yesj1234 commited on
Commit
0d6fb72
1 Parent(s): a8ca915

Upload folder using huggingface_hub

Browse files
Files changed (46) hide show
  1. .gitattributes +3 -0
  2. README.md +72 -0
  3. all_results.json +22 -0
  4. checkpoint-30000/config.json +59 -0
  5. checkpoint-30000/generation_config.json +12 -0
  6. checkpoint-30000/optimizer.pt +3 -0
  7. checkpoint-30000/pytorch_model.bin +3 -0
  8. checkpoint-30000/rng_state_0.pth +3 -0
  9. checkpoint-30000/rng_state_1.pth +3 -0
  10. checkpoint-30000/rng_state_2.pth +3 -0
  11. checkpoint-30000/rng_state_3.pth +3 -0
  12. checkpoint-30000/scheduler.pt +3 -0
  13. checkpoint-30000/sentencepiece.bpe.model +3 -0
  14. checkpoint-30000/special_tokens_map.json +69 -0
  15. checkpoint-30000/tokenizer.json +3 -0
  16. checkpoint-30000/tokenizer_config.json +528 -0
  17. checkpoint-30000/trainer_state.json +419 -0
  18. checkpoint-30000/training_args.bin +3 -0
  19. checkpoint-7500/config.json +59 -0
  20. checkpoint-7500/generation_config.json +12 -0
  21. checkpoint-7500/optimizer.pt +3 -0
  22. checkpoint-7500/pytorch_model.bin +3 -0
  23. checkpoint-7500/rng_state_0.pth +3 -0
  24. checkpoint-7500/rng_state_1.pth +3 -0
  25. checkpoint-7500/rng_state_2.pth +3 -0
  26. checkpoint-7500/rng_state_3.pth +3 -0
  27. checkpoint-7500/scheduler.pt +3 -0
  28. checkpoint-7500/sentencepiece.bpe.model +3 -0
  29. checkpoint-7500/special_tokens_map.json +69 -0
  30. checkpoint-7500/tokenizer.json +3 -0
  31. checkpoint-7500/tokenizer_config.json +528 -0
  32. checkpoint-7500/trainer_state.json +119 -0
  33. checkpoint-7500/training_args.bin +3 -0
  34. config.json +59 -0
  35. eval_results.json +10 -0
  36. generated_predictions.txt +0 -0
  37. generation_config.json +12 -0
  38. predict_results.json +9 -0
  39. pytorch_model.bin +3 -0
  40. sentencepiece.bpe.model +3 -0
  41. special_tokens_map.json +69 -0
  42. tokenizer.json +3 -0
  43. tokenizer_config.json +528 -0
  44. train_results.json +8 -0
  45. trainer_state.json +428 -0
  46. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* 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
 
 
 
 
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
+ checkpoint-30000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-7500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ko
4
+ - zh
5
+ base_model: facebook/mbart-large-50-many-to-many-mmt
6
+ tags:
7
+ - generated_from_trainer
8
+ metrics:
9
+ - bleu
10
+ model-index:
11
+ - name: kozh_mbartLarge_50p_run3_tokenize
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # kozh_mbartLarge_50p_run3_tokenize
19
+
20
+ 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.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 1.3103
23
+ - Bleu: 51.0209
24
+ - Gen Len: 13.3475
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 5e-05
44
+ - train_batch_size: 4
45
+ - eval_batch_size: 4
46
+ - seed: 42
47
+ - distributed_type: multi-GPU
48
+ - num_devices: 4
49
+ - gradient_accumulation_steps: 4
50
+ - total_train_batch_size: 64
51
+ - total_eval_batch_size: 16
52
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
+ - lr_scheduler_type: linear
54
+ - lr_scheduler_warmup_steps: 1500
55
+ - num_epochs: 10
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
60
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
61
+ | 1.0808 | 2.0 | 7500 | 1.3103 | 51.0184 | 13.3575 |
62
+ | 0.6519 | 3.99 | 15000 | 1.3856 | 51.6667 | 13.4112 |
63
+ | 0.3867 | 5.99 | 22500 | 1.5243 | 51.5686 | 13.432 |
64
+ | 0.236 | 7.98 | 30000 | 1.6158 | 51.4674 | 13.291 |
65
+
66
+
67
+ ### Framework versions
68
+
69
+ - Transformers 4.34.1
70
+ - Pytorch 2.1.0+cu121
71
+ - Datasets 2.14.6
72
+ - Tokenizers 0.14.1
all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 7.98,
3
+ "eval_bleu": 51.0209,
4
+ "eval_gen_len": 13.3475,
5
+ "eval_loss": 1.3103234767913818,
6
+ "eval_runtime": 1618.9873,
7
+ "eval_samples": 30070,
8
+ "eval_samples_per_second": 18.573,
9
+ "eval_steps_per_second": 1.161,
10
+ "predict_bleu": 51.1483,
11
+ "predict_gen_len": 13.278,
12
+ "predict_loss": 1.3004177808761597,
13
+ "predict_runtime": 1614.5402,
14
+ "predict_samples": 30071,
15
+ "predict_samples_per_second": 18.625,
16
+ "predict_steps_per_second": 1.164,
17
+ "train_loss": 0.7653622683207194,
18
+ "train_runtime": 99492.172,
19
+ "train_samples": 240570,
20
+ "train_samples_per_second": 24.18,
21
+ "train_steps_per_second": 0.378
22
+ }
checkpoint-30000/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": true,
8
+ "architectures": [
9
+ "MBartForConditionalGeneration"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 1024,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 4096,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 12,
20
+ "decoder_start_token_id": 2,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 2,
28
+ "forced_bos_token_id": 250025,
29
+ "forced_eos_token_id": 2,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "max_length": 200,
44
+ "max_position_embeddings": 1024,
45
+ "model_type": "mbart",
46
+ "normalize_before": true,
47
+ "normalize_embedding": true,
48
+ "num_beams": 5,
49
+ "num_hidden_layers": 12,
50
+ "output_past": true,
51
+ "pad_token_id": 1,
52
+ "scale_embedding": true,
53
+ "static_position_embeddings": false,
54
+ "tokenizer_class": "MBart50Tokenizer",
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.34.1",
57
+ "use_cache": true,
58
+ "vocab_size": 250054
59
+ }
checkpoint-30000/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "forced_bos_token_id": 250025,
7
+ "forced_eos_token_id": 2,
8
+ "max_length": 200,
9
+ "num_beams": 5,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.34.1"
12
+ }
checkpoint-30000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78356180ca609eed0a9f640d2304d9693c43c0b5ff2f11b4d1186b4b09134f5b
3
+ size 4887473903
checkpoint-30000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9b43176d91d4a366fb462db96659948f12e969a35cd511d3947eb78f99b1389
3
+ size 2444694490
checkpoint-30000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48838e33150f029816a402d1dc2cf9daaf89fee589eeb1cb175d7ee1104e4afb
3
+ size 15024
checkpoint-30000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce3730fcf957dd1fec4a13627c470fb7ce69ee9214a930a1808b8a20b1c61623
3
+ size 15024
checkpoint-30000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0690c73e93f84bbc2fd11c31861dd0f888dafe4d34ea25f865c170e662c7993
3
+ size 15024
checkpoint-30000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:380f2c0417b29d6b3021d178c2dc62df7d9e7dd1bdbe7b9d2ceeaecb56890f87
3
+ size 15024
checkpoint-30000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c0dc97b241acda8db842958830e60da9038d276ab1ef48e3da39955051fcbda
3
+ size 1064
checkpoint-30000/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
