Hugging Face's logo

FiveC
/
TADA-checkpoints

Transformers
Safetensors
checkpoint-archive
Model card Files
xet
 Community
FiveC commited on
Commit
918e9ee
·
verified ·
1 Parent(s): e92ed73

Archive 9 reviewed checkpoints

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +9 -0
  2. checkpoints/za-zh-rd-za/.gitattributes +36 -0
  3. checkpoints/za-zh-rd-za/README.md +63 -0
  4. checkpoints/za-zh-rd-za/config.json +55 -0
  5. checkpoints/za-zh-rd-za/generation_config.json +37 -0
  6. checkpoints/za-zh-rd-za/model.safetensors +3 -0
  7. checkpoints/za-zh-rd-za/tokenizer.json +3 -0
  8. checkpoints/za-zh-rd-za/tokenizer_config.json +73 -0
  9. checkpoints/za-zh-rd-za/training_args.bin +3 -0
  10. checkpoints/za-zh-ri-za/.gitattributes +36 -0
  11. checkpoints/za-zh-ri-za/README.md +63 -0
  12. checkpoints/za-zh-ri-za/config.json +55 -0
  13. checkpoints/za-zh-ri-za/generation_config.json +37 -0
  14. checkpoints/za-zh-ri-za/model.safetensors +3 -0
  15. checkpoints/za-zh-ri-za/tokenizer.json +3 -0
  16. checkpoints/za-zh-ri-za/tokenizer_config.json +73 -0
  17. checkpoints/za-zh-ri-za/training_args.bin +3 -0
  18. checkpoints/za-zh-rs-za/.gitattributes +36 -0
  19. checkpoints/za-zh-rs-za/README.md +63 -0
  20. checkpoints/za-zh-rs-za/config.json +55 -0
  21. checkpoints/za-zh-rs-za/generation_config.json +37 -0
  22. checkpoints/za-zh-rs-za/model.safetensors +3 -0
  23. checkpoints/za-zh-rs-za/tokenizer.json +3 -0
  24. checkpoints/za-zh-rs-za/tokenizer_config.json +73 -0
  25. checkpoints/za-zh-rs-za/training_args.bin +3 -0
  26. checkpoints/za-zh-theme/.gitattributes +36 -0
  27. checkpoints/za-zh-theme/README.md +63 -0
  28. checkpoints/za-zh-theme/config.json +55 -0
  29. checkpoints/za-zh-theme/generation_config.json +37 -0
  30. checkpoints/za-zh-theme/model.safetensors +3 -0
  31. checkpoints/za-zh-theme/tokenizer.json +3 -0
  32. checkpoints/za-zh-theme/tokenizer_config.json +73 -0
  33. checkpoints/za-zh-theme/training_args.bin +3 -0
  34. checkpoints/za-zh-tssr-za/.gitattributes +36 -0
  35. checkpoints/za-zh-tssr-za/README.md +63 -0
  36. checkpoints/za-zh-tssr-za/config.json +55 -0
  37. checkpoints/za-zh-tssr-za/generation_config.json +37 -0
  38. checkpoints/za-zh-tssr-za/model.safetensors +3 -0
  39. checkpoints/za-zh-tssr-za/tokenizer.json +3 -0
  40. checkpoints/za-zh-tssr-za/tokenizer_config.json +73 -0
  41. checkpoints/za-zh-tssr-za/training_args.bin +3 -0
  42. checkpoints/za_zh_sc/.gitattributes +36 -0
  43. checkpoints/za_zh_sc/README.md +62 -0
  44. checkpoints/za_zh_sc/config.json +55 -0
  45. checkpoints/za_zh_sc/generation_config.json +37 -0
  46. checkpoints/za_zh_sc/model.safetensors +3 -0
  47. checkpoints/za_zh_sc/tokenizer.json +3 -0
  48. checkpoints/za_zh_sc/tokenizer_config.json +20 -0
  49. checkpoints/za_zh_sc/training_args.bin +3 -0
  50. checkpoints/zh-za-synonyms/.gitattributes +36 -0
.gitattributes CHANGED
@@ -50,3 +50,12 @@ checkpoints/za_CN-zh_CN/tokenizer.json filter=lfs diff=lfs merge=lfs -text
50
  checkpoints/za_CN-zh_CN-switchout/tokenizer.json filter=lfs diff=lfs merge=lfs -text
51
  checkpoints/zh_CN-za_CN-switchout/tokenizer.json filter=lfs diff=lfs merge=lfs -text
52
  checkpoints/za-zh-synonyms/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
50
  checkpoints/za_CN-zh_CN-switchout/tokenizer.json filter=lfs diff=lfs merge=lfs -text
51
  checkpoints/zh_CN-za_CN-switchout/tokenizer.json filter=lfs diff=lfs merge=lfs -text
52
  checkpoints/za-zh-synonyms/tokenizer.json filter=lfs diff=lfs merge=lfs -text
53
+ checkpoints/za-zh-theme/tokenizer.json filter=lfs diff=lfs merge=lfs -text
54
+ checkpoints/zh-za-theme/tokenizer.json filter=lfs diff=lfs merge=lfs -text
55
+ checkpoints/zh-za-synonyms/tokenizer.json filter=lfs diff=lfs merge=lfs -text
56
+ checkpoints/za-zh-rs-za/tokenizer.json filter=lfs diff=lfs merge=lfs -text
57
+ checkpoints/za-zh-rd-za/tokenizer.json filter=lfs diff=lfs merge=lfs -text
58
+ checkpoints/za-zh-ri-za/tokenizer.json filter=lfs diff=lfs merge=lfs -text
59
+ checkpoints/za_zh_sc/tokenizer.json filter=lfs diff=lfs merge=lfs -text
60
