Hugging Face's logo

yesj1234
/
mbart-mmt_mid3_ko-ja

Text2Text Generation
Transformers
PyTorch
Korean
Japanese
mbart
Generated from Trainer
Inference Endpoints
Model card Files Community
yesj1234 commited on
Commit
21cd619
•
1 Parent(s): 87ae9d3

Upload folder using huggingface_hub

Browse files
Files changed (49) hide show
  1. .gitattributes +3 -0
  2. README.md +89 -0
  3. added_tokens.json +59 -0
  4. all_results.json +22 -0
  5. checkpoint-25500/added_tokens.json +59 -0
  6. checkpoint-25500/config.json +59 -0
  7. checkpoint-25500/generation_config.json +12 -0
  8. checkpoint-25500/optimizer.pt +3 -0
  9. checkpoint-25500/pytorch_model.bin +3 -0
  10. checkpoint-25500/rng_state_0.pth +3 -0
  11. checkpoint-25500/rng_state_1.pth +3 -0
  12. checkpoint-25500/rng_state_2.pth +3 -0
  13. checkpoint-25500/rng_state_3.pth +3 -0
  14. checkpoint-25500/scheduler.pt +3 -0
  15. checkpoint-25500/sentencepiece.bpe.model +3 -0
  16. checkpoint-25500/special_tokens_map.json +63 -0
  17. checkpoint-25500/tokenizer.json +3 -0
  18. checkpoint-25500/tokenizer_config.json +528 -0
  19. checkpoint-25500/trainer_state.json +495 -0
  20. checkpoint-25500/training_args.bin +3 -0
  21. checkpoint-31500/added_tokens.json +59 -0
  22. checkpoint-31500/config.json +59 -0
  23. checkpoint-31500/generation_config.json +12 -0
  24. checkpoint-31500/optimizer.pt +3 -0
  25. checkpoint-31500/pytorch_model.bin +3 -0
  26. checkpoint-31500/rng_state_0.pth +3 -0
  27. checkpoint-31500/rng_state_1.pth +3 -0
  28. checkpoint-31500/rng_state_2.pth +3 -0
  29. checkpoint-31500/rng_state_3.pth +3 -0
  30. checkpoint-31500/scheduler.pt +3 -0
  31. checkpoint-31500/sentencepiece.bpe.model +3 -0
  32. checkpoint-31500/special_tokens_map.json +63 -0
  33. checkpoint-31500/tokenizer.json +3 -0
  34. checkpoint-31500/tokenizer_config.json +528 -0
  35. checkpoint-31500/trainer_state.json +607 -0
  36. checkpoint-31500/training_args.bin +3 -0
  37. config.json +59 -0
  38. eval_results.json +10 -0
  39. generated_predictions.txt +0 -0
  40. generation_config.json +12 -0
  41. predict_results.json +9 -0
  42. pytorch_model.bin +3 -0
  43. sentencepiece.bpe.model +3 -0
  44. special_tokens_map.json +63 -0
  45. tokenizer.json +3 -0
  46. tokenizer_config.json +528 -0
  47. train_results.json +8 -0
  48. trainer_state.json +616 -0
  49. 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-25500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-31500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ko
4
+ - ja
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: mbart-mmt_mid3_ko-ja
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
+ # mbart-mmt_mid3_ko-ja
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: 0.8652
23
+ - Bleu: 10.1883
24
+ - Gen Len: 17.2057
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: 2
50
+ - total_train_batch_size: 32
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: 500
55
+ - num_epochs: 35
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
60
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
61
+ | 1.6216 | 0.23 | 1500 | 1.5229 | 2.686 | 17.599 |
62
+ | 1.3587 | 0.46 | 3000 | 1.3061 | 4.0749 | 17.3772 |
63
+ | 1.2279 | 0.68 | 4500 | 1.1881 | 5.2878 | 17.3642 |
64
+ | 1.1408 | 0.91 | 6000 | 1.0994 | 5.4783 | 17.4093 |
65
+ | 0.9977 | 1.14 | 7500 | 1.0313 | 7.6015 | 17.36 |
66
+ | 0.9582 | 1.37 | 9000 | 0.9918 | 8.2303 | 17.3526 |
67
+ | 0.9525 | 1.59 | 10500 | 0.9811 | 8.2837 | 17.2597 |
68
+ | 0.9415 | 1.82 | 12000 | 0.9589 | 8.1592 | 17.2241 |
69
+ | 0.856 | 2.05 | 13500 | 0.9462 | 7.8401 | 17.4066 |
70
+ | 0.8273 | 2.28 | 15000 | 0.9336 | 8.6082 | 17.1918 |
71
+ | 0.8066 | 2.5 | 16500 | 0.9220 | 9.7751 | 17.5198 |
72
+ | 0.784 | 2.73 | 18000 | 0.8949 | 10.292 | 17.4097 |
73
+ | 0.8016 | 2.96 | 19500 | 0.8958 | 9.0262 | 17.4097 |
74
+ | 0.6872 | 3.19 | 21000 | 0.9043 | 9.7549 | 17.2672 |
75
+ | 0.7107 | 3.42 | 22500 | 0.8994 | 10.3016 | 17.0973 |
76
+ | 0.6726 | 3.64 | 24000 | 0.8747 | 10.5183 | 17.2871 |
77
+ | 0.6699 | 3.87 | 25500 | 0.8652 | 10.1883 | 17.2057 |
78
+ | 0.612 | 4.1 | 27000 | 0.8949 | 9.5697 | 17.2443 |
79
+ | 0.621 | 4.33 | 28500 | 0.8904 | 10.8592 | 17.329 |
80
+ | 0.6219 | 4.55 | 30000 | 0.8772 | 10.925 | 17.482 |
81
+ | 0.6164 | 4.78 | 31500 | 0.8694 | 11.8749 | 17.1624 |
82
+
83
+
84
+ ### Framework versions
85
+
86
+ - Transformers 4.34.0
87
+ - Pytorch 2.1.0+cu121
88
+ - Datasets 2.14.5
89
+ - Tokenizers 0.14.1
added_tokens.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<mask>": 250053,
4
+ "<pad>": 1,
5
+ "<s>": 0,
6
+ "<unk>": 3,
7
+ "af_ZA": 250026,
8
+ "ar_AR": 250001,
9
+ "az_AZ": 250027,
10
+ "bn_IN": 250028,
11
+ "cs_CZ": 250002,
12
+ "de_DE": 250003,
13
+ "en_XX": 250004,
14
+ "es_XX": 250005,
15
+ "et_EE": 250006,
16
+ "fa_IR": 250029,
17
+ "fi_FI": 250007,
18
+ "fr_XX": 250008,
19
+ "gl_ES": 250051,
20
+ "gu_IN": 250009,
21
+ "he_IL": 250030,
22
+ "hi_IN": 250010,
23
+ "hr_HR": 250031,
24
+ "id_ID": 250032,
25
+ "it_IT": 250011,
26
+ "ja_XX": 250012,
27
+ "ka_GE": 250033,
28
+ "kk_KZ": 250013,
29
+ "km_KH": 250034,
30
+ "ko_KR": 250014,
31
+ "lt_LT": 250015,
32
+ "lv_LV": 250016,
33
+ "mk_MK": 250035,
34
+ "ml_IN": 250036,
35
+ "mn_MN": 250037,
36
+ "mr_IN": 250038,
37
+ "my_MM": 250017,
38
+ "ne_NP": 250018,
39
+ "nl_XX": 250019,
40
+ "pl_PL": 250039,
41
+ "ps_AF": 250040,
42
+ "pt_XX": 250041,
43
+ "ro_RO": 250020,
44
+ "ru_RU": 250021,
45
+ "si_LK": 250022,
46
+ "sl_SI": 250052,
47
+ "sv_SE": 250042,
48
+ "sw_KE": 250043,
49
+ "ta_IN": 250044,
50
+ "te_IN": 250045,
51
+ "th_TH": 250046,
52
+ "tl_XX": 250047,
53
+ "tr_TR": 250023,
54
+ "uk_UA": 250048,
55
+ "ur_PK": 250049,
56
+ "vi_VN": 250024,
57
+ "xh_ZA": 250050,
58
+ "zh_CN": 250025
59
+ }
all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.78,
3
+ "eval_bleu": 10.1883,
4
+ "eval_gen_len": 17.2057,
5
+ "eval_loss": 0.865190327167511,
6
+ "eval_runtime": 852.9227,
7
+ "eval_samples": 13172,
8
+ "eval_samples_per_second": 15.443,
9
+ "eval_steps_per_second": 0.966,
10
+ "predict_bleu": 12.9009,
11
+ "predict_gen_len": 17.3525,
12
+ "predict_loss": 0.8587990403175354,
13
+ "predict_runtime": 852.0225,
14
+ "predict_samples": 13173,
15
+ "predict_samples_per_second": 15.461,
16
+ "predict_steps_per_second": 0.967,
17
+ "train_loss": 0.9323235357375372,
18
+ "train_runtime": 42332.75,
19
+ "train_samples": 105385,
20
+ "train_samples_per_second": 87.131,
21
+ "train_steps_per_second": 5.446
22
+ }
checkpoint-25500/added_tokens.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<mask>": 250053,
4
+ "<pad>": 1,
5
+ "<s>": 0,
6
+ "<unk>": 3,
7
+ "af_ZA": 250026,
8
+ "ar_AR": 250001,
9
+ "az_AZ": 250027,
10
+ "bn_IN": 250028,
11
+ "cs_CZ": 250002,
12
+ "de_DE": 250003,
13
+ "en_XX": 250004,
14
+ "es_XX": 250005,
15
+ "et_EE": 250006,
16
+ "fa_IR": 250029,
17
+ "fi_FI": 250007,
18
+ "fr_XX": 250008,
19
+ "gl_ES": 250051,
20
+ "gu_IN": 250009,
21
+ "he_IL": 250030,
22
+ "hi_IN": 250010,
23
+ "hr_HR": 250031,
24
+ "id_ID": 250032,
25
+ "it_IT": 250011,
26
+ "ja_XX": 250012,
27
+ "ka_GE": 250033,
28
+ "kk_KZ": 250013,
29
+ "km_KH": 250034,
30
+ "ko_KR": 250014,
31
+ "lt_LT": 250015,
32
+ "lv_LV": 250016,
33
+ "mk_MK": 250035,
34
+ "ml_IN": 250036,
35
+ "mn_MN": 250037,
36
+ "mr_IN": 250038,
37
+ "my_MM": 250017,
38
+ "ne_NP": 250018,
39
+ "nl_XX": 250019,
40
+ "pl_PL": 250039,
41
+ "ps_AF": 250040,
42
+ "pt_XX": 250041,
43
+ "ro_RO": 250020,
44
+ "ru_RU": 250021,
45
+ "si_LK": 250022,
46
+ "sl_SI": 250052,
47
+ "sv_SE": 250042,
48
+ "sw_KE": 250043,
49
+ "ta_IN": 250044,
50
+ "te_IN": 250045,
51
+ "th_TH": 250046,
52
+ "tl_XX": 250047,
53
+ "tr_TR": 250023,
54
+ "uk_UA": 250048,
55
+ "ur_PK": 250049,
56
+ "vi_VN": 250024,
57
+ "xh_ZA": 250050,
58
+ "zh_CN": 250025
59
+ }
checkpoint-25500/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": 250012,
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": "4.34.0",
57
+ "use_cache": true,
58
+ "vocab_size": 250054
59
+ }
checkpoint-25500/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": 250012,
7
+ "forced_eos_token_id": 2,
8
+ "max_length": 200,
9
+ "num_beams": 5,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.34.0"
12
+ }
checkpoint-25500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8abe026330f789831997000ad4648be89a0d71a16d003919a6749736d8dbbfe
3
+ size 4887473903
checkpoint-25500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f258bcdd1f066aee1e118b0e00fc14c3548496a5043413075894fa0a8c8a3b4c
3
+ size 2444694490
checkpoint-25500/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48bd4adeec150c2f4ba12e6729bc97260a6d83ba4e6fa4d3dbe138ec3d6b96f3
3
+ size 15024
checkpoint-25500/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ef4f3003d00aeba00f432f3b1b23434f689722217acc9f5210225dee019a7fd
3
+ size 15024
checkpoint-25500/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58b418c246b1daa2dbd031b7c17ccab4864d06c4e20d91a0d9423d457a52a095
3
+ size 15024
checkpoint-25500/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:957688f8ff5badb1c5b34a3fb28ddb48f13203e0e217a26d5bab9e70986590fb
3
+ size 15024
checkpoint-25500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05cebe049035b5ec6afc344610f9a1f98dee4830325eda32f4c6368d38c8f8fb
3
+ size 1064
checkpoint-25500/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-25500/special_tokens_map.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<mask>",
60
+ "pad_token": "<pad>",
61
+ "sep_token": "</s>",
62
+ "unk_token": "<unk>"
63
+ }
checkpoint-25500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42a72efab312df69f4dda3c5e1d7eca7b8645f96023493a3834070caf20a2180
3
+ size 17109939
