yesj1234 commited on
Commit
ee13c06
·
1 Parent(s): d85acab

Upload folder using huggingface_hub

Browse files
Files changed (49) hide show
  1. .gitattributes +3 -0
  2. README.md +83 -0
  3. added_tokens.json +59 -0
  4. all_results.json +22 -0
  5. checkpoint-11000/added_tokens.json +59 -0
  6. checkpoint-11000/config.json +59 -0
  7. checkpoint-11000/generation_config.json +12 -0
  8. checkpoint-11000/optimizer.pt +3 -0
  9. checkpoint-11000/pytorch_model.bin +3 -0
  10. checkpoint-11000/rng_state_0.pth +3 -0
  11. checkpoint-11000/rng_state_1.pth +3 -0
  12. checkpoint-11000/rng_state_2.pth +3 -0
  13. checkpoint-11000/rng_state_3.pth +3 -0
  14. checkpoint-11000/scheduler.pt +3 -0
  15. checkpoint-11000/sentencepiece.bpe.model +3 -0
  16. checkpoint-11000/special_tokens_map.json +63 -0
  17. checkpoint-11000/tokenizer.json +3 -0
  18. checkpoint-11000/tokenizer_config.json +528 -0
  19. checkpoint-11000/trainer_state.json +261 -0
  20. checkpoint-11000/training_args.bin +3 -0
  21. checkpoint-15000/added_tokens.json +59 -0
  22. checkpoint-15000/config.json +59 -0
  23. checkpoint-15000/generation_config.json +12 -0
  24. checkpoint-15000/optimizer.pt +3 -0
  25. checkpoint-15000/pytorch_model.bin +3 -0
  26. checkpoint-15000/rng_state_0.pth +3 -0
  27. checkpoint-15000/rng_state_1.pth +3 -0
  28. checkpoint-15000/rng_state_2.pth +3 -0
  29. checkpoint-15000/rng_state_3.pth +3 -0
  30. checkpoint-15000/scheduler.pt +3 -0
  31. checkpoint-15000/sentencepiece.bpe.model +3 -0
  32. checkpoint-15000/special_tokens_map.json +63 -0
  33. checkpoint-15000/tokenizer.json +3 -0
  34. checkpoint-15000/tokenizer_config.json +528 -0
  35. checkpoint-15000/trainer_state.json +349 -0
  36. checkpoint-15000/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 +358 -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-11000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-15000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ko
4
+ - en
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: ko-en_mbartLarge_exp20p_linear_decay
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
+ # ko-en_mbartLarge_exp20p_linear_decay
19
+
20
+ This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on an unknown dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 1.2291
23
+ - Bleu: 26.9332
24
+ - Gen Len: 18.743
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: 10
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
60
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
61
+ | 1.4396 | 0.23 | 1000 | 1.3815 | 21.7052 | 18.6047 |
62
+ | 1.338 | 0.46 | 2000 | 1.3044 | 23.7087 | 18.9939 |
63
+ | 1.2938 | 0.7 | 3000 | 1.2556 | 24.6339 | 18.8866 |
64
+ | 1.251 | 0.93 | 4000 | 1.2229 | 25.2975 | 19.0918 |
65
+ | 0.9843 | 1.16 | 5000 | 1.2309 | 25.609 | 18.7589 |
66
+ | 0.9874 | 1.39 | 6000 | 1.2101 | 26.1792 | 18.8287 |
67
+ | 0.9838 | 1.62 | 7000 | 1.2053 | 26.024 | 18.4025 |
68
+ | 0.9927 | 1.86 | 8000 | 1.1907 | 26.3148 | 19.09 |
69
+ | 0.7835 | 2.09 | 9000 | 1.2300 | 26.5613 | 18.7196 |
70
+ | 0.7437 | 2.32 | 10000 | 1.2358 | 26.8232 | 18.6513 |
71
+ | 0.7585 | 2.55 | 11000 | 1.2291 | 26.9203 | 18.7513 |
