End of training
Browse files- README.md +72 -0
- config.json +40 -0
- model.safetensors +3 -0
- runs/Mar10_15-14-06_efcb1301e604/events.out.tfevents.1710083681.efcb1301e604.1365.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: aubmindlab/bert-base-arabertv02
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
model-index:
|
8 |
+
- name: ar-poem-classification
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# ar-poem-classification
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.1427
|
20 |
+
- Macro F1: 0.6954
|
21 |
+
- Accuracy: 0.6944
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 2e-05
|
41 |
+
- train_batch_size: 16
|
42 |
+
- eval_batch_size: 128
|
43 |
+
- seed: 25
|
44 |
+
- gradient_accumulation_steps: 5
|
45 |
+
- total_train_batch_size: 80
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- num_epochs: 12
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Macro F1 | Accuracy |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
|
54 |
+
| No log | 1.0 | 250 | 1.0896 | 0.5319 | 0.5334 |
|
55 |
+
| 1.114 | 2.0 | 500 | 0.9989 | 0.5864 | 0.5826 |
|
56 |
+
| 1.114 | 3.0 | 750 | 0.9993 | 0.5942 | 0.5976 |
|
57 |
+
| 0.8219 | 4.0 | 1000 | 0.9949 | 0.6042 | 0.609 |
|
58 |
+
| 0.8219 | 5.0 | 1250 | 0.9813 | 0.6337 | 0.6366 |
|
59 |
+
| 0.563 | 6.0 | 1500 | 0.9666 | 0.6657 | 0.6654 |
|
60 |
+
| 0.563 | 7.0 | 1750 | 1.0253 | 0.6686 | 0.6668 |
|
61 |
+
| 0.3763 | 8.0 | 2000 | 1.0150 | 0.6951 | 0.6936 |
|
62 |
+
| 0.3763 | 9.0 | 2250 | 1.0619 | 0.6872 | 0.6872 |
|
63 |
+
| 0.2525 | 10.0 | 2500 | 1.1035 | 0.6929 | 0.6922 |
|
64 |
+
| 0.2525 | 11.0 | 2750 | 1.1352 | 0.6952 | 0.6944 |
|
65 |
+
| 0.184 | 12.0 | 3000 | 1.1427 | 0.6954 | 0.6944 |
|
66 |
+
|
67 |
+
|
68 |
+
### Framework versions
|
69 |
+
|
70 |
+
- Transformers 4.38.2
|
71 |
+
- Pytorch 2.1.0+cu121
|
72 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "aubmindlab/bert-base-arabertv02",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
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 |
+
"id2label": {
|
12 |
+
"0": "\u0627\u0644\u0639\u0635\u0631 \u0627\u0644\u0623\u0646\u062f\u0644\u0633\u064a",
|
13 |
+
"1": "\u0627\u0644\u0639\u0635\u0631 \u0627\u0644\u0627\u064a\u0648\u0628\u064a",
|
14 |
+
"2": "\u0627\u0644\u0639\u0635\u0631 \u0627\u0644\u0639\u0628\u0627\u0633\u064a",
|
15 |
+
"3": "\u0627\u0644\u0639\u0635\u0631 \u0627\u0644\u0645\u0645\u0644\u0648\u0643\u064a",
|
16 |
+
"4": "\u0627\u0644\u0639\u0635\u0631 \u062d\u062f\u064a\u062b"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": {
|
21 |
+
"\u0627\u0644\u0639\u0635\u0631 \u0627\u0644\u0623\u0646\u062f\u0644\u0633\u064a": 0,
|
22 |
+
"\u0627\u0644\u0639\u0635\u0631 \u0627\u0644\u0627\u064a\u0648\u0628\u064a": 1,
|
23 |
+
"\u0627\u0644\u0639\u0635\u0631 \u0627\u0644\u0639\u0628\u0627\u0633\u064a": 2,
|
24 |
+
"\u0627\u0644\u0639\u0635\u0631 \u0627\u0644\u0645\u0645\u0644\u0648\u0643\u064a": 3,
|
25 |
+
"\u0627\u0644\u0639\u0635\u0631 \u062d\u062f\u064a\u062b": 4
|
26 |
+
},
|
27 |
+
"layer_norm_eps": 1e-12,
|
28 |
+
"max_position_embeddings": 512,
|
29 |
+
"model_type": "bert",
|
30 |
+
"num_attention_heads": 12,
|
31 |
+
"num_hidden_layers": 12,
|
32 |
+
"pad_token_id": 0,
|
33 |
+
"position_embedding_type": "absolute",
|
34 |
+
"problem_type": "single_label_classification",
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.38.2",
|
37 |
+
"type_vocab_size": 2,
|
38 |
+
"use_cache": true,
|
39 |
+
"vocab_size": 64000
|
40 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9927535cfd46eeeff65a0163d74ca1485e520ef31ca4c1111e4c59a2c8dbdf2a
|
3 |
+
size 540812300
|
runs/Mar10_15-14-06_efcb1301e604/events.out.tfevents.1710083681.efcb1301e604.1365.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f11f1d99b072c5c3563c796f83b660fd4eb1a331ba26f921b2a42e02498d6c22
|
3 |
+
size 10913
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd99bddc44849282bcef30368837746e59ce5ab82566fda4d5c635f099472f74
|
3 |
+
size 4920
|