+ checkpoints/zh_za_sc/tokenizer.json filter=lfs diff=lfs merge=lfs -text
61
+ checkpoints/za-zh-tssr-za/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoints/za-zh-rd-za/.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoints/za-zh-rd-za/README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: facebook/mbart-large-50-many-to-many-mmt
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - sacrebleu
8
+ model-index:
9
+ - name: za-zh-rd-za
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
+ # za-zh-rd-za
17
+
18
+ This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 2.9474
21
+ - Sacrebleu: 4.4145
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
+ - learning_rate: 2e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 16
43
+ - seed: 42
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 3
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Sacrebleu |
52
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|
53
+ | 1.5105 | 1.0 | 1185 | 2.8866 | 2.3746 |
54
+ | 0.7597 | 2.0 | 2370 | 2.8919 | 2.4519 |
55
+ | 0.4917 | 3.0 | 3555 | 2.9474 | 4.4145 |
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - Transformers 5.0.0
61
+ - Pytorch 2.10.0+cu128
62
+ - Datasets 4.0.0
63
+ - Tokenizers 0.22.2
checkpoints/za-zh-rd-za/config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 3,
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "MBartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "dtype": "float32",
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "gradient_checkpointing": false,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1",
31
+ "2": "LABEL_2"
32
+ },
33
+ "init_std": 0.02,
34
+ "is_decoder": false,
35
+ "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_2": 2
40
+ },
41
+ "max_position_embeddings": 1024,
42
+ "model_type": "mbart",
43
+ "normalize_before": true,
44
+ "normalize_embedding": true,
45
+ "num_hidden_layers": 12,
46
+ "output_past": true,
47
+ "pad_token_id": 1,
48
+ "scale_embedding": true,
49
+ "static_position_embeddings": false,
50
+ "tie_word_embeddings": true,
51
+ "tokenizer_class": "MBart50Tokenizer",
52
+ "transformers_version": "5.0.0",
53
+ "use_cache": false,
54
+ "vocab_size": 250054
55
+ }
checkpoints/za-zh-rd-za/generation_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": false,
3
+ "assistant_confidence_threshold": 0.4,
4
+ "assistant_lookbehind": 10,
5
+ "bos_token_id": 0,
6
+ "decoder_start_token_id": 2,
7
+ "diversity_penalty": 0.0,
8
+ "do_sample": false,
9
+ "early_stopping": true,
10
+ "encoder_no_repeat_ngram_size": 0,
11
+ "encoder_repetition_penalty": 1.0,
12
+ "eos_token_id": 2,
13
+ "epsilon_cutoff": 0.0,
14
+ "eta_cutoff": 0.0,
15
+ "forced_eos_token_id": 2,
16
+ "length_penalty": 1.0,
17
+ "max_length": 200,
18
+ "min_length": 0,
19
+ "no_repeat_ngram_size": 0,
20
+ "num_assistant_tokens": 20,
21
+ "num_assistant_tokens_schedule": "constant",
22
+ "num_beam_groups": 1,
23
+ "num_beams": 5,
24
+ "num_return_sequences": 1,
25
+ "output_scores": false,
26
+ "pad_token_id": 1,
27
+ "remove_invalid_values": false,
28
+ "repetition_penalty": 1.0,
29
+ "return_dict_in_generate": false,
30
+ "target_lookbehind": 10,
31
+ "temperature": 1.0,
32
+ "top_k": 50,
33
+ "top_p": 1.0,
34
+ "transformers_version": "5.0.0",
35
+ "typical_p": 1.0,
36
+ "use_cache": true
37
+ }
checkpoints/za-zh-rd-za/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77ac7f2f1fffd22e6ddf23bddbfc9bb2f345f6825ac64ce966bb9b96e6d216a7
3
+ size 2444578688
checkpoints/za-zh-rd-za/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e673ccd228f195203d0ca7520a3e75b660426c6d0cda003d28f43d49069a48d8
3
+ size 16793291
checkpoints/za-zh-rd-za/tokenizer_config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "extra_special_tokens": [
7
+ "<s>",
8
+ "</s>",
9
+ "ar_AR",
10
+ "cs_CZ",
11
+ "de_DE",
12
+ "en_XX",
13
+ "es_XX",
14
+ "et_EE",
15
+ "fi_FI",
16
+ "fr_XX",
17
+ "gu_IN",
18
+ "hi_IN",
19
+ "it_IT",
20
+ "ja_XX",
21
+ "kk_KZ",
22
+ "ko_KR",
23
+ "lt_LT",
24
+ "lv_LV",
25
+ "my_MM",
26
+ "ne_NP",
27
+ "nl_XX",
28
+ "ro_RO",
29
+ "ru_RU",
30