72
+ | 0.7631 | 2.78 | 12000 | 1.2170 | 26.8668 | 18.5441 |
73
+ | 0.7428 | 3.02 | 13000 | 1.3272 | 26.2506 | 18.6959 |
74
+ | 0.5502 | 3.25 | 14000 | 1.3392 | 26.419 | 18.6722 |
75
+ | 0.5577 | 3.48 | 15000 | 1.3204 | 26.1621 | 18.7036 |
76
+
77
+
78
+ ### Framework versions
79
+
80
+ - Transformers 4.34.0
81
+ - Pytorch 2.1.0+cu121
82
+ - Datasets 2.14.5
83
+ - 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": 3.48,
3
+ "eval_bleu": 26.9332,
4
+ "eval_gen_len": 18.743,
5
+ "eval_loss": 1.2291104793548584,
6
+ "eval_runtime": 1079.9427,
7
+ "eval_samples": 17237,
8
+ "eval_samples_per_second": 15.961,
9
+ "eval_steps_per_second": 0.998,
10
+ "predict_bleu": 27.0802,
11
+ "predict_gen_len": 18.6654,
12
+ "predict_loss": 1.210374116897583,
13
+ "predict_runtime": 1080.6681,
14
+ "predict_samples": 17237,
15
+ "predict_samples_per_second": 15.95,
16
+ "predict_steps_per_second": 0.998,
17
+ "train_loss": 0.9628536214192709,
18
+ "train_runtime": 41969.1276,
19
+ "train_samples": 137900,
20
+ "train_samples_per_second": 32.857,
21
+ "train_steps_per_second": 1.027
22
+ }
checkpoint-11000/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-11000/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": 250004,
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-11000/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": 250004,
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-11000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c330ee4b1ad88247fbc90c278052c56e2555f82ac6a13f326cf527ebddf7228
3
+ size 4887473903
checkpoint-11000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:872f9acd2ad040ba0d0ccc5df8a1c7c33ad04a27f4c16e4258fbae96146d1f5c
3
+ size 2444694490
checkpoint-11000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39f45a5cdd458337d4a80a688d37f2dcd7e2fc475cfc7a16361a894011997042
3
+ size 15024
checkpoint-11000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bb7f5091e8ffc9db2c3fbb75fc4df750b58055c1f287f8504d3c81d0591d604
3
+ size 15024
checkpoint-11000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:379e23f4bfdc29184642dc7edf8c5da70df784102f35e87e52b5eae9f07edcf2
3
+ size 15024
checkpoint-11000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26b9f45e051672f40ac7125b2ebd6e8921947fe2edc5ad4c6130fd1734fbc11f
3
+ size 15024
checkpoint-11000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:605f1c8ca12c41f0252e21f599835b78eebada32fd1984e72284d149edc3a881
3
+ size 1064
checkpoint-11000/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-11000/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-11000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3a71a6430f26d8667787032844b9efe0d820460f1eb2e56a96b5f171813bc1a
3
+ size 17109939
checkpoint-11000/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": "en_XX",
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
checkpoint-11000/trainer_state.json ADDED
@@ -0,0 +1,261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 26.9203,
3
+ "best_model_checkpoint": "./ko-en_mbartLarge_exp20p_linear_decay/checkpoint-11000",
4
+ "epoch": 2.552500290056851,
5
+ "eval_steps": 1000,
6
