salbatarni
commited on
Commit
•
83ebd7a
1
Parent(s):
67b7e44
Training in progress, step 30
Browse files- README.md +72 -0
- config.json +32 -0
- model.safetensors +3 -0
- runs/Aug29_05-37-12_0bdfdf23bcd7/events.out.tfevents.1724909835.0bdfdf23bcd7.23.0 +3 -0
- runs/Aug29_05-38-40_0bdfdf23bcd7/events.out.tfevents.1724909921.0bdfdf23bcd7.23.1 +3 -0
- runs/Aug29_05-40-17_0bdfdf23bcd7/events.out.tfevents.1724910018.0bdfdf23bcd7.23.2 +3 -0
- runs/Aug29_05-41-50_0bdfdf23bcd7/events.out.tfevents.1724910111.0bdfdf23bcd7.23.3 +3 -0
- runs/Aug29_05-43-25_0bdfdf23bcd7/events.out.tfevents.1724910207.0bdfdf23bcd7.23.4 +3 -0
- runs/Aug29_05-44-20_0bdfdf23bcd7/events.out.tfevents.1724910261.0bdfdf23bcd7.23.5 +3 -0
- runs/Aug29_05-45-22_0bdfdf23bcd7/events.out.tfevents.1724910324.0bdfdf23bcd7.23.6 +3 -0
- runs/Aug29_05-46-14_0bdfdf23bcd7/events.out.tfevents.1724910375.0bdfdf23bcd7.23.7 +3 -0
- runs/Aug29_05-47-02_0bdfdf23bcd7/events.out.tfevents.1724910423.0bdfdf23bcd7.23.8 +3 -0
- runs/Aug29_05-48-33_0bdfdf23bcd7/events.out.tfevents.1724910514.0bdfdf23bcd7.23.9 +3 -0
- runs/Aug29_05-50-00_0bdfdf23bcd7/events.out.tfevents.1724910601.0bdfdf23bcd7.23.10 +3 -0
- runs/Aug29_05-51-03_0bdfdf23bcd7/events.out.tfevents.1724910665.0bdfdf23bcd7.23.11 +3 -0
- runs/Aug29_05-52-19_0bdfdf23bcd7/events.out.tfevents.1724910740.0bdfdf23bcd7.23.12 +3 -0
- runs/Aug29_05-53-50_0bdfdf23bcd7/events.out.tfevents.1724910831.0bdfdf23bcd7.23.13 +3 -0
- runs/Aug29_05-55-19_0bdfdf23bcd7/events.out.tfevents.1724910920.0bdfdf23bcd7.23.14 +3 -0
- runs/Aug29_05-56-57_0bdfdf23bcd7/events.out.tfevents.1724911018.0bdfdf23bcd7.23.15 +3 -0
- runs/Aug29_05-58-34_0bdfdf23bcd7/events.out.tfevents.1724911116.0bdfdf23bcd7.23.16 +3 -0
- runs/Aug29_06-00-05_0bdfdf23bcd7/events.out.tfevents.1724911206.0bdfdf23bcd7.23.17 +3 -0
- runs/Aug29_06-01-39_0bdfdf23bcd7/events.out.tfevents.1724911300.0bdfdf23bcd7.23.18 +3 -0
- runs/Aug29_06-02-42_0bdfdf23bcd7/events.out.tfevents.1724911363.0bdfdf23bcd7.23.19 +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 |
+
model-index:
|
6 |
+
- name: arabert_baseline_development_task3_fold0
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# arabert_baseline_development_task3_fold0
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) on the None dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 0.8217
|
18 |
+
- Qwk: -0.0645
|
19 |
+
- Mse: 0.7668
|
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: 2e-05
|
39 |
+
- train_batch_size: 16
|
40 |
+
- eval_batch_size: 16
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 10
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
|
49 |
+
|:-------------:|:------:|:----:|:---------------:|:-------:|:------:|
|
50 |
+
| No log | 0.6667 | 2 | 3.8893 | -0.0248 | 3.7493 |
|
51 |
+
| No log | 1.3333 | 4 | 1.6163 | -0.1603 | 1.5205 |
|
52 |
+
| No log | 2.0 | 6 | 1.3910 | -0.0522 | 1.3168 |
|
53 |
+
| No log | 2.6667 | 8 | 0.9920 | -0.1846 | 0.9528 |
|
54 |
+
| No log | 3.3333 | 10 | 0.9604 | -0.5098 | 0.9287 |
|
55 |
+