+ "si_LK",
31
+ "tr_TR",
32
+ "vi_VN",
33
+ "zh_CN",
34
+ "af_ZA",
35
+ "az_AZ",
36
+ "bn_IN",
37
+ "fa_IR",
38
+ "he_IL",
39
+ "hr_HR",
40
+ "id_ID",
41
+ "ka_GE",
42
+ "km_KH",
43
+ "mk_MK",
44
+ "ml_IN",
45
+ "mn_MN",
46
+ "mr_IN",
47
+ "pl_PL",
48
+ "ps_AF",
49
+ "pt_XX",
50
+ "sv_SE",
51
+ "sw_KE",
52
+ "ta_IN",
53
+ "te_IN",
54
+ "th_TH",
55
+ "tl_XX",
56
+ "uk_UA",
57
+ "ur_PK",
58
+ "xh_ZA",
59
+ "gl_ES",
60
+ "sl_SI"
61
+ ],
62
+ "is_local": false,
63
+ "language_codes": "ML50",
64
+ "mask_token": "<mask>",
65
+ "model_max_length": 1000000000000000019884624838656,
66
+ "pad_token": "<pad>",
67
+ "sep_token": "</s>",
68
+ "src_lang": "zh_CN",
69
+ "tgt_lang": null,
70
+ "tokenizer_class": "MBart50Tokenizer",
71
+ "unk_id": 0,
72
+ "unk_token": "<unk>"
73
+ }
checkpoints/za-zh-rd-za/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d273db7d95286e56942812d0cf9eab28029a22dde0b56a1c4306a6a3d9cd8ee
3
+ size 5393
checkpoints/za-zh-ri-za/.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoints/za-zh-ri-za/README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: facebook/mbart-large-50-many-to-many-mmt
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - sacrebleu
8
+ model-index:
9
+ - name: za-zh-ri-za
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
+ # za-zh-ri-za
17
+
18
+ This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 2.8529
21
+ - Sacrebleu: 4.6252
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
+ - learning_rate: 2e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 16
43
+ - seed: 42
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 3
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Sacrebleu |
52
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|
53
+ | 0.8773 | 1.0 | 1545 | 2.7437 | 3.8543 |
54
+ | 0.2678 | 2.0 | 3090 | 2.8529 | 4.6252 |
55
+ | 0.1240 | 3.0 | 4635 | 2.9385 | 3.6222 |
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - Transformers 5.0.0
61
+ - Pytorch 2.10.0+cu128
62
+ - Datasets 4.0.0
63
+ - Tokenizers 0.22.2
checkpoints/za-zh-ri-za/config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 3,
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "MBartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "dtype": "float32",
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "gradient_checkpointing": false,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1",
31
+ "2": "LABEL_2"
32
+ },
33
+ "init_std": 0.02,
34
+ "is_decoder": false,
35
+ "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_2": 2
40
+ },
41
+ "max_position_embeddings": 1024,
42
+ "model_type": "mbart",
43
+ "normalize_before": true,
44
+ "normalize_embedding": true,
45
+ "num_hidden_layers": 12,
46
+ "output_past": true,
47
+ "pad_token_id": 1,
48
+ "scale_embedding": true,
49
+ "static_position_embeddings": false,
50
+ "tie_word_embeddings": true,
51
+ "tokenizer_class": "MBart50Tokenizer",
52
+ "transformers_version": "5.0.0",
53
+ "use_cache": false,
54
+ "vocab_size": 250054
55
+ }
checkpoints/za-zh-ri-za/generation_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": false,
3
+ "assistant_confidence_threshold": 0.4,
4
+ "assistant_lookbehind": 10,
5
+ "bos_token_id": 0,
6
+ "decoder_start_token_id": 2,
7
+ "diversity_penalty": 0.0,
8
+ "do_sample": false,
9
+ "early_stopping": true,
10
+ "encoder_no_repeat_ngram_size": 0,
11
+ "encoder_repetition_penalty": 1.0,
12
+ "eos_token_id": 2,
13
+ "epsilon_cutoff": 0.0,
14
+ "eta_cutoff": 0.0,
15
+ "forced_eos_token_id": 2,
16
+ "length_penalty": 1.0,
17
+ "max_length": 200,
18
+ "min_length": 0,
19
+ "no_repeat_ngram_size": 0,
20
+ "num_assistant_tokens": 20,
21
+ "num_assistant_tokens_schedule": "constant",
22
+ "num_beam_groups": 1,
23
+ "num_beams": 5,
24
+ "num_return_sequences": 1,
25
+ "output_scores": false,
26
+ "pad_token_id": 1,
27
+ "remove_invalid_values": false,
28
+ "repetition_penalty": 1.0,
29
+ "return_dict_in_generate": false,
30
+ "target_lookbehind": 10,
31
+ "temperature": 1.0,
32
+ "top_k": 50,
33
+ "top_p": 1.0,
34
+ "transformers_version": "5.0.0",
35
+ "typical_p": 1.0,
36
+ "use_cache": true
