spokkazo commited on
Commit
8c66192
1 Parent(s): de1ebd2

Training complete

Browse files
Files changed (3) hide show
  1. README.md +74 -0
  2. generation_config.json +16 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: Helsinki-NLP/opus-mt-en-es
4
+ tags:
5
+ - translation
6
+ - generated_from_trainer
7
+ datasets:
8
+ - kde4
9
+ metrics:
10
+ - bleu
11
+ model-index:
12
+ - name: marian-finetuned-kde4-en-to-fr
13
+ results:
14
+ - task:
15
+ name: Sequence-to-sequence Language Modeling
16
+ type: text2text-generation
17
+ dataset:
18
+ name: kde4
19
+ type: kde4
20
+ config: en-es
21
+ split: train
22
+ args: en-es
23
+ metrics:
24
+ - name: Bleu
25
+ type: bleu
26
+ value: 54.18962460925094
27
+ ---
28
+
29
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
+ should probably proofread and complete it, then remove this comment. -->
31
+
32
+ # marian-finetuned-kde4-en-to-fr
33
+
34
+ This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-es](https://huggingface.co/Helsinki-NLP/opus-mt-en-es) on the kde4 dataset.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 0.7669
37
+ - Bleu: 54.1896
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: 32
58
+ - eval_batch_size: 64
59
+ - seed: 42
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - num_epochs: 3
63
+ - mixed_precision_training: Native AMP
64
+
65
+ ### Training results
66
+
67
+
68
+
69
+ ### Framework versions
70
+
71
+ - Transformers 4.35.2
72
+ - Pytorch 2.1.1+cu121
73
+ - Datasets 2.15.0
74
+ - Tokenizers 0.15.0
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 65000
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 65000,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 4,
13
+ "pad_token_id": 65000,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.35.2"
16
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b340e5c4115d3f66d290c477cc355213b3265de49090a96c68d28042acc33b7b
3
  size 309965092
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc582622eeb3c0732a2a7a6bb15fe72ab2e5c75a94f959575ca467f169fc5367
3
  size 309965092