Hugging Face's logo

kalese
/
opus-mt-en-bkm

Text2Text Generation
Transformers
TensorBoard
Safetensors
marian
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
kalese commited on
Commit
13849ac
•
1 Parent(s): afcf560

End of training

Browse files
Files changed (4) hide show
  1. README.md +100 -0
  2. generation_config.json +16 -0
  3. model.safetensors +1 -1
  4. runs/Apr03_10-39-07_8eb53fe594f9/events.out.tfevents.1712140842.8eb53fe594f9.445.0 +2 -2
README.md ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: Helsinki-NLP/opus-mt-en-ro
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - arrow
8
+ metrics:
9
+ - bleu
10
+ model-index:
11
+ - name: opus-mt-en-bkm
12
+ results:
13
+ - task:
14
+ name: Sequence-to-sequence Language Modeling
15
+ type: text2text-generation
16
+ dataset:
17
+ name: arrow
18
+ type: arrow
19
+ config: default
20
+ split: train
21
+ args: default
22
+ metrics:
23
+ - name: Bleu
24
+ type: bleu
25
+ value: 14.5684
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # opus-mt-en-bkm
32
+
33
+ This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ro](https://huggingface.co/Helsinki-NLP/opus-mt-en-ro) on the arrow dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 1.1597
36
+ - Bleu: 14.5684
37
+ - Gen Len: 58.4294
38
+
39
+ ## Model description
40
+
41
+ More information needed
42
+
43
+ ## Intended uses & limitations
44
+
45
+ More information needed
46
+
47
+ ## Training and evaluation data
48
+
49
+ More information needed
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 2e-05
57
+ - train_batch_size: 16
58
+ - eval_batch_size: 16
59
+ - seed: 42
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - num_epochs: 25
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
67
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
68
+ | 3.3983 | 1.0 | 974 | 1.9251 | 3.7894 | 60.1579 |
69
+ | 1.9429 | 2.0 | 1948 | 1.6720 | 5.7083 | 58.6443 |
70
+ | 1.7118 | 3.0 | 2922 | 1.5389 | 7.1977 | 58.8536 |
71
+ | 1.5647 | 4.0 | 3896 | 1.4484 | 8.4631 | 57.9068 |
72
+ | 1.4611 | 5.0 | 4870 | 1.3836 | 9.5314 | 59.3106 |
73
+ | 1.3735 | 6.0 | 5844 | 1.3357 | 10.1879 | 59.5501 |
74
+ | 1.3078 | 7.0 | 6818 | 1.3014 | 10.9172 | 59.4968 |
75
+ | 1.245 | 8.0 | 7792 | 1.2737 | 11.445 | 59.585 |
76
+ | 1.2048 | 9.0 | 8766 | 1.2485 | 11.9346 | 58.3275 |
77
+ | 1.1648 | 10.0 | 9740 | 1.2298 | 12.3049 | 58.7768 |
78
+ | 1.1272 | 11.0 | 10714 | 1.2176 | 12.7287 | 58.1549 |
79
+ | 1.086 | 12.0 | 11688 | 1.2043 | 13.0962 | 59.2217 |
80
+ | 1.0595 | 13.0 | 12662 | 1.1973 | 13.3375 | 58.6736 |
81
+ | 1.0343 | 14.0 | 13636 | 1.1844 | 13.3963 | 58.2763 |
82
+ | 1.0174 | 15.0 | 14610 | 1.1797 | 13.7067 | 58.1738 |
83
+ | 0.9923 | 16.0 | 15584 | 1.1757 | 13.9467 | 59.3246 |
84
+ | 0.9703 | 17.0 | 16558 | 1.1704 | 14.1023 | 58.9813 |
85
+ | 0.9589 | 18.0 | 17532 | 1.1663 | 14.2842 | 58.401 |
86
+ | 0.9472 | 19.0 | 18506 | 1.1662 | 14.2109 | 58.4796 |
87
+ | 0.9262 | 20.0 | 19480 | 1.1635 | 14.3872 | 58.1601 |
88
+ | 0.9147 | 21.0 | 20454 | 1.1606 | 14.4983 | 58.7417 |
89
+ | 0.9162 | 22.0 | 21428 | 1.1630 | 14.5229 | 58.4345 |
90
+ | 0.9012 | 23.0 | 22402 | 1.1607 | 14.6204 | 58.0767 |
91
+ | 0.899 | 24.0 | 23376 | 1.1600 | 14.5681 | 58.4357 |
92
+ | 0.8934 | 25.0 | 24350 | 1.1597 | 14.5684 | 58.4294 |
93
+
94
+
95
+ ### Framework versions
96
+
97
+ - Transformers 4.39.3
98
+ - Pytorch 2.2.1+cu121
99
+ - Datasets 2.18.0
100
+ - Tokenizers 0.15.2
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 59542
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 59542,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 4,
13
+ "pad_token_id": 59542,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.39.3"
16
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c25676f4df2cfe0665556f528fbed4104ceb154835409bf65c72240fec0e4c83
3
  size 298765276
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9b409101e277016b808ef0bde1a53e41c18c1ab6752752267ad0e6537dca2ca
3
  size 298765276
runs/Apr03_10-39-07_8eb53fe594f9/events.out.tfevents.1712140842.8eb53fe594f9.445.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:941ff14c806a6721569d954a829bdee2248006233f601ce13b0120a8cdfc4a1b
3
- size 24597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8404e7c2dda4d5a228cc3fc650cb1c458994d123931c88e5ffd7387a1739309b
3
+ size 25334