+ "global_step": 11000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.12,
13
+ "learning_rate": 5e-05,
14
+ "loss": 1.557,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.23,
19
+ "learning_rate": 4.941300774829773e-05,
20
+ "loss": 1.4396,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.23,
25
+ "eval_bleu": 21.7052,
26
+ "eval_gen_len": 18.6047,
27
+ "eval_loss": 1.381515622138977,
28
+ "eval_runtime": 1113.9878,
29
+ "eval_samples_per_second": 15.473,
30
+ "eval_steps_per_second": 0.968,
31
+ "step": 1000
32
+ },
33
+ {
34
+ "epoch": 0.35,
35
+ "learning_rate": 4.8826015496595445e-05,
36
+ "loss": 1.3838,
37
+ "step": 1500
38
+ },
39
+ {
40
+ "epoch": 0.46,
41
+ "learning_rate": 4.823902324489317e-05,
42
+ "loss": 1.338,
43
+ "step": 2000
44
+ },
45
+ {
46
+ "epoch": 0.46,
47
+ "eval_bleu": 23.7087,
48
+ "eval_gen_len": 18.9939,
49
+ "eval_loss": 1.3043569326400757,
50
+ "eval_runtime": 1109.0361,
51
+ "eval_samples_per_second": 15.542,
52
+ "eval_steps_per_second": 0.972,
53
+ "step": 2000
54
+ },
55
+ {
56
+ "epoch": 0.58,
57
+ "learning_rate": 4.7652030993190894e-05,
58
+ "loss": 1.3081,
59
+ "step": 2500
60
+ },
61
+ {
62
+ "epoch": 0.7,
63
+ "learning_rate": 4.706503874148862e-05,
64
+ "loss": 1.2938,
65
+ "step": 3000
66
+ },
67
+ {
68
+ "epoch": 0.7,
69
+ "eval_bleu": 24.6339,
70
+ "eval_gen_len": 18.8866,
71
+ "eval_loss": 1.2555760145187378,
72
+ "eval_runtime": 1131.9789,
73
+ "eval_samples_per_second": 15.227,
74
+ "eval_steps_per_second": 0.952,
75
+ "step": 3000
76
+ },
77
+ {
78
+ "epoch": 0.81,
79
+ "learning_rate": 4.6478046489786336e-05,
80
+ "loss": 1.2587,
81
+ "step": 3500
82
+ },
83
+ {
84
+ "epoch": 0.93,
85
+ "learning_rate": 4.589105423808406e-05,
86
+ "loss": 1.251,
87
+ "step": 4000
88
+ },
89
+ {
90
+ "epoch": 0.93,
91
+ "eval_bleu": 25.2975,
92
+ "eval_gen_len": 19.0918,
93
+ "eval_loss": 1.2229138612747192,
94
+ "eval_runtime": 1120.4864,
95
+ "eval_samples_per_second": 15.383,
96
+ "eval_steps_per_second": 0.962,
97
+ "step": 4000
98
+ },
99
+ {
100
+ "epoch": 1.04,
101
+ "learning_rate": 4.530406198638178e-05,
102
+ "loss": 1.135,
103
+ "step": 4500
104
+ },
105
+ {
106
+ "epoch": 1.16,
107
+ "learning_rate": 4.47170697346795e-05,
108
+ "loss": 0.9843,
109
+ "step": 5000
110
+ },
111
+ {
112
+ "epoch": 1.16,
113
+ "eval_bleu": 25.609,
114
+ "eval_gen_len": 18.7589,
115
+ "eval_loss": 1.2308591604232788,
116
+ "eval_runtime": 1118.1785,
117
+ "eval_samples_per_second": 15.415,
118
+ "eval_steps_per_second": 0.964,
119
+ "step": 5000
120
+ },
121
+ {
122
+ "epoch": 1.28,
123
+ "learning_rate": 4.413007748297723e-05,
124
+ "loss": 0.9916,
125
+ "step": 5500
126
+ },
127
+ {
128
+ "epoch": 1.39,
129
+ "learning_rate": 4.354308523127495e-05,
130
+ "loss": 0.9874,
131
+ "step": 6000
132
+ },
133
+ {
134
+ "epoch": 1.39,
135
+ "eval_bleu": 26.1792,
136
+ "eval_gen_len": 18.8287,
137
+ "eval_loss": 1.2100664377212524,
138
+ "eval_runtime": 1093.6874,
139
+ "eval_samples_per_second": 15.76,
140
+ "eval_steps_per_second": 0.986,
141
+ "step": 6000
142
+ },
143
+ {
144
+ "epoch": 1.51,
145
+ "learning_rate": 4.295609297957267e-05,
146
+ "loss": 0.9931,
147
+ "step": 6500
148
+ },
149
+ {
150