checkpoint-25500/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": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "250002": {
44
+ "content": "cs_CZ",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "250003": {
52
+ "content": "de_DE",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "250004": {
60
+ "content": "en_XX",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "250005": {
68
+ "content": "es_XX",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "250006": {
76
+ "content": "et_EE",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "250007": {
84
+ "content": "fi_FI",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "250008": {
92
+ "content": "fr_XX",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "250009": {
100
+ "content": "gu_IN",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "250010": {
108
+ "content": "hi_IN",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "250011": {
116
+ "content": "it_IT",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "250012": {
124
+ "content": "ja_XX",
125
+ "lstrip": true,
126
+ "normalized": false,
127
+ "rstrip": true,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "250013": {
132
+ "content": "kk_KZ",
133
+ "lstrip": true,
134
+ "normalized": false,
135
+ "rstrip": true,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "250014": {
140
+ "content": "ko_KR",
141
+ "lstrip": true,
142
+ "normalized": false,
143
+ "rstrip": true,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "250015": {
148
+ "content": "lt_LT",
149
+ "lstrip": true,
150
+ "normalized": false,
151
+ "rstrip": true,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "250016": {
156
+ "content": "lv_LV",
157
+ "lstrip": true,
158
+ "normalized": false,
159
+ "rstrip": true,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "250017": {
164
+ "content": "my_MM",
165
+ "lstrip": true,
166
+ "normalized": false,
167
+ "rstrip": true,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "250018": {
172
+ "content": "ne_NP",
173
+ "lstrip": true,
174
+ "normalized": false,
175
+ "rstrip": true,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "250019": {
180
+ "content": "nl_XX",
181
+ "lstrip": true,
182
+ "normalized": false,
183
+ "rstrip": true,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "250020": {
188
+ "content": "ro_RO",
189
+ "lstrip": true,
190
+ "normalized": false,
191
+ "rstrip": true,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "250021": {
196
+ "content": "ru_RU",
197
+ "lstrip": true,
198
+ "normalized": false,
199
+ "rstrip": true,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "250022": {
204
+ "content": "si_LK",
205
+ "lstrip": true,
206
+ "normalized": false,
207
+ "rstrip": true,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "250023": {
212
+ "content": "tr_TR",
213
+ "lstrip": true,
214
+ "normalized": false,
215
+ "rstrip": true,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "250024": {
220
+ "content": "vi_VN",
221
+ "lstrip": true,
222
+ "normalized": false,
223
+ "rstrip": true,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "250025": {
228
+ "content": "zh_CN",
229
+ "lstrip": true,
230
+ "normalized": false,
231
+ "rstrip": true,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "250026": {
236
+ "content": "af_ZA",
237
+ "lstrip": true,
238
+ "normalized": false,
239
+ "rstrip": true,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "250027": {
244
+ "content": "az_AZ",
245
+ "lstrip": true,
246
+ "normalized": false,
247
+ "rstrip": true,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "250028": {
252
+ "content": "bn_IN",
253
+ "lstrip": true,
254
+ "normalized": false,
255
+ "rstrip": true,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "250029": {
260
+ "content": "fa_IR",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": true,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "250030": {
268
+ "content": "he_IL",
269
+ "lstrip": true,
270
+ "normalized": false,
271
+ "rstrip": true,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "250031": {
276
+ "content": "hr_HR",
277
+ "lstrip": true,
278
+ "normalized": false,
279
+ "rstrip": true,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "250032": {
284
+ "content": "id_ID",
285
+ "lstrip": true,
286
+ "normalized": false,
287
+ "rstrip": true,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "250033": {
292
+ "content": "ka_GE",
293
+ "lstrip": true,
294
+ "normalized": false,
295
+ "rstrip": true,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "250034": {
300
+ "content": "km_KH",
301
+ "lstrip": true,
302
+ "normalized": false,
303
+ "rstrip": true,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "250035": {
308
+ "content": "mk_MK",
309
+ "lstrip": true,
310
+ "normalized": false,
311
+ "rstrip": true,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "250036": {
316
+ "content": "ml_IN",
317
+ "lstrip": true,
318
+ "normalized": false,
319
+ "rstrip": true,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "250037": {
324
+ "content": "mn_MN",
325
+ "lstrip": true,
326
+ "normalized": false,
327
+ "rstrip": true,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "250038": {
332
+ "content": "mr_IN",
333
+ "lstrip": true,
334
+ "normalized": false,
335
+ "rstrip": true,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "250039": {
340
+ "content": "pl_PL",
341
+ "lstrip": true,
342
+ "normalized": false,
343
+ "rstrip": true,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "250040": {
348
+ "content": "ps_AF",
349
+ "lstrip": true,
350
+ "normalized": false,
351
+ "rstrip": true,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "250041": {
356
+ "content": "pt_XX",
357
+ "lstrip": true,
358
+ "normalized": false,
359
+ "rstrip": true,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "250042": {
364
+ "content": "sv_SE",
365
+ "lstrip": true,
366
+ "normalized": false,
367
+ "rstrip": true,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "250043": {
372
+ "content": "sw_KE",
373
+ "lstrip": true,
374
+ "normalized": false,
375
+ "rstrip": true,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "250044": {
380
+ "content": "ta_IN",
381
+ "lstrip": true,
382
+ "normalized": false,
383
+ "rstrip": true,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "250045": {
388
+ "content": "te_IN",
389
+ "lstrip": true,
390
+ "normalized": false,
391
+ "rstrip": true,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "250046": {
396
+ "content": "th_TH",
397
+ "lstrip": true,
398
+ "normalized": false,
399
+ "rstrip": true,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "250047": {
404
+ "content": "tl_XX",
405
+ "lstrip": true,
406
+ "normalized": false,
407
+ "rstrip": true,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "250048": {
412
+ "content": "uk_UA",
413
+ "lstrip": true,
414
+ "normalized": false,
415
+ "rstrip": true,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "250049": {
420
+ "content": "ur_PK",
421
+ "lstrip": true,
422
+ "normalized": false,
423
+ "rstrip": true,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "250050": {
428
+ "content": "xh_ZA",
429
+ "lstrip": true,
430
+ "normalized": false,
431
+ "rstrip": true,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "250051": {
436
+ "content": "gl_ES",
437
+ "lstrip": true,
438
+ "normalized": false,
439
+ "rstrip": true,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "250052": {
444
+ "content": "sl_SI",
445
+ "lstrip": true,
446
+ "normalized": false,
447
+ "rstrip": true,
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": "ja_XX",
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
checkpoint-25500/trainer_state.json ADDED
@@ -0,0 +1,495 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.865190327167511,
3
+ "best_model_checkpoint": "./mbart-mmt_mid3_ko-ja/checkpoint-25500",
4
+ "epoch": 3.8712615758311824,
5
+ "eval_steps": 1500,
6
+ "global_step": 25500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.08,
13
+ "learning_rate": 5e-05,
14
+ "loss": 3.3601,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.15,
19
+ "learning_rate": 4.98913256102067e-05,
20
+ "loss": 2.106,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.23,
25
+ "learning_rate": 4.97826512204134e-05,
26
+ "loss": 1.6216,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.23,
31
+ "eval_bleu": 2.686,
32
+ "eval_gen_len": 17.599,
33
+ "eval_loss": 1.522924780845642,
34
+ "eval_runtime": 866.1912,
35
+ "eval_samples_per_second": 15.207,
36
+ "eval_steps_per_second": 0.951,
37
+ "step": 1500
38
+ },
39
+ {
40
+ "epoch": 0.3,
41
+ "learning_rate": 4.96739768306201e-05,
42
+ "loss": 1.508,
43
+ "step": 2000
44
+ },
45
+ {
46
+ "epoch": 0.38,
47
+ "learning_rate": 4.95653024408268e-05,
48
+ "loss": 1.4292,
49
+ "step": 2500
50
+ },
51
+ {
52
+ "epoch": 0.46,
53
+ "learning_rate": 4.945662805103349e-05,
54
+ "loss": 1.3587,
55
+ "step": 3000
56
+ },
57
+ {
58
+ "epoch": 0.46,
59
+ "eval_bleu": 4.0749,
60
+ "eval_gen_len": 17.3772,
61
+ "eval_loss": 1.306133508682251,
62
+ "eval_runtime": 848.4414,
63
+ "eval_samples_per_second": 15.525,
64
+ "eval_steps_per_second": 0.971,
65
+ "step": 3000
66
+ },
67
+ {
68
+ "epoch": 0.53,
69
+ "learning_rate": 4.9347953661240194e-05,
70
+ "loss": 1.3063,
71
+ "step": 3500
72
+ },
73
+ {
74
+ "epoch": 0.61,
75
+ "learning_rate": 4.923927927144689e-05,
76
+ "loss": 1.2722,
77
+ "step": 4000
78
+ },
79
+ {
80
+ "epoch": 0.68,
81
+ "learning_rate": 4.9130604881653594e-05,
82
+ "loss": 1.2279,
83
+ "step": 4500
84
+ },
85
+ {
86
+ "epoch": 0.68,
87
+ "eval_bleu": 5.2878,
88
+ "eval_gen_len": 17.3642,
89
+ "eval_loss": 1.1880881786346436,
90
+ "eval_runtime": 848.9163,