37
+ }
checkpoints/za-zh-ri-za/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7be6dd690a158b9febc5c3b73258d952faca884743456e30fac3c7bafbc55d62
3
+ size 2444578688
checkpoints/za-zh-ri-za/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e673ccd228f195203d0ca7520a3e75b660426c6d0cda003d28f43d49069a48d8
3
+ size 16793291
checkpoints/za-zh-ri-za/tokenizer_config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "extra_special_tokens": [
7
+ "<s>",
8
+ "</s>",
9
+ "ar_AR",
10
+ "cs_CZ",
11
+ "de_DE",
12
+ "en_XX",
13
+ "es_XX",
14
+ "et_EE",
15
+ "fi_FI",
16
+ "fr_XX",
17
+ "gu_IN",
18
+ "hi_IN",
19
+ "it_IT",
20
+ "ja_XX",
21
+ "kk_KZ",
22
+ "ko_KR",
23
+ "lt_LT",
24
+ "lv_LV",
25
+ "my_MM",
26
+ "ne_NP",
27
+ "nl_XX",
28
+ "ro_RO",
29
+ "ru_RU",
30
+ "si_LK",
31
+ "tr_TR",
32
+ "vi_VN",
33
+ "zh_CN",
34
+ "af_ZA",
35
+ "az_AZ",
36
+ "bn_IN",
37
+ "fa_IR",
38
+ "he_IL",
39
+ "hr_HR",
40
+ "id_ID",
41
+ "ka_GE",
42
+ "km_KH",
43
+ "mk_MK",
44
+ "ml_IN",
45
+ "mn_MN",
46
+ "mr_IN",
47
+ "pl_PL",
48
+ "ps_AF",
49
+ "pt_XX",
50
+ "sv_SE",
51
+ "sw_KE",
52
+ "ta_IN",
53
+ "te_IN",
54
+ "th_TH",
55
+ "tl_XX",
56
+ "uk_UA",
57
+ "ur_PK",
58
+ "xh_ZA",
59
+ "gl_ES",
60
+ "sl_SI"
61
+ ],
62
+ "is_local": false,
63
+ "language_codes": "ML50",
64
+ "mask_token": "<mask>",
65
+ "model_max_length": 1000000000000000019884624838656,
66
+ "pad_token": "<pad>",
67
+ "sep_token": "</s>",
68
+ "src_lang": "zh_CN",
69
+ "tgt_lang": null,
70
+ "tokenizer_class": "MBart50Tokenizer",
71
+ "unk_id": 0,
72
+ "unk_token": "<unk>"
73
+ }
checkpoints/za-zh-ri-za/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0101d6469f336a9c3a1133f0e59e983735bf2883b8a46cfc6c9993e89462e8e6
3
+ size 5393
checkpoints/za-zh-rs-za/.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoints/za-zh-rs-za/README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: facebook/mbart-large-50-many-to-many-mmt
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - sacrebleu
8
+ model-index:
9
+ - name: za-zh-rs-za
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
+ # za-zh-rs-za
17
+
18
+ This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 3.2987
21
+ - Sacrebleu: 2.6285
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
+ - learning_rate: 2e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 16
43
+ - seed: 42
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 3
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Sacrebleu |
52
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|
53
+ | 1.9199 | 1.0 | 1236 | 3.2717 | 1.9790 |
54
+ | 1.1039 | 2.0 | 2472 | 3.2611 | 0.9655 |
55
+ | 0.7351 | 3.0 | 3708 | 3.2987 | 2.6285 |
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - Transformers 5.0.0
61
+ - Pytorch 2.10.0+cu128
62
+ - Datasets 4.0.0
63
+ - Tokenizers 0.22.2
checkpoints/za-zh-rs-za/config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 3,
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "MBartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "dtype": "float32",
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "gradient_checkpointing": false,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1",
31
+ "2": "LABEL_2"
32
+ },
33
+ "init_std": 0.02,
34
+ "is_decoder": false,
35
+ "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_2": 2
40
+ },
41
+ "max_position_embeddings": 1024,
42
+ "model_type": "mbart",
43
+ "normalize_before": true,
44
+ "normalize_embedding": true,
45
+ "num_hidden_layers": 12,
46
+ "output_past": true,
47
+ "pad_token_id": 1,
48
+ "scale_embedding": true,
49
+ "static_position_embeddings": false,
50
+ "tie_word_embeddings": true,
51
+ "tokenizer_class": "MBart50Tokenizer",
52
+ "transformers_version": "5.0.0",
53
+ "use_cache": false,
54
+ "vocab_size": 250054
55
+ }
checkpoints/za-zh-rs-za/generation_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": false,
3
+ "assistant_confidence_threshold": 0.4,
4
+ "assistant_lookbehind": 10,
5
+ "bos_token_id": 0,
6
+ "decoder_start_token_id": 2,
7
+ "diversity_penalty": 0.0,
8
+ "do_sample": false,
9
+ "early_stopping": true,
10