checkpoint-30000/special_tokens_map.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN",
28
+ "af_ZA",
29
+ "az_AZ",
30
+ "bn_IN",
31
+ "fa_IR",
32
+ "he_IL",
33
+ "hr_HR",
34
+ "id_ID",
35
+ "ka_GE",
36
+ "km_KH",
37
+ "mk_MK",
38
+ "ml_IN",
39
+ "mn_MN",
40
+ "mr_IN",
41
+ "pl_PL",
42
+ "ps_AF",
43
+ "pt_XX",
44
+ "sv_SE",
45
+ "sw_KE",
46
+ "ta_IN",
47
+ "te_IN",
48
+ "th_TH",
49
+ "tl_XX",
50
+ "uk_UA",
51
+ "ur_PK",
52
+ "xh_ZA",
53
+ "gl_ES",
54
+ "sl_SI"
55
+ ],
56
+ "bos_token": "<s>",
57
+ "cls_token": "<s>",
58
+ "eos_token": "</s>",
59
+ "mask_token": {
60
+ "content": "<mask>",
61
+ "lstrip": true,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ "pad_token": "<pad>",
67
+ "sep_token": "</s>",
68
+ "unk_token": "<unk>"
69
+ }
checkpoint-30000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:035e5ed43f8e238be4dd88ade3b92960da904cadf57ce02c14f5f59c4b531b91
3
+ size 17110043
checkpoint-30000/tokenizer_config.json ADDED
@@ -0,0 +1,528 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "ar_AR",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "250002": {
44
+ "content": "cs_CZ",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "250003": {
52
+ "content": "de_DE",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "250004": {
60
+ "content": "en_XX",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "250005": {
68
+ "content": "es_XX",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "250006": {
76
+ "content": "et_EE",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "250007": {
84
+ "content": "fi_FI",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "250008": {
92
+ "content": "fr_XX",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "250009": {
100
+ "content": "gu_IN",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "250010": {
108
+ "content": "hi_IN",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "250011": {
116
+ "content": "it_IT",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "250012": {
124
+ "content": "ja_XX",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "250013": {
132
+ "content": "kk_KZ",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "250014": {
140
+ "content": "ko_KR",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "250015": {
148
+ "content": "lt_LT",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "250016": {
156
+ "content": "lv_LV",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "250017": {
164
+ "content": "my_MM",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "250018": {
172
+ "content": "ne_NP",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "250019": {
180
+ "content": "nl_XX",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "250020": {
188
+ "content": "ro_RO",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "250021": {
196
+ "content": "ru_RU",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "250022": {
204
+ "content": "si_LK",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "250023": {
212
+ "content": "tr_TR",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "250024": {
220
+ "content": "vi_VN",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "250025": {
228
+ "content": "zh_CN",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "250026": {
236
+ "content": "af_ZA",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "250027": {
244
+ "content": "az_AZ",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "250028": {
252
+ "content": "bn_IN",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "250029": {
260
+ "content": "fa_IR",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "250030": {
268
+ "content": "he_IL",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "250031": {
276
+ "content": "hr_HR",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "250032": {
284
+ "content": "id_ID",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "250033": {
292
+ "content": "ka_GE",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "250034": {
300
+ "content": "km_KH",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "250035": {
308
+ "content": "mk_MK",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "250036": {
316
+ "content": "ml_IN",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "250037": {
324
+ "content": "mn_MN",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "250038": {
332
+ "content": "mr_IN",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "250039": {
340
+ "content": "pl_PL",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "250040": {
348
+ "content": "ps_AF",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "250041": {
356
+ "content": "pt_XX",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "250042": {
364
+ "content": "sv_SE",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "250043": {
372
+ "content": "sw_KE",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "250044": {
380
+ "content": "ta_IN",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "250045": {
388
+ "content": "te_IN",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "250046": {
396
+ "content": "th_TH",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "250047": {
404
+ "content": "tl_XX",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "250048": {
412
+ "content": "uk_UA",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "250049": {
420
+ "content": "ur_PK",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "250050": {
428
+ "content": "xh_ZA",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "250051": {
436
+ "content": "gl_ES",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "250052": {
444
+ "content": "sl_SI",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "250053": {
452
+ "content": "<mask>",
453
+ "lstrip": true,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ }
459
+ },
460
+ "additional_special_tokens": [
461
+ "ar_AR",
462
+ "cs_CZ",
463
+ "de_DE",
464
+ "en_XX",
465
+ "es_XX",
466
+ "et_EE",
467
+ "fi_FI",
468
+ "fr_XX",
469
+ "gu_IN",
470
+ "hi_IN",
471
+ "it_IT",
472
+ "ja_XX",
473
+ "kk_KZ",
474
+ "ko_KR",
475
+ "lt_LT",
476
+ "lv_LV",
477
+ "my_MM",
478
+ "ne_NP",
479
+ "nl_XX",
480
+ "ro_RO",
481
+ "ru_RU",
482
+ "si_LK",
483
+ "tr_TR",
484
+ "vi_VN",
485
+ "zh_CN",
486
+ "af_ZA",
487
+ "az_AZ",
488
+ "bn_IN",
489
+ "fa_IR",
490
+ "he_IL",
491
+ "hr_HR",
492
+ "id_ID",
493
+ "ka_GE",
494
+ "km_KH",
495
+ "mk_MK",
496
+ "ml_IN",
497
+ "mn_MN",
498
+ "mr_IN",
499
+ "pl_PL",
500
+ "ps_AF",
501
+ "pt_XX",
502
+ "sv_SE",
503
+ "sw_KE",
504
+ "ta_IN",
505
+ "te_IN",
506
+ "th_TH",
507
+ "tl_XX",
508
+ "uk_UA",
509
+ "ur_PK",
510
+ "xh_ZA",
511
+ "gl_ES",
512
+ "sl_SI"
513
+ ],
514
+ "bos_token": "<s>",
515
+ "clean_up_tokenization_spaces": true,
516
+ "cls_token": "<s>",
517