+ "epoch": 1.62,
151
+ "learning_rate": 4.2369100727870395e-05,
152
+ "loss": 0.9838,
153
+ "step": 7000
154
+ },
155
+ {
156
+ "epoch": 1.62,
157
+ "eval_bleu": 26.024,
158
+ "eval_gen_len": 18.4025,
159
+ "eval_loss": 1.2053465843200684,
160
+ "eval_runtime": 1074.6707,
161
+ "eval_samples_per_second": 16.039,
162
+ "eval_steps_per_second": 1.003,
163
+ "step": 7000
164
+ },
165
+ {
166
+ "epoch": 1.74,
167
+ "learning_rate": 4.178210847616812e-05,
168
+ "loss": 0.9931,
169
+ "step": 7500
170
+ },
171
+ {
172
+ "epoch": 1.86,
173
+ "learning_rate": 4.1195116224465844e-05,
174
+ "loss": 0.9927,
175
+ "step": 8000
176
+ },
177
+ {
178
+ "epoch": 1.86,
179
+ "eval_bleu": 26.3148,
180
+ "eval_gen_len": 19.09,
181
+ "eval_loss": 1.1906589269638062,
182
+ "eval_runtime": 1112.0878,
183
+ "eval_samples_per_second": 15.5,
184
+ "eval_steps_per_second": 0.969,
185
+ "step": 8000
186
+ },
187
+ {
188
+ "epoch": 1.97,
189
+ "learning_rate": 4.060812397276356e-05,
190
+ "loss": 0.9921,
191
+ "step": 8500
192
+ },
193
+ {
194
+ "epoch": 2.09,
195
+ "learning_rate": 4.0021131721061286e-05,
196
+ "loss": 0.7835,
197
+ "step": 9000
198
+ },
199
+ {
200
+ "epoch": 2.09,
201
+ "eval_bleu": 26.5613,
202
+ "eval_gen_len": 18.7196,
203
+ "eval_loss": 1.2300479412078857,
204
+ "eval_runtime": 1083.4234,
205
+ "eval_samples_per_second": 15.91,
206
+ "eval_steps_per_second": 0.995,
207
+ "step": 9000
208
+ },
209
+ {
210
+ "epoch": 2.2,
211
+ "learning_rate": 3.9434139469359004e-05,
212
+ "loss": 0.7268,
213
+ "step": 9500
214
+ },
215
+ {
216
+ "epoch": 2.32,
217
+ "learning_rate": 3.884714721765673e-05,
218
+ "loss": 0.7437,
219
+ "step": 10000
220
+ },
221
+ {
222
+ "epoch": 2.32,
223
+ "eval_bleu": 26.8232,
224
+ "eval_gen_len": 18.6513,
225
+ "eval_loss": 1.2358065843582153,
226
+ "eval_runtime": 1078.4504,
227
+ "eval_samples_per_second": 15.983,
228
+ "eval_steps_per_second": 1.0,
229
+ "step": 10000
230
+ },
231
+ {
232
+ "epoch": 2.44,
233
+ "learning_rate": 3.826015496595445e-05,
234
+ "loss": 0.7532,
235
+ "step": 10500
236
+ },
237
+ {
238
+ "epoch": 2.55,
239
+ "learning_rate": 3.767316271425218e-05,
240
+ "loss": 0.7585,
241
+ "step": 11000
242
+ },
243
+ {
244
+ "epoch": 2.55,
245
+ "eval_bleu": 26.9203,
246
+ "eval_gen_len": 18.7513,
247
+ "eval_loss": 1.2291104793548584,
248
+ "eval_runtime": 1083.6296,
249
+ "eval_samples_per_second": 15.907,
250
+ "eval_steps_per_second": 0.995,
251
+ "step": 11000
252
+ }
253
+ ],
254
+ "logging_steps": 500,
255
+ "max_steps": 43090,
256
+ "num_train_epochs": 10,
257
+ "save_steps": 1000,
258
+ "total_flos": 7.62829678313472e+17,
259
+ "trial_name": null,
260
+ "trial_params": null
261
+ }
checkpoint-11000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91607c7bfad43ad04ea3fed68b9ccfcd999071a12acc321f89b877d6c7150cbc
3
+ size 4728
checkpoint-15000/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-15000/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": 250004,
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-15000/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": 250004,