91
+ "eval_samples_per_second": 15.516,
92
+ "eval_steps_per_second": 0.971,
93
+ "step": 4500
94
+ },
95
+ {
96
+ "epoch": 0.76,
97
+ "learning_rate": 4.902193049186029e-05,
98
+ "loss": 1.203,
99
+ "step": 5000
100
+ },
101
+ {
102
+ "epoch": 0.83,
103
+ "learning_rate": 4.891325610206699e-05,
104
+ "loss": 1.1744,
105
+ "step": 5500
106
+ },
107
+ {
108
+ "epoch": 0.91,
109
+ "learning_rate": 4.880458171227369e-05,
110
+ "loss": 1.1408,
111
+ "step": 6000
112
+ },
113
+ {
114
+ "epoch": 0.91,
115
+ "eval_bleu": 5.4783,
116
+ "eval_gen_len": 17.4093,
117
+ "eval_loss": 1.0994044542312622,
118
+ "eval_runtime": 903.2669,
119
+ "eval_samples_per_second": 14.583,
120
+ "eval_steps_per_second": 0.912,
121
+ "step": 6000
122
+ },
123
+ {
124
+ "epoch": 0.99,
125
+ "learning_rate": 4.8695907322480386e-05,
126
+ "loss": 1.1196,
127
+ "step": 6500
128
+ },
129
+ {
130
+ "epoch": 1.06,
131
+ "learning_rate": 4.858723293268709e-05,
132
+ "loss": 1.014,
133
+ "step": 7000
134
+ },
135
+ {
136
+ "epoch": 1.14,
137
+ "learning_rate": 4.847855854289378e-05,
138
+ "loss": 0.9977,
139
+ "step": 7500
140
+ },
141
+ {
142
+ "epoch": 1.14,
143
+ "eval_bleu": 7.6015,
144
+ "eval_gen_len": 17.36,
145
+ "eval_loss": 1.0312957763671875,
146
+ "eval_runtime": 872.8057,
147
+ "eval_samples_per_second": 15.092,
148
+ "eval_steps_per_second": 0.944,
149
+ "step": 7500
150
+ },
151
+ {
152
+ "epoch": 1.21,
153
+ "learning_rate": 4.836988415310048e-05,
154
+ "loss": 0.9903,
155
+ "step": 8000
156
+ },
157
+ {
158
+ "epoch": 1.29,
159
+ "learning_rate": 4.826120976330718e-05,
160
+ "loss": 0.9752,
161
+ "step": 8500
162
+ },
163
+ {
164
+ "epoch": 1.37,
165
+ "learning_rate": 4.815253537351388e-05,
166
+ "loss": 0.9582,
167
+ "step": 9000
168
+ },
169
+ {
170
+ "epoch": 1.37,
171
+ "eval_bleu": 8.2303,
172
+ "eval_gen_len": 17.3526,
173
+ "eval_loss": 0.9917855262756348,
174
+ "eval_runtime": 851.0578,
175
+ "eval_samples_per_second": 15.477,
176
+ "eval_steps_per_second": 0.968,
177
+ "step": 9000
178
+ },
179
+ {
180
+ "epoch": 1.44,
181
+ "learning_rate": 4.804386098372058e-05,
182
+ "loss": 0.9684,
183
+ "step": 9500
184
+ },
185
+ {
186
+ "epoch": 1.52,
187
+ "learning_rate": 4.793518659392728e-05,
188
+ "loss": 0.9641,
189
+ "step": 10000
190
+ },
191
+ {
192
+ "epoch": 1.59,
193
+ "learning_rate": 4.782651220413398e-05,
194
+ "loss": 0.9525,
195
+ "step": 10500
196
+ },
197
+ {
198
+ "epoch": 1.59,
199
+ "eval_bleu": 8.2837,
200
+ "eval_gen_len": 17.2597,
201
+ "eval_loss": 0.981093168258667,
202
+ "eval_runtime": 868.378,
203
+ "eval_samples_per_second": 15.169,
204
+ "eval_steps_per_second": 0.949,
205
+ "step": 10500
206
+ },
207
+ {
208
+ "epoch": 1.67,
209
+ "learning_rate": 4.7717837814340674e-05,
210
+ "loss": 0.943,
211
+ "step": 11000
212
+ },
213
+ {
214
+ "epoch": 1.75,
215
+ "learning_rate": 4.760916342454738e-05,
216
+ "loss": 0.936,
217
+ "step": 11500
218
+ },
219
+ {
220
+ "epoch": 1.82,
221
+ "learning_rate": 4.750048903475407e-05,
222
+ "loss": 0.9415,
223
+ "step": 12000
224
+ },
225
+ {
226
+ "epoch": 1.82,
227
+ "eval_bleu": 8.1592,
228
+ "eval_gen_len": 17.2241,
229
+ "eval_loss": 0.9589386582374573,
230
+ "eval_runtime": 853.0091,
231
+ "eval_samples_per_second": 15.442,
232
+ "eval_steps_per_second": 0.966,
233
+ "step": 12000
234
+ },
235
+ {
236
+ "epoch": 1.9,
237
+ "learning_rate": 4.739181464496077e-05,
238
+ "loss": 0.9327,
239
+ "step": 12500
240
+ },
241
+ {
242
+ "epoch": 1.97,
243
+ "learning_rate": 4.7283140255167467e-05,
244
+ "loss": 0.9219,
245
+ "step": 13000
246
+ },
247
+ {
248
+ "epoch": 2.05,
249
+ "learning_rate": 4.717446586537417e-05,
250
+ "loss": 0.856,
251
+ "step": 13500
252
+ },
253
+ {
254
+ "epoch": 2.05,
255
+ "eval_bleu": 7.8401,
256
+ "eval_gen_len": 17.4066,
257
+ "eval_loss": 0.9462171196937561,
258
+ "eval_runtime": 870.9328,
259
+ "eval_samples_per_second": 15.124,
260
+ "eval_steps_per_second": 0.946,
261
+ "step": 13500
262
+ },
263
+ {
264
+ "epoch": 2.13,
265
+ "learning_rate": 4.7065791475580866e-05,
266
+ "loss": 0.816,
267
+ "step": 14000
268
+ },
269
+ {
270
+ "epoch": 2.2,
271
+ "learning_rate": 4.695711708578757e-05,
272
+ "loss": 0.819,
273
+ "step": 14500
274
+ },
275
+ {
276
+ "epoch": 2.28,
277
+ "learning_rate": 4.6848442695994266e-05,
278
+ "loss": 0.8273,
279
+ "step": 15000
280
+ },
281
+ {
282
+ "epoch": 2.28,
283
+ "eval_bleu": 8.6082,
284
+ "eval_gen_len": 17.1918,
285
+ "eval_loss": 0.9335508942604065,
286
+ "eval_runtime": 847.8053,
287
+ "eval_samples_per_second": 15.537,
288
+ "eval_steps_per_second": 0.972,
289
+ "step": 15000
290
+ },
291
+ {
292
+ "epoch": 2.35,
293
+ "learning_rate": 4.673976830620096e-05,
294
+ "loss": 0.8154,
295
+ "step": 15500
296
+ },
297
+ {
298
+ "epoch": 2.43,
299
+ "learning_rate": 4.6631093916407665e-05,
300
+ "loss": 0.8281,
301
+ "step": 16000
302
+ },
303
+ {
304
+ "epoch": 2.5,
305
+ "learning_rate": 4.6522419526614355e-05,
306
+ "loss": 0.8066,
307
+ "step": 16500
308
+ },
309
+ {
310
+ "epoch": 2.5,
311
+ "eval_bleu": 9.7751,
312
+ "eval_gen_len": 17.5198,
313
+ "eval_loss": 0.921973466873169,
314
+ "eval_runtime": 888.35,
315
+ "eval_samples_per_second": 14.827,
316
+ "eval_steps_per_second": 0.928,
317
+ "step": 16500
318
+ },
319
+ {
320
+ "epoch": 2.58,
321
+ "learning_rate": 4.641374513682106e-05,
322
+ "loss": 0.812,
323
+ "step": 17000
324
+ },
325
+ {
326
+ "epoch": 2.66,
327
+ "learning_rate": 4.6305070747027754e-05,
328
+ "loss": 0.8117,
329
+ "step": 17500
330
+ },
331
+ {
332
+ "epoch": 2.73,
333
+ "learning_rate": 4.619639635723446e-05,
334
+ "loss": 0.784,
335
+ "step": 18000
336
+ },
337
+ {
338
+ "epoch": 2.73,
339
+ "eval_bleu": 10.292,
340
+ "eval_gen_len": 17.4097,
341
+ "eval_loss": 0.8948560357093811,
342
+ "eval_runtime": 887.752,
343
+ "eval_samples_per_second": 14.837,
344
+ "eval_steps_per_second": 0.928,
345
+ "step": 18000
346
+ },
347
+ {
348
+ "epoch": 2.81,
349
+ "learning_rate": 4.6087721967441154e-05,
350
+ "loss": 0.8113,
351
+ "step": 18500
352
+ },
353
+ {
354
+ "epoch": 2.88,
355
+ "learning_rate": 4.597904757764786e-05,
356
+ "loss": 0.7942,
357
+ "step": 19000
358
+ },
359
+ {
360
+ "epoch": 2.96,
361
+ "learning_rate": 4.5870373187854554e-05,
362
+ "loss": 0.8016,
363
+ "step": 19500
364
+ },
365
+ {
366
+ "epoch": 2.96,
367
+ "eval_bleu": 9.0262,
368
+ "eval_gen_len": 17.4097,
369
+ "eval_loss": 0.8958194255828857,
370
+ "eval_runtime": 868.3186,
371
+ "eval_samples_per_second": 15.17,
372
+ "eval_steps_per_second": 0.949,
373
+ "step": 19500
374
+ },
375
+ {
376
+ "epoch": 3.04,
377
+ "learning_rate": 4.576169879806125e-05,
378
+ "loss": 0.7417,
379
+ "step": 20000
380
+ },
381
+ {
382
+ "epoch": 3.11,
383
+ "learning_rate": 4.5653024408267946e-05,
384
+ "loss": 0.683,
385
+ "step": 20500
386
+ },
387
+ {
388
+ "epoch": 3.19,
389
+ "learning_rate": 4.554435001847465e-05,
390
+ "loss": 0.6872,
391
+ "step": 21000
392
+ },
393
+ {
394
+ "epoch": 3.19,
395
+ "eval_bleu": 9.7549,
396
+ "eval_gen_len": 17.2672,
397
+ "eval_loss": 0.9043093919754028,
398
+ "eval_runtime": 855.9409,
399
+ "eval_samples_per_second": 15.389,
400
+ "eval_steps_per_second": 0.963,
401
+ "step": 21000
402
+ },
403
+ {
404
+ "epoch": 3.26,
405
+ "learning_rate": 4.5435675628681346e-05,
406
+ "loss": 0.6928,
407
+ "step": 21500
408
+ },
409
+ {
410
+ "epoch": 3.34,
411
+ "learning_rate": 4.532700123888804e-05,
412
+ "loss": 0.6973,
413
+ "step": 22000
414
+ },
415
+ {
416
+ "epoch": 3.42,
417
+ "learning_rate": 4.5218326849094746e-05,
418
+ "loss": 0.7107,
419
+ "step": 22500
420
+ },
421
+ {
422
+ "epoch": 3.42,
423
+ "eval_bleu": 10.3016,
424
+ "eval_gen_len": 17.0973,
425
+ "eval_loss": 0.8993721008300781,
426
+ "eval_runtime": 837.6757,
427
+ "eval_samples_per_second": 15.724,
428
+ "eval_steps_per_second": 0.984,
429
+ "step": 22500
430
+ },
431
+ {
432
+ "epoch": 3.49,
433
+ "learning_rate": 4.510965245930144e-05,
434
+ "loss": 0.6899,
435
+ "step": 23000
436
+ },
437
+ {
438
+ "epoch": 3.57,
439
+ "learning_rate": 4.5000978069508145e-05,
440
+ "loss": 0.6794,
441
+ "step": 23500
442
+ },
443
+ {
444
+ "epoch": 3.64,
445
+ "learning_rate": 4.489230367971484e-05,
446
+ "loss": 0.6726,
447
+ "step": 24000
448
+ },
449
+ {
450
+ "epoch": 3.64,
451
+ "eval_bleu": 10.5183,
452
+ "eval_gen_len": 17.2871,
453
+ "eval_loss": 0.8746942281723022,
454
+ "eval_runtime": 850.8583,
455
+ "eval_samples_per_second": 15.481,
456
+ "eval_steps_per_second": 0.968,
457
+ "step": 24000
458
+ },
459
+ {
460
+ "epoch": 3.72,
461
+ "learning_rate": 4.4783629289921545e-05,
462
+ "loss": 0.6782,
463
+ "step": 24500
464
+ },
465
+ {
466
+ "epoch": 3.8,
467
+ "learning_rate": 4.4674954900128234e-05,
468
+ "loss": 0.6821,
469
+ "step": 25000
470
+ },
471
+ {
472
+ "epoch": 3.87,
473
+ "learning_rate": 4.456628051033494e-05,
474
+ "loss": 0.6699,
475
+ "step": 25500
476
+ },
477
+ {
478
+ "epoch": 3.87,
479
+ "eval_bleu": 10.1883,
480
+ "eval_gen_len": 17.2057,
481
+ "eval_loss": 0.865190327167511,
482
+ "eval_runtime": 852.5269,
483
+ "eval_samples_per_second": 15.451,
484
+ "eval_steps_per_second": 0.967,
485
+ "step": 25500
486
+ }
487
+ ],
488
+ "logging_steps": 500,
489
+ "max_steps": 230545,
490
+ "num_train_epochs": 35,
491
+ "save_steps": 1500,
492
+ "total_flos": 8.843276416230359e+17,
493
+ "trial_name": null,
494
+ "trial_params": null
495
+ }
checkpoint-25500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc9f6c6258b97f2d71469d8e4060b04e88838a9f1196109d8271a7ced4355f5a
3
+ size 4728
checkpoint-31500/added_tokens.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<mask>": 250053,
4
+ "<pad>": 1,
5
+ "<s>": 0,
6
+ "<unk>": 3,
7
+ "af_ZA": 250026,
8
+ "ar_AR": 250001,