+ "eos_token": "</s>",
518
+ "language_codes": "ML50",
519
+ "mask_token": "<mask>",
520
+ "model_max_length": 1000000000000000019884624838656,
521
+ "pad_token": "<pad>",
522
+ "sep_token": "</s>",
523
+ "sp_model_kwargs": {},
524
+ "src_lang": "ko_KR",
525
+ "tgt_lang": "zh_CN",
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
checkpoint-30000/trainer_state.json ADDED
@@ -0,0 +1,419 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.3103234767913818,
3
+ "best_model_checkpoint": "./kozh_mbartLarge_50p_run3_tokenize/checkpoint-7500",
4
+ "epoch": 7.980845969672785,
5
+ "eval_steps": 7500,
6
+ "global_step": 30000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.13,
13
+ "learning_rate": 1.6666666666666667e-05,
14
+ "loss": 2.5913,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.27,
19
+ "learning_rate": 3.3333333333333335e-05,
20
+ "loss": 1.8919,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.4,
25
+ "learning_rate": 5e-05,
26
+ "loss": 1.7345,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.53,
31
+ "learning_rate": 4.930728733721253e-05,
32
+ "loss": 1.6451,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.67,
37
+ "learning_rate": 4.861457467442505e-05,
38
+ "loss": 1.5539,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.8,
43
+ "learning_rate": 4.792186201163758e-05,
44
+ "loss": 1.512,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.93,
49
+ "learning_rate": 4.72291493488501e-05,
50
+ "loss": 1.4671,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 1.06,
55
+ "learning_rate": 4.6536436686062625e-05,
56
+ "loss": 1.417,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 1.2,
61
+ "learning_rate": 4.5843724023275146e-05,
62
+ "loss": 1.3449,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 1.33,
67
+ "learning_rate": 4.515101136048767e-05,
68
+ "loss": 1.2543,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 1.46,
73
+ "learning_rate": 4.4458298697700194e-05,
74
+ "loss": 1.1794,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 1.6,
79
+ "learning_rate": 4.376558603491272e-05,
80
+ "loss": 1.1359,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 1.73,
85
+ "learning_rate": 4.307287337212524e-05,
86
+ "loss": 1.1075,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 1.86,
91
+ "learning_rate": 4.238016070933777e-05,
92
+ "loss": 1.1079,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 2.0,
97
+ "learning_rate": 4.168744804655029e-05,
98
+ "loss": 1.0808,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 2.0,
103
+ "eval_bleu": 51.0184,
104
+ "eval_gen_len": 13.3575,
105
+ "eval_loss": 1.3103234767913818,
106
+ "eval_runtime": 1625.4898,
107
+ "eval_samples_per_second": 18.499,
108
+ "eval_steps_per_second": 1.157,
109
+ "step": 7500
110
+ },
111
+ {
112
+ "epoch": 2.13,
113
+ "learning_rate": 4.099473538376282e-05,
114
+ "loss": 1.053,
115
+ "step": 8000
116
+ },
117
+ {
118
+ "epoch": 2.26,
119
+ "learning_rate": 4.0302022720975344e-05,
120
+ "loss": 0.9994,
121
+ "step": 8500
122
+ },
123
+ {
124
+ "epoch": 2.39,
125
+ "learning_rate": 3.9609310058187865e-05,
126
+ "loss": 0.9291,
127
+ "step": 9000
128
+ },
129
+ {
130
+ "epoch": 2.53,
131
+ "learning_rate": 3.891659739540039e-05,
132
+ "loss": 0.8958,
133
+ "step": 9500
134
+ },
135
+ {
136
+ "epoch": 2.66,
137
+ "learning_rate": 3.822388473261291e-05,
138
+ "loss": 0.8643,
139
+ "step": 10000
140
+ },
141
+ {
142
+ "epoch": 2.79,
143
+ "learning_rate": 3.753117206982544e-05,
144
+ "loss": 0.8633,
145
+ "step": 10500
146
+ },
147
+ {
148
+ "epoch": 2.93,
149
+ "learning_rate": 3.683845940703796e-05,
150
+ "loss": 0.8519,
151
+ "step": 11000
152
+ },
153
+ {
154
+ "epoch": 3.06,
155
+ "learning_rate": 3.614574674425049e-05,
156
+ "loss": 0.8366,
157
+ "step": 11500
158
+ },
159
+ {
160
+ "epoch": 3.19,
161
+ "learning_rate": 3.545303408146301e-05,
162
+ "loss": 0.8027,
163
+ "step": 12000
164
+ },
165
+ {
166
+ "epoch": 3.33,
167
+ "learning_rate": 3.4760321418675535e-05,
168
+ "loss": 0.7519,
169
+ "step": 12500
170
+ },
171
+ {
172
+ "epoch": 3.46,
173
+ "learning_rate": 3.4067608755888056e-05,
174
+ "loss": 0.7062,
175
+ "step": 13000
176
+ },
177
+ {
178
+ "epoch": 3.59,
179
+ "learning_rate": 3.337489609310058e-05,
180
+ "loss": 0.6797,
181
+ "step": 13500
182
+ },
183
+ {
184
+ "epoch": 3.72,
185
+ "learning_rate": 3.2682183430313104e-05,
186
+ "loss": 0.6629,
187
+ "step": 14000
188
+ },
189
+ {
190
+ "epoch": 3.86,
191
+ "learning_rate": 3.198947076752563e-05,
192
+ "loss": 0.6719,
193
+ "step": 14500
194
+ },
195
+ {
196
+ "epoch": 3.99,
197
+ "learning_rate": 3.129675810473816e-05,
198
+ "loss": 0.6519,
199
+ "step": 15000
200
+ },
201
+ {
202
+ "epoch": 3.99,
203
+ "eval_bleu": 51.6667,
204
+ "eval_gen_len": 13.4112,
205
+ "eval_loss": 1.3856228590011597,
206
+ "eval_runtime": 1615.8993,
207
+ "eval_samples_per_second": 18.609,
208
+ "eval_steps_per_second": 1.163,
209
+ "step": 15000
210
+ },
211
+ {
212
+ "epoch": 4.12,
213
+ "learning_rate": 3.060404544195068e-05,
214
+ "loss": 0.6434,
215
+ "step": 15500
216
+ },
217
+ {
218
+ "epoch": 4.26,
219
+ "learning_rate": 2.9911332779163203e-05,
220
+ "loss": 0.6042,
221
+ "step": 16000
222
+ },
223
+ {
224
+ "epoch": 4.39,
225
+ "learning_rate": 2.9218620116375727e-05,
226
+ "loss": 0.5549,
227
+ "step": 16500
228
+ },
229
+ {
230
+ "epoch": 4.52,
231
+ "learning_rate": 2.852590745358825e-05,
232
+ "loss": 0.535,
233
+ "step": 17000
234
+ },
235
+ {
236
+ "epoch": 4.66,
237
+ "learning_rate": 2.7833194790800778e-05,
238
+ "loss": 0.5144,
239
+ "step": 17500
240
+ },
241
+ {
242
+ "epoch": 4.79,
243
+ "learning_rate": 2.7140482128013302e-05,
244
+ "loss": 0.518,
245
+ "step": 18000
246
+ },
247
+ {
248
+ "epoch": 4.92,
249
+ "learning_rate": 2.6447769465225826e-05,
250
+ "loss": 0.5116,
251
+ "step": 18500
252
+ },
253
+ {
254
+ "epoch": 5.05,
255
+ "learning_rate": 2.575505680243835e-05,
256
+ "loss": 0.5012,
257
+ "step": 19000
258
+ },
259
+ {
260
+ "epoch": 5.19,
261
+ "learning_rate": 2.5062344139650874e-05,
262
+ "loss": 0.4845,
263
+ "step": 19500
264
+ },
265
+ {
266
+ "epoch": 5.32,
267
+ "learning_rate": 2.4369631476863397e-05,
268
+ "loss": 0.4486,
269
+ "step": 20000
270
+ },
271
+ {
272
+ "epoch": 5.45,
273
+ "learning_rate": 2.367691881407592e-05,
274
+ "loss": 0.4172,
275
+ "step": 20500
276
+ },
277
+ {
278
+ "epoch": 5.59,
279
+ "learning_rate": 2.2984206151288445e-05,
280
+ "loss": 0.4,
281
+ "step": 21000
282
+ },
283
+ {
284
+ "epoch": 5.72,
285
+ "learning_rate": 2.229149348850097e-05,
286
+ "loss": 0.3908,
287
+ "step": 21500
288
+ },
289
+ {
290
+ "epoch": 5.85,
291
+ "learning_rate": 2.1598780825713493e-05,
292
+ "loss": 0.4034,
293
+ "step": 22000
294
+ },
295
+ {
296
+ "epoch": 5.99,
297
+ "learning_rate": 2.0906068162926017e-05,