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-15000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:923ccd908ac0c742a1d526463a00b26801ec83ca978cc08a9baea665e2765287
3
+ size 4887473903
checkpoint-15000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4d5dab55bf4f6301143ade80d5cc058f95fbcf8c71e756567685570ab993b36
3
+ size 2444694490
checkpoint-15000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:312f5fc5fbc55ed884df58c847c50fc2a5d10a86239971772f1dc4f8aedaab4e
3
+ size 15024
checkpoint-15000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3f12faa4b3cba59886588647e69a18d1116dd3671b24a220e5e9f5e079b4547
3
+ size 15024
checkpoint-15000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc9811e8eb89cc3dc9656ac13d922f1bd4ea4e4047380a4a3e592f123e8d52dc
3
+ size 15024
checkpoint-15000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8582c18394547879766417bdc9182e5715c2c115650f738cfe78cc87abbd1e15
3
+ size 15024
checkpoint-15000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c04d8a9316dae2873ddcf2e355ff437ef83a469fdfc7abce9b2bd4e5443c90
3
+ size 1064
checkpoint-15000/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-15000/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-15000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3a71a6430f26d8667787032844b9efe0d820460f1eb2e56a96b5f171813bc1a
3
+ size 17109939
checkpoint-15000/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": "en_XX",
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
checkpoint-15000/trainer_state.json ADDED
@@ -0,0 +1,349 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 26.9203,
3
+ "best_model_checkpoint": "./ko-en_mbartLarge_exp20p_linear_decay/checkpoint-11000",
4
+ "epoch": 3.4806822137138878,
5
+ "eval_steps": 1000,
6
+ "global_step": 15000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.12,
13
+ "learning_rate": 5e-05,
14
+ "loss": 1.557,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.23,
19
+ "learning_rate": 4.941300774829773e-05,
20
+ "loss": 1.4396,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.23,
25
+ "eval_bleu": 21.7052,
26
+ "eval_gen_len": 18.6047,
27
+ "eval_loss": 1.381515622138977,
28
+ "eval_runtime": 1113.9878,
29
+ "eval_samples_per_second": 15.473,
30
+ "eval_steps_per_second": 0.968,
31
+ "step": 1000
32
+ },
33
+ {
34
+ "epoch": 0.35,
35
+ "learning_rate": 4.8826015496595445e-05,
36
+ "loss": 1.3838,
37
+ "step": 1500
38
+ },
39
+ {
40
+ "epoch": 0.46,
41
+ "learning_rate": 4.823902324489317e-05,
42
+ "loss": 1.338,
43
+ "step": 2000
44
+ },
45
+ {
46
+ "epoch": 0.46,
47
+ "eval_bleu": 23.7087,
48
+ "eval_gen_len": 18.9939,
49
+ "eval_loss": 1.3043569326400757,
50
+ "eval_runtime": 1109.0361,
51
+ "eval_samples_per_second": 15.542,
52
+ "eval_steps_per_second": 0.972,
53
+ "step": 2000
54
+ },
55
+ {
56
+ "epoch": 0.58,
57
+ "learning_rate": 4.7652030993190894e-05,
58
+ "loss": 1.3081,
59
+ "step": 2500
60
+ },
61
+ {
62
+ "epoch": 0.7,
63
+ "learning_rate": 4.706503874148862e-05,
64
+ "loss": 1.2938,
65
+ "step": 3000
66
+ },
67
+ {
68
+ "epoch": 0.7,
69
+ "eval_bleu": 24.6339,
70
+ "eval_gen_len": 18.8866,
71
+ "eval_loss": 1.2555760145187378,
72
+ "eval_runtime": 1131.9789,
73
+ "eval_samples_per_second": 15.227,
74