9
+ "az_AZ": 250027,
10
+ "bn_IN": 250028,
11
+ "cs_CZ": 250002,
12
+ "de_DE": 250003,
13
+ "en_XX": 250004,
14
+ "es_XX": 250005,
15
+ "et_EE": 250006,
16
+ "fa_IR": 250029,
17
+ "fi_FI": 250007,
18
+ "fr_XX": 250008,
19
+ "gl_ES": 250051,
20
+ "gu_IN": 250009,
21
+ "he_IL": 250030,
22
+ "hi_IN": 250010,
23
+ "hr_HR": 250031,
24
+ "id_ID": 250032,
25
+ "it_IT": 250011,
26
+ "ja_XX": 250012,
27
+ "ka_GE": 250033,
28
+ "kk_KZ": 250013,
29
+ "km_KH": 250034,
30
+ "ko_KR": 250014,
31
+ "lt_LT": 250015,
32
+ "lv_LV": 250016,
33
+ "mk_MK": 250035,
34
+ "ml_IN": 250036,
35
+ "mn_MN": 250037,
36
+ "mr_IN": 250038,
37
+ "my_MM": 250017,
38
+ "ne_NP": 250018,
39
+ "nl_XX": 250019,
40
+ "pl_PL": 250039,
41
+ "ps_AF": 250040,
42
+ "pt_XX": 250041,
43
+ "ro_RO": 250020,
44
+ "ru_RU": 250021,
45
+ "si_LK": 250022,
46
+ "sl_SI": 250052,
47
+ "sv_SE": 250042,
48
+ "sw_KE": 250043,
49
+ "ta_IN": 250044,
50
+ "te_IN": 250045,
51
+ "th_TH": 250046,
52
+ "tl_XX": 250047,
53
+ "tr_TR": 250023,
54
+ "uk_UA": 250048,
55
+ "ur_PK": 250049,
56
+ "vi_VN": 250024,
57
+ "xh_ZA": 250050,
58
+ "zh_CN": 250025
59
+ }
checkpoint-31500/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": 250012,
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": "4.34.0",
57
+ "use_cache": true,
58
+ "vocab_size": 250054
59
+ }
checkpoint-31500/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": 250012,
7
+ "forced_eos_token_id": 2,
8
+ "max_length": 200,
9
+ "num_beams": 5,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.34.0"
12
+ }
checkpoint-31500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30877681d02e4e23baf523ba65e624dcacd84d8e15c77c28b077cbbcf8849ed2
3
+ size 4887473903
checkpoint-31500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0890eb1cdf01e4e5ccf37463a7f74b0deae3839ba99143c3c49dfcda3a0a1034
3
+ size 2444694490
checkpoint-31500/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbf16e22b5641961f32b44e9cc536fa249fe938dae8575ca5ecf98aba57c9b9c
3
+ size 15024
checkpoint-31500/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:219587efbe194e805def6ff9b7697ca59c397b18f4b0f790e80ea7c4aaa283f0
3
+ size 15024
checkpoint-31500/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80c73b752d1199a0e3c572982dc4a00c1aa6550a9bd1339c9cccc4c17d836b4a
3
+ size 15024
checkpoint-31500/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75337d8af8412f1b8ec8a76c0001b1e99ca9b6bd68d70633a8e34a6c33bf3406
3
+ size 15024
checkpoint-31500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac6a2d2345443585e183ba151f81df7fdf3ee19c99a22bdef5685077c45b3d04
3
+ size 1064
checkpoint-31500/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-31500/special_tokens_map.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<mask>",
60
+ "pad_token": "<pad>",
61
+ "sep_token": "</s>",
62
+ "unk_token": "<unk>"
63
+ }
checkpoint-31500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42a72efab312df69f4dda3c5e1d7eca7b8645f96023493a3834070caf20a2180
3
+ size 17109939
checkpoint-31500/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": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "250002": {
44
+ "content": "cs_CZ",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "250003": {
52
+ "content": "de_DE",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "250004": {
60
+ "content": "en_XX",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "250005": {
68
+ "content": "es_XX",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "250006": {
76
+ "content": "et_EE",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "250007": {
84
+ "content": "fi_FI",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "250008": {
92
+ "content": "fr_XX",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "250009": {
100
+ "content": "gu_IN",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "250010": {
108
+ "content": "hi_IN",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "250011": {
116
+ "content": "it_IT",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "250012": {
124
+ "content": "ja_XX",
125
+ "lstrip": true,
126
+ "normalized": false,
127
+ "rstrip": true,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "250013": {
132
+ "content": "kk_KZ",
133
+ "lstrip": true,
134
+ "normalized": false,
135
+ "rstrip": true,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "250014": {
140
+ "content": "ko_KR",
141
+ "lstrip": true,
142
+ "normalized": false,
143
+ "rstrip": true,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "250015": {
148
+ "content": "lt_LT",
149
+ "lstrip": true,
150
+ "normalized": false,
151
+ "rstrip": true,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "250016": {
156
+ "content": "lv_LV",
157
+ "lstrip": true,
158
+ "normalized": false,
159
+ "rstrip": true,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "250017": {
164
+ "content": "my_MM",
165
+ "lstrip": true,
166
+ "normalized": false,
167
+ "rstrip": true,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "250018": {
172
+ "content": "ne_NP",
173
+ "lstrip": true,
174
+ "normalized": false,
175
+ "rstrip": true,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "250019": {
180
+ "content": "nl_XX",
181
+ "lstrip": true,
182
+ "normalized": false,
183
+ "rstrip": true,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "250020": {
188
+ "content": "ro_RO",
189
+ "lstrip": true,
190
+ "normalized": false,
191
+ "rstrip": true,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "250021": {
196
+ "content": "ru_RU",
197
+ "lstrip": true,
198
+ "normalized": false,
199
+ "rstrip": true,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "250022": {
204
+ "content": "si_LK",
205
+ "lstrip": true,
206
+ "normalized": false,
207
+ "rstrip": true,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "250023": {
212
+ "content": "tr_TR",
213
+ "lstrip": true,
214
+ "normalized": false,
215
+ "rstrip": true,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "250024": {
220
+ "content": "vi_VN",
221
+ "lstrip": true,
222
+ "normalized": false,
223
+ "rstrip": true,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "250025": {
228
+ "content": "zh_CN",
229
+ "lstrip": true,
230
+ "normalized": false,
231
+ "rstrip": true,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "250026": {
236
+ "content": "af_ZA",
237
+ "lstrip": true,
238
+ "normalized": false,
239
+ "rstrip": true,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "250027": {
244
+ "content": "az_AZ",
245
+ "lstrip": true,
246
+ "normalized": false,
247
+ "rstrip": true,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "250028": {
252
+ "content": "bn_IN",
253
+ "lstrip": true,
254
+ "normalized": false,
255
+ "rstrip": true,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "250029": {
260
+ "content": "fa_IR",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": true,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "250030": {
268
+ "content": "he_IL",
269
+ "lstrip": true,
270
+ "normalized": false,
271
+ "rstrip": true,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "250031": {
276
+ "content": "hr_HR",
277
+ "lstrip": true,
278
+ "normalized": false,
279
+ "rstrip": true,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "250032": {
284
+ "content": "id_ID",
285
+ "lstrip": true,
286
+ "normalized": false,
287
+ "rstrip": true,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "250033": {
292
+ "content": "ka_GE",
293
+ "lstrip": true,
294
+ "normalized": false,
295
+ "rstrip": true,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "250034": {
300
+ "content": "km_KH",
301
+ "lstrip": true,
302
+ "normalized": false,
303
+ "rstrip": true,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "250035": {
308
+ "content": "mk_MK",
309
+ "lstrip": true,
310
+ "normalized": false,
311
+ "rstrip": true,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "250036": {
316
+ "content": "ml_IN",
317
+ "lstrip": true,
318
+ "normalized": false,
319
+ "rstrip": true,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "250037": {
324
+ "content": "mn_MN",
325
+ "lstrip": true,
326
+ "normalized": false,
327
+ "rstrip": true,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "250038": {
332
+ "content": "mr_IN",
333
+ "lstrip": true,
334
+ "normalized": false,
335
+ "rstrip": true,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "250039": {
340
+ "content": "pl_PL",
341
+ "lstrip": true,
342
+ "normalized": false,
343
+ "rstrip": true,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "250040": {
348
+ "content": "ps_AF",
349
+ "lstrip": true,
350
+ "normalized": false,
351
+ "rstrip": true,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "250041": {
356
+ "content": "pt_XX",
357
+ "lstrip": true,
358
+ "normalized": false,
359
+ "rstrip": true,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "250042": {
364
+ "content": "sv_SE",
365
+ "lstrip": true,
366
+ "normalized": false,
367
+ "rstrip": true,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "250043": {
372
+ "content": "sw_KE",
373
+ "lstrip": true,
374
+ "normalized": false,
375
+ "rstrip": true,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "250044": {
380
+ "content": "ta_IN",
381
+ "lstrip": true,
382
+ "normalized": false,
383
+ "rstrip": true,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "250045": {
388
+ "content": "te_IN",
389
+ "lstrip": true,
390
+ "normalized": false,
391
+ "rstrip": true,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "250046": {
396
+ "content": "th_TH",
397
+ "lstrip": true,
398
+ "normalized": false,
399
+ "rstrip": true,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "250047": {
404
+ "content": "tl_XX",
