilingual-uncased",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.26.0",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 105879
31
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.39,
3
+ "eval_accuracy": 0.8897356664039185,
4
+ "eval_loss": 0.45863792300224304,
5
+ "eval_runtime": 4431.9499,
6
+ "eval_samples": 662729,
7
+ "eval_samples_per_second": 149.534,
8
+ "eval_steps_per_second": 4.673,
9
+ "perplexity": 1.5819178230194426
10
+ }
generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.26.0"
5
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0429edae80b6dc74fb7b5b7f81603f7d25977d948c6b49a3507e06045b6732e
3
+ size 669926955
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": true,
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "name_or_path": "../models/bert-base-multilingual-uncased",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "special_tokens_map_file": null,
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.39,
3
+ "train_loss": 0.6286116640401175,
4
+ "train_runtime": 410211.7129,
5
+ "train_samples": 12666977,
6
+ "train_samples_per_second": 73.655,
7
+ "train_steps_per_second": 2.302
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e1b19875a988383f0ea9b8891a44e7be5a583bd833541fb1b70e0b49b96ae7c
3
+ size 3567
vocab.txt ADDED
The diff for this file is too large to render. See raw diff