salbatarni
commited on
Commit
•
a8c583f
1
Parent(s):
8fa8ffb
Training in progress, step 40
Browse files- README.md +77 -0
- config.json +32 -0
- model.safetensors +3 -0
- runs/Aug28_14-04-11_b965fc3fcb70/events.out.tfevents.1724853854.b965fc3fcb70.23.0 +3 -0
- runs/Aug28_14-05-19_b965fc3fcb70/events.out.tfevents.1724853920.b965fc3fcb70.23.1 +3 -0
- runs/Aug28_14-06-28_b965fc3fcb70/events.out.tfevents.1724853989.b965fc3fcb70.23.2 +3 -0
- runs/Aug28_14-07-44_b965fc3fcb70/events.out.tfevents.1724854065.b965fc3fcb70.23.3 +3 -0
- runs/Aug28_14-08-55_b965fc3fcb70/events.out.tfevents.1724854136.b965fc3fcb70.23.4 +3 -0
- runs/Aug28_14-10-10_b965fc3fcb70/events.out.tfevents.1724854211.b965fc3fcb70.23.5 +3 -0
- runs/Aug28_14-11-23_b965fc3fcb70/events.out.tfevents.1724854285.b965fc3fcb70.23.6 +3 -0
- runs/Aug28_14-12-36_b965fc3fcb70/events.out.tfevents.1724854358.b965fc3fcb70.23.7 +3 -0
- runs/Aug28_14-13-48_b965fc3fcb70/events.out.tfevents.1724854429.b965fc3fcb70.23.8 +3 -0
- runs/Aug28_14-15-03_b965fc3fcb70/events.out.tfevents.1724854504.b965fc3fcb70.23.9 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: aubmindlab/bert-base-arabertv02
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: arabert_baseline_grammar_task8_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_grammar_task8_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: 0.5087
|
18 |
+
- Qwk: 0.6725
|
19 |
+
- Mse: 0.5087
|
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 | 0.5 | 2 | 2.2317 | 0.0 | 2.2317 |
|
51 |
+
| No log | 1.0 | 4 | 1.4866 | 0.2297 | 1.4866 |
|
52 |
+
| No log | 1.5 | 6 | 1.0270 | 0.5643 | 1.0270 |
|
53 |
+
| No log | 2.0 | 8 | 1.1388 | 0.4074 | 1.1388 |
|
54 |
+
| No log | 2.5 | 10 | 1.0946 | 0.4074 | 1.0946 |
|
55 |
+
| No log | 3.0 | 12 | 0.5591 | 0.6159 | 0.5591 |
|
56 |
+
| No log | 3.5 | 14 | 0.5042 | 0.6216 | 0.5042 |
|
57 |
+
| No log | 4.0 | 16 | 0.4874 | 0.6585 | 0.4874 |
|
58 |
+
| No log | 4.5 | 18 | 0.5862 | 0.6053 | 0.5862 |
|
59 |
+
| No log | 5.0 | 20 | 0.7098 | 0.5549 | 0.7098 |
|
60 |
+
| No log | 5.5 | 22 | 0.6879 | 0.5549 | 0.6879 |
|
61 |
+
| No log | 6.0 | 24 | 0.5641 | 0.6053 | 0.5641 |
|
62 |
+
| No log | 6.5 | 26 | 0.5895 | 0.6725 | 0.5895 |
|
63 |
+
| No log | 7.0 | 28 | 0.6417 | 0.6211 | 0.6417 |
|
64 |
+
| No log | 7.5 | 30 | 0.7537 | 0.6211 | 0.7537 |
|
65 |
+
| No log | 8.0 | 32 | 0.6776 | 0.6211 | 0.6776 |
|
66 |
+
| No log | 8.5 | 34 | 0.6081 | 0.6211 | 0.6081 |
|
67 |
+
| No log | 9.0 | 36 | 0.5508 | 0.6725 | 0.5508 |
|
68 |
+
| No log | 9.5 | 38 | 0.5104 | 0.6725 | 0.5104 |
|
69 |
+
| No log | 10.0 | 40 | 0.5087 | 0.6725 | 0.5087 |
|
70 |
+
|
71 |
+
|
72 |
+
### Framework versions
|
73 |
+
|
74 |
+
- Transformers 4.44.0
|
75 |
+
- Pytorch 2.4.0
|
76 |
+
- Datasets 2.21.0
|
77 |
+
- 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 sha256:07102c26376644033400b681061122ac0118b14d4398030b73a5083a6bc4f839
|
3 |
+
size 540799996
|
runs/Aug28_14-04-11_b965fc3fcb70/events.out.tfevents.1724853854.b965fc3fcb70.23.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:298598dfe1da29a1015205226aa6363759f7403d354272186033671b01edd32d
|
3 |
+
size 12475
|
runs/Aug28_14-05-19_b965fc3fcb70/events.out.tfevents.1724853920.b965fc3fcb70.23.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fc98b756644e3fa0d5dd9f786526938fc723e9202ff3b683cb7a9e157beb07a
|
3 |
+
size 12475
|
runs/Aug28_14-06-28_b965fc3fcb70/events.out.tfevents.1724853989.b965fc3fcb70.23.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99c2ad69faf0c48edf643651e6a7bdd8b0ca5f241179aa180bd95e026caaa1d8
|
3 |
+
size 12474
|
runs/Aug28_14-07-44_b965fc3fcb70/events.out.tfevents.1724854065.b965fc3fcb70.23.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1cc0be9457cfda04be03e8a064f99377b1ff840c9b92df5230493d259c205ba
|
3 |
+
size 12474
|
runs/Aug28_14-08-55_b965fc3fcb70/events.out.tfevents.1724854136.b965fc3fcb70.23.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a99c264aee715d7461b3b8b32b995ab8d22f394b6730bbde18365098e54db87
|
3 |
+
size 12468
|
runs/Aug28_14-10-10_b965fc3fcb70/events.out.tfevents.1724854211.b965fc3fcb70.23.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37facc491dfb303a0f95a08715c359323380f0a28710839ab117a763f4a5087e
|
3 |
+
size 12468
|
runs/Aug28_14-11-23_b965fc3fcb70/events.out.tfevents.1724854285.b965fc3fcb70.23.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:153789340fa6f9f2fe86cbd6bfe5e6d00899d5a7672c6b0ffab78dd2da0f9a5f
|
3 |
+
size 12472
|
runs/Aug28_14-12-36_b965fc3fcb70/events.out.tfevents.1724854358.b965fc3fcb70.23.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4833e10dc263d7843c5498c0272b3193d3d40303bebbc3bb22ee60772d13c8d
|
3 |
+
size 12472
|
runs/Aug28_14-13-48_b965fc3fcb70/events.out.tfevents.1724854429.b965fc3fcb70.23.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1ddcaa5736f2331edfeda4400359e0d8bd2691bedbb8b3211b933afc3d3cceb
|
3 |
+
size 12470
|
runs/Aug28_14-15-03_b965fc3fcb70/events.out.tfevents.1724854504.b965fc3fcb70.23.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e476370353624c91a17633aa67a64d0ccaa133836d22a65fbe068327b6fc725
|
3 |
+
size 12470
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a8d0a8c35958942e6fb1f66f3c46c2a4023905f78397ff7f974be427a9dbf36
|
3 |
+
size 5240
|