+ "encoder_no_repeat_ngram_size": 0,
11
+ "encoder_repetition_penalty": 1.0,
12
+ "eos_token_id": 2,
13
+ "epsilon_cutoff": 0.0,
14
+ "eta_cutoff": 0.0,
15
+ "forced_eos_token_id": 2,
16
+ "length_penalty": 1.0,
17
+ "max_length": 200,
18
+ "min_length": 0,
19
+ "no_repeat_ngram_size": 0,
20
+ "num_assistant_tokens": 20,
21
+ "num_assistant_tokens_schedule": "constant",
22
+ "num_beam_groups": 1,
23
+ "num_beams": 5,
24
+ "num_return_sequences": 1,
25
+ "output_scores": false,
26
+ "pad_token_id": 1,
27
+ "remove_invalid_values": false,
28
+ "repetition_penalty": 1.0,
29
+ "return_dict_in_generate": false,
30
+ "target_lookbehind": 10,
31
+ "temperature": 1.0,
32
+ "top_k": 50,
33
+ "top_p": 1.0,
34
+ "transformers_version": "5.0.0",
35
+ "typical_p": 1.0,
36
+ "use_cache": true
37
+ }
checkpoints/za-zh-rs-za/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd05e336e86c84789be5d9ca3b7d527841d5d7cb8db0ebd444ec5459a6793bc8
3
+ size 2444578688
checkpoints/za-zh-rs-za/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e673ccd228f195203d0ca7520a3e75b660426c6d0cda003d28f43d49069a48d8
3
+ size 16793291
checkpoints/za-zh-rs-za/tokenizer_config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "extra_special_tokens": [
7
+ "<s>",
8
+ "</s>",
9
+ "ar_AR",
10
+ "cs_CZ",
11
+ "de_DE",
12
+ "en_XX",
13
+ "es_XX",
14
+ "et_EE",
15
+ "fi_FI",
16
+ "fr_XX",
17
+ "gu_IN",
18
+ "hi_IN",
19
+ "it_IT",
20
+ "ja_XX",
21
+ "kk_KZ",
22
+ "ko_KR",
23
+ "lt_LT",
24
+ "lv_LV",
25
+ "my_MM",
26
+ "ne_NP",
27
+ "nl_XX",
28
+ "ro_RO",
29
+ "ru_RU",
30
+ "si_LK",
31
+ "tr_TR",
32
+ "vi_VN",
33
+ "zh_CN",
34
+ "af_ZA",
35
+ "az_AZ",
36
+ "bn_IN",
37
+ "fa_IR",
38
+ "he_IL",
39
+ "hr_HR",
40
+ "id_ID",
41
+ "ka_GE",
42
+ "km_KH",
43
+ "mk_MK",
44
+ "ml_IN",
45
+ "mn_MN",
46
+ "mr_IN",
47
+ "pl_PL",
48
+ "ps_AF",
49
+ "pt_XX",
50
+ "sv_SE",
51
+ "sw_KE",
52
+ "ta_IN",
53
+ "te_IN",
54
+ "th_TH",
55
+ "tl_XX",
56
+ "uk_UA",
57
+ "ur_PK",
58
+ "xh_ZA",
59
+ "gl_ES",
60
+ "sl_SI"
61
+ ],
62
+ "is_local": false,
63
+ "language_codes": "ML50",
64
+ "mask_token": "<mask>",
65
+ "model_max_length": 1000000000000000019884624838656,
66
+ "pad_token": "<pad>",
67
+ "sep_token": "</s>",
68
+ "src_lang": "zh_CN",
69
+ "tgt_lang": null,
70
+ "tokenizer_class": "MBart50Tokenizer",
71
+ "unk_id": 0,
72
+ "unk_token": "<unk>"
73
+ }
checkpoints/za-zh-rs-za/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:548cff87467b53c387d590852d47224d6903ef95c6b3792f71aa9a43a291a4ac
3
+ size 5393
checkpoints/za-zh-theme/.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoints/za-zh-theme/README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: facebook/mbart-large-50-many-to-many-mmt
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - sacrebleu
8
+ model-index:
9
+ - name: za-zh-theme
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
+ # za-zh-theme
17
+
18
+ This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 2.7864
21
+ - Sacrebleu: 6.6442
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
+ - learning_rate: 2e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 16
43
+ - seed: 42
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 3
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Sacrebleu |
52
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|
53
+ | 0.4156 | 1.0 | 1678 | 2.7864 | 6.6442 |
54
+ | 0.1474 | 2.0 | 3356 | 2.8686 | 5.0403 |
55
+ | 0.0730 | 3.0 | 5034 | 2.9130 | 6.2466 |
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - Transformers 5.0.0
61
+ - Pytorch 2.10.0+cu128
62
+ - Datasets 4.0.0
63
+ - Tokenizers 0.22.2
checkpoints/za-zh-theme/config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 3,
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "MBartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "dtype": "float32",
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "gradient_checkpointing": false,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1",
31
+ "2": "LABEL_2"
32
+ },
33
+ "init_std": 0.02,
34
+ "is_decoder": false,
35
+ "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_2": 2
40