405
+ "lstrip": true,
406
+ "normalized": false,
407
+ "rstrip": true,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "250048": {
412
+ "content": "uk_UA",
413
+ "lstrip": true,
414
+ "normalized": false,
415
+ "rstrip": true,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "250049": {
420
+ "content": "ur_PK",
421
+ "lstrip": true,
422
+ "normalized": false,
423
+ "rstrip": true,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "250050": {
428
+ "content": "xh_ZA",
429
+ "lstrip": true,
430
+ "normalized": false,
431
+ "rstrip": true,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "250051": {
436
+ "content": "gl_ES",
437
+ "lstrip": true,
438
+ "normalized": false,
439
+ "rstrip": true,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "250052": {
444
+ "content": "sl_SI",
445
+ "lstrip": true,
446
+ "normalized": false,
447
+ "rstrip": true,
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": "ja_XX",
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
checkpoint-31500/trainer_state.json ADDED
@@ -0,0 +1,607 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.865190327167511,
3
+ "best_model_checkpoint": "./mbart-mmt_mid3_ko-ja/checkpoint-25500",
4
+ "epoch": 4.782146652497343,
5
+ "eval_steps": 1500,
6
+ "global_step": 31500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.08,
13
+ "learning_rate": 5e-05,
14
+ "loss": 3.3601,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.15,
19
+ "learning_rate": 4.98913256102067e-05,
20
+ "loss": 2.106,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.23,
25
+ "learning_rate": 4.97826512204134e-05,
26
+ "loss": 1.6216,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.23,
31
+ "eval_bleu": 2.686,
32
+ "eval_gen_len": 17.599,
33
+ "eval_loss": 1.522924780845642,
34
+ "eval_runtime": 866.1912,
35
+ "eval_samples_per_second": 15.207,
36
+ "eval_steps_per_second": 0.951,
37
+ "step": 1500
38
+ },
39
+ {
40
+ "epoch": 0.3,
41
+ "learning_rate": 4.96739768306201e-05,
42
+ "loss": 1.508,
43
+ "step": 2000
44
+ },
45
+ {
46
+ "epoch": 0.38,
47
+ "learning_rate": 4.95653024408268e-05,
48
+ "loss": 1.4292,
49
+ "step": 2500
50
+ },
51
+ {
52
+ "epoch": 0.46,
53
+ "learning_rate": 4.945662805103349e-05,
54
+ "loss": 1.3587,
55
+ "step": 3000
56
+ },
57
+ {
58
+ "epoch": 0.46,
59
+ "eval_bleu": 4.0749,
60
+ "eval_gen_len": 17.3772,
61
+ "eval_loss": 1.306133508682251,
62
+ "eval_runtime": 848.4414,
63
+ "eval_samples_per_second": 15.525,
64
+ "eval_steps_per_second": 0.971,
65
+ "step": 3000
66
+ },
67
+ {
68
+ "epoch": 0.53,
69
+ "learning_rate": 4.9347953661240194e-05,
70
+ "loss": 1.3063,
71
+ "step": 3500
72
+ },
73
+ {
74
+ "epoch": 0.61,
75
+ "learning_rate": 4.923927927144689e-05,
76
+ "loss": 1.2722,
77
+ "step": 4000
78
+ },
79
+ {
80
+ "epoch": 0.68,
81
+ "learning_rate": 4.9130604881653594e-05,
82
+ "loss": 1.2279,
83
+ "step": 4500
84
+ },
85
+ {
86
+ "epoch": 0.68,
87
+ "eval_bleu": 5.2878,
88
+ "eval_gen_len": 17.3642,
89
+ "eval_loss": 1.1880881786346436,
90
+ "eval_runtime": 848.9163,
91
+ "eval_samples_per_second": 15.516,
92
+ "eval_steps_per_second": 0.971,
93
+ "step": 4500
94
+ },
95
+ {
96
+ "epoch": 0.76,
97
+ "learning_rate": 4.902193049186029e-05,
98
+ "loss": 1.203,
99
+ "step": 5000
100
+ },
101
+ {
102
+ "epoch": 0.83,
103
+ "learning_rate": 4.891325610206699e-05,
104
+ "loss": 1.1744,
105
+ "step": 5500
106
+ },
107
+ {
108
+ "epoch": 0.91,
109
+ "learning_rate": 4.880458171227369e-05,
110
+ "loss": 1.1408,
111
+ "step": 6000
112
+ },
113
+ {
114
+ "epoch": 0.91,
115
+ "eval_bleu": 5.4783,
116
+ "eval_gen_len": 17.4093,
117
+ "eval_loss": 1.0994044542312622,
118
+ "eval_runtime": 903.2669,
119
+ "eval_samples_per_second": 14.583,
120
+ "eval_steps_per_second": 0.912,
121
+ "step": 6000
122
+ },
123
+ {
124
+ "epoch": 0.99,
125
+ "learning_rate": 4.8695907322480386e-05,
126
+ "loss": 1.1196,
127
+ "step": 6500
128
+ },
129
+ {
130
+ "epoch": 1.06,
131
+ "learning_rate": 4.858723293268709e-05,
132
+ "loss": 1.014,
133
+ "step": 7000
134
+ },
135
+ {
136
+ "epoch": 1.14,
137
+ "learning_rate": 4.847855854289378e-05,
138
+ "loss": 0.9977,
139
+ "step": 7500
140
+ },
141
+ {
142
+ "epoch": 1.14,
143
+ "eval_bleu": 7.6015,
144
+ "eval_gen_len": 17.36,
145
+ "eval_loss": 1.0312957763671875,
146
+ "eval_runtime": 872.8057,
147
+ "eval_samples_per_second": 15.092,
148
+ "eval_steps_per_second": 0.944,
149
+ "step": 7500
150
+ },
151
+ {
152
+ "epoch": 1.21,
153
+ "learning_rate": 4.836988415310048e-05,
154
+ "loss": 0.9903,
155
+ "step": 8000
156
+ },
157
+ {
158
+ "epoch": 1.29,
159
+ "learning_rate": 4.826120976330718e-05,
160
+ "loss": 0.9752,
161
+ "step": 8500
162
+ },
163
+ {
164
+ "epoch": 1.37,
165
+ "learning_rate": 4.815253537351388e-05,
166
+ "loss": 0.9582,
167
+ "step": 9000
168
+ },
169
+ {
170
+ "epoch": 1.37,
171
+ "eval_bleu": 8.2303,
172
+ "eval_gen_len": 17.3526,
173
+ "eval_loss": 0.9917855262756348,
174
+ "eval_runtime": 851.0578,
175
+ "eval_samples_per_second": 15.477,
176
+ "eval_steps_per_second": 0.968,
177
+ "step": 9000
178
+ },
179
+ {
180
+ "epoch": 1.44,
181
+ "learning_rate": 4.804386098372058e-05,
182
+ "loss": 0.9684,
183
+ "step": 9500
184
+ },
185
+ {
186
+ "epoch": 1.52,
187
+ "learning_rate": 4.793518659392728e-05,
188
+ "loss": 0.9641,
189
+ "step": 10000
190
+ },
191
+ {
192
+ "epoch": 1.59,
193
+ "learning_rate": 4.782651220413398e-05,
194
+ "loss": 0.9525,
195
+ "step": 10500
196
+ },
197
+ {
198
+ "epoch": 1.59,
199
+ "eval_bleu": 8.2837,
200
+ "eval_gen_len": 17.2597,
201
+ "eval_loss": 0.981093168258667,
202
+ "eval_runtime": 868.378,
203
+ "eval_samples_per_second": 15.169,
204
+ "eval_steps_per_second": 0.949,
205
+ "step": 10500
206
+ },
207
+ {
208
+ "epoch": 1.67,
209
+ "learning_rate": 4.7717837814340674e-05,
210
+ "loss": 0.943,
211
+ "step": 11000
212
+ },
213
+ {
214
+ "epoch": 1.75,
215
+ "learning_rate": 4.760916342454738e-05,
216
+ "loss": 0.936,
217
+ "step": 11500
218
+ },
219
+ {
220
+ "epoch": 1.82,
221
+ "learning_rate": 4.750048903475407e-05,
222
+ "loss": 0.9415,
223
+ "step": 12000
224
+ },
225
+ {
226
+ "epoch": 1.82,
227
+ "eval_bleu": 8.1592,
228
+ "eval_gen_len": 17.2241,
229
+ "eval_loss": 0.9589386582374573,
230
+ "eval_runtime": 853.0091,
231
+ "eval_samples_per_second": 15.442,
232
+ "eval_steps_per_second": 0.966,
233
+ "step": 12000
234
+ },
235
+ {
236
+ "epoch": 1.9,
237
+ "learning_rate": 4.739181464496077e-05,
238
+ "loss": 0.9327,
239
+ "step": 12500
240
+ },
241
+ {
242
+ "epoch": 1.97,
243
+ "learning_rate": 4.7283140255167467e-05,
244
+ "loss": 0.9219,
245
+ "step": 13000
246
+ },
247
+ {
248
+ "epoch": 2.05,
249
+ "learning_rate": 4.717446586537417e-05,
250
+ "loss": 0.856,
251
+ "step": 13500
252
+ },
253
+ {
254
+ "epoch": 2.05,
255
+ "eval_bleu": 7.8401,
256
+ "eval_gen_len": 17.4066,
257
+ "eval_loss": 0.9462171196937561,
258
+ "eval_runtime": 870.9328,
259
+ "eval_samples_per_second": 15.124,
260
+ "eval_steps_per_second": 0.946,
261
+ "step": 13500
262
+ },
263
+ {
264
+ "epoch": 2.13,
265
+ "learning_rate": 4.7065791475580866e-05,
266
+ "loss": 0.816,
267
+ "step": 14000
268
+ },
269
+ {
270
+ "epoch": 2.2,
271
+ "learning_rate": 4.695711708578757e-05,
272
+ "loss": 0.819,
273
+ "step": 14500
274
+ },
275
+ {
276
+ "epoch": 2.28,
277
+ "learning_rate": 4.6848442695994266e-05,
278
+ "loss": 0.8273,
279
+ "step": 15000
280
+ },
281
+ {
282
+ "epoch": 2.28,
283
+ "eval_bleu": 8.6082,
284
+ "eval_gen_len": 17.1918,
285
+ "eval_loss": 0.9335508942604065,
286
+ "eval_runtime": 847.8053,
287
+ "eval_samples_per_second": 15.537,
288
+ "eval_steps_per_second": 0.972,
289
+ "step": 15000
290
+ },
291
+ {
292
+ "epoch": 2.35,
293
+ "learning_rate": 4.673976830620096e-05,
294
+ "loss": 0.8154,
295
+ "step": 15500
296
+ },
297
+ {
298
+ "epoch": 2.43,
299
+ "learning_rate": 4.6631093916407665e-05,
300
+ "loss": 0.8281,
301
+ "step": 16000
302
+ },
303
+ {
304
+ "epoch": 2.5,
305
+ "learning_rate": 4.6522419526614355e-05,
306
+ "loss": 0.8066,
307
+ "step": 16500
308
+ },
309
+ {
310
+ "epoch": 2.5,
311
+ "eval_bleu": 9.7751,
312
+ "eval_gen_len": 17.5198,
313
+ "eval_loss": 0.921973466873169,
314
+ "eval_runtime": 888.35,
315
+ "eval_samples_per_second": 14.827,
316
+ "eval_steps_per_second": 0.928,
317
+ "step": 16500
318
+ },
319
+ {
320
+ "epoch": 2.58,
321
+ "learning_rate": 4.641374513682106e-05,
322
+ "loss": 0.812,
323
+ "step": 17000
324
+ },
325
+ {
326
+ "epoch": 2.66,
327
+ "learning_rate": 4.6305070747027754e-05,
328
+ "loss": 0.8117,
329
+ "step": 17500
330
+ },
331
+ {
332
+ "epoch": 2.73,
333
+ "learning_rate": 4.619639635723446e-05,
334
+ "loss": 0.784,
335
+ "step": 18000
336
+ },
337
+ {
338
+ "epoch": 2.73,
339
+ "eval_bleu": 10.292,
340
+ "eval_gen_len": 17.4097,
341
+ "eval_loss": 0.8948560357093811,
342
+ "eval_runtime": 887.752,
343
+ "eval_samples_per_second": 14.837,
344
+ "eval_steps_per_second": 0.928,
345
+ "step": 18000
346
+ },
347
+ {
348
+ "epoch": 2.81,
349
+ "learning_rate": 4.6087721967441154e-05,
350
+ "loss": 0.8113,
351
+ "step": 18500
352
+ },
353
+ {
354
+ "epoch": 2.88,
355
+ "learning_rate": 4.597904757764786e-05,
356
+ "loss": 0.7942,
357
+ "step": 19000
358
+ },
359
+ {
360
+ "epoch": 2.96,
361
+ "learning_rate": 4.5870373187854554e-05,
362
+ "loss": 0.8016,
363
+ "step": 19500
364
+ },
365
+ {
366
+ "epoch": 2.96,
367
+ "eval_bleu": 9.0262,
368
+ "eval_gen_len": 17.4097,
369
+ "eval_loss": 0.8958194255828857,
370
+ "eval_runtime": 868.3186,
371
+ "eval_samples_per_second": 15.17,
372
+ "eval_steps_per_second": 0.949,
373
+ "step": 19500
374
+ },
375
+ {
376
+ "epoch": 3.04,
377
+ "learning_rate": 4.576169879806125e-05,
378
+ "loss": 0.7417,
379
+ "step": 20000
