Hugging Face's logo

itsmeussa
/
AdabTranslate-Darija

Text2Text Generation
Transformers
TensorBoard
Safetensors
mbart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
itsmeussa commited on
Commit
5d2887a
·
verified ·
1 Parent(s): ad9a7d0

Model save

Browse files
Files changed (3) hide show
  1. README.md +96 -0
  2. generation_config.json +11 -0
  3. runs/Mar25_12-22-44_1a7a55143cd0/events.out.tfevents.1711369370.1a7a55143cd0.14274.0 +2 -2
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: moussaKam/arabart
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - bleu
8
+ model-index:
9
+ - name: AdabTranslate-Darija
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # AdabTranslate-Darija
17
+
18
+ This model is a fine-tuned version of [moussaKam/arabart](https://huggingface.co/moussaKam/arabart) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 1.0892
21
+ - Bleu: 46.4939
22
+ - Gen Len: 9.6377
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 5e-05
42
+ - train_batch_size: 16
43
+ - eval_batch_size: 16
44
+ - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - num_epochs: 5.0
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
52
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
53
+ | 2.7196 | 0.14 | 200 | 1.9204 | 28.0708 | 9.7786 |
54
+ | 2.212 | 0.27 | 400 | 1.7376 | 31.2914 | 9.7633 |
55
+ | 1.9878 | 0.41 | 600 | 1.6152 | 33.3474 | 9.4964 |
56
+ | 1.8387 | 0.54 | 800 | 1.5276 | 35.4738 | 9.6621 |
57
+ | 1.7844 | 0.68 | 1000 | 1.4492 | 37.1222 | 9.5365 |
58
+ | 1.7389 | 0.81 | 1200 | 1.4085 | 37.6104 | 9.5614 |
59
+ | 1.6553 | 0.95 | 1400 | 1.3584 | 38.8845 | 9.7191 |
60
+ | 1.4817 | 1.08 | 1600 | 1.3305 | 39.4105 | 9.5849 |
61
+ | 1.3841 | 1.22 | 1800 | 1.2946 | 40.0041 | 9.5134 |
62
+ | 1.329 | 1.36 | 2000 | 1.2702 | 40.4855 | 9.5927 |
63
+ | 1.2938 | 1.49 | 2200 | 1.2410 | 41.433 | 9.6166 |
64
+ | 1.2812 | 1.63 | 2400 | 1.2333 | 42.0317 | 9.7487 |
65
+ | 1.234 | 1.76 | 2600 | 1.2066 | 42.0791 | 9.5668 |
66
+ | 1.2652 | 1.9 | 2800 | 1.1808 | 42.9113 | 9.6416 |
67
+ | 1.1726 | 2.03 | 3000 | 1.1849 | 42.8411 | 9.6397 |
68
+ | 1.0367 | 2.17 | 3200 | 1.1817 | 43.2576 | 9.6385 |
69
+ | 1.052 | 2.31 | 3400 | 1.1714 | 43.4972 | 9.6456 |
70
+ | 1.0222 | 2.44 | 3600 | 1.1486 | 43.7071 | 9.637 |
71
+ | 0.9921 | 2.58 | 3800 | 1.1437 | 44.278 | 9.6048 |
72
+ | 1.053 | 2.71 | 4000 | 1.1305 | 44.8293 | 9.6804 |
73
+ | 1.0093 | 2.85 | 4200 | 1.1247 | 44.8092 | 9.6187 |
74
+ | 1.0177 | 2.98 | 4400 | 1.1108 | 45.2717 | 9.6331 |
75
+ | 0.8833 | 3.12 | 4600 | 1.1225 | 45.2862 | 9.6317 |
76
+ | 0.8604 | 3.25 | 4800 | 1.1161 | 45.2156 | 9.625 |
77
+ | 0.8712 | 3.39 | 5000 | 1.1139 | 45.2736 | 9.5955 |
78
+ | 0.865 | 3.53 | 5200 | 1.1137 | 45.7609 | 9.6828 |
79
+ | 0.8821 | 3.66 | 5400 | 1.0981 | 45.742 | 9.6779 |
80
+ | 0.8532 | 3.8 | 5600 | 1.0934 | 45.6965 | 9.5956 |
81
+ | 0.8515 | 3.93 | 5800 | 1.0954 | 46.0175 | 9.6165 |
82
+ | 0.7878 | 4.07 | 6000 | 1.0941 | 45.96 | 9.6382 |
83
+ | 0.7652 | 4.2 | 6200 | 1.0988 | 45.8692 | 9.6138 |
84
+ | 0.7841 | 4.34 | 6400 | 1.0991 | 46.1438 | 9.6514 |
85
+ | 0.7432 | 4.47 | 6600 | 1.0961 | 46.1105 | 9.6212 |
86
+ | 0.7918 | 4.61 | 6800 | 1.0910 | 46.305 | 9.6477 |
87
+ | 0.7638 | 4.75 | 7000 | 1.0901 | 46.4753 | 9.6439 |
88
+ | 0.7448 | 4.88 | 7200 | 1.0892 | 46.4939 | 9.6377 |
89
+
90
+
91
+ ### Framework versions
92
+
93
+ - Transformers 4.40.0.dev0
94
+ - Pytorch 2.2.1+cu121
95
+ - Datasets 2.18.0
96
+ - Tokenizers 0.15.2
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "forced_eos_token_id": 2,
7
+ "no_repeat_ngram_size": 3,
8
+ "num_beams": 4,
9
+ "pad_token_id": 1,
10
+ "transformers_version": "4.40.0.dev0"
11
+ }
runs/Mar25_12-22-44_1a7a55143cd0/events.out.tfevents.1711369370.1a7a55143cd0.14274.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53e39a8fe2be21d6c82fbcc655472aa2dce00777a8397def47eb3395f0f256aa
3
- size 26480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0080b477a949dfb30908d14847644f57e9888f778e51a5f7d3b1670e09b8eb8
3
+ size 26834