298
+ "loss": 0.3867,
299
+ "step": 22500
300
+ },
301
+ {
302
+ "epoch": 5.99,
303
+ "eval_bleu": 51.5686,
304
+ "eval_gen_len": 13.432,
305
+ "eval_loss": 1.5243059396743774,
306
+ "eval_runtime": 1619.767,
307
+ "eval_samples_per_second": 18.564,
308
+ "eval_steps_per_second": 1.161,
309
+ "step": 22500
310
+ },
311
+ {
312
+ "epoch": 6.12,
313
+ "learning_rate": 2.021335550013854e-05,
314
+ "loss": 0.3857,
315
+ "step": 23000
316
+ },
317
+ {
318
+ "epoch": 6.25,
319
+ "learning_rate": 1.9520642837351065e-05,
320
+ "loss": 0.3601,
321
+ "step": 23500
322
+ },
323
+ {
324
+ "epoch": 6.38,
325
+ "learning_rate": 1.8827930174563592e-05,
326
+ "loss": 0.3289,
327
+ "step": 24000
328
+ },
329
+ {
330
+ "epoch": 6.52,
331
+ "learning_rate": 1.8135217511776116e-05,
332
+ "loss": 0.3148,
333
+ "step": 24500
334
+ },
335
+ {
336
+ "epoch": 6.65,
337
+ "learning_rate": 1.744250484898864e-05,
338
+ "loss": 0.3033,
339
+ "step": 25000
340
+ },
341
+ {
342
+ "epoch": 6.78,
343
+ "learning_rate": 1.6749792186201167e-05,
344
+ "loss": 0.3056,
345
+ "step": 25500
346
+ },
347
+ {
348
+ "epoch": 6.92,
349
+ "learning_rate": 1.605707952341369e-05,
350
+ "loss": 0.3055,
351
+ "step": 26000
352
+ },
353
+ {
354
+ "epoch": 7.05,
355
+ "learning_rate": 1.5364366860626215e-05,
356
+ "loss": 0.2993,
357
+ "step": 26500
358
+ },
359
+ {
360
+ "epoch": 7.18,
361
+ "learning_rate": 1.4671654197838739e-05,
362
+ "loss": 0.2928,
363
+ "step": 27000
364
+ },
365
+ {
366
+ "epoch": 7.32,
367
+ "learning_rate": 1.3978941535051263e-05,
368
+ "loss": 0.2674,
369
+ "step": 27500
370
+ },
371
+ {
372
+ "epoch": 7.45,
373
+ "learning_rate": 1.3286228872263787e-05,
374
+ "loss": 0.2481,
375
+ "step": 28000
376
+ },
377
+ {
378
+ "epoch": 7.58,
379
+ "learning_rate": 1.259351620947631e-05,
380
+ "loss": 0.2385,
381
+ "step": 28500
382
+ },
383
+ {
384
+ "epoch": 7.71,
385
+ "learning_rate": 1.1900803546688833e-05,
386
+ "loss": 0.2339,
387
+ "step": 29000
388
+ },
389
+ {
390
+ "epoch": 7.85,
391
+ "learning_rate": 1.1208090883901359e-05,
392
+ "loss": 0.2439,
393
+ "step": 29500
394
+ },
395
+ {
396
+ "epoch": 7.98,
397
+ "learning_rate": 1.0515378221113883e-05,
398
+ "loss": 0.236,
399
+ "step": 30000
400
+ },
401
+ {
402
+ "epoch": 7.98,
403
+ "eval_bleu": 51.4674,
404
+ "eval_gen_len": 13.291,
405
+ "eval_loss": 1.6158065795898438,
406
+ "eval_runtime": 1612.187,
407
+ "eval_samples_per_second": 18.652,
408
+ "eval_steps_per_second": 1.166,
409
+ "step": 30000
410
+ }
411
+ ],
412
+ "logging_steps": 500,
413
+ "max_steps": 37590,
414
+ "num_train_epochs": 10,
415
+ "save_steps": 7500,
416
+ "total_flos": 4.16088915443712e+18,
417
+ "trial_name": null,
418
+ "trial_params": null
419
+ }
checkpoint-30000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc43c1fa357997a7641b8ec50104a7d6fe547fca49c5d5ed627d4c99d5e5c09d
3
+ size 4728
checkpoint-7500/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": true,
8
+ "architectures": [
9
+ "MBartForConditionalGeneration"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 1024,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 4096,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 12,
20
+ "decoder_start_token_id": 2,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 2,
28
+ "forced_bos_token_id": 250025,
29
+ "forced_eos_token_id": 2,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "max_length": 200,
44
+ "max_position_embeddings": 1024,
45
+ "model_type": "mbart",
46
+ "normalize_before": true,
47
+ "normalize_embedding": true,
48
+ "num_beams": 5,
49
+ "num_hidden_layers": 12,
50
+ "output_past": true,
51
+ "pad_token_id": 1,
52
+ "scale_embedding": true,
53
+ "static_position_embeddings": false,
54
+ "tokenizer_class": "MBart50Tokenizer",
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.34.1",
57
+ "use_cache": true,
58
+ "vocab_size": 250054
59
+ }
checkpoint-7500/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "forced_bos_token_id": 250025,
7
+ "forced_eos_token_id": 2,
8
+ "max_length": 200,
9
+ "num_beams": 5,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.34.1"
12
+ }
checkpoint-7500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a29e5adba8ec2a7fb3bedf9c1c2835e43ee53fc8b39af81979a61b1124f9a5a7
3
+ size 4887473903
checkpoint-7500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04f902714543a0d9c2de8dedf5311488c83e9f6397cb15213bf957c8c4c43f3a
3
+ size 2444694490
checkpoint-7500/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2203be15fc57126ede786179da3b76fd3ca404b5057599155f69b0c2ffc25aba
3
+ size 15024
checkpoint-7500/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b8cfeac661d7d1226d9654b3638ea4cab3430ce54e05148eed9c6145daabbf0
3
+ size 15024
checkpoint-7500/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0f19ba2b16c388d3d7296321250450872fb9cee8580ba9c111e3582dc561bd9
3
+ size 15024
checkpoint-7500/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31f86aa57505120b3fafdf4a2f10da384507f3ba0f41cf6f6f9cf79c9ad1eaa7
3
+ size 15024
checkpoint-7500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc4d7a566fb62540a0912e313d85071941fe007fd46aa0fa20edad857dd0f755
3
+ size 1064
checkpoint-7500/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
checkpoint-7500/special_tokens_map.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN",
28
+ "af_ZA",
29
+ "az_AZ",
30
+ "bn_IN",
31
+ "fa_IR",
32
+ "he_IL",
33
+ "hr_HR",
34
+ "id_ID",
35
+ "ka_GE",
36
+ "km_KH",
37
+ "mk_MK",
38
+ "ml_IN",
39
+ "mn_MN",
40
+ "mr_IN",
41
+ "pl_PL",
42
+ "ps_AF",
43
+ "pt_XX",
44
+ "sv_SE",
45
+ "sw_KE",
46
+ "ta_IN",
47
+ "te_IN",
48
+ "th_TH",
49
+ "tl_XX",
50
+ "uk_UA",
51
+ "ur_PK",
52
+ "xh_ZA",
53
+ "gl_ES",
54
+ "sl_SI"
55
+ ],
56
+ "bos_token": "<s>",
57
+ "cls_token": "<s>",
58
+ "eos_token": "</s>",
59
+ "mask_token": {
60
+ "content": "<mask>",
61
+ "lstrip": true,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ "pad_token": "<pad>",
67
+ "sep_token": "</s>",
68
+ "unk_token": "<unk>"
69
+ }
checkpoint-7500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:035e5ed43f8e238be4dd88ade3b92960da904cadf57ce02c14f5f59c4b531b91
3
+ size 17110043
checkpoint-7500/tokenizer_config.json ADDED
@@ -0,0 +1,528 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "ar_AR",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "250002": {
44
+ "content": "cs_CZ",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "250003": {
52
+ "content": "de_DE",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "250004": {
60
+ "content": "en_XX",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "250005": {
68
+ "content": "es_XX",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "250006": {
76
+ "content": "et_EE",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "250007": {