+ },
41
+ "max_position_embeddings": 1024,
42
+ "model_type": "mbart",
43
+ "normalize_before": true,
44
+ "normalize_embedding": true,
45
+ "num_hidden_layers": 12,
46
+ "output_past": true,
47
+ "pad_token_id": 1,
48
+ "scale_embedding": true,
49
+ "static_position_embeddings": false,
50
+ "tie_word_embeddings": true,
51
+ "tokenizer_class": "MBart50Tokenizer",
52
+ "transformers_version": "5.0.0",
53
+ "use_cache": false,
54
+ "vocab_size": 250054
55
+ }
checkpoints/za-zh-theme/generation_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": false,
3
+ "assistant_confidence_threshold": 0.4,
4
+ "assistant_lookbehind": 10,
5
+ "bos_token_id": 0,
6
+ "decoder_start_token_id": 2,
7
+ "diversity_penalty": 0.0,
8
+ "do_sample": false,
9
+ "early_stopping": true,
10
+ "encoder_no_repeat_ngram_size": 0,
11
+ "encoder_repetition_penalty": 1.0,
12
+ "eos_token_id": 2,
13
+ "epsilon_cutoff": 0.0,
14
+ "eta_cutoff": 0.0,
15
+ "forced_eos_token_id": 2,
16
+ "length_penalty": 1.0,
17
+ "max_length": 200,
18
+ "min_length": 0,
19
+ "no_repeat_ngram_size": 0,
20
+ "num_assistant_tokens": 20,
21
+ "num_assistant_tokens_schedule": "constant",
22
+ "num_beam_groups": 1,
23
+ "num_beams": 5,
24
+ "num_return_sequences": 1,
25
+ "output_scores": false,
26
+ "pad_token_id": 1,
27
+ "remove_invalid_values": false,
28
+ "repetition_penalty": 1.0,
29
+ "return_dict_in_generate": false,
30
+ "target_lookbehind": 10,
31
+ "temperature": 1.0,
32
+ "top_k": 50,
33
+ "top_p": 1.0,
34
+ "transformers_version": "5.0.0",
35
+ "typical_p": 1.0,
36
+ "use_cache": true
37
+ }
checkpoints/za-zh-theme/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ace579aefd498d0ea9ab41882b3d8faae2eaafcf5a1f4b294898bff25c25a5a
3
+ size 2444578688
checkpoints/za-zh-theme/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e673ccd228f195203d0ca7520a3e75b660426c6d0cda003d28f43d49069a48d8
3
+ size 16793291
checkpoints/za-zh-theme/tokenizer_config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "extra_special_tokens": [
7
+ "<s>",
8
+ "</s>",
9
+ "ar_AR",
10
+ "cs_CZ",
11
+ "de_DE",
12
+ "en_XX",
13
+ "es_XX",
14
+ "et_EE",
15
+ "fi_FI",
16
+ "fr_XX",
17
+ "gu_IN",
18
+ "hi_IN",
19
+ "it_IT",
20
+ "ja_XX",
21
+ "kk_KZ",
22
+ "ko_KR",
23
+ "lt_LT",
24
+ "lv_LV",
25
+ "my_MM",
26
+ "ne_NP",
27
+ "nl_XX",
28
+ "ro_RO",
29
+ "ru_RU",
30
+ "si_LK",
31
+ "tr_TR",
32
+ "vi_VN",
33
+ "zh_CN",
34
+ "af_ZA",
35
+ "az_AZ",
36
+ "bn_IN",
37
+ "fa_IR",
38
+ "he_IL",
39
+ "hr_HR",
40
+ "id_ID",
41
+ "ka_GE",
42
+ "km_KH",
43
+ "mk_MK",
44
+ "ml_IN",
45
+ "mn_MN",
46
+ "mr_IN",
47
+ "pl_PL",
48
+ "ps_AF",
49
+ "pt_XX",
50
+ "sv_SE",
51
+ "sw_KE",
52
+ "ta_IN",
53
+ "te_IN",
54
+ "th_TH",
55
+ "tl_XX",
56
+ "uk_UA",
57
+ "ur_PK",
58
+ "xh_ZA",
59
+ "gl_ES",
60
+ "sl_SI"
61
+ ],
62
+ "is_local": false,
63
+ "language_codes": "ML50",
64
+ "mask_token": "<mask>",
65
+ "model_max_length": 1000000000000000019884624838656,
66
+ "pad_token": "<pad>",
67
+ "sep_token": "</s>",
68
+ "src_lang": "zh_CN",
69
+ "tgt_lang": null,
70
+ "tokenizer_class": "MBart50Tokenizer",
71
+ "unk_id": 0,
72
+ "unk_token": "<unk>"
73
+ }
checkpoints/za-zh-theme/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed56aa4a87ea643d4bf09369d4f664069629d656b05e2efe1e8600d91267cde7
3
+ size 5393
checkpoints/za-zh-tssr-za/.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoints/za-zh-tssr-za/README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: facebook/mbart-large-50-many-to-many-mmt
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - sacrebleu
8
+ model-index:
9
+ - name: za-zh-tssr-za
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
+ # za-zh-tssr-za
17
+
18
+ This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.4848
21
+ - Sacrebleu: 5.5321
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
+ - learning_rate: 2e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 16
43
+ - seed: 42
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 3
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Sacrebleu |
52
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|
53
