Hugging Face's logo

mptrigo
/
run1

Transformers
PyTorch
TensorBoard
marian
text2text-generation
Generated from Trainer
Model card Files
xet
Metrics Community
1
mptrigo commited on
Commit
af248e5
·
1 Parent(s): 40186a7

add model

Browse files
Files changed (16) hide show
  1. .gitignore +1 -0
  2. README.md +87 -0
  3. config.json +60 -0
  4. pytorch_model.bin +3 -0
  5. runs/Jan20_11-07-38_marina-GL65-9SEK/1642673321.4916918/events.out.tfevents.1642673321.marina-GL65-9SEK.21732.1 +3 -0
  6. runs/Jan20_11-07-38_marina-GL65-9SEK/1642673684.728874/events.out.tfevents.1642673684.marina-GL65-9SEK.21732.3 +3 -0
  7. runs/Jan20_11-07-38_marina-GL65-9SEK/events.out.tfevents.1642673321.marina-GL65-9SEK.21732.0 +3 -0
  8. runs/Jan20_11-07-38_marina-GL65-9SEK/events.out.tfevents.1642673684.marina-GL65-9SEK.21732.2 +3 -0
  9. runs/Jan20_11-16-32_marina-GL65-9SEK/1642673803.0359886/events.out.tfevents.1642673803.marina-GL65-9SEK.26448.1 +3 -0
  10. runs/Jan20_11-16-32_marina-GL65-9SEK/events.out.tfevents.1642673803.marina-GL65-9SEK.26448.0 +3 -0
  11. source.spm +0 -0
  12. special_tokens_map.json +1 -0
  13. target.spm +0 -0
  14. tokenizer_config.json +1 -0
  15. training_args.bin +3 -0
  16. vocab.json +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - bleu
7
+ model_index:
8
+ - name: run1
9
+ results:
10
+ - task:
11
+ name: Sequence-to-sequence Language Modeling
12
+ type: text2text-generation
13
+ metric:
14
+ name: Bleu
15
+ type: bleu
16
+ value: 8.4217
17
+ ---
18
+
19
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
20
+ should probably proofread and complete it, then remove this comment. -->
21
+
22
+ # run1
23
+
24
+ This model is a fine-tuned version of [Helsinki-NLP/opus-mt-es-es](https://huggingface.co/Helsinki-NLP/opus-mt-es-es) on an unkown dataset.
25
+ It achieves the following results on the evaluation set:
26
+ - Loss: 3.1740
27
+ - Bleu: 8.4217
28
+ - Gen Len: 15.9457
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 2e-05
48
+ - train_batch_size: 4
49
+ - eval_batch_size: 4
50
+ - seed: 42
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: linear
53
+ - num_epochs: 20
54
+ - mixed_precision_training: Native AMP
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
59
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
60
+ | No log | 1.0 | 250 | 4.2342 | 0.8889 | 83.4022 |
61
+ | 4.6818 | 2.0 | 500 | 3.7009 | 4.1671 | 35.587 |
62
+ | 4.6818 | 3.0 | 750 | 3.4737 | 7.6414 | 23.9674 |
63
+ | 3.4911 | 4.0 | 1000 | 3.3713 | 7.7512 | 18.6957 |
64
+ | 3.4911 | 5.0 | 1250 | 3.2689 | 8.0901 | 19.4674 |
65
+ | 3.0164 | 6.0 | 1500 | 3.2194 | 8.5708 | 25.0543 |
66
+ | 3.0164 | 7.0 | 1750 | 3.1853 | 9.5275 | 23.9239 |
67
+ | 2.6954 | 8.0 | 2000 | 3.1562 | 8.5635 | 18.9674 |
68
+ | 2.6954 | 9.0 | 2250 | 3.1564 | 8.2031 | 17.5978 |
69
+ | 2.4503 | 10.0 | 2500 | 3.1314 | 8.5638 | 18.1522 |
70
+ | 2.4503 | 11.0 | 2750 | 3.1511 | 8.8428 | 17.913 |
71
+ | 2.2554 | 12.0 | 3000 | 3.1513 | 8.1244 | 17.0 |
72
+ | 2.2554 | 13.0 | 3250 | 3.1664 | 8.0157 | 16.2717 |
73
+ | 2.1202 | 14.0 | 3500 | 3.1656 | 8.7758 | 16.6087 |
74
+ | 2.1202 | 15.0 | 3750 | 3.1550 | 8.4637 | 16.4565 |
75
+ | 2.0082 | 16.0 | 4000 | 3.1702 | 8.2488 | 15.8587 |
76
+ | 2.0082 | 17.0 | 4250 | 3.1725 | 8.609 | 16.3043 |
77
+ | 1.9274 | 18.0 | 4500 | 3.1750 | 8.4476 | 15.8043 |
78
+ | 1.9274 | 19.0 | 4750 | 3.1734 | 8.4753 | 16.5543 |