380
+ },
381
+ {
382
+ "epoch": 3.11,
383
+ "learning_rate": 4.5653024408267946e-05,
384
+ "loss": 0.683,
385
+ "step": 20500
386
+ },
387
+ {
388
+ "epoch": 3.19,
389
+ "learning_rate": 4.554435001847465e-05,
390
+ "loss": 0.6872,
391
+ "step": 21000
392
+ },
393
+ {
394
+ "epoch": 3.19,
395
+ "eval_bleu": 9.7549,
396
+ "eval_gen_len": 17.2672,
397
+ "eval_loss": 0.9043093919754028,
398
+ "eval_runtime": 855.9409,
399
+ "eval_samples_per_second": 15.389,
400
+ "eval_steps_per_second": 0.963,
401
+ "step": 21000
402
+ },
403
+ {
404
+ "epoch": 3.26,
405
+ "learning_rate": 4.5435675628681346e-05,
406
+ "loss": 0.6928,
407
+ "step": 21500
408
+ },
409
+ {
410
+ "epoch": 3.34,
411
+ "learning_rate": 4.532700123888804e-05,
412
+ "loss": 0.6973,
413
+ "step": 22000
414
+ },
415
+ {
416
+ "epoch": 3.42,
417
+ "learning_rate": 4.5218326849094746e-05,
418
+ "loss": 0.7107,
419
+ "step": 22500
420
+ },
421
+ {
422
+ "epoch": 3.42,
423
+ "eval_bleu": 10.3016,
424
+ "eval_gen_len": 17.0973,
425
+ "eval_loss": 0.8993721008300781,
426
+ "eval_runtime": 837.6757,
427
+ "eval_samples_per_second": 15.724,
428
+ "eval_steps_per_second": 0.984,
429
+ "step": 22500
430
+ },
431
+ {
432
+ "epoch": 3.49,
433
+ "learning_rate": 4.510965245930144e-05,
434
+ "loss": 0.6899,
435
+ "step": 23000
436
+ },
437
+ {
438
+ "epoch": 3.57,
439
+ "learning_rate": 4.5000978069508145e-05,
440
+ "loss": 0.6794,
441
+ "step": 23500
442
+ },
443
+ {
444
+ "epoch": 3.64,
445
+ "learning_rate": 4.489230367971484e-05,
446
+ "loss": 0.6726,
447
+ "step": 24000
448
+ },
449
+ {
450
+ "epoch": 3.64,
451
+ "eval_bleu": 10.5183,
452
+ "eval_gen_len": 17.2871,
453
+ "eval_loss": 0.8746942281723022,
454
+ "eval_runtime": 850.8583,
455
+ "eval_samples_per_second": 15.481,
456
+ "eval_steps_per_second": 0.968,
457
+ "step": 24000
458
+ },
459
+ {
460
+ "epoch": 3.72,
461
+ "learning_rate": 4.4783629289921545e-05,
462
+ "loss": 0.6782,
463
+ "step": 24500
464
+ },
465
+ {
466
+ "epoch": 3.8,
467
+ "learning_rate": 4.4674954900128234e-05,
468
+ "loss": 0.6821,
469
+ "step": 25000
470
+ },
471
+ {
472
+ "epoch": 3.87,
473
+ "learning_rate": 4.456628051033494e-05,
474
+ "loss": 0.6699,
475
+ "step": 25500
476
+ },
477
+ {
478
+ "epoch": 3.87,
479
+ "eval_bleu": 10.1883,
480
+ "eval_gen_len": 17.2057,
481
+ "eval_loss": 0.865190327167511,
482
+ "eval_runtime": 852.5269,
483
+ "eval_samples_per_second": 15.451,
484
+ "eval_steps_per_second": 0.967,
485
+ "step": 25500
486
+ },
487
+ {
488
+ "epoch": 3.95,
489
+ "learning_rate": 4.4457606120541634e-05,
490
+ "loss": 0.7029,
491
+ "step": 26000
492
+ },
493
+ {
494
+ "epoch": 4.02,
495
+ "learning_rate": 4.434893173074833e-05,
496
+ "loss": 0.6761,
497
+ "step": 26500
498
+ },
499
+ {
500
+ "epoch": 4.1,
501
+ "learning_rate": 4.4240257340955033e-05,
502
+ "loss": 0.612,
503
+ "step": 27000
504
+ },
505
+ {
506
+ "epoch": 4.1,
507
+ "eval_bleu": 9.5697,
508
+ "eval_gen_len": 17.2443,
509
+ "eval_loss": 0.8949306607246399,
510
+ "eval_runtime": 850.694,
511
+ "eval_samples_per_second": 15.484,
512
+ "eval_steps_per_second": 0.969,
513
+ "step": 27000
514
+ },
515
+ {
516
+ "epoch": 4.17,
517
+ "learning_rate": 4.413158295116173e-05,
518
+ "loss": 0.6119,
519
+ "step": 27500
520
+ },
521
+ {
522
+ "epoch": 4.25,
523
+ "learning_rate": 4.402290856136843e-05,
524
+ "loss": 0.6094,
525
+ "step": 28000
526
+ },
527
+ {
528
+ "epoch": 4.33,
529
+ "learning_rate": 4.391423417157513e-05,
530
+ "loss": 0.621,
531
+ "step": 28500
532
+ },
533
+ {
534
+ "epoch": 4.33,
535
+ "eval_bleu": 10.8592,
536
+ "eval_gen_len": 17.329,
537
+ "eval_loss": 0.8904227614402771,
538
+ "eval_runtime": 868.3516,
539
+ "eval_samples_per_second": 15.169,
540
+ "eval_steps_per_second": 0.949,
541
+ "step": 28500
542
+ },
543
+ {
544
+ "epoch": 4.4,
545
+ "learning_rate": 4.380555978178183e-05,
546
+ "loss": 0.6302,
547
+ "step": 29000
548
+ },
549
+ {
550
+ "epoch": 4.48,
551
+ "learning_rate": 4.369688539198852e-05,
552
+ "loss": 0.6206,
553
+ "step": 29500
554
+ },
555
+ {
556
+ "epoch": 4.55,
557
+ "learning_rate": 4.3588211002195225e-05,
558
+ "loss": 0.6219,
559
+ "step": 30000
560
+ },
561
+ {
562
+ "epoch": 4.55,
563
+ "eval_bleu": 10.925,
564
+ "eval_gen_len": 17.482,
565
+ "eval_loss": 0.8771834969520569,
566
+ "eval_runtime": 864.4075,
567
+ "eval_samples_per_second": 15.238,
568
+ "eval_steps_per_second": 0.953,
569
+ "step": 30000
570
+ },
571
+ {
572
+ "epoch": 4.63,
573
+ "learning_rate": 4.347953661240192e-05,
574
+ "loss": 0.6166,
575
+ "step": 30500
576
+ },
577
+ {
578
+ "epoch": 4.71,
579
+ "learning_rate": 4.337086222260862e-05,
580
+ "loss": 0.6057,
581
+ "step": 31000
582
+ },
583
+ {
584
+ "epoch": 4.78,
585
+ "learning_rate": 4.326218783281532e-05,
586
+ "loss": 0.6164,
587
+ "step": 31500
588
+ },
589
+ {
590
+ "epoch": 4.78,
591
+ "eval_bleu": 11.8749,
592
+ "eval_gen_len": 17.1624,
593
+ "eval_loss": 0.8693726658821106,
594
+ "eval_runtime": 846.6139,
595
+ "eval_samples_per_second": 15.558,
596
+ "eval_steps_per_second": 0.973,
597
+ "step": 31500
598
+ }
599
+ ],
600
+ "logging_steps": 500,
601
+ "max_steps": 230545,
602
+ "num_train_epochs": 35,
603
+ "save_steps": 1500,
604
+ "total_flos": 1.0923720993448919e+18,
605
+ "trial_name": null,
606
+ "trial_params": null
607
+ }
checkpoint-31500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc9f6c6258b97f2d71469d8e4060b04e88838a9f1196109d8271a7ced4355f5a
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": 250012,
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": "4.34.0",
57
+ "use_cache": true,
58
+ "vocab_size": 250054
59
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.78,
3
+ "eval_bleu": 10.1883,
4
+ "eval_gen_len": 17.2057,
5
+ "eval_loss": 0.865190327167511,
6
+ "eval_runtime": 852.9227,
7
+ "eval_samples": 13172,
8
+ "eval_samples_per_second": 15.443,
9
+ "eval_steps_per_second": 0.966
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": 250012,
7
+ "forced_eos_token_id": 2,
8
+ "max_length": 200,
9
+ "num_beams": 5,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.34.0"
12
+ }
predict_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "predict_bleu": 12.9009,
3
+ "predict_gen_len": 17.3525,
4
+ "predict_loss": 0.8587990403175354,
5
+ "predict_runtime": 852.0225,
6
+ "predict_samples": 13173,
7
+ "predict_samples_per_second": 15.461,
8
+ "predict_steps_per_second": 0.967
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f258bcdd1f066aee1e118b0e00fc14c3548496a5043413075894fa0a8c8a3b4c
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 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<mask>",
60
+ "pad_token": "<pad>",
61
+ "sep_token": "</s>",
62
+ "unk_token": "<unk>"
63
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42a72efab312df69f4dda3c5e1d7eca7b8645f96023493a3834070caf20a2180
3
+ size 17109939
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": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "250002": {
44
+ "content": "cs_CZ",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "250003": {
52
+ "content": "de_DE",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "250004": {
60
+ "content": "en_XX",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "250005": {
68
+ "content": "es_XX",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "250006": {
76
+ "content": "et_EE",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "250007": {
84
+ "content": "fi_FI",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "250008": {
92
+ "content": "fr_XX",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "250009": {
100
+ "content": "gu_IN",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "250010": {
108
+ "content": "hi_IN",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "250011": {
116
+ "content": "it_IT",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "250012": {
124
+ "content": "ja_XX",
125
+ "lstrip": true,
126
+ "normalized": false,
127
+ "rstrip": true,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "250013": {
132
+ "content": "kk_KZ",
133
+ "lstrip": true,
134
+ "normalized": false,
135
+ "rstrip": true,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "250014": {
140
+ "content": "ko_KR",
141
+ "lstrip": true,
142
+ "normalized": false,
143
+ "rstrip": true,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "250015": {
148
+ "content": "lt_LT",
149
+ "lstrip": true,
150
+ "normalized": false,
151
+ "rstrip": true,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "250016": {
156
+ "content": "lv_LV",
157
+ "lstrip": true,
158
+ "normalized": false,
159
+ "rstrip": true,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "250017": {
164
+ "content": "my_MM",
165
+ "lstrip": true,
166
+ "normalized": false,
167
+ "rstrip": true,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "250018": {
172
+ "content": "ne_NP",
173
+ "lstrip": true,
174
+ "normalized": false,
175
+ "rstrip": true,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "250019": {
180
+ "content": "nl_XX",
181
+ "lstrip": true,
182
+ "normalized": false,
183
+ "rstrip": true,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "250020": {
188
+ "content": "ro_RO",
189
+ "lstrip": true,
190
+ "normalized": false,
191
+ "rstrip": true,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "250021": {
196
+ "content": "ru_RU",
197
+ "lstrip": true,
198
+ "normalized": false,
199
+ "rstrip": true,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "250022": {
204
+ "content": "si_LK",
205
+ "lstrip": true,
206
+ "normalized": false,
207
+ "rstrip": true,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "250023": {
212
+ "content": "tr_TR",
213
+ "lstrip": true,
