salbatarni commited on
Commit
a525489
1 Parent(s): b4703a5

Training in progress, step 60

Browse files
README.md ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: aubmindlab/bert-base-arabertv02
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: arabert_baseline_relevance_task1_fold1
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_relevance_task1_fold1
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: 0.0669
18
+ - Qwk: 0.0233
19
+ - Mse: 0.0682
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 | 0.3333 | 2 | 0.9611 | -0.0186 | 0.9691 |
51
+ | No log | 0.6667 | 4 | 0.2075 | -0.0851 | 0.2124 |
52
+ | No log | 1.0 | 6 | 0.1656 | 0.0207 | 0.1701 |
53
+ | No log | 1.3333 | 8 | 0.1145 | 0.0392 | 0.1165 |
54
+ | No log | 1.6667 | 10 | 0.1145 | 0.0165 | 0.1165 |
55
+ | No log | 2.0 | 12 | 0.1921 | 0.0 | 0.1938 |
56
+ | No log | 2.3333 | 14 | 0.2095 | 0.0 | 0.2110 |
57
+ | No log | 2.6667 | 16 | 0.1634 | 0.0 | 0.1651 |
58
+ | No log | 3.0 | 18 | 0.0995 | 0.0 | 0.1002 |
59
+ | No log | 3.3333 | 20 | 0.1102 | 0.0050 | 0.1101 |
60
+ | No log | 3.6667 | 22 | 0.1004 | 0.0165 | 0.1002 |
61
+ | No log | 4.0 | 24 | 0.0724 | 0.0233 | 0.0728 |
62
+ | No log | 4.3333 | 26 | 0.0523 | 0.0233 | 0.0531 |
63
+ | No log | 4.6667 | 28 | 0.0574 | 0.0233 | 0.0583 |
64
+ | No log | 5.0 | 30 | 0.0614 | 0.0233 | 0.0626 |
65
+ | No log | 5.3333 | 32 | 0.0663 | 0.0233 | 0.0676 |
66
+ | No log | 5.6667 | 34 | 0.0729 | 0.0233 | 0.0742 |
67
+ | No log | 6.0 | 36 | 0.0631 | 0.0308 | 0.0641 |
68
+ | No log | 6.3333 | 38 | 0.0561 | 0.0597 | 0.0563 |
69
+ | No log | 6.6667 | 40 | 0.0579 | 0.0870 | 0.0579 |
70
+ | No log | 7.0 | 42 | 0.0563 | 0.0597 | 0.0566 |
71
+ | No log | 7.3333 | 44 | 0.0596 | 0.0308 | 0.0606 |
72
+ | No log | 7.6667 | 46 | 0.0661 | 0.0308 | 0.0673 |
73
+ | No log | 8.0 | 48 | 0.0735 | 0.0050 | 0.0747 |
74
+ | No log | 8.3333 | 50 | 0.0721 | 0.0105 | 0.0733 |
75
+ | No log | 8.6667 | 52 | 0.0679 | 0.0233 | 0.0690 |
76
+ | No log | 9.0 | 54 | 0.0657 | 0.0233 | 0.0669 |
77
+ | No log | 9.3333 | 56 | 0.0652 | 0.0233 | 0.0664 |
78
+ | No log | 9.6667 | 58 | 0.0664 | 0.0233 | 0.0677 |
79
+ | No log | 10.0 | 60 | 0.0669 | 0.0233 | 0.0682 |
80
+
81
+
82
+ ### Framework versions
83
+
84
+ - Transformers 4.44.0
85
+ - Pytorch 2.4.0
86
+ - Datasets 2.21.0
87
+ - 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:e034c50087d773f7f39e18f1cbebd03a1e46698b345096cfb3335756bec00131
3
+ size 540799996
runs/Aug27_16-09-30_353807a3cce0/events.out.tfevents.1724774972.353807a3cce0.22.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54fa446542380eb3979f377bf211254a65d52cf818e9d030327897cb521cab4d
3
+ size 16052
runs/Aug27_16-10-58_353807a3cce0/events.out.tfevents.1724775059.353807a3cce0.22.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9967b63c6e7651bcd5ad48439eea86e65496cad31a1ea88f6891b1a3eb507d1
3
+ size 16052
runs/Aug27_16-12-28_353807a3cce0/events.out.tfevents.1724775150.353807a3cce0.22.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce0cd044ff60d5f6c3ae4d825e5400aa4c21f8501b205fb999bd64cb08e45639
3
+ size 16052
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3c235372feec28c086a822e32de7471eb2e3803c7088951963c56887dede069
3
+ size 5240