BounharAbdelaziz commited on
Commit
78c0117
1 Parent(s): 66d4f69

BounharAbdelaziz/Terjman-Large

Browse files
Files changed (3) hide show
  1. README.md +103 -0
  2. generation_config.json +16 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-4.0
3
+ base_model: Helsinki-NLP/opus-mt-tc-big-en-ar
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - bleu
8
+ model-index:
9
+ - name: Terjman-Large
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
+ # Terjman-Large
17
+
18
+ This model is a fine-tuned version of [Helsinki-NLP/opus-mt-tc-big-en-ar](https://huggingface.co/Helsinki-NLP/opus-mt-tc-big-en-ar) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 3.2078
21
+ - Bleu: 8.3292
22
+ - Gen Len: 34.4959
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: 3e-05
42
+ - train_batch_size: 22
43
+ - eval_batch_size: 22
44
+ - seed: 42
45
+ - gradient_accumulation_steps: 4
46
+ - total_train_batch_size: 88
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_ratio: 0.03
50
+ - num_epochs: 40
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
55
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|:-------:|
56
+ | No log | 0.9982 | 407 | 4.3938 | 4.6056 | 22.6033 |
57
+ | 5.1616 | 1.9988 | 815 | 3.7257 | 5.8319 | 30.9201 |
58
+ | 3.902 | 2.9994 | 1223 | 3.5214 | 6.7311 | 32.9091 |
59
+ | 3.5737 | 4.0 | 1631 | 3.4204 | 7.3684 | 32.1433 |
60
+ | 3.4576 | 4.9982 | 2038 | 3.3562 | 7.8632 | 34.5399 |
61
+ | 3.4576 | 5.9988 | 2446 | 3.3151 | 7.9739 | 35.3278 |
62
+ | 3.3833 | 6.9994 | 2854 | 3.2884 | 8.0825 | 35.8292 |
63
+ | 3.3358 | 8.0 | 3262 | 3.2681 | 8.2765 | 34.5427 |
64
+ | 3.3069 | 8.9982 | 3669 | 3.2517 | 8.1019 | 33.584 |
65
+ | 3.2769 | 9.9988 | 4077 | 3.2404 | 8.106 | 33.3802 |
66
+ | 3.2769 | 10.9994 | 4485 | 3.2342 | 8.3037 | 33.303 |
67
+ | 3.2777 | 12.0 | 4893 | 3.2284 | 8.0674 | 33.3967 |
68
+ | 3.2476 | 12.9982 | 5300 | 3.2226 | 8.2883 | 33.8154 |
69
+ | 3.2611 | 13.9988 | 5708 | 3.2189 | 8.3537 | 34.0413 |
70
+ | 3.2511 | 14.9994 | 6116 | 3.2159 | 8.1365 | 34.5014 |
71
+ | 3.2437 | 16.0 | 6524 | 3.2140 | 8.3549 | 34.0606 |
72
+ | 3.2437 | 16.9982 | 6931 | 3.2131 | 8.2507 | 34.303 |
73
+ | 3.2498 | 17.9988 | 7339 | 3.2116 | 8.2928 | 33.9945 |
74
+ | 3.2341 | 18.9994 | 7747 | 3.2105 | 8.337 | 33.7052 |
75
+ | 3.2403 | 20.0 | 8155 | 3.2098 | 8.3179 | 34.3526 |
76
+ | 3.2229 | 20.9982 | 8562 | 3.2094 | 8.3848 | 34.2039 |
77
+ | 3.2229 | 21.9988 | 8970 | 3.2090 | 8.2042 | 34.6529 |
78
+ | 3.2379 | 22.9994 | 9378 | 3.2086 | 8.4227 | 34.0275 |
79
+ | 3.2257 | 24.0 | 9786 | 3.2082 | 8.3515 | 34.3306 |
80
+ | 3.2526 | 24.9982 | 10193 | 3.2085 | 8.4089 | 34.4986 |
81
+ | 3.2206 | 25.9988 | 10601 | 3.2082 | 8.476 | 34.6226 |
82
+ | 3.2288 | 26.9994 | 11009 | 3.2083 | 8.4452 | 33.697 |
83
+ | 3.2288 | 28.0 | 11417 | 3.2080 | 8.29 | 34.0331 |
84
+ | 3.2251 | 28.9982 | 11824 | 3.2080 | 8.35 | 34.2948 |
85
+ | 3.2302 | 29.9988 | 12232 | 3.2078 | 8.4408 | 33.416 |
86
+ | 3.21 | 30.9994 | 12640 | 3.2079 | 8.2934 | 34.0854 |
87
+ | 3.2271 | 32.0 | 13048 | 3.2079 | 8.4573 | 33.3912 |
88
+ | 3.2271 | 32.9982 | 13455 | 3.2078 | 8.4055 | 34.2452 |
89
+ | 3.2428 | 33.9988 | 13863 | 3.2079 | 8.5107 | 34.5152 |
90
+ | 3.2303 | 34.9994 | 14271 | 3.2080 | 8.3734 | 34.2562 |
91
+ | 3.2129 | 36.0 | 14679 | 3.2079 | 8.3193 | 34.4628 |
92
+ | 3.2119 | 36.9982 | 15086 | 3.2082 | 8.4122 | 34.2121 |
93
+ | 3.2119 | 37.9988 | 15494 | 3.2078 | 8.3585 | 33.8843 |
94
+ | 3.2445 | 38.9994 | 15902 | 3.2079 | 8.3968 | 34.6722 |
95
+ | 3.2356 | 39.9264 | 16280 | 3.2078 | 8.3292 | 34.4959 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.40.2
101
+ - Pytorch 2.2.1+cu121
102
+ - Datasets 2.19.1
103
+ - Tokenizers 0.19.1
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 61246
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 61246,
9
+ "eos_token_id": 25897,
10
+ "forced_eos_token_id": 25897,
11
+ "max_length": 512,
12
+ "num_beams": 4,
13
+ "pad_token_id": 61246,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.40.2"
16
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93639c5a09f839e5ce65537e945d94db9c51b7c4edce56660fc14b5a1111c7ab
3
  size 478300886
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c33bf0b0d2a3310bef6c28ffc9cb33de060cdb550ccfc8d7313fe9de8f3659a1
3
  size 478300886