79
+ | 1.888 | 20.0 | 5000 | 3.1740 | 8.4217 | 15.9457 |
80
+
81
+
82
+ ### Framework versions
83
+
84
+ - Transformers 4.9.2
85
+ - Pytorch 1.9.0+cu102
86
+ - Datasets 1.11.1.dev0
87
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-es-es",
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
+ 33252
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": 33252,
26
+ "dropout": 0.1,
27
+ "encoder_attention_heads": 8,
28
+ "encoder_ffn_dim": 2048,
29
+ "encoder_layerdrop": 0.0,
30
+ "encoder_layers": 6,
31
+ "eos_token_id": 0,
32
+ "forced_eos_token_id": 0,
33
+ "gradient_checkpointing": false,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1",
37
+ "2": "LABEL_2"
38
+ },
39
+ "init_std": 0.02,
40
+ "is_encoder_decoder": true,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1,
44
+ "LABEL_2": 2
45
+ },
46
+ "max_length": 512,
47
+ "max_position_embeddings": 512,
48
+ "model_type": "marian",
49
+ "normalize_before": false,
50
+ "normalize_embedding": false,
51
+ "num_beams": 4,
52
+ "num_hidden_layers": 6,
53
+ "pad_token_id": 33252,
54
+ "scale_embedding": true,
55
+ "static_position_embeddings": true,
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.9.2",
58
+ "use_cache": true,
59
+ "vocab_size": 33253
60
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc97b326c88fa2058a82da19947445f2e11e4351d7e232c204c4cf933ee8b5e1
3
+ size 244873605
runs/Jan20_11-07-38_marina-GL65-9SEK/1642673321.4916918/events.out.tfevents.1642673321.marina-GL65-9SEK.21732.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aed3fa4f03185525756bb7dec3ef72f39f4c6817bbaa4a47becc8e5b69f2e70
3
+ size 4334
runs/Jan20_11-07-38_marina-GL65-9SEK/1642673684.728874/events.out.tfevents.1642673684.marina-GL65-9SEK.21732.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:921f20d0ef925c3f1883df52b43cc7dd13d86dd5baeb6dd98c721f909a951483
3
+ size 4334
runs/Jan20_11-07-38_marina-GL65-9SEK/events.out.tfevents.1642673321.marina-GL65-9SEK.21732.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f048e4c50b09ec772887d35a4cf636bc24e03300307ed38154b53988e5ac747c
3
+ size 3722
runs/Jan20_11-07-38_marina-GL65-9SEK/events.out.tfevents.1642673684.marina-GL65-9SEK.21732.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6c6c0bef0aa08901b23b055d77bc5aa28b0d520c4d532b206c8f6ca057e1139
3
+ size 3722
runs/Jan20_11-16-32_marina-GL65-9SEK/1642673803.0359886/events.out.tfevents.1642673803.marina-GL65-9SEK.26448.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:859a848cf2ab42e7cc10a901f577581fcf00bcc5c7df4150d8a5a0dd76e4f418
3
+ size 4334
runs/Jan20_11-16-32_marina-GL65-9SEK/events.out.tfevents.1642673803.marina-GL65-9SEK.26448.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a894d6a790c68d4c7219880b0661dbd7aa909c8662db7511b18147d70c1cc861
3
+ size 13046
source.spm ADDED
Binary file (813 kB). View file
 
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
target.spm ADDED
Binary file (813 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"source_lang": "es", "target_lang": "es", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "Helsinki-NLP/opus-mt-es-es", "tokenizer_class": "MarianTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:138cf9a6bf58ea4ea04e1e796016b7634957ff2c5f25b7805310b795179d5435
3
+ size 2735
vocab.json ADDED
The diff for this file is too large to render. See raw diff