84
+ "content": "fi_FI",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "250008": {
92
+ "content": "fr_XX",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "250009": {
100
+ "content": "gu_IN",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "250010": {
108
+ "content": "hi_IN",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "250011": {
116
+ "content": "it_IT",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "250012": {
124
+ "content": "ja_XX",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "250013": {
132
+ "content": "kk_KZ",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "250014": {
140
+ "content": "ko_KR",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "250015": {
148
+ "content": "lt_LT",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "250016": {
156
+ "content": "lv_LV",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "250017": {
164
+ "content": "my_MM",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "250018": {
172
+ "content": "ne_NP",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "250019": {
180
+ "content": "nl_XX",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "250020": {
188
+ "content": "ro_RO",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "250021": {
196
+ "content": "ru_RU",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "250022": {
204
+ "content": "si_LK",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "250023": {
212
+ "content": "tr_TR",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "250024": {
220
+ "content": "vi_VN",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "250025": {
228
+ "content": "zh_CN",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "250026": {
236
+ "content": "af_ZA",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "250027": {
244
+ "content": "az_AZ",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "250028": {
252
+ "content": "bn_IN",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "250029": {
260
+ "content": "fa_IR",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "250030": {
268
+ "content": "he_IL",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "250031": {
276
+ "content": "hr_HR",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "250032": {
284
+ "content": "id_ID",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "250033": {
292
+ "content": "ka_GE",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "250034": {
300
+ "content": "km_KH",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "250035": {
308
+ "content": "mk_MK",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "250036": {
316
+ "content": "ml_IN",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "250037": {
324
+ "content": "mn_MN",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "250038": {
332
+ "content": "mr_IN",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "250039": {
340
+ "content": "pl_PL",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "250040": {
348
+ "content": "ps_AF",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "250041": {
356
+ "content": "pt_XX",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "250042": {
364
+ "content": "sv_SE",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "250043": {
372
+ "content": "sw_KE",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "250044": {
380
+ "content": "ta_IN",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "250045": {
388
+ "content": "te_IN",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "250046": {
396
+ "content": "th_TH",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "250047": {
404
+ "content": "tl_XX",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "250048": {
412
+ "content": "uk_UA",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "250049": {
420
+ "content": "ur_PK",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "250050": {
428
+ "content": "xh_ZA",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "250051": {
436
+ "content": "gl_ES",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "250052": {
444
+ "content": "sl_SI",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "250053": {
452
+ "content": "<mask>",
453
+ "lstrip": true,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ }
459
+ },
460
+ "additional_special_tokens": [
461
+ "ar_AR",
462
+ "cs_CZ",
463
+ "de_DE",
464
+ "en_XX",
465
+ "es_XX",
466
+ "et_EE",
467
+ "fi_FI",
468
+ "fr_XX",
469
+ "gu_IN",
470
+ "hi_IN",
471
+ "it_IT",
472
+ "ja_XX",
473
+ "kk_KZ",
474
+ "ko_KR",
475
+ "lt_LT",
476
+ "lv_LV",
477
+ "my_MM",
478
+ "ne_NP",
479
+ "nl_XX",
480
+ "ro_RO",
481
+ "ru_RU",
482
+ "si_LK",
483
+ "tr_TR",
484
+ "vi_VN",
485
+ "zh_CN",
486
+ "af_ZA",
487
+ "az_AZ",
488
+ "bn_IN",
489
+ "fa_IR",
490
+ "he_IL",
491
+ "hr_HR",
492
+ "id_ID",
493
+ "ka_GE",
494
+ "km_KH",
495
+ "mk_MK",
496
+ "ml_IN",
497
+ "mn_MN",
498
+ "mr_IN",
499
+ "pl_PL",
500
+ "ps_AF",
501
+ "pt_XX",
502
+ "sv_SE",
503
+ "sw_KE",
504
+ "ta_IN",
505
+ "te_IN",
506
+ "th_TH",
507
+ "tl_XX",
508
+ "uk_UA",
509
+ "ur_PK",
510
+ "xh_ZA",
511
+ "gl_ES",
512
+ "sl_SI"
513
+ ],
514
+ "bos_token": "<s>",
515
+ "clean_up_tokenization_spaces": true,
516
+ "cls_token": "<s>",
517
+ "eos_token": "</s>",
518
+ "language_codes": "ML50",
519
+ "mask_token": "<mask>",
520
+ "model_max_length": 1000000000000000019884624838656,
521
+ "pad_token": "<pad>",
522
+ "sep_token": "</s>",
523
+ "sp_model_kwargs": {},
524
+ "src_lang": "ko_KR",
525
+ "tgt_lang": "zh_CN",
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
checkpoint-7500/trainer_state.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.3103234767913818,
3
+ "best_model_checkpoint": "./kozh_mbartLarge_50p_run3_tokenize/checkpoint-7500",
4
+ "epoch": 1.9952114924181963,
5
+ "eval_steps": 7500,
6
+ "global_step": 7500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.13,
13
+ "learning_rate": 1.6666666666666667e-05,
14
+ "loss": 2.5913,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.27,
19
+ "learning_rate": 3.3333333333333335e-05,
20
+ "loss": 1.8919,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.4,
25
+ "learning_rate": 5e-05,
26
+ "loss": 1.7345,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.53,
31
+ "learning_rate": 4.930728733721253e-05,
32
+ "loss": 1.6451,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.67,
37
+ "learning_rate": 4.861457467442505e-05,
38
+ "loss": 1.5539,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.8,
43
+ "learning_rate": 4.792186201163758e-05,
44
+ "loss": 1.512,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.93,
49
+ "learning_rate": 4.72291493488501e-05,
50
+ "loss": 1.4671,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 1.06,
55
+ "learning_rate": 4.6536436686062625e-05,
56
