beanslmao commited on
Commit
8e5fd1c
1 Parent(s): 7e18b8a

End of training

Browse files
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: Helsinki-NLP/opus-mt-en-es
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - bleu
8
+ model-index:
9
+ - name: hensinki-en-es-finetuned-english-to-spanish-tateoba
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # hensinki-en-es-finetuned-english-to-spanish-tateoba
17
+
18
+ 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 None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.5236
21
+ - Bleu: 58.629
22
+ - Gen Len: 8.6642
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 2e-05
42
+ - train_batch_size: 16
43
+ - eval_batch_size: 16
44
+ - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - num_epochs: 5
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
53
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
54
+ | 0.5416 | 1.0 | 7069 | 0.5150 | 58.2349 | 8.6272 |
55
+ | 0.457 | 2.0 | 14138 | 0.5116 | 58.5559 | 8.6372 |
56
+ | 0.4021 | 3.0 | 21207 | 0.5172 | 58.7017 | 8.6416 |
57
+ | 0.3477 | 4.0 | 28276 | 0.5202 | 58.6269 | 8.6579 |
58
+ | 0.3254 | 5.0 | 35345 | 0.5236 | 58.629 | 8.6642 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - Transformers 4.38.2
64
+ - Pytorch 2.1.0+cu121
65
+ - Datasets 2.18.0
66
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-en-es",
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
+ "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
+ "extra_pos_embeddings": 65001,
33
+ "force_bos_token_to_be_generated": false,
34
+ "forced_eos_token_id": 0,
35
+ "gradient_checkpointing": false,
36
+ "id2label": {
37
+ "0": "LABEL_0",
38
+ "1": "LABEL_1",
39
+ "2": "LABEL_2"
40
+ },
41
+ "init_std": 0.02,
42
+ "is_encoder_decoder": true,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1,
46
+ "LABEL_2": 2
47
+ },
48
+ "max_length": 512,
49
+ "max_position_embeddings": 512,
50
+ "model_type": "marian",
51
+ "normalize_before": false,
52
+ "normalize_embedding": false,
53
+ "num_beams": 4,
54
+ "num_hidden_layers": 6,
55
+ "pad_token_id": 65000,
56
+ "scale_embedding": true,
57
+ "share_encoder_decoder_embeddings": true,
58
+ "static_position_embeddings": true,
59
+ "torch_dtype": "float32",
60
+ "transformers_version": "4.38.2",
61
+ "use_cache": true,
62
+ "vocab_size": 65001
63
+ }
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": "4.38.2"
16
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7219c09bf68607d49289094fbb41fe8411dbf9d97151ff08483ca02f1e2c2ba0
3
+ size 309965092
source.spm ADDED
Binary file (802 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 (826 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "65000": {
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
+ "separate_vocabs": false,
33
+ "source_lang": "eng",
34
+ "sp_model_kwargs": {},
35
+ "target_lang": "spa",
36
+ "tokenizer_class": "MarianTokenizer",
37
+ "unk_token": "<unk>"
38
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:282c80d64627102eac88b0a58eaccded969965e4d4c646c653a174ff13c8a3ab
3
+ size 5112
vocab.json ADDED
The diff for this file is too large to render. See raw diff