minhngca commited on
Commit
30efbc4
1 Parent(s): dddcd1a

minhngca_lab2_effcient

Browse files
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: Helsinki-NLP/opus-mt-en-fr
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - kde4
8
+ metrics:
9
+ - bleu
10
+ model-index:
11
+ - name: lab2_efficient
12
+ results:
13
+ - task:
14
+ name: Sequence-to-sequence Language Modeling
15
+ type: text2text-generation
16
+ dataset:
17
+ name: kde4
18
+ type: kde4
19
+ config: en-fr
20
+ split: train
21
+ args: en-fr
22
+ metrics:
23
+ - name: Bleu
24
+ type: bleu
25
+ value: 50.31117150239878
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # lab2_efficient
32
+
33
+ This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-fr](https://huggingface.co/Helsinki-NLP/opus-mt-en-fr) on the kde4 dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.9594
36
+ - Bleu: 50.3112
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 2e-05
56
+ - train_batch_size: 64
57
+ - eval_batch_size: 64
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 2
60
+ - total_train_batch_size: 128
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: cosine
63
+ - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 2
65
+ - mixed_precision_training: Native AMP
66
+
67
+ ### Training results
68
+
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.38.1
74
+ - Pytorch 2.1.0+cu121
75
+ - Datasets 2.17.1
76
+ - Tokenizers 0.15.2
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": "4.38.1",
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": "4.38.1"
16
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4d85f2125bd0ab4b8dbb093e4acf2a6f0892a286953f281efe1e481a4f4a650
3
+ size 298705768
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 sha256:6aa35fcdb0da1c1c6495ba0d2bc2b8b38a5a0c023c4431985f2684a9cadaf0d4
3
+ size 5112
vocab.json ADDED
The diff for this file is too large to render. See raw diff