| No log | 4.0 | 12 | 0.7779 | -0.1308 | 0.7306 |
|
56 |
+
| No log | 4.6667 | 14 | 0.7914 | 0.0 | 0.7387 |
|
57 |
+
| No log | 5.3333 | 16 | 0.8497 | 0.0 | 0.7909 |
|
58 |
+
| No log | 6.0 | 18 | 0.8019 | 0.0351 | 0.7466 |
|
59 |
+
| No log | 6.6667 | 20 | 0.7900 | 0.0748 | 0.7369 |
|
60 |
+
| No log | 7.3333 | 22 | 0.7934 | -0.0645 | 0.7422 |
|
61 |
+
| No log | 8.0 | 24 | 0.8050 | -0.0645 | 0.7531 |
|
62 |
+
| No log | 8.6667 | 26 | 0.8063 | -0.0645 | 0.7543 |
|
63 |
+
| No log | 9.3333 | 28 | 0.8142 | -0.0645 | 0.7607 |
|
64 |
+
| No log | 10.0 | 30 | 0.8217 | -0.0645 | 0.7668 |
|
65 |
+
|
66 |
+
|
67 |
+
### Framework versions
|
68 |
+
|
69 |
+
- Transformers 4.44.0
|
70 |
+
- Pytorch 2.4.0
|
71 |
+
- Datasets 2.21.0
|
72 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "LABEL_0"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"label2id": {
|
17 |
+
"LABEL_0": 0
|
18 |
+
},
|
19 |
+
"layer_norm_eps": 1e-12,
|
20 |
+
"max_position_embeddings": 512,
|
21 |
+
"model_type": "bert",
|
22 |
+
"num_attention_heads": 12,
|
23 |
+
"num_hidden_layers": 12,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"position_embedding_type": "absolute",
|
26 |
+
"problem_type": "regression",
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.44.0",
|
29 |
+
"type_vocab_size": 2,
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 64000
|
32 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4804c03ea34c7a5fb90c039f44fa665612cc1dba10e6c11b9ba1a1eed6e3f977
|
3 |
+
size 540799996
|
runs/Aug29_05-37-12_0bdfdf23bcd7/events.out.tfevents.1724909835.0bdfdf23bcd7.23.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc6448351031981871b2117ef5c708d84292c3b9aa443174fdff418f5526c665
|
3 |
+
size 16055
|
runs/Aug29_05-38-40_0bdfdf23bcd7/events.out.tfevents.1724909921.0bdfdf23bcd7.23.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e50e5e5300ef6b8cf4fb4241085d501b5c134121f50aba5b53d6410f89b348a8
|
3 |
+
size 16055
|
runs/Aug29_05-40-17_0bdfdf23bcd7/events.out.tfevents.1724910018.0bdfdf23bcd7.23.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85bb0f760a39f86588b25f63454d6b1b0d8bf5d001ef4c590d2b988cb3b6fbcb
|
3 |
+
size 16055
|
runs/Aug29_05-41-50_0bdfdf23bcd7/events.out.tfevents.1724910111.0bdfdf23bcd7.23.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e28c97e14e695df546b9af4f516607de462d524c782da1f3c230054837ce2d6
|
3 |
+
size 16055
|
runs/Aug29_05-43-25_0bdfdf23bcd7/events.out.tfevents.1724910207.0bdfdf23bcd7.23.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb5afbfd81a852eb18c72a05a9061e61e85584b6fe897f654d59b3133cfd4b7f
|
3 |
+
size 10685
|
runs/Aug29_05-44-20_0bdfdf23bcd7/events.out.tfevents.1724910261.0bdfdf23bcd7.23.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b610c9ed076001aa29bf23e266c6b9306f81361bce2e8043b591e63270e63e1
|
3 |
+
size 10685
|
runs/Aug29_05-45-22_0bdfdf23bcd7/events.out.tfevents.1724910324.0bdfdf23bcd7.23.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6efdb89e9cfe44d336be09dd31f4620e0289189110371492522565f5145810cb
|
3 |
+