+ | 0.3205 | 1.0 | 407 | 0.5258 | 5.5128 |
54
+ | 0.1870 | 2.0 | 814 | 0.4896 | 4.1458 |
55
+ | 0.1451 | 3.0 | 1221 | 0.4848 | 5.5321 |
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - Transformers 5.0.0
61
+ - Pytorch 2.10.0+cu128
62
+ - Datasets 4.0.0
63
+ - Tokenizers 0.22.2
checkpoints/za-zh-tssr-za/config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 3,
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "MBartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "dtype": "float32",
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "gradient_checkpointing": false,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1",
31
+ "2": "LABEL_2"
32
+ },
33
+ "init_std": 0.02,
34
+ "is_decoder": false,
35
+ "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_2": 2
40
+ },
41
+ "max_position_embeddings": 1024,
42
+ "model_type": "mbart",
43
+ "normalize_before": true,
44
+ "normalize_embedding": true,
45
+ "num_hidden_layers": 12,
46
+ "output_past": true,
47
+ "pad_token_id": 1,
48
+ "scale_embedding": true,
49
+ "static_position_embeddings": false,
50
+ "tie_word_embeddings": true,
51
+ "tokenizer_class": "MBart50Tokenizer",
52
+ "transformers_version": "5.0.0",
53
+ "use_cache": false,
54
+ "vocab_size": 250054
55
+ }
checkpoints/za-zh-tssr-za/generation_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": false,
3
+ "assistant_confidence_threshold": 0.4,
4
+ "assistant_lookbehind": 10,
5
+ "bos_token_id": 0,
6
+ "decoder_start_token_id": 2,
7
+ "diversity_penalty": 0.0,
8
+ "do_sample": false,
9
+ "early_stopping": true,
10
+ "encoder_no_repeat_ngram_size": 0,
11
+ "encoder_repetition_penalty": 1.0,
12
+ "eos_token_id": 2,
13
+ "epsilon_cutoff": 0.0,
14
+ "eta_cutoff": 0.0,
15
+ "forced_eos_token_id": 2,
16
+ "length_penalty": 1.0,
17
+ "max_length": 200,
18
+ "min_length": 0,
19
+ "no_repeat_ngram_size": 0,
20
+ "num_assistant_tokens": 20,
21
+ "num_assistant_tokens_schedule": "constant",
22
+ "num_beam_groups": 1,
23
+ "num_beams": 5,
24
+ "num_return_sequences": 1,
25
+ "output_scores": false,
26
+ "pad_token_id": 1,
27
+ "remove_invalid_values": false,
28
+ "repetition_penalty": 1.0,
29
+ "return_dict_in_generate": false,
30
+ "target_lookbehind": 10,
31
+ "temperature": 1.0,
32
+ "top_k": 50,
33
+ "top_p": 1.0,
34
+ "transformers_version": "5.0.0",
35
+ "typical_p": 1.0,
36
+ "use_cache": true
37
+ }
checkpoints/za-zh-tssr-za/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:526c866f7219de54f8805eb6a74a36554feb25cfac41bfd4e5a1026da39d4c6c
3
+ size 2444578688
checkpoints/za-zh-tssr-za/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e673ccd228f195203d0ca7520a3e75b660426c6d0cda003d28f43d49069a48d8
3
+ size 16793291
checkpoints/za-zh-tssr-za/tokenizer_config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "extra_special_tokens": [
7
+ "<s>",
8
+ "</s>",
9
+ "ar_AR",
10
+ "cs_CZ",
11
+ "de_DE",
12
+ "en_XX",
13
+ "es_XX",
14
+ "et_EE",
15
+ "fi_FI",
16
+ "fr_XX",
17
+ "gu_IN",
18
+ "hi_IN",
19
+ "it_IT",
20
+ "ja_XX",
21
+ "kk_KZ",
22
+ "ko_KR",
23
+ "lt_LT",
24
+ "lv_LV",
25
+ "my_MM",
26
+ "ne_NP",
27
+ "nl_XX",
28
+ "ro_RO",
29
+ "ru_RU",
30
+ "si_LK",
31
+ "tr_TR",
32
+ "vi_VN",
33
+ "zh_CN",
34
+ "af_ZA",
35
+ "az_AZ",
36
+ "bn_IN",
37
+ "fa_IR",
38
+ "he_IL",
39
+ "hr_HR",
40
+ "id_ID",
41
+ "ka_GE",
42
+ "km_KH",
43
+ "mk_MK",
44
+ "ml_IN",
45
+ "mn_MN",
46
+ "mr_IN",
47
+ "pl_PL",
48
+ "ps_AF",
49
+ "pt_XX",
50
+ "sv_SE",
51
+ "sw_KE",
52
+ "ta_IN",
53
+ "te_IN",
54
+ "th_TH",
55
+ "tl_XX",
56
+ "uk_UA",
57
+ "ur_PK",
58
+ "xh_ZA",
59
+ "gl_ES",
60
+ "sl_SI"
61
+ ],
62
+ "is_local": false,
63
+ "language_codes": "ML50",
64
+ "mask_token": "<mask>",
65
+ "model_max_length": 1000000000000000019884624838656,
66
+ "pad_token": "<pad>",
67
+ "sep_token": "</s>",
68
+ "src_lang": "zh_CN",
69
+ "tgt_lang": null,
70
+ "tokenizer_class": "MBart50Tokenizer",
71
+ "unk_id": 0,
72
+ "unk_token": "<unk>"
73
+ }
checkpoints/za-zh-tssr-za/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2736c870aeb7071be9641339d024aff43187bd624ff5e779a1dcb0058fe62556
3
+ size 5393
