dadada commited on
Commit
e6c208e
1 Parent(s): 357fef7
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - bleu
7
+ model_index:
8
+ - name: opus-mt-zh-en-ep1-renri-zh-to-en
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: 18.2579
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
+ # opus-mt-zh-en-ep1-renri-zh-to-en
23
+
24
+ This model is a fine-tuned version of [Helsinki-NLP/opus-mt-zh-en](https://huggingface.co/Helsinki-NLP/opus-mt-zh-en) on an unkown dataset.
25
+ It achieves the following results on the evaluation set:
26
+ - Loss: 2.2192
27
+ - Bleu: 18.2579
28
+ - Gen Len: 28.4817
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: 1e-05
48
+ - train_batch_size: 32
49
+ - eval_batch_size: 32
50
+ - seed: 42
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: linear
53
+ - num_epochs: 1
54
+ - mixed_precision_training: Native AMP
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
59
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
60
+ | 2.2194 | 1.0 | 59472 | 2.2192 | 18.2579 | 28.4817 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - Transformers 4.9.2
66
+ - Pytorch 1.9.0+cu102
67
+ - Datasets 1.11.0
68
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-zh-en",
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
+ "dropout": 0.1,
26
+ "encoder_attention_heads": 8,
27
+ "encoder_ffn_dim": 2048,
28
+ "encoder_layerdrop": 0.0,
29
+ "encoder_layers": 6,
30
+ "eos_token_id": 0,
31
+ "extra_pos_embeddings": 65001,
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": 6,
52
+ "num_hidden_layers": 6,
53
+ "pad_token_id": 65000,
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": 65001
60
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:269d5b8de62299bb739714bc5baf9b0d5561440489ffb64271b5a6af0e06d0f6
3
+ size 310020485
runs/Aug22_02-46-14_7e49732c97b7/1629600384.3153653/events.out.tfevents.1629600384.7e49732c97b7.180.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f7e365f3352824a8f307e4fbed29cead31dc0d5fdcfec4789cd1fa1b8a20bc3
3
+ size 4334
runs/Aug22_02-46-14_7e49732c97b7/events.out.tfevents.1629600384.7e49732c97b7.180.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cd0335d8a71caa9eab0516d0d321806d1c836afaa71ada43339c475ada6573c
3
+ size 23263
source.spm ADDED
Binary file (805 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 (807 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"source_lang": "zho", "target_lang": "eng", "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-zh-en", "tokenizer_class": "MarianTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cda08e246ecd52fed150b12326f832a962a42a7a8db7535c4020401c5976b7b2
3
+ size 2735
vocab.json ADDED
The diff for this file is too large to render. See raw diff