Commit
•
6a17883
1
Parent(s):
ee0bba9
Training in progress, epoch 1
Browse files- README.md +56 -0
- config.json +62 -0
- generation_config.json +16 -0
- model.safetensors +3 -0
- runs/May16_07-15-17_d38779830b64/events.out.tfevents.1715843768.d38779830b64.487.0 +3 -0
- runs/May16_07-40-35_d38779830b64/events.out.tfevents.1715845243.d38779830b64.487.1 +3 -0
- runs/May16_07-57-42_d38779830b64/events.out.tfevents.1715846269.d38779830b64.487.2 +3 -0
- runs/May16_09-11-14_d38779830b64/events.out.tfevents.1715850678.d38779830b64.30874.0 +3 -0
- source.spm +0 -0
- special_tokens_map.json +5 -0
- target.spm +0 -0
- tokenizer_config.json +39 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: Helsinki-NLP/opus-mt-fr-en
|
4 |
+
tags:
|
5 |
+
- translation
|
6 |
+
- generated_from_trainer
|
7 |
+
datasets:
|
8 |
+
- kde4
|
9 |
+
model-index:
|
10 |
+
- name: Wordfly-eng-fr
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# Wordfly-eng-fr
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-fr-en](https://huggingface.co/Helsinki-NLP/opus-mt-fr-en) on the kde4 dataset.
|
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: 32
|
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: 3
|
45 |
+
- mixed_precision_training: Native AMP
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
|
50 |
+
|
51 |
+
### Framework versions
|
52 |
+
|
53 |
+
- Transformers 4.40.2
|
54 |
+
- Pytorch 2.2.1+cu121
|
55 |
+
- Datasets 2.19.1
|
56 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Helsinki-NLP/opus-mt-en-fr",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "swish",
|
6 |
+
"add_bias_logits": false,
|
7 |
+
"add_final_layer_norm": false,
|
8 |
+
"architectures": [
|
9 |
+
"MarianMTModel"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.0,
|
12 |
+
"bad_words_ids": [
|
13 |
+
[
|
14 |
+
59513
|
15 |
+
]
|
16 |
+
],
|
17 |
+
"bos_token_id": 0,
|
18 |
+
"classif_dropout": 0.0,
|
19 |
+
"classifier_dropout": 0.0,
|
20 |
+
"d_model": 512,
|
21 |
+
"decoder_attention_heads": 8,
|
22 |
+
"decoder_ffn_dim": 2048,
|
23 |
+
"decoder_layerdrop": 0.0,
|
24 |
+
"decoder_layers": 6,
|
25 |
+
"decoder_start_token_id": 59513,
|
26 |
+
"decoder_vocab_size": 59514,
|
27 |
+
"dropout": 0.1,
|
28 |
+
"encoder_attention_heads": 8,
|
29 |
+
"encoder_ffn_dim": 2048,
|
30 |
+
"encoder_layerdrop": 0.0,
|
31 |
+
"encoder_layers": 6,
|
32 |
+
"eos_token_id": 0,
|
33 |
+
"forced_eos_token_id": 0,
|
34 |
+
"gradient_checkpointing": false,
|
35 |
+
"id2label": {
|
36 |
+
"0": "LABEL_0",
|
37 |
+
"1": "LABEL_1",
|
38 |
+
"2": "LABEL_2"
|
39 |
+
},
|
40 |
+
"init_std": 0.02,
|
41 |
+
"is_encoder_decoder": true,
|
42 |
+
"label2id": {
|
43 |
+
"LABEL_0": 0,
|
44 |
+
"LABEL_1": 1,
|
45 |
+
"LABEL_2": 2
|
46 |
+
},
|
47 |
+
"max_length": 512,
|
48 |
+
"max_position_embeddings": 512,
|
49 |
+
"model_type": "marian",
|
50 |
+
"normalize_before": false,
|
51 |
+
"normalize_embedding": false,
|
52 |
+
"num_beams": 4,
|
53 |
+
"num_hidden_layers": 6,
|
54 |
+
"pad_token_id": 59513,
|
55 |
+
"scale_embedding": true,
|
56 |
+
"share_encoder_decoder_embeddings": true,
|
57 |
+
"static_position_embeddings": true,
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.40.2",
|
60 |
+
"use_cache": true,
|
61 |
+
"vocab_size": 59514
|
62 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bad_words_ids": [
|
3 |
+
[
|
4 |
+
59513
|
5 |
+
]
|
6 |
+
],
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"decoder_start_token_id": 59513,
|
9 |
+
"eos_token_id": 0,
|
10 |
+
"forced_eos_token_id": 0,
|
11 |
+
"max_length": 512,
|
12 |
+
"num_beams": 4,
|
13 |
+
"pad_token_id": 59513,
|
14 |
+
"renormalize_logits": true,
|
15 |
+
"transformers_version": "4.40.2"
|
16 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be86731d69bee60d17d277399777c430c97c405aca05c3329b7c8978aac0edf9
|
3 |
+
size 298705768
|
runs/May16_07-15-17_d38779830b64/events.out.tfevents.1715843768.d38779830b64.487.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d8766a7b5c2294753b7ff9ba87e9020acbc1484b2fdbc9bd9de1cd284ba623a
|
3 |
+
size 8040
|
runs/May16_07-40-35_d38779830b64/events.out.tfevents.1715845243.d38779830b64.487.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84aa28a37fc0f026b0a7fe1d3745f18397c67b6d2deb036bfbe82fb749d1cd5d
|
3 |
+
size 5815
|
runs/May16_07-57-42_d38779830b64/events.out.tfevents.1715846269.d38779830b64.487.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:342d97cc9dde9f7108caa67986df70e0367ddf3457632a7c7626c78568ad75ca
|
3 |
+
size 12471
|
runs/May16_09-11-14_d38779830b64/events.out.tfevents.1715850678.d38779830b64.30874.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8bc0ced594b009bbd0f8696a18a6074fbd1e41ff6e99dc81a9b796544b17929
|
3 |
+
size 7686
|
source.spm
ADDED
Binary file (778 kB). View file
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
target.spm
ADDED
Binary file (802 kB). View file
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "</s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<unk>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"59513": {
|
20 |
+
"content": "<pad>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"clean_up_tokenization_spaces": true,
|
29 |
+
"eos_token": "</s>",
|
30 |
+
"model_max_length": 512,
|
31 |
+
"pad_token": "<pad>",
|
32 |
+
"return_tensors": "pt",
|
33 |
+
"separate_vocabs": false,
|
34 |
+
"source_lang": "en",
|
35 |
+
"sp_model_kwargs": {},
|
36 |
+
"target_lang": "fr",
|
37 |
+
"tokenizer_class": "MarianTokenizer",
|
38 |
+
"unk_token": "<unk>"
|
39 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8011c04688804cf436b55c238937fc08cb63ef17c82193ded656bfcc41bdd68
|
3 |
+
size 5176
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|