Upload 13 files
Browse files- README.md +55 -0
- all_results.json +15 -0
- config.json +25 -0
- eval_results.json +10 -0
- generation_config.json +5 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +49 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
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-Scratch
|
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-Scratch
|
15 |
+
|
16 |
+
This model was trained from scratch on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.9436
|
19 |
+
- Accuracy: 0.8078
|
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 |
+
- num_epochs: 3.0
|
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": 3.0,
|
3 |
+
"eval_accuracy": 0.8077953820649405,
|
4 |
+
"eval_loss": 0.9435999393463135,
|
5 |
+
"eval_runtime": 2301.809,
|
6 |
+
"eval_samples": 445055,
|
7 |
+
"eval_samples_per_second": 193.35,
|
8 |
+
"eval_steps_per_second": 6.042,
|
9 |
+
"perplexity": 2.5692138042068984,
|
10 |
+
"train_loss": 2.538804254183028,
|
11 |
+
"train_runtime": 274559.0377,
|
12 |
+
"train_samples": 8200540,
|
13 |
+
"train_samples_per_second": 89.604,
|
14 |
+
"train_steps_per_second": 2.8
|
15 |
+
}
|
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "../models/FromScratch-65k",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
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 |
+
"position_embedding_type": "absolute",
|
20 |
+
"torch_dtype": "float32",
|
21 |
+
"transformers_version": "4.26.0",
|
22 |
+
"type_vocab_size": 2,
|
23 |
+
"use_cache": true,
|
24 |
+
"vocab_size": 65000
|
25 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.8077953820649405,
|
4 |
+
"eval_loss": 0.9435999393463135,
|
5 |
+
"eval_runtime": 2301.809,
|
6 |
+
"eval_samples": 445055,
|
7 |
+
"eval_samples_per_second": 193.35,
|
8 |
+
"eval_steps_per_second": 6.042,
|
9 |
+
"perplexity": 2.5692138042068984
|
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 sha256:4113fc17130afba020499bcc303486e15c5affe7b074da4860b987afd8087f48
|
3 |
+
size 544183147
|
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 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"max_len": 512,
|
7 |
+
"model_max_length": 512,
|
8 |
+
"name_or_path": "../models/FromScratch-65k",
|
9 |
+
"never_split": [
|
10 |
+
"+ู",
|
11 |
+
"+ูู
ุง",
|
12 |
+
"ู+",
|
13 |
+
"+ูุง",
|
14 |
+
"+ูู",
|
15 |
+
"ู+",
|
16 |
+
"+ูู",
|
17 |
+
"+ุงู",
|
18 |
+
"+ูู
",
|
19 |
+
"+ุฉ",
|
20 |
+
"[ุจุฑูุฏ]",
|
21 |
+
"ูู+",
|
22 |
+
"+ู",
|
23 |
+
"+ุช",
|
24 |
+
"+ู",
|
25 |
+
"ุณ+",
|
26 |
+
"ู+",
|
27 |
+
"[ู
ุณุชุฎุฏู
]",
|
28 |
+
"+ูู
",
|
29 |
+
"+ุง",
|
30 |
+
"ุจ+",
|
31 |
+
"ู+",
|
32 |
+
"+ูุง",
|
33 |
+
"+ูุง",
|
34 |
+
"+ูู",
|
35 |
+
"+ูู
ุง",
|
36 |
+
"ุงู+",
|
37 |
+
"+ู",
|
38 |
+
"+ูู",
|
39 |
+
"+ุงุช",
|
40 |
+
"[ุฑุงุจุท]"
|
41 |
+
],
|
42 |
+
"pad_token": "[PAD]",
|
43 |
+
"sep_token": "[SEP]",
|
44 |
+
"special_tokens_map_file": null,
|
45 |
+
"strip_accents": null,
|
46 |
+
"tokenize_chinese_chars": true,
|
47 |
+
"tokenizer_class": "BertTokenizer",
|
48 |
+
"unk_token": "[UNK]"
|
49 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 2.538804254183028,
|
4 |
+
"train_runtime": 274559.0377,
|
5 |
+
"train_samples": 8200540,
|
6 |
+
"train_samples_per_second": 89.604,
|
7 |
+
"train_steps_per_second": 2.8
|
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 sha256:4a92614fb5cb4de0152b8683eebb7f43e4556b86c98872e02b9cb4878e299665
|
3 |
+
size 3567
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|