+ "eval_steps_per_second": 0.952,
75
+ "step": 3000
76
+ },
77
+ {
78
+ "epoch": 0.81,
79
+ "learning_rate": 4.6478046489786336e-05,
80
+ "loss": 1.2587,
81
+ "step": 3500
82
+ },
83
+ {
84
+ "epoch": 0.93,
85
+ "learning_rate": 4.589105423808406e-05,
86
+ "loss": 1.251,
87
+ "step": 4000
88
+ },
89
+ {
90
+ "epoch": 0.93,
91
+ "eval_bleu": 25.2975,
92
+ "eval_gen_len": 19.0918,
93
+ "eval_loss": 1.2229138612747192,
94
+ "eval_runtime": 1120.4864,
95
+ "eval_samples_per_second": 15.383,
96
+ "eval_steps_per_second": 0.962,
97
+ "step": 4000
98
+ },
99
+ {
100
+ "epoch": 1.04,
101
+ "learning_rate": 4.530406198638178e-05,
102
+ "loss": 1.135,
103
+ "step": 4500
104
+ },
105
+ {
106
+ "epoch": 1.16,
107
+ "learning_rate": 4.47170697346795e-05,
108
+ "loss": 0.9843,
109
+ "step": 5000
110
+ },
111
+ {
112
+ "epoch": 1.16,
113
+ "eval_bleu": 25.609,
114
+ "eval_gen_len": 18.7589,
115
+ "eval_loss": 1.2308591604232788,
116
+ "eval_runtime": 1118.1785,
117
+ "eval_samples_per_second": 15.415,
118
+ "eval_steps_per_second": 0.964,
119
+ "step": 5000
120
+ },
121
+ {
122
+ "epoch": 1.28,
123
+ "learning_rate": 4.413007748297723e-05,
124
+ "loss": 0.9916,
125
+ "step": 5500
126
+ },
127
+ {
128
+ "epoch": 1.39,
129
+ "learning_rate": 4.354308523127495e-05,
130
+ "loss": 0.9874,
131
+ "step": 6000
132
+ },
133
+ {
134
+ "epoch": 1.39,
135
+ "eval_bleu": 26.1792,
136
+ "eval_gen_len": 18.8287,
137
+ "eval_loss": 1.2100664377212524,
138
+ "eval_runtime": 1093.6874,
139
+ "eval_samples_per_second": 15.76,
140
+ "eval_steps_per_second": 0.986,
141
+ "step": 6000
142
+ },
143
+ {
144
+ "epoch": 1.51,
145
+ "learning_rate": 4.295609297957267e-05,
146
+ "loss": 0.9931,
147
+ "step": 6500
148
+ },
149
+ {
150
+ "epoch": 1.62,
151
+ "learning_rate": 4.2369100727870395e-05,
152
+ "loss": 0.9838,
153
+ "step": 7000
154
+ },
155
+ {
156
+ "epoch": 1.62,
157
+ "eval_bleu": 26.024,
158
+ "eval_gen_len": 18.4025,
159
+ "eval_loss": 1.2053465843200684,
160
+ "eval_runtime": 1074.6707,
161
+ "eval_samples_per_second": 16.039,
162
+ "eval_steps_per_second": 1.003,
163
+ "step": 7000
164
+ },
165
+ {
166
+ "epoch": 1.74,
167
+ "learning_rate": 4.178210847616812e-05,
168
+ "loss": 0.9931,
169
+ "step": 7500
170
+ },
171
+ {
172
+ "epoch": 1.86,
173
+ "learning_rate": 4.1195116224465844e-05,
174
+ "loss": 0.9927,
175
+ "step": 8000
176
+ },
177
+ {
178
+ "epoch": 1.86,
179
+ "eval_bleu": 26.3148,
180
+ "eval_gen_len": 19.09,
181
+ "eval_loss": 1.1906589269638062,
182
+ "eval_runtime": 1112.0878,
183
+ "eval_samples_per_second": 15.5,
184
+ "eval_steps_per_second": 0.969,
185
+ "step": 8000
186
+ },
187
+ {
188
+ "epoch": 1.97,
189
+ "learning_rate": 4.060812397276356e-05,
190
+ "loss": 0.9921,
191
+ "step": 8500
192
+ },
193
+ {
194
+ "epoch": 2.09,
195
+ "learning_rate": 4.0021131721061286e-05,
196
+ "loss": 0.7835,
197
+ "step": 9000
198
+ },
199
+ {
200
+ "epoch": 2.09,
201
+ "eval_bleu": 26.5613,
202
+ "eval_gen_len": 18.7196,
203
+ "eval_loss": 1.2300479412078857,
204
+ "eval_runtime": 1083.4234,
205
+ "eval_samples_per_second": 15.91,
206
+ "eval_steps_per_second": 0.995,
207
+ "step": 9000
208
+ },
209
+ {
210
+ "epoch": 2.2,
211
