salbatarni
commited on
Commit
•
111a673
1
Parent(s):
1ad5d6d
Training in progress, step 160
Browse files- README.md +132 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: aubmindlab/bert-base-arabertv02
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: arabert_cross_development_task1_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_cross_development_task1_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: 0.8306
|
18 |
+
- Qwk: 0.2565
|
19 |
+
- Mse: 0.8306
|
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: 64
|
40 |
+
- eval_batch_size: 64
|
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 | 0.1333 | 2 | 4.0034 | -0.0039 | 4.0034 |
|
51 |
+
| No log | 0.2667 | 4 | 1.7572 | 0.0385 | 1.7572 |
|
52 |
+
| No log | 0.4 | 6 | 0.8795 | 0.1253 | 0.8795 |
|
53 |
+
| No log | 0.5333 | 8 | 1.0722 | 0.1468 | 1.0722 |
|
54 |
+
| No log | 0.6667 | 10 | 1.9981 | 0.0739 | 1.9981 |
|
55 |
+
| No log | 0.8 | 12 | 1.4228 | 0.1298 | 1.4228 |
|
56 |
+
| No log | 0.9333 | 14 | 0.7120 | 0.1720 | 0.7120 |
|
57 |
+
| No log | 1.0667 | 16 | 0.5182 | 0.2951 | 0.5182 |
|
58 |
+
| No log | 1.2 | 18 | 0.6133 | 0.2736 | 0.6133 |
|
59 |
+
| No log | 1.3333 | 20 | 1.1336 | 0.1776 | 1.1336 |
|
60 |
+
| No log | 1.4667 | 22 | 1.2656 | 0.1714 | 1.2656 |
|
61 |
+
| No log | 1.6 | 24 | 0.8675 | 0.2380 | 0.8675 |
|
62 |
+
| No log | 1.7333 | 26 | 0.5730 | 0.3050 | 0.5730 |
|
63 |
+
| No log | 1.8667 | 28 | 0.5924 | 0.2784 | 0.5924 |
|
64 |
+
| No log | 2.0 | 30 | 0.6861 | 0.2120 | 0.6861 |
|
65 |
+
| No log | 2.1333 | 32 | 0.8867 | 0.2029 | 0.8867 |
|
66 |
+
| No log | 2.2667 | 34 | 0.9172 | 0.2121 | 0.9172 |
|
67 |
+
| No log | 2.4 | 36 | 0.7721 | 0.2159 | 0.7721 |
|
68 |
+
| No log | 2.5333 | 38 | 0.8001 | 0.2277 | 0.8001 |
|
69 |
+
| No log | 2.6667 | 40 | 0.8684 | 0.2498 | 0.8684 |
|
70 |
+
| No log | 2.8 | 42 | 0.9570 | 0.2264 | 0.9570 |
|
71 |
+
| No log | 2.9333 | 44 | 0.8803 | 0.2439 | 0.8803 |
|
72 |
+
| No log | 3.0667 | 46 | 0.7435 | 0.2799 | 0.7435 |
|
73 |
+
| No log | 3.2 | 48 | 0.6805 | 0.3082 | 0.6805 |
|
74 |
+
| No log | 3.3333 | 50 | 0.8424 | 0.2730 | 0.8424 |
|
75 |
+
| No log | 3.4667 | 52 | 0.8402 | 0.2670 | 0.8402 |
|
76 |
+
| No log | 3.6 | 54 | 0.8115 | 0.2861 | 0.8115 |
|
77 |
+
| No log | 3.7333 | 56 | 0.8179 | 0.2776 | 0.8179 |
|
78 |
+
| No log | 3.8667 | 58 | 0.7692 | 0.2822 | 0.7692 |
|
79 |
+
| No log | 4.0 | 60 | 0.6605 | 0.2944 | 0.6605 |
|
80 |
+
| No log | 4.1333 | 62 | 0.6724 | 0.3033 | 0.6724 |
|
81 |
+
| No log | 4.2667 | 64 | 0.7918 | 0.2700 | 0.7918 |
|
82 |
+
| No log | 4.4 | 66 | 0.9373 | 0.2649 | 0.9373 |
|
83 |
+
| No log | 4.5333 | 68 | 0.8734 | 0.2482 | 0.8734 |
|
84 |
+
| No log | 4.6667 | 70 | 0.6994 | 0.2866 | 0.6994 |
|
85 |
+
| No log | 4.8 | 72 | 0.5761 | 0.3307 | 0.5761 |
|
86 |
+
| No log | 4.9333 | 74 | 0.6497 | 0.2879 | 0.6497 |