+ "loss": 1.417,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 1.2,
61
+ "learning_rate": 4.5843724023275146e-05,
62
+ "loss": 1.3449,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 1.33,
67
+ "learning_rate": 4.515101136048767e-05,
68
+ "loss": 1.2543,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 1.46,
73
+ "learning_rate": 4.4458298697700194e-05,
74
+ "loss": 1.1794,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 1.6,
79
+ "learning_rate": 4.376558603491272e-05,
80
+ "loss": 1.1359,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 1.73,
85
+ "learning_rate": 4.307287337212524e-05,
86
+ "loss": 1.1075,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 1.86,
91
+ "learning_rate": 4.238016070933777e-05,
92
+ "loss": 1.1079,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 2.0,
97
+ "learning_rate": 4.168744804655029e-05,
98
+ "loss": 1.0808,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 2.0,
103
+ "eval_bleu": 51.0184,
104
+ "eval_gen_len": 13.3575,
105
+ "eval_loss": 1.3103234767913818,
106
+ "eval_runtime": 1625.4898,
107
+ "eval_samples_per_second": 18.499,
108
+ "eval_steps_per_second": 1.157,
109
+ "step": 7500
110
+ }
111
+ ],
112
+ "logging_steps": 500,
113
+ "max_steps": 37590,
114
+ "num_train_epochs": 10,
115
+ "save_steps": 7500,
116
+ "total_flos": 1.04022228860928e+18,
117
+ "trial_name": null,
118
+ "trial_params": null
119
+ }
checkpoint-7500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc43c1fa357997a7641b8ec50104a7d6fe547fca49c5d5ed627d4c99d5e5c09d
3
+ size 4728
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": true,
8
+ "architectures": [
9
+ "MBartForConditionalGeneration"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 1024,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 4096,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 12,
20
+ "decoder_start_token_id": 2,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 2,
28
+ "forced_bos_token_id": 250025,
29
+ "forced_eos_token_id": 2,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "max_length": 200,
44
+ "max_position_embeddings": 1024,
45
+ "model_type": "mbart",
46
+ "normalize_before": true,
47
+ "normalize_embedding": true,
48
+ "num_beams": 5,
49
+ "num_hidden_layers": 12,
50
+ "output_past": true,
51
+ "pad_token_id": 1,
52
+ "scale_embedding": true,
53
+ "static_position_embeddings": false,
54
+ "tokenizer_class": "MBart50Tokenizer",
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.34.1",
57
+ "use_cache": true,
58
+ "vocab_size": 250054
59
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 7.98,
3
+ "eval_bleu": 51.0209,
4
+ "eval_gen_len": 13.3475,
5
+ "eval_loss": 1.3103234767913818,
6
+ "eval_runtime": 1618.9873,
7
+ "eval_samples": 30070,
8
+ "eval_samples_per_second": 18.573,
9
+ "eval_steps_per_second": 1.161
10
+ }
generated_predictions.txt ADDED
The diff for this file is too large to render. See raw diff
 
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "forced_bos_token_id": 250025,
7
+ "forced_eos_token_id": 2,
8
+ "max_length": 200,
9
+ "num_beams": 5,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.34.1"
12
+ }
predict_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "predict_bleu": 51.1483,
3
+ "predict_gen_len": 13.278,
4
+ "predict_loss": 1.3004177808761597,
5
+ "predict_runtime": 1614.5402,
6
+ "predict_samples": 30071,
7
+ "predict_samples_per_second": 18.625,
8
+ "predict_steps_per_second": 1.164
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04f902714543a0d9c2de8dedf5311488c83e9f6397cb15213bf957c8c4c43f3a
3
+ size 2444694490
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN",
28
+ "af_ZA",
29
+ "az_AZ",
30
+ "bn_IN",
31
+ "fa_IR",
32
+ "he_IL",
33
+ "hr_HR",
34
+ "id_ID",
35
+ "ka_GE",
36
+ "km_KH",
37
+ "mk_MK",
38
+ "ml_IN",
39
+ "mn_MN",
40
+ "mr_IN",
41
+ "pl_PL",
42
+ "ps_AF",
43
+ "pt_XX",
44
+ "sv_SE",
45
+ "sw_KE",
46
+ "ta_IN",
47
+ "te_IN",
48
+ "th_TH",
49
+ "tl_XX",
50
+ "uk_UA",
51
+ "ur_PK",
52
+ "xh_ZA",
53
+ "gl_ES",
54
+ "sl_SI"
55
+ ],
56
+ "bos_token": "<s>",
57
+ "cls_token": "<s>",
58
+ "eos_token": "</s>",
59
+ "mask_token": {
60
+ "content": "<mask>",
61
+ "lstrip": true,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ "pad_token": "<pad>",
67
+ "sep_token": "</s>",
68
+ "unk_token": "<unk>"
69
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:035e5ed43f8e238be4dd88ade3b92960da904cadf57ce02c14f5f59c4b531b91
3
+ size 17110043
tokenizer_config.json ADDED
@@ -0,0 +1,528 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "ar_AR",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "250002": {
44
+ "content": "cs_CZ",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "250003": {
52
+ "content": "de_DE",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "250004": {
60
+ "content": "en_XX",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "250005": {
68
+ "content": "es_XX",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "250006": {
76
+ "content": "et_EE",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "250007": {
84
+ "content": "fi_FI",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "250008": {
92
+ "content": "fr_XX",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "250009": {
100
+ "content": "gu_IN",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "250010": {
108
+ "content": "hi_IN",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "250011": {
116
+ "content": "it_IT",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "250012": {
124
+ "content": "ja_XX",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "250013": {
132
+ "content": "kk_KZ",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "250014": {
140
+ "content": "ko_KR",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "250015": {
148
+ "content": "lt_LT",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "250016": {
156
+ "content": "lv_LV",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "250017": {
164
+ "content": "my_MM",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "250018": {
172
+ "content": "ne_NP",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "250019": {
180
+ "content": "nl_XX",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "250020": {
188
+ "content": "ro_RO",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "250021": {
196
+ "content": "ru_RU",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "250022": {
204
+ "content": "si_LK",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "250023": {
212
+ "content": "tr_TR",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "250024": {
220
+ "content": "vi_VN",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "250025": {
228
+ "content": "zh_CN",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "250026": {