+ "learning_rate": 3.9434139469359004e-05,
212
+ "loss": 0.7268,
213
+ "step": 9500
214
+ },
215
+ {
216
+ "epoch": 2.32,
217
+ "learning_rate": 3.884714721765673e-05,
218
+ "loss": 0.7437,
219
+ "step": 10000
220
+ },
221
+ {
222
+ "epoch": 2.32,
223
+ "eval_bleu": 26.8232,
224
+ "eval_gen_len": 18.6513,
225
+ "eval_loss": 1.2358065843582153,
226
+ "eval_runtime": 1078.4504,
227
+ "eval_samples_per_second": 15.983,
228
+ "eval_steps_per_second": 1.0,
229
+ "step": 10000
230
+ },
231
+ {
232
+ "epoch": 2.44,
233
+ "learning_rate": 3.826015496595445e-05,
234
+ "loss": 0.7532,
235
+ "step": 10500
236
+ },
237
+ {
238
+ "epoch": 2.55,
239
+ "learning_rate": 3.767316271425218e-05,
240
+ "loss": 0.7585,
241
+ "step": 11000
242
+ },
243
+ {
244
+ "epoch": 2.55,
245
+ "eval_bleu": 26.9203,
246
+ "eval_gen_len": 18.7513,
247
+ "eval_loss": 1.2291104793548584,
248
+ "eval_runtime": 1083.6296,
249
+ "eval_samples_per_second": 15.907,
250
+ "eval_steps_per_second": 0.995,
251
+ "step": 11000
252
+ },
253
+ {
254
+ "epoch": 2.67,
255
+ "learning_rate": 3.7086170462549895e-05,
256
+ "loss": 0.7627,
257
+ "step": 11500
258
+ },
259
+ {
260
+ "epoch": 2.78,
261
+ "learning_rate": 3.649917821084762e-05,
262
+ "loss": 0.7631,
263
+ "step": 12000
264
+ },
265
+ {
266
+ "epoch": 2.78,
267
+ "eval_bleu": 26.8668,
268
+ "eval_gen_len": 18.5441,
269
+ "eval_loss": 1.217042088508606,
270
+ "eval_runtime": 1079.6719,
271
+ "eval_samples_per_second": 15.965,
272
+ "eval_steps_per_second": 0.998,
273
+ "step": 12000
274
+ },
275
+ {
276
+ "epoch": 2.9,
277
+ "learning_rate": 3.591218595914534e-05,
278
+ "loss": 0.772,
279
+ "step": 12500
280
+ },
281
+ {
282
+ "epoch": 3.02,
283
+ "learning_rate": 3.532519370744307e-05,
284
+ "loss": 0.7428,
285
+ "step": 13000
286
+ },
287
+ {
288
+ "epoch": 3.02,
289
+ "eval_bleu": 26.2506,
290
+ "eval_gen_len": 18.6959,
291
+ "eval_loss": 1.3271690607070923,
292
+ "eval_runtime": 1081.5187,
293
+ "eval_samples_per_second": 15.938,
294
+ "eval_steps_per_second": 0.997,
295
+ "step": 13000
296
+ },
297
+ {
298
+ "epoch": 3.13,
299
+ "learning_rate": 3.473820145574079e-05,
300
+ "loss": 0.5342,
301
+ "step": 13500
302
+ },
303
+ {
304
+ "epoch": 3.25,
305
+ "learning_rate": 3.415120920403851e-05,
306
+ "loss": 0.5502,
307
+ "step": 14000
308
+ },
309
+ {
310
+ "epoch": 3.25,
311
+ "eval_bleu": 26.419,
312
+ "eval_gen_len": 18.6722,
313
+ "eval_loss": 1.3392120599746704,
314
+ "eval_runtime": 1080.7472,
315
+ "eval_samples_per_second": 15.949,
316
+ "eval_steps_per_second": 0.997,
317
+ "step": 14000
318
+ },
319
+ {
320
+ "epoch": 3.36,
321
+ "learning_rate": 3.356421695233623e-05,
322
+ "loss": 0.5541,
323
+ "step": 14500
324
+ },
325
+ {
326
+ "epoch": 3.48,
327
+ "learning_rate": 3.2977224700633954e-05,
328
+ "loss": 0.5577,
329
+ "step": 15000
330
+ },
331
+ {
332
+ "epoch": 3.48,
333
+ "eval_bleu": 26.1621,
334
+ "eval_gen_len": 18.7036,
335
+ "eval_loss": 1.320376992225647,
336
+ "eval_runtime": 1082.8765,
337
+ "eval_samples_per_second": 15.918,
338
+ "eval_steps_per_second": 0.995,
339
+ "step": 15000
340
+ }
341
+ ],
342
+ "logging_steps": 500,
343
+ "max_steps": 43090,
344