214
+ "normalized": false,
215
+ "rstrip": true,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "250024": {
220
+ "content": "vi_VN",
221
+ "lstrip": true,
222
+ "normalized": false,
223
+ "rstrip": true,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "250025": {
228
+ "content": "zh_CN",
229
+ "lstrip": true,
230
+ "normalized": false,
231
+ "rstrip": true,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "250026": {
236
+ "content": "af_ZA",
237
+ "lstrip": true,
238
+ "normalized": false,
239
+ "rstrip": true,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "250027": {
244
+ "content": "az_AZ",
245
+ "lstrip": true,
246
+ "normalized": false,
247
+ "rstrip": true,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "250028": {
252
+ "content": "bn_IN",
253
+ "lstrip": true,
254
+ "normalized": false,
255
+ "rstrip": true,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "250029": {
260
+ "content": "fa_IR",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": true,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "250030": {
268
+ "content": "he_IL",
269
+ "lstrip": true,
270
+ "normalized": false,
271
+ "rstrip": true,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "250031": {
276
+ "content": "hr_HR",
277
+ "lstrip": true,
278
+ "normalized": false,
279
+ "rstrip": true,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "250032": {
284
+ "content": "id_ID",
285
+ "lstrip": true,
286
+ "normalized": false,
287
+ "rstrip": true,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "250033": {
292
+ "content": "ka_GE",
293
+ "lstrip": true,
294
+ "normalized": false,
295
+ "rstrip": true,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "250034": {
300
+ "content": "km_KH",
301
+ "lstrip": true,
302
+ "normalized": false,
303
+ "rstrip": true,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "250035": {
308
+ "content": "mk_MK",
309
+ "lstrip": true,
310
+ "normalized": false,
311
+ "rstrip": true,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "250036": {
316
+ "content": "ml_IN",
317
+ "lstrip": true,
318
+ "normalized": false,
319
+ "rstrip": true,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "250037": {
324
+ "content": "mn_MN",
325
+ "lstrip": true,
326
+ "normalized": false,
327
+ "rstrip": true,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "250038": {
332
+ "content": "mr_IN",
333
+ "lstrip": true,
334
+ "normalized": false,
335
+ "rstrip": true,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "250039": {
340
+ "content": "pl_PL",
341
+ "lstrip": true,
342
+ "normalized": false,
343
+ "rstrip": true,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "250040": {
348
+ "content": "ps_AF",
349
+ "lstrip": true,
350
+ "normalized": false,
351
+ "rstrip": true,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "250041": {
356
+ "content": "pt_XX",
357
+ "lstrip": true,
358
+ "normalized": false,
359
+ "rstrip": true,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "250042": {
364
+ "content": "sv_SE",
365
+ "lstrip": true,
366
+ "normalized": false,
367
+ "rstrip": true,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "250043": {
372
+ "content": "sw_KE",
373
+ "lstrip": true,
374
+ "normalized": false,
375
+ "rstrip": true,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "250044": {
380
+ "content": "ta_IN",
381
+ "lstrip": true,
382
+ "normalized": false,
383
+ "rstrip": true,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "250045": {
388
+ "content": "te_IN",
389
+ "lstrip": true,
390
+ "normalized": false,
391
+ "rstrip": true,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "250046": {
396
+ "content": "th_TH",
397
+ "lstrip": true,
398
+ "normalized": false,
399
+ "rstrip": true,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "250047": {
404
+ "content": "tl_XX",
405
+ "lstrip": true,
406
+ "normalized": false,
407
+ "rstrip": true,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "250048": {
412
+ "content": "uk_UA",
413
+ "lstrip": true,
414
+ "normalized": false,
415
+ "rstrip": true,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "250049": {
420
+ "content": "ur_PK",
421
+ "lstrip": true,
422
+ "normalized": false,
423
+ "rstrip": true,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "250050": {
428
+ "content": "xh_ZA",
429
+ "lstrip": true,
430
+ "normalized": false,
431
+ "rstrip": true,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "250051": {
436
+ "content": "gl_ES",
437
+ "lstrip": true,
438
+ "normalized": false,
439
+ "rstrip": true,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "250052": {
444
+ "content": "sl_SI",
445
+ "lstrip": true,
446
+ "normalized": false,
447
+ "rstrip": true,
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": "ja_XX",
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.78,
3
+ "train_loss": 0.9323235357375372,
4
+ "train_runtime": 42332.75,
5
+ "train_samples": 105385,
6
+ "train_samples_per_second": 87.131,
7
+ "train_steps_per_second": 5.446
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,616 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.865190327167511,
3
+ "best_model_checkpoint": "./mbart-mmt_mid3_ko-ja/checkpoint-25500",
4
+ "epoch": 4.782146652497343,
5
+ "eval_steps": 1500,
6
+ "global_step": 31500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.08,
13
+ "learning_rate": 5e-05,
14
+ "loss": 3.3601,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.15,
19
+ "learning_rate": 4.98913256102067e-05,
20
+ "loss": 2.106,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.23,
25
+ "learning_rate": 4.97826512204134e-05,
26
+ "loss": 1.6216,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.23,
31
+ "eval_bleu": 2.686,
32
+ "eval_gen_len": 17.599,
33
+ "eval_loss": 1.522924780845642,
34
+ "eval_runtime": 866.1912,
35
+ "eval_samples_per_second": 15.207,
36
+ "eval_steps_per_second": 0.951,
37
+ "step": 1500
38
+ },
39
+ {
40
+ "epoch": 0.3,
41
+ "learning_rate": 4.96739768306201e-05,
42
+ "loss": 1.508,
43
+ "step": 2000
44
+ },
45
+ {
46
+ "epoch": 0.38,
47
+ "learning_rate": 4.95653024408268e-05,
48
+ "loss": 1.4292,
49
+ "step": 2500
50
+ },
51
+ {
52
+ "epoch": 0.46,
53
+ "learning_rate": 4.945662805103349e-05,
54
+ "loss": 1.3587,
55
+ "step": 3000
56
+ },
57
+ {
58
+ "epoch": 0.46,
59
+ "eval_bleu": 4.0749,
60
+ "eval_gen_len": 17.3772,
61
+ "eval_loss": 1.306133508682251,
62
+ "eval_runtime": 848.4414,
63
+ "eval_samples_per_second": 15.525,
64
+ "eval_steps_per_second": 0.971,
65
+ "step": 3000
66
+ },
67
+ {
68
+ "epoch": 0.53,
69
+ "learning_rate": 4.9347953661240194e-05,
70
+ "loss": 1.3063,
71
+ "step": 3500
72
+ },
73
+ {
74
+ "epoch": 0.61,
75
+ "learning_rate": 4.923927927144689e-05,
76
+ "loss": 1.2722,
77
+ "step": 4000
78
+ },
79
+ {
80
+ "epoch": 0.68,
81
+ "learning_rate": 4.9130604881653594e-05,
82
+ "loss": 1.2279,
83
+ "step": 4500
84
+ },
85
+ {
86
+ "epoch": 0.68,
87
+ "eval_bleu": 5.2878,
88
+ "eval_gen_len": 17.3642,
89
+ "eval_loss": 1.1880881786346436,
90
+ "eval_runtime": 848.9163,
91
+ "eval_samples_per_second": 15.516,
92
+ "eval_steps_per_second": 0.971,
93
+ "step": 4500
94
+ },
95
+ {
96
+ "epoch": 0.76,
97
+ "learning_rate": 4.902193049186029e-05,
98
+ "loss": 1.203,
99
+ "step": 5000
100
+ },
101
+ {
102
+ "epoch": 0.83,
103
+ "learning_rate": 4.891325610206699e-05,
104
+ "loss": 1.1744,
105
+ "step": 5500
106
+ },
107
+ {
108
+ "epoch": 0.91,
109
+ "learning_rate": 4.880458171227369e-05,
110
+ "loss": 1.1408,
111
+ "step": 6000
112
+ },
113
+ {
114
+ "epoch": 0.91,
115
+ "eval_bleu": 5.4783,
116
+ "eval_gen_len": 17.4093,
117
+ "eval_loss": 1.0994044542312622,
118
+ "eval_runtime": 903.2669,
119
+ "eval_samples_per_second": 14.583,
120
+ "eval_steps_per_second": 0.912,
121
+ "step": 6000
122
+ },
123
+ {
124
+ "epoch": 0.99,
125
+ "learning_rate": 4.8695907322480386e-05,
126
+ "loss": 1.1196,
127
+ "step": 6500
128
+ },
129
+ {
130
+ "epoch": 1.06,
131
+ "learning_rate": 4.858723293268709e-05,
132
+ "loss": 1.014,
133
+ "step": 7000
134
+ },
135
+ {
136
+ "epoch": 1.14,
137
+ "learning_rate": 4.847855854289378e-05,
138
+ "loss": 0.9977,
139
+ "step": 7500
140
+ },
141
+ {
142
+ "epoch": 1.14,
143
+ "eval_bleu": 7.6015,
144
+ "eval_gen_len": 17.36,
145
+ "eval_loss": 1.0312957763671875,
146
+ "eval_runtime": 872.8057,
147
+ "eval_samples_per_second": 15.092,
148
+ "eval_steps_per_second": 0.944,
149
+ "step": 7500
150
+ },
151
+ {
152
+ "epoch": 1.21,
153
+ "learning_rate": 4.836988415310048e-05,
154
+ "loss": 0.9903,
155
+ "step": 8000
156
+ },
157
+ {
158
+ "epoch": 1.29,
159
+ "learning_rate": 4.826120976330718e-05,
160
+ "loss": 0.9752,
161
+ "step": 8500
162
+ },
163
+ {
164
+ "epoch": 1.37,
165
+ "learning_rate": 4.815253537351388e-05,
166
+ "loss": 0.9582,
167
+ "step": 9000
168
+ },
169
+ {
170
+ "epoch": 1.37,
171
+ "eval_bleu": 8.2303,
172
+ "eval_gen_len": 17.3526,
173
+ "eval_loss": 0.9917855262756348,
174
+ "eval_runtime": 851.0578,
175
+ "eval_samples_per_second": 15.477,
176
+ "eval_steps_per_second": 0.968,
177
+ "step": 9000
178
+ },
179
+ {
180
+ "epoch": 1.44,
181
+ "learning_rate": 4.804386098372058e-05,
182
+ "loss": 0.9684,
183
+ "step": 9500
184
+ },
185
+ {
186
+ "epoch": 1.52,
187
+ "learning_rate": 4.793518659392728e-05,
188
+ "loss": 0.9641,
189
+ "step": 10000
190
+ },
191
+ {
192
+ "epoch": 1.59,
193
+ "learning_rate": 4.782651220413398e-05,
194
+ "loss": 0.9525,
195
+ "step": 10500
196
+ },
197
+ {
198
+ "epoch": 1.59,
199
+ "eval_bleu": 8.2837,
200
+ "eval_gen_len": 17.2597,
201
+ "eval_loss": 0.981093168258667,
202
+ "eval_runtime": 868.378,
203
+ "eval_samples_per_second": 15.169,
204
+ "eval_steps_per_second": 0.949,