236
+ "content": "af_ZA",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "250027": {
244
+ "content": "az_AZ",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "250028": {
252
+ "content": "bn_IN",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "250029": {
260
+ "content": "fa_IR",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "250030": {
268
+ "content": "he_IL",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "250031": {
276
+ "content": "hr_HR",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "250032": {
284
+ "content": "id_ID",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "250033": {
292
+ "content": "ka_GE",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "250034": {
300
+ "content": "km_KH",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "250035": {
308
+ "content": "mk_MK",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "250036": {
316
+ "content": "ml_IN",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "250037": {
324
+ "content": "mn_MN",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "250038": {
332
+ "content": "mr_IN",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "250039": {
340
+ "content": "pl_PL",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "250040": {
348
+ "content": "ps_AF",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "250041": {
356
+ "content": "pt_XX",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "250042": {
364
+ "content": "sv_SE",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "250043": {
372
+ "content": "sw_KE",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "250044": {
380
+ "content": "ta_IN",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "250045": {
388
+ "content": "te_IN",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "250046": {
396
+ "content": "th_TH",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "250047": {
404
+ "content": "tl_XX",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "250048": {
412
+ "content": "uk_UA",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "250049": {
420
+ "content": "ur_PK",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "250050": {
428
+ "content": "xh_ZA",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "250051": {
436
+ "content": "gl_ES",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "250052": {
444
+ "content": "sl_SI",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "250053": {
452
+ "content": "<mask>",
453
+ "lstrip": true,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ }
459
+ },
460
+ "additional_special_tokens": [
461
+ "ar_AR",
462
+ "cs_CZ",
463
+ "de_DE",
464
+ "en_XX",
465
+ "es_XX",
466
+ "et_EE",
467
+ "fi_FI",
468
+ "fr_XX",
469
+ "gu_IN",
470
+ "hi_IN",
471
+ "it_IT",
472
+ "ja_XX",
473
+ "kk_KZ",
474
+ "ko_KR",
475
+ "lt_LT",
476
+ "lv_LV",
477
+ "my_MM",
478
+ "ne_NP",
479
+ "nl_XX",
480
+ "ro_RO",
481
+ "ru_RU",
482
+ "si_LK",
483
+ "tr_TR",
484
+ "vi_VN",
485
+ "zh_CN",
486
+ "af_ZA",
487
+ "az_AZ",
488
+ "bn_IN",
489
+ "fa_IR",
490
+ "he_IL",
491
+ "hr_HR",
492
+ "id_ID",
493
+ "ka_GE",
494
+ "km_KH",
495
+ "mk_MK",
496
+ "ml_IN",
497
+ "mn_MN",
498
+ "mr_IN",
499
+ "pl_PL",
500
+ "ps_AF",
501
+ "pt_XX",
502
+ "sv_SE",
503
+ "sw_KE",
504
+ "ta_IN",
505
+ "te_IN",
506
+ "th_TH",
507
+ "tl_XX",
508
+ "uk_UA",
509
+ "ur_PK",
510
+ "xh_ZA",
511
+ "gl_ES",
512
+ "sl_SI"
513
+ ],
514
+ "bos_token": "<s>",
515
+ "clean_up_tokenization_spaces": true,
516
+ "cls_token": "<s>",
517
+ "eos_token": "</s>",
518
+ "language_codes": "ML50",
519
+ "mask_token": "<mask>",
520
+ "model_max_length": 1000000000000000019884624838656,
521
+ "pad_token": "<pad>",
522
+ "sep_token": "</s>",
523
+ "sp_model_kwargs": {},
524
+ "src_lang": "ko_KR",
525
+ "tgt_lang": "zh_CN",
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 7.98,
3
+ "train_loss": 0.7653622683207194,
4
+ "train_runtime": 99492.172,
5
+ "train_samples": 240570,
6
+ "train_samples_per_second": 24.18,
7
+ "train_steps_per_second": 0.378
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,428 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.3103234767913818,
3
+ "best_model_checkpoint": "./kozh_mbartLarge_50p_run3_tokenize/checkpoint-7500",
4
+ "epoch": 7.980845969672785,
5
+ "eval_steps": 7500,
6
+ "global_step": 30000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.13,
13
+ "learning_rate": 1.6666666666666667e-05,
14
+ "loss": 2.5913,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.27,
19
+ "learning_rate": 3.3333333333333335e-05,
20
+ "loss": 1.8919,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.4,
25
+ "learning_rate": 5e-05,
26
+ "loss": 1.7345,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.53,
31
+ "learning_rate": 4.930728733721253e-05,
32
+ "loss": 1.6451,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.67,
37
+ "learning_rate": 4.861457467442505e-05,
38
+ "loss": 1.5539,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.8,
43
+ "learning_rate": 4.792186201163758e-05,
44
+ "loss": 1.512,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.93,
49
+ "learning_rate": 4.72291493488501e-05,
50
+ "loss": 1.4671,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 1.06,
55
+ "learning_rate": 4.6536436686062625e-05,
56
+ "loss": 1.417,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 1.2,
61
+ "learning_rate": 4.5843724023275146e-05,
62
+ "loss": 1.3449,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 1.33,
67
+ "learning_rate": 4.515101136048767e-05,
68
+ "loss": 1.2543,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 1.46,
73
+ "learning_rate": 4.4458298697700194e-05,
74
+ "loss": 1.1794,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 1.6,
79
+ "learning_rate": 4.376558603491272e-05,
80
+ "loss": 1.1359,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 1.73,
85
+ "learning_rate": 4.307287337212524e-05,
86
+ "loss": 1.1075,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 1.86,
91
+ "learning_rate": 4.238016070933777e-05,
92
+ "loss": 1.1079,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 2.0,
97
+ "learning_rate": 4.168744804655029e-05,
98
+ "loss": 1.0808,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 2.0,
103
+ "eval_bleu": 51.0184,
104
+ "eval_gen_len": 13.3575,
105
+ "eval_loss": 1.3103234767913818,
106
+ "eval_runtime": 1625.4898,
107
+ "eval_samples_per_second": 18.499,
108
+ "eval_steps_per_second": 1.157,
109
+ "step": 7500
110
+ },
111
+ {
112
+ "epoch": 2.13,
113
+ "learning_rate": 4.099473538376282e-05,
114
+ "loss": 1.053,
115
+ "step": 8000
116
+ },
117
+ {
118
+ "epoch": 2.26,
119
+ "learning_rate": 4.0302022720975344e-05,
120
+ "loss": 0.9994,
121
+ "step": 8500
122
+ },
123
+ {
124
+ "epoch": 2.39,
125
+ "learning_rate": 3.9609310058187865e-05,
126