+ "num_train_epochs": 10,
345
+ "save_steps": 1000,
346
+ "total_flos": 1.04022228860928e+18,
347
+ "trial_name": null,
348
+ "trial_params": null
349
+ }
checkpoint-15000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91607c7bfad43ad04ea3fed68b9ccfcd999071a12acc321f89b877d6c7150cbc
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": 250004,
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": 3.48,
3
+ "eval_bleu": 26.9332,
4
+ "eval_gen_len": 18.743,
5
+ "eval_loss": 1.2291104793548584,
6
+ "eval_runtime": 1079.9427,
7
+ "eval_samples": 17237,
8
+ "eval_samples_per_second": 15.961,
9
+ "eval_steps_per_second": 0.998
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": 250004,
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": 27.0802,
3
+ "predict_gen_len": 18.6654,
4
+ "predict_loss": 1.210374116897583,
5
+ "predict_runtime": 1080.6681,
6
+ "predict_samples": 17237,
7
+ "predict_samples_per_second": 15.95,
8
+ "predict_steps_per_second": 0.998
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:872f9acd2ad040ba0d0ccc5df8a1c7c33ad04a27f4c16e4258fbae96146d1f5c
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:d3a71a6430f26d8667787032844b9efe0d820460f1eb2e56a96b5f171813bc1a
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": "en_XX",
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.48,
3
+ "train_loss": 0.9628536214192709,
4
+ "train_runtime": 41969.1276,
5
+ "train_samples": 137900,
6
+ "train_samples_per_second": 32.857,
7
+ "train_steps_per_second": 1.027
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,358 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 26.9203,
3
+ "best_model_checkpoint": "./ko-en_mbartLarge_exp20p_linear_decay/checkpoint-11000",
4
+ "epoch": 3.4806822137138878,
5
+ "eval_steps": 1000,
6
+ "global_step": 15000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.12,
13
+ "learning_rate": 5e-05,
14
+ "loss": 1.557,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.23,
19
+ "learning_rate": 4.941300774829773e-05,
20
+ "loss": 1.4396,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.23,
25
+ "eval_bleu": 21.7052,
26
+ "eval_gen_len": 18.6047,
27
+ "eval_loss": 1.381515622138977,
28
+ "eval_runtime": 1113.9878,
29
+ "eval_samples_per_second": 15.473,
30
+ "eval_steps_per_second": 0.968,
31
+ "step": 1000
32
+ },
33
+ {
34
+ "epoch": 0.35,
35
+ "learning_rate": 4.8826015496595445e-05,
36
+ "loss": 1.3838,
37
+ "step": 1500
38
+ },
39
+ {
40
+ "epoch": 0.46,
41
+ "learning_rate": 4.823902324489317e-05,
42
+ "loss": 1.338,
43
+ "step": 2000
44
+ },
45
+ {
46
+ "epoch": 0.46,
47
+ "eval_bleu": 23.7087,
48
+ "eval_gen_len": 18.9939,
49
+ "eval_loss": 1.3043569326400757,
50
+ "eval_runtime": 1109.0361,
51
+ "eval_samples_per_second": 15.542,
52
+ "eval_steps_per_second": 0.972,
53
+ "step": 2000
54
+ },
55
+ {
56
+ "epoch": 0.58,
57
+ "learning_rate": 4.7652030993190894e-05,
58
+ "loss": 1.3081,
59
+ "step": 2500
60
+ },
61
+ {
62
+ "epoch": 0.7,
63
+ "learning_rate": 4.706503874148862e-05,
64
+ "loss": 1.2938,
65
+ "step": 3000
66
+ },
67
+ {
68
+ "epoch": 0.7,
69
+ "eval_bleu": 24.6339,
70
+ "eval_gen_len": 18.8866,
71
+ "eval_loss": 1.2555760145