salbatarni commited on
Commit
6f99c92
1 Parent(s): 3abc813

Training in progress, step 40

Browse files
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_relevance_task8_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_task8_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: 0.2901
18
+ - Qwk: 0.4096
19
+ - Mse: 0.2901
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 | 0.6071 | -0.1667 | 0.6071 |
51
+ | No log | 1.0 | 4 | 0.6292 | -0.0548 | 0.6292 |
52
+ | No log | 1.5 | 6 | 0.5112 | 0.3467 | 0.5112 |
53
+ | No log | 2.0 | 8 | 0.2941 | 0.2000 | 0.2941 |
54
+ | No log | 2.5 | 10 | 0.2595 | 0.3171 | 0.2595 |
55
+ | No log | 3.0 | 12 | 0.3011 | 0.3171 | 0.3011 |
56
+ | No log | 3.5 | 14 | 0.2934 | 0.3171 | 0.2934 |
57
+ | No log | 4.0 | 16 | 0.2489 | 0.3171 | 0.2489 |
58
+ | No log | 4.5 | 18 | 0.2716 | 0.4096 | 0.2716 |
59
+ | No log | 5.0 | 20 | 0.3200 | 0.3099 | 0.3200 |
60
+ | No log | 5.5 | 22 | 0.3416 | 0.2000 | 0.3416 |
61
+ | No log | 6.0 | 24 | 0.3237 | 0.4096 | 0.3237 |
62
+ | No log | 6.5 | 26 | 0.2949 | 0.4096 | 0.2949 |
63
+ | No log | 7.0 | 28 | 0.2821 | 0.4096 | 0.2821 |
64
+ | No log | 7.5 | 30 | 0.2766 | 0.4096 | 0.2766 |
65
+ | No log | 8.0 | 32 | 0.2780 | 0.4096 | 0.2780 |
66
+ | No log | 8.5 | 34 | 0.2807 | 0.4096 | 0.2807 |
67
+ | No log | 9.0 | 36 | 0.2841 | 0.4096 | 0.2841 |
68
+ | No log | 9.5 | 38 | 0.2889 | 0.4096 | 0.2889 |
69
+ | No log | 10.0 | 40 | 0.2901 | 0.4096 | 0.2901 |
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 sha256:82d6c83f79c3ad4d398ad115d7393e492c577c3ed1c717c747e45eba8adb1e2c
3
+ size 540799996
runs/Aug28_07-42-05_be8f70187d33/events.out.tfevents.1724830928.be8f70187d33.24.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a0edb1996b829c3f013695615992b20616cb5d8568856b5e4e7e4840f4a4d62
3
+ size 12472
runs/Aug28_07-43-09_be8f70187d33/events.out.tfevents.1724830990.be8f70187d33.24.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bad99e9d68a02f92c6be30cca898a2cfe1c6e755b7661e8d821af3b49abd2ae
3
+ size 12472
runs/Aug28_07-44-15_be8f70187d33/events.out.tfevents.1724831056.be8f70187d33.24.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:872c0faa8463893ce03c97e177a227719d52d98641577eaa505995bd524b0e5f
3
+ size 12473
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c4515de98c0c0d75a9b41e5f453a540c970f1cb7d7fae6970836731a580c884
3
+ size 5240