size 8895
|
runs/Aug29_05-46-14_0bdfdf23bcd7/events.out.tfevents.1724910375.0bdfdf23bcd7.23.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0ec587c78c178912638cdad9f9860237ea9b362e7987e9677c16a6fdc7a8534
|
3 |
+
size 8895
|
runs/Aug29_05-47-02_0bdfdf23bcd7/events.out.tfevents.1724910423.0bdfdf23bcd7.23.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfcabba89d98afb997623bec1aaa343932fb8acad892e0b68a6825a2e64a2506
|
3 |
+
size 16055
|
runs/Aug29_05-48-33_0bdfdf23bcd7/events.out.tfevents.1724910514.0bdfdf23bcd7.23.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29a225dd316309f6153363578a8f6477611556c78522e72e555f0f7c19926740
|
3 |
+
size 16055
|
runs/Aug29_05-50-00_0bdfdf23bcd7/events.out.tfevents.1724910601.0bdfdf23bcd7.23.10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:443e1ab3c596c6604182ee73fd1dad929f14e7f287c9f1f935a37bb8d8a834e4
|
3 |
+
size 12475
|
runs/Aug29_05-51-03_0bdfdf23bcd7/events.out.tfevents.1724910665.0bdfdf23bcd7.23.11
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3551d4907badd80d180998db1322d93d5718a186136899328d178f3980a3871f
|
3 |
+
size 12475
|
runs/Aug29_05-52-19_0bdfdf23bcd7/events.out.tfevents.1724910740.0bdfdf23bcd7.23.12
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25f454a52c4ab290a452eebab99e415d9faf3bcd6458723ce7b619f594e31222
|
3 |
+
size 16055
|
runs/Aug29_05-53-50_0bdfdf23bcd7/events.out.tfevents.1724910831.0bdfdf23bcd7.23.13
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc523861992110fd5699858ade2a2eb416e0e9df7d12fb26bef460ef57214245
|
3 |
+
size 16055
|
runs/Aug29_05-55-19_0bdfdf23bcd7/events.out.tfevents.1724910920.0bdfdf23bcd7.23.14
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17b5f9d7a8487bc60334f34514a2770974667855f5dfe88fb96affe8b8aecc62
|
3 |
+
size 16054
|
runs/Aug29_05-56-57_0bdfdf23bcd7/events.out.tfevents.1724911018.0bdfdf23bcd7.23.15
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65b34c1396cd93601569ecd8fca7cd2a26dcdd9954f7833a84b5fa5249996069
|
3 |
+
size 16054
|
runs/Aug29_05-58-34_0bdfdf23bcd7/events.out.tfevents.1724911116.0bdfdf23bcd7.23.16
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1155aad3794649513fa31fac861c619b10d7c233038941fe4b6ec13e5444a1f8
|
3 |
+
size 16054
|
runs/Aug29_06-00-05_0bdfdf23bcd7/events.out.tfevents.1724911206.0bdfdf23bcd7.23.17
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c61ef173f3e4ea250aa1e6d08a63655d29c9b0616f2a2985729c7a4b16a26142
|
3 |
+
size 16054
|
runs/Aug29_06-01-39_0bdfdf23bcd7/events.out.tfevents.1724911300.0bdfdf23bcd7.23.18
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f9c63fe5c12882727a9798926c6e294862a8a67a0dea71acddf5ab7087c65ec
|
3 |
+
size 10684
|
runs/Aug29_06-02-42_0bdfdf23bcd7/events.out.tfevents.1724911363.0bdfdf23bcd7.23.19
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f779e6462bafe59016a7ee29be1616c38f77f1fba02742237093a63dd62465bb
|
3 |
+
size 10684
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52541a2c5e5360fe9b52168e04bc9432ce7a4ea6a3d4bde9220387e839a7a903
|
3 |
+
size 5240
|