|
87 |
+
| No log | 5.0667 | 76 | 0.7333 | 0.2628 | 0.7333 |
|
88 |
+
| No log | 5.2 | 78 | 1.0341 | 0.2345 | 1.0341 |
|
89 |
+
| No log | 5.3333 | 80 | 1.1378 | 0.2214 | 1.1378 |
|
90 |
+
| No log | 5.4667 | 82 | 0.9255 | 0.2527 | 0.9255 |
|
91 |
+
| No log | 5.6 | 84 | 0.6589 | 0.3108 | 0.6589 |
|
92 |
+
| No log | 5.7333 | 86 | 0.5709 | 0.3576 | 0.5709 |
|
93 |
+
| No log | 5.8667 | 88 | 0.6392 | 0.2982 | 0.6392 |
|
94 |
+
| No log | 6.0 | 90 | 0.7919 | 0.2436 | 0.7919 |
|
95 |
+
| No log | 6.1333 | 92 | 0.7855 | 0.2412 | 0.7855 |
|
96 |
+
| No log | 6.2667 | 94 | 0.6800 | 0.2919 | 0.6800 |
|
97 |
+
| No log | 6.4 | 96 | 0.6850 | 0.2998 | 0.6850 |
|
98 |
+
| No log | 6.5333 | 98 | 0.8473 | 0.2545 | 0.8473 |
|
99 |
+
| No log | 6.6667 | 100 | 0.9780 | 0.2417 | 0.9780 |
|
100 |
+
| No log | 6.8 | 102 | 0.9663 | 0.2331 | 0.9663 |
|
101 |
+
| No log | 6.9333 | 104 | 0.8213 | 0.2337 | 0.8213 |
|
102 |
+
| No log | 7.0667 | 106 | 0.6942 | 0.2789 | 0.6942 |
|
103 |
+
| No log | 7.2 | 108 | 0.7119 | 0.2738 | 0.7119 |
|
104 |
+
| No log | 7.3333 | 110 | 0.8067 | 0.2517 | 0.8067 |
|
105 |
+
| No log | 7.4667 | 112 | 0.8998 | 0.2447 | 0.8998 |
|
106 |
+
| No log | 7.6 | 114 | 0.9907 | 0.2199 | 0.9907 |
|
107 |
+
| No log | 7.7333 | 116 | 0.9290 | 0.2364 | 0.9290 |
|
108 |
+
| No log | 7.8667 | 118 | 0.7925 | 0.2551 | 0.7925 |
|
109 |
+
| No log | 8.0 | 120 | 0.7137 | 0.2738 | 0.7137 |
|
110 |
+
| No log | 8.1333 | 122 | 0.7202 | 0.2753 | 0.7202 |
|
111 |
+
| No log | 8.2667 | 124 | 0.7738 | 0.2663 | 0.7738 |
|
112 |
+
| No log | 8.4 | 126 | 0.8078 | 0.2539 | 0.8078 |
|
113 |
+
| No log | 8.5333 | 128 | 0.8794 | 0.2516 | 0.8794 |
|
114 |
+
| No log | 8.6667 | 130 | 0.9809 | 0.2362 | 0.9809 |
|
115 |
+
| No log | 8.8 | 132 | 1.0066 | 0.2362 | 1.0066 |
|
116 |
+
| No log | 8.9333 | 134 | 0.9524 | 0.2397 | 0.9524 |
|
117 |
+
| No log | 9.0667 | 136 | 0.8849 | 0.2464 | 0.8849 |
|
118 |
+
| No log | 9.2 | 138 | 0.8285 | 0.2565 | 0.8285 |
|
119 |
+
| No log | 9.3333 | 140 | 0.7806 | 0.2545 | 0.7806 |
|
120 |
+
| No log | 9.4667 | 142 | 0.7707 | 0.2569 | 0.7707 |
|
121 |
+
| No log | 9.6 | 144 | 0.7836 | 0.2545 | 0.7836 |
|
122 |
+
| No log | 9.7333 | 146 | 0.8063 | 0.2550 | 0.8063 |
|
123 |
+
| No log | 9.8667 | 148 | 0.8258 | 0.2565 | 0.8258 |
|
124 |
+
| No log | 10.0 | 150 | 0.8306 | 0.2565 | 0.8306 |
|
125 |
+
|
126 |
+
|
127 |
+
### Framework versions
|
128 |
+
|
129 |
+
- Transformers 4.44.0
|
130 |
+
- Pytorch 2.4.0
|
131 |
+
- Datasets 2.21.0
|
132 |
+
- 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 sha256:87239092dea3c4e9088ba1e99d351e186305e317321abed5e8108be5898f7b32
|
3 |
+
size 540799996
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:700aaba66f5741ee25a66df5ecfc4fe5878c87ff78994c847489e5059b904525
|
3 |
+
size 5240
|