Training in progress epoch 0
Browse files- .gitattributes +2 -0
- README.md +55 -0
- config.json +63 -0
- logs/train/events.out.tfevents.1652784472.3f01de8560c6.72.0.v2 +3 -0
- logs/validation/events.out.tfevents.1652794721.3f01de8560c6.72.1.v2 +3 -0
- source.spm +3 -0
- special_tokens_map.json +1 -0
- target.spm +3 -0
- tf_model.h5 +3 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -25,3 +25,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
source.spm filter=lfs diff=lfs merge=lfs -text
|
29 |
+
target.spm filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_keras_callback
|
5 |
+
model-index:
|
6 |
+
- name: adeebt/opus-mt-en-ROMANCE-finetuned-en-to-ro
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
11 |
+
probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# adeebt/opus-mt-en-ROMANCE-finetuned-en-to-ro
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ROMANCE](https://huggingface.co/Helsinki-NLP/opus-mt-en-ROMANCE) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 0.7147
|
18 |
+
- Validation Loss: 1.2474
|
19 |
+
- Train Bleu: 26.0422
|
20 |
+
- Train Gen Len: 51.6875
|
21 |
+
- Epoch: 0
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
41 |
+
- training_precision: float32
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
| Train Loss | Validation Loss | Train Bleu | Train Gen Len | Epoch |
|
46 |
+
|:----------:|:---------------:|:----------:|:-------------:|:-----:|
|
47 |
+
| 0.7147 | 1.2474 | 26.0422 | 51.6875 | 0 |
|
48 |
+
|
49 |
+
|
50 |
+
### Framework versions
|
51 |
+
|
52 |
+
- Transformers 4.19.2
|
53 |
+
- TensorFlow 2.8.0
|
54 |
+
- Datasets 2.2.1
|
55 |
+
- Tokenizers 0.12.1
|
config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Helsinki-NLP/opus-mt-en-ROMANCE",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "swish",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"MarianMTModel"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"bad_words_ids": [
|
12 |
+
[
|
13 |
+
65000
|
14 |
+
]
|
15 |
+
],
|
16 |
+
"bos_token_id": 0,
|
17 |
+
"classif_dropout": 0.0,
|
18 |
+
"classifier_dropout": 0.0,
|
19 |
+
"d_model": 512,
|
20 |
+
"decoder_attention_heads": 8,
|
21 |
+
"decoder_ffn_dim": 2048,
|
22 |
+
"decoder_layerdrop": 0.0,
|
23 |
+
"decoder_layers": 6,
|
24 |
+
"decoder_start_token_id": 65000,
|
25 |
+
"decoder_vocab_size": 65001,
|
26 |
+
"do_blenderbot_90_layernorm": false,
|
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 |
+
"extra_pos_embeddings": 0,
|
34 |
+
"force_bos_token_to_be_generated": false,
|
35 |
+
"forced_eos_token_id": 0,
|
36 |
+
"gradient_checkpointing": false,
|
37 |
+
"id2label": {
|
38 |
+
"0": "LABEL_0",
|
39 |
+
"1": "LABEL_1",
|
40 |
+
"2": "LABEL_2"
|
41 |
+
},
|
42 |
+
"init_std": 0.02,
|
43 |
+
"is_encoder_decoder": true,
|
44 |
+
"label2id": {
|
45 |
+
"LABEL_0": 0,
|
46 |
+
"LABEL_1": 1,
|
47 |
+
"LABEL_2": 2
|
48 |
+
},
|
49 |
+
"max_length": 512,
|
50 |
+
"max_position_embeddings": 512,
|
51 |
+
"model_type": "marian",
|
52 |
+
"normalize_before": false,
|
53 |
+
"normalize_embedding": false,
|
54 |
+
"num_beams": 4,
|
55 |
+
"num_hidden_layers": 6,
|
56 |
+
"pad_token_id": 65000,
|
57 |
+
"scale_embedding": true,
|
58 |
+
"share_encoder_decoder_embeddings": true,
|
59 |
+
"static_position_embeddings": true,
|
60 |
+
"transformers_version": "4.19.2",
|
61 |
+
"use_cache": true,
|
62 |
+
"vocab_size": 65001
|
63 |
+
}
|
logs/train/events.out.tfevents.1652784472.3f01de8560c6.72.0.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5555762e789dc27d97ff885e68892802ad78f6582050a3d0db50a98771ae251e
|
3 |
+
size 3377400
|
logs/validation/events.out.tfevents.1652794721.3f01de8560c6.72.1.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bfe8939466c1eee974073db0b478438efdcdb6d7cdd0920bfd34a253cdf0fb9
|
3 |
+
size 195
|
source.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1f89e7b05828846baf19109a61029a36838f1c4f3defc218e6aee0ee2787864
|
3 |
+
size 779155
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
target.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e54632fe5ce5ef4108a827daccc121b7cd4ea589fbb4bd856b8dd06086166b2
|
3 |
+
size 799001
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8039f9f07e16b907c46c1224600bac32554a361ba39c9b20b79bd0f0ead12c99
|
3 |
+
size 312319188
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"source_lang": "en", "target_lang": "fr+fr_BE+fr_CA+fr_FR+wa+frp+oc+ca+rm+lld+fur+lij+lmo+es+es_AR+es_CL+es_CO+es_CR+es_DO+es_EC+es_ES+es_GT+es_HN+es_MX+es_NI+es_PA+es_PE+es_PR+es_SV+es_UY+es_VE+pt+pt_br+pt_BR+pt_PT+gl+lad+an+mwl+it+it_IT+co+nap+scn+vec+sc+ro+la", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "separate_vocabs": false, "special_tokens_map_file": null, "name_or_path": "Helsinki-NLP/opus-mt-en-ROMANCE", "tokenizer_class": "MarianTokenizer"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|