+ "loss": 0.9291,
127
+ "step": 9000
128
+ },
129
+ {
130
+ "epoch": 2.53,
131
+ "learning_rate": 3.891659739540039e-05,
132
+ "loss": 0.8958,
133
+ "step": 9500
134
+ },
135
+ {
136
+ "epoch": 2.66,
137
+ "learning_rate": 3.822388473261291e-05,
138
+ "loss": 0.8643,
139
+ "step": 10000
140
+ },
141
+ {
142
+ "epoch": 2.79,
143
+ "learning_rate": 3.753117206982544e-05,
144
+ "loss": 0.8633,
145
+ "step": 10500
146
+ },
147
+ {
148
+ "epoch": 2.93,
149
+ "learning_rate": 3.683845940703796e-05,
150
+ "loss": 0.8519,
151
+ "step": 11000
152
+ },
153
+ {
154
+ "epoch": 3.06,
155
+ "learning_rate": 3.614574674425049e-05,
156
+ "loss": 0.8366,
157
+ "step": 11500
158
+ },
159
+ {
160
+ "epoch": 3.19,
161
+ "learning_rate": 3.545303408146301e-05,
162
+ "loss": 0.8027,
163
+ "step": 12000
164
+ },
165
+ {
166
+ "epoch": 3.33,
167
+ "learning_rate": 3.4760321418675535e-05,
168
+ "loss": 0.7519,
169
+ "step": 12500
170
+ },
171
+ {
172
+ "epoch": 3.46,
173
+ "learning_rate": 3.4067608755888056e-05,
174
+ "loss": 0.7062,
175
+ "step": 13000
176
+ },
177
+ {
178
+ "epoch": 3.59,
179
+ "learning_rate": 3.337489609310058e-05,
180
+ "loss": 0.6797,
181
+ "step": 13500
182
+ },
183
+ {
184
+ "epoch": 3.72,
185
+ "learning_rate": 3.2682183430313104e-05,
186
+ "loss": 0.6629,
187
+ "step": 14000
188
+ },
189
+ {
190
+ "epoch": 3.86,
191
+ "learning_rate": 3.198947076752563e-05,
192
+ "loss": 0.6719,
193
+ "step": 14500
194
+ },
195
+ {
196
+ "epoch": 3.99,
197
+ "learning_rate": 3.129675810473816e-05,
198
+ "loss": 0.6519,
199
+ "step": 15000
200
+ },
201
+ {
202
+ "epoch": 3.99,
203
+ "eval_bleu": 51.6667,
204
+ "eval_gen_len": 13.4112,
205
+ "eval_loss": 1.3856228590011597,
206
+ "eval_runtime": 1615.8993,
207
+ "eval_samples_per_second": 18.609,
208
+ "eval_steps_per_second": 1.163,
209
+ "step": 15000
210
+ },
211
+ {
212
+ "epoch": 4.12,
213
+ "learning_rate": 3.060404544195068e-05,
214
+ "loss": 0.6434,
215
+ "step": 15500
216
+ },
217
+ {
218
+ "epoch": 4.26,
219
+ "learning_rate": 2.9911332779163203e-05,
220
+ "loss": 0.6042,
221
+ "step": 16000
222
+ },
223
+ {
224
+ "epoch": 4.39,
225
+ "learning_rate": 2.9218620116375727e-05,
226
+ "loss": 0.5549,
227
+ "step": 16500
228
+ },
229
+ {
230
+ "epoch": 4.52,
231
+ "learning_rate": 2.852590745358825e-05,
232
+ "loss": 0.535,
233
+ "step": 17000
234
+ },
235
+ {
236
+ "epoch": 4.66,
237
+ "learning_rate": 2.7833194790800778e-05,
238
+ "loss": 0.5144,
239
+ "step": 17500
240
+ },
241
+ {
242
+ "epoch": 4.79,
243
+ "learning_rate": 2.7140482128013302e-05,
244
+ "loss": 0.518,
245
+ "step": 18000
246
+ },
247
+ {
248
+ "epoch": 4.92,
249
+ "learning_rate": 2.6447769465225826e-05,
250
+ "loss": 0.5116,
251
+ "step": 18500
252
+ },
253
+ {
254
+ "epoch": 5.05,
255
+ "learning_rate": 2.575505680243835e-05,
256
+ "loss": 0.5012,
257
+ "step": 19000
258
+ },
259
+ {
260
+ "epoch": 5.19,
261
+ "learning_rate": 2.5062344139650874e-05,
262
+ "loss": 0.4845,
263
+ "step": 19500
264
+ },
265
+ {
266
+ "epoch": 5.32,
267
+ "learning_rate": 2.4369631476863397e-05,
268
+ "loss": 0.4486,
269
+ "step": 20000
270
+ },
271
+ {
272
+ "epoch": 5.45,
273
+ "learning_rate": 2.367691881407592e-05,
274
+ "loss": 0.4172,
275
+ "step": 20500
276
+ },
277
+ {
278
+ "epoch": 5.59,
279
+ "learning_rate": 2.2984206151288445e-05,
280
+ "loss": 0.4,
281
+ "step": 21000
282
+ },
283
+ {
284
+ "epoch": 5.72,
285
+ "learning_rate": 2.229149348850097e-05,
286
+ "loss": 0.3908,
287
+ "step": 21500
288
+ },
289
+ {
290
+ "epoch": 5.85,
291
+ "learning_rate": 2.1598780825713493e-05,
292
+ "loss": 0.4034,
293
+ "step": 22000
294
+ },
295
+ {
296
+ "epoch": 5.99,
297
+ "learning_rate": 2.0906068162926017e-05,
298
+ "loss": 0.3867,
299
+ "step": 22500
300
+ },
301
+ {
302
+ "epoch": 5.99,
303
+ "eval_bleu": 51.5686,
304
+ "eval_gen_len": 13.432,
305
+ "eval_loss": 1.5243059396743774,
306
+ "eval_runtime": 1619.767,
307
+ "eval_samples_per_second": 18.564,
308
+ "eval_steps_per_second": 1.161,
309
+ "step": 22500
310
+ },
311
+ {
312
+ "epoch": 6.12,
313
+ "learning_rate": 2.021335550013854e-05,
314
+ "loss": 0.3857,
315
+ "step": 23000
316
+ },
317
+ {
318
+ "epoch": 6.25,
319
+ "learning_rate": 1.9520642837351065e-05,
320
+ "loss": 0.3601,
321
+ "step": 23500
322
+ },
323
+ {
324
+ "epoch": 6.38,
325
+ "learning_rate": 1.8827930174563592e-05,
326
+ "loss": 0.3289,
327
+ "step": 24000
328
+ },
329
+ {
330
+ "epoch": 6.52,
331
+ "learning_rate": 1.8135217511776116e-05,
332
+ "loss": 0.3148,
333
+ "step": 24500
334
+ },
335
+ {
336
+ "epoch": 6.65,
337
+ "learning_rate": 1.744250484898864e-05,
338
+ "loss": 0.3033,
339
+ "step": 25000
340
+ },
341
+ {
342
+ "epoch": 6.78,
343
+ "learning_rate": 1.6749792186201167e-05,
344
+ "loss": 0.3056,
345
+ "step": 25500
346
+ },
347
+ {
348
+ "epoch": 6.92,
349
+ "learning_rate": 1.605707952341369e-05,
350
+ "loss": 0.3055,
351
+ "step": 26000
352
+ },
353
+ {
354
+ "epoch": 7.05,
355
+ "learning_rate": 1.5364366860626215e-05,
356
+ "loss": 0.2993,
357
+ "step": 26500
358
+ },
359
+ {
360
+ "epoch": 7.18,
361
+ "learning_rate": 1.4671654197838739e-05,
362
+ "loss": 0.2928,
363
+ "step": 27000
364
+ },
365
+ {
366
+ "epoch": 7.32,
367
+ "learning_rate": 1.3978941535051263e-05,
368
+ "loss": 0.2674,
369
+ "step": 27500
370
+ },
371
+ {
372
+ "epoch": 7.45,
373
+ "learning_rate": 1.3286228872263787e-05,
374
+ "loss": 0.2481,
375
+ "step": 28000
376
+ },
377
+ {
378
+ "epoch": 7.58,
379
+ "learning_rate": 1.259351620947631e-05,
380
+ "loss": 0.2385,
381
+ "step": 28500
382
+ },
383
+ {
384
+ "epoch": 7.71,
385
+ "learning_rate": 1.1900803546688833e-05,
386
+ "loss": 0.2339,
387
+ "step": 29000
388
+ },
389
+ {
390
+ "epoch": 7.85,
391
+ "learning_rate": 1.1208090883901359e-05,
392
+ "loss": 0.2439,
393
+ "step": 29500
394
+ },
395
+ {
396
+ "epoch": 7.98,
397
+ "learning_rate": 1.0515378221113883e-05,
398
+ "loss": 0.236,
399
+ "step": 30000
400
+ },
401
+ {
402
+ "epoch": 7.98,
403
+ "eval_bleu": 51.4674,
404
+ "eval_gen_len": 13.291,
405
+ "eval_loss": 1.6158065795898438,
406
+ "eval_runtime": 1612.187,
407
+ "eval_samples_per_second": 18.652,
408
+ "eval_steps_per_second": 1.166,
409
+ "step": 30000
410
+ },
411
+ {
412
+ "epoch": 7.98,
413
+ "step": 30000,
414
+ "total_flos": 4.16088915443712e+18,
415
+ "train_loss": 0.7653622683207194,
416
+ "train_runtime": 99492.172,
417
+ "train_samples_per_second": 24.18,
418
+ "train_steps_per_second": 0.378
419
+ }
420
+ ],
421
+ "logging_steps": 500,
422
+ "max_steps": 37590,
423
+ "num_train_epochs": 10,
424
+ "save_steps": 7500,
425
+ "total_flos": 4.16088915443712e+18,
426
+ "trial_name": null,
427
+ "trial_params": null
428
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc43c1fa357997a7641b8ec50104a7d6fe547fca49c5d5ed627d4c99d5e5c09d
3
+ size 4728