checkpoints/za_zh_sc/.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoints/za_zh_sc/README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: facebook/mbart-large-50-many-to-many-mmt
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - sacrebleu
8
+ model-index:
9
+ - name: za_zh_sc
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
+ # za_zh_sc
17
+
18
+ This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 2.9950
21
+ - Sacrebleu: 4.4405
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
+ - learning_rate: 2e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 16
43
+ - seed: 42
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 2
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Sacrebleu |
52
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|
53
+ | 2.5108 | 1.0 | 309 | 2.9950 | 4.4405 |
54
+ | 1.7678 | 2.0 | 618 | 2.8134 | 3.4752 |
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - Transformers 5.0.0
60
+ - Pytorch 2.10.0+cu128
61
+ - Datasets 4.0.0
62
+ - Tokenizers 0.22.2
checkpoints/za_zh_sc/config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 3,
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "MBartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "dtype": "float32",
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "gradient_checkpointing": false,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1",
31
+ "2": "LABEL_2"
32
+ },
33
+ "init_std": 0.02,
34
+ "is_decoder": false,
35
+ "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_2": 2
40
+ },
41
+ "max_position_embeddings": 1024,
42
+ "model_type": "mbart",
43
+ "normalize_before": true,
44
+ "normalize_embedding": true,
45
+ "num_hidden_layers": 12,
46
+ "output_past": true,
47
+ "pad_token_id": 1,
48
+ "scale_embedding": true,
49
+ "static_position_embeddings": false,
50
+ "tie_word_embeddings": true,
51
+ "tokenizer_class": "MBart50Tokenizer",
52
+ "transformers_version": "5.0.0",
53
+ "use_cache": false,
54
+ "vocab_size": 250055
55
+ }
checkpoints/za_zh_sc/generation_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": false,
3
+ "assistant_confidence_threshold": 0.4,
4
+ "assistant_lookbehind": 10,
5
+ "bos_token_id": 0,
6
+ "decoder_start_token_id": 2,
7
+ "diversity_penalty": 0.0,
8
+ "do_sample": false,
9
+ "early_stopping": true,
10
+ "encoder_no_repeat_ngram_size": 0,
11
+ "encoder_repetition_penalty": 1.0,
12
+ "eos_token_id": 2,
13
+ "epsilon_cutoff": 0.0,
14
+ "eta_cutoff": 0.0,
15
+ "forced_eos_token_id": 2,
16
+ "length_penalty": 1.0,
17
+ "max_length": 200,
18
+ "min_length": 0,
19
+ "no_repeat_ngram_size": 0,
20
+ "num_assistant_tokens": 20,
21
+ "num_assistant_tokens_schedule": "constant",
22
+ "num_beam_groups": 1,
23
+ "num_beams": 5,
24
+ "num_return_sequences": 1,
25
+ "output_scores": false,
26
+ "pad_token_id": 1,
27
+ "remove_invalid_values": false,
28
+ "repetition_penalty": 1.0,
29
+ "return_dict_in_generate": false,
30
+ "target_lookbehind": 10,
31
+ "temperature": 1.0,
32
+ "top_k": 50,
33
+ "top_p": 1.0,
34
+ "transformers_version": "5.0.0",
35
+ "typical_p": 1.0,
36
+ "use_cache": true
37
+ }
checkpoints/za_zh_sc/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0e7cc73ae9b3435c2455575f9d3217bdf54f799f014084d890f3f42b524e902
3
+ size 2444582788
checkpoints/za_zh_sc/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eeb5a28135f15f64314077af5cae74547d898c979266144ecd95f709e76b008
3
+ size 16793473
checkpoints/za_zh_sc/tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "extra_special_tokens": [
7
+ "<SEP>"
8
+ ],
9
+ "is_local": false,
10
+ "language_codes": "ML50",
11
+ "mask_token": "<mask>",
12
+ "model_max_length": 1000000000000000019884624838656,
13
+ "pad_token": "<pad>",
14
+ "sep_token": "</s>",
15
+ "src_lang": "zh_CN",
16
+ "tgt_lang": null,
17
+ "tokenizer_class": "MBart50Tokenizer",
18
+ "unk_id": 0,
19
+ "unk_token": "<unk>"
20
+ }
checkpoints/za_zh_sc/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c86211a54299f4647a5833604b3acbcad70a287337769adf2678c85bc368b635
3
+ size 5329
checkpoints/zh-za-synonyms/.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text