205
+ "step": 10500
206
+ },
207
+ {
208
+ "epoch": 1.67,
209
+ "learning_rate": 4.7717837814340674e-05,
210
+ "loss": 0.943,
211
+ "step": 11000
212
+ },
213
+ {
214
+ "epoch": 1.75,
215
+ "learning_rate": 4.760916342454738e-05,
216
+ "loss": 0.936,
217
+ "step": 11500
218
+ },
219
+ {
220
+ "epoch": 1.82,
221
+ "learning_rate": 4.750048903475407e-05,
222
+ "loss": 0.9415,
223
+ "step": 12000
224
+ },
225
+ {
226
+ "epoch": 1.82,
227
+ "eval_bleu": 8.1592,
228
+ "eval_gen_len": 17.2241,
229
+ "eval_loss": 0.9589386582374573,
230
+ "eval_runtime": 853.0091,
231
+ "eval_samples_per_second": 15.442,
232
+ "eval_steps_per_second": 0.966,
233
+ "step": 12000
234
+ },
235
+ {
236
+ "epoch": 1.9,
237
+ "learning_rate": 4.739181464496077e-05,
238
+ "loss": 0.9327,
239
+ "step": 12500
240
+ },
241
+ {
242
+ "epoch": 1.97,
243
+ "learning_rate": 4.7283140255167467e-05,
244
+ "loss": 0.9219,
245
+ "step": 13000
246
+ },
247
+ {
248
+ "epoch": 2.05,
249
+ "learning_rate": 4.717446586537417e-05,
250
+ "loss": 0.856,
251
+ "step": 13500
252
+ },
253
+ {
254
+ "epoch": 2.05,
255
+ "eval_bleu": 7.8401,
256
+ "eval_gen_len": 17.4066,
257
+ "eval_loss": 0.9462171196937561,
258
+ "eval_runtime": 870.9328,
259
+ "eval_samples_per_second": 15.124,
260
+ "eval_steps_per_second": 0.946,
261
+ "step": 13500
262
+ },
263
+ {
264
+ "epoch": 2.13,
265
+ "learning_rate": 4.7065791475580866e-05,
266
+ "loss": 0.816,
267
+ "step": 14000
268
+ },
269
+ {
270
+ "epoch": 2.2,
271
+ "learning_rate": 4.695711708578757e-05,
272
+ "loss": 0.819,
273
+ "step": 14500
274
+ },
275
+ {
276
+ "epoch": 2.28,
277
+ "learning_rate": 4.6848442695994266e-05,
278
+ "loss": 0.8273,
279
+ "step": 15000
280
+ },
281
+ {
282
+ "epoch": 2.28,
283
+ "eval_bleu": 8.6082,
284
+ "eval_gen_len": 17.1918,
285
+ "eval_loss": 0.9335508942604065,
286
+ "eval_runtime": 847.8053,
287
+ "eval_samples_per_second": 15.537,
288
+ "eval_steps_per_second": 0.972,
289
+ "step": 15000
290
+ },
291
+ {
292
+ "epoch": 2.35,
293
+ "learning_rate": 4.673976830620096e-05,
294
+ "loss": 0.8154,
295
+ "step": 15500
296
+ },
297
+ {
298
+ "epoch": 2.43,
299
+ "learning_rate": 4.6631093916407665e-05,
300
+ "loss": 0.8281,
301
+ "step": 16000
302
+ },
303
+ {
304
+ "epoch": 2.5,
305
+ "learning_rate": 4.6522419526614355e-05,
306
+ "loss": 0.8066,
307
+ "step": 16500
308
+ },
309
+ {
310
+ "epoch": 2.5,
311
+ "eval_bleu": 9.7751,
312
+ "eval_gen_len": 17.5198,
313
+ "eval_loss": 0.921973466873169,
314
+ "eval_runtime": 888.35,
315
+ "eval_samples_per_second": 14.827,
316
+ "eval_steps_per_second": 0.928,
317
+ "step": 16500
318
+ },
319
+ {
320
+ "epoch": 2.58,
321
+ "learning_rate": 4.641374513682106e-05,
322
+ "loss": 0.812,
323
+ "step": 17000
324
+ },
325
+ {
326
+ "epoch": 2.66,
327
+ "learning_rate": 4.6305070747027754e-05,
328
+ "loss": 0.8117,
329
+ "step": 17500
330
+ },
331
+ {
332
+ "epoch": 2.73,
333
+ "learning_rate": 4.619639635723446e-05,
334
+ "loss": 0.784,
335
+ "step": 18000
336
+ },
337
+ {
338
+ "epoch": 2.73,
339
+ "eval_bleu": 10.292,
340
+ "eval_gen_len": 17.4097,
341
+ "eval_loss": 0.8948560357093811,
342
+ "eval_runtime": 887.752,
343
+ "eval_samples_per_second": 14.837,
344
+ "eval_steps_per_second": 0.928,
345
+ "step": 18000
346
+ },
347
+ {
348
+ "epoch": 2.81,
349
+ "learning_rate": 4.6087721967441154e-05,
350
+ "loss": 0.8113,
351
+ "step": 18500
352
+ },
353
+ {
354
+ "epoch": 2.88,
355
+ "learning_rate": 4.597904757764786e-05,
356
+ "loss": 0.7942,
357
+ "step": 19000
358
+ },
359
+ {
360
+ "epoch": 2.96,
361
+ "learning_rate": 4.5870373187854554e-05,
362
+ "loss": 0.8016,
363
+ "step": 19500
364
+ },
365
+ {
366
+ "epoch": 2.96,
367
+ "eval_bleu": 9.0262,
368
+ "eval_gen_len": 17.4097,
369
+ "eval_loss": 0.8958194255828857,
370
+ "eval_runtime": 868.3186,
371
+ "eval_samples_per_second": 15.17,
372
+ "eval_steps_per_second": 0.949,
373
+ "step": 19500
374
+ },
375
+ {
376
+ "epoch": 3.04,
377
+ "learning_rate": 4.576169879806125e-05,
378
+ "loss": 0.7417,
379
+ "step": 20000
380
+ },
381
+ {
382
+ "epoch": 3.11,
383
+ "learning_rate": 4.5653024408267946e-05,
384
+ "loss": 0.683,
385
+ "step": 20500
386
+ },
387
+ {
388
+ "epoch": 3.19,
389
+ "learning_rate": 4.554435001847465e-05,
390
+ "loss": 0.6872,
391
+ "step": 21000
392
+ },
393
+ {
394
+ "epoch": 3.19,
395
+ "eval_bleu": 9.7549,
396
+ "eval_gen_len": 17.2672,
397
+ "eval_loss": 0.9043093919754028,
398
+ "eval_runtime": 855.9409,
399
+ "eval_samples_per_second": 15.389,
400
+ "eval_steps_per_second": 0.963,
401
+ "step": 21000
402
+ },
403
+ {
404
+ "epoch": 3.26,
405
+ "learning_rate": 4.5435675628681346e-05,
406
+ "loss": 0.6928,
407
+ "step": 21500
408
+ },
409
+ {
410
+ "epoch": 3.34,
411
+ "learning_rate": 4.532700123888804e-05,
412
+ "loss": 0.6973,
413
+ "step": 22000
414
+ },
415
+ {
416
+ "epoch": 3.42,
417
+ "learning_rate": 4.5218326849094746e-05,
418
+ "loss": 0.7107,
419
+ "step": 22500
420
+ },
421
+ {
422
+ "epoch": 3.42,
423
+ "eval_bleu": 10.3016,
424
+ "eval_gen_len": 17.0973,
425
+ "eval_loss": 0.8993721008300781,
426
+ "eval_runtime": 837.6757,
427
+ "eval_samples_per_second": 15.724,
428
+ "eval_steps_per_second": 0.984,
429
+ "step": 22500
430
+ },
431
+ {
432
+ "epoch": 3.49,
433
+ "learning_rate": 4.510965245930144e-05,
434
+ "loss": 0.6899,
435
+ "step": 23000
436
+ },
437
+ {
438
+ "epoch": 3.57,
439
+ "learning_rate": 4.5000978069508145e-05,
440
+ "loss": 0.6794,
441
+ "step": 23500
442
+ },
443
+ {
444
+ "epoch": 3.64,
445
+ "learning_rate": 4.489230367971484e-05,
446
+ "loss": 0.6726,
447
+ "step": 24000
448
+ },
449
+ {
450
+ "epoch": 3.64,
451
+ "eval_bleu": 10.5183,
452
+ "eval_gen_len": 17.2871,
453
+ "eval_loss": 0.8746942281723022,
454
+ "eval_runtime": 850.8583,
455
+ "eval_samples_per_second": 15.481,
456
+ "eval_steps_per_second": 0.968,
457
+ "step": 24000
458
+ },
459
+ {
460
+ "epoch": 3.72,
461
+ "learning_rate": 4.4783629289921545e-05,
462
+ "loss": 0.6782,
463
+ "step": 24500
464
+ },
465
+ {
466
+ "epoch": 3.8,
467
+ "learning_rate": 4.4674954900128234e-05,
468
+ "loss": 0.6821,
469
+ "step": 25000
470
+ },
471
+ {
472
+ "epoch": 3.87,
473
+ "learning_rate": 4.456628051033494e-05,
474
+ "loss": 0.6699,
475
+ "step": 25500
476
+ },
477
+ {
478
+ "epoch": 3.87,
479
+ "eval_bleu": 10.1883,
480
+ "eval_gen_len": 17.2057,
481
+ "eval_loss": 0.865190327167511,
482
+ "eval_runtime": 852.5269,
483
+ "eval_samples_per_second": 15.451,
484
+ "eval_steps_per_second": 0.967,
485
+ "step": 25500
486
+ },
487
+ {
488
+ "epoch": 3.95,
489
+ "learning_rate": 4.4457606120541634e-05,
490
+ "loss": 0.7029,
491
+ "step": 26000
492
+ },
493
+ {
494
+ "epoch": 4.02,
495
+ "learning_rate": 4.434893173074833e-05,
496
+ "loss": 0.6761,
497
+ "step": 26500
498
+ },
499
+ {
500
+ "epoch": 4.1,
501
+ "learning_rate": 4.4240257340955033e-05,
502
+ "loss": 0.612,
503
+ "step": 27000
504
+ },
505
+ {
506
+ "epoch": 4.1,
507
+ "eval_bleu": 9.5697,
508
+ "eval_gen_len": 17.2443,
509
+ "eval_loss": 0.8949306607246399,
510
+ "eval_runtime": 850.694,
511
+ "eval_samples_per_second": 15.484,
512
+ "eval_steps_per_second": 0.969,
513
+ "step": 27000
514
+ },
515
+ {
516
+ "epoch": 4.17,
517
+ "learning_rate": 4.413158295116173e-05,
518
+ "loss": 0.6119,
519
+ "step": 27500
520
+ },
521
+ {
522
+ "epoch": 4.25,
523
+ "learning_rate": 4.402290856136843e-05,
524
+ "loss": 0.6094,
525
+ "step": 28000
526
+ },
527
+ {
528
+ "epoch": 4.33,
529
+ "learning_rate": 4.391423417157513e-05,
530
+ "loss": 0.621,
531
+ "step": 28500
532
+ },
533
+ {
534
+ "epoch": 4.33,
535
+ "eval_bleu": 10.8592,
536
+ "eval_gen_len": 17.329,
537
+ "eval_loss": 0.8904227614402771,
538
+ "eval_runtime": 868.3516,
539
+ "eval_samples_per_second": 15.169,
540
+ "eval_steps_per_second": 0.949,
541
+ "step": 28500
542
+ },
543
+ {
544
+ "epoch": 4.4,
545
+ "learning_rate": 4.380555978178183e-05,
546
+ "loss": 0.6302,
547
+ "step": 29000
548
+ },
549
+ {
550
+ "epoch": 4.48,
551
+ "learning_rate": 4.369688539198852e-05,
552
+ "loss": 0.6206,
553
+ "step": 29500
554
+ },
555
+ {
556
+ "epoch": 4.55,
557
+ "learning_rate": 4.3588211002195225e-05,
558
+ "loss": 0.6219,
559
+ "step": 30000
560
+ },
561
+ {
562
+ "epoch": 4.55,
563
+ "eval_bleu": 10.925,
564
+ "eval_gen_len": 17.482,
565
+ "eval_loss": 0.8771834969520569,
566
+ "eval_runtime": 864.4075,
567
+ "eval_samples_per_second": 15.238,
568
+ "eval_steps_per_second": 0.953,
569
+ "step": 30000
570
+ },
571
+ {
572
+ "epoch": 4.63,
573
+ "learning_rate": 4.347953661240192e-05,
574
+ "loss": 0.6166,
575
+ "step": 30500
576
+ },
577
+ {
578
+ "epoch": 4.71,
579
+ "learning_rate": 4.337086222260862e-05,
580
+ "loss": 0.6057,
581
+ "step": 31000
582
+ },
583
+ {
584
+ "epoch": 4.78,
585
+ "learning_rate": 4.326218783281532e-05,
586
+ "loss": 0.6164,
587
+ "step": 31500
588
+ },
589
+ {
590
+ "epoch": 4.78,
591
+ "eval_bleu": 11.8749,
592
+ "eval_gen_len": 17.1624,
593
+ "eval_loss": 0.8693726658821106,
594
+ "eval_runtime": 846.6139,
595
+ "eval_samples_per_second": 15.558,
596
+ "eval_steps_per_second": 0.973,
597
+ "step": 31500
598
+ },
599
+ {
600
+ "epoch": 4.78,
601
+ "step": 31500,
602
+ "total_flos": 1.0923720993448919e+18,
603
+ "train_loss": 0.9323235357375372,
604
+ "train_runtime": 42332.75,
605
+ "train_samples_per_second": 87.131,
606
+ "train_steps_per_second": 5.446
607
+ }
608
+ ],
609
+ "logging_steps": 500,
610
+ "max_steps": 230545,
611
+ "num_train_epochs": 35,
612
+ "save_steps": 1500,
613
+ "total_flos": 1.0923720993448919e+18,
614
+ "trial_name": null,
615
+ "trial_params": null
616
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc9f6c6258b97f2d71469d8e4060b04e88838a9f1196109d8271a7ced4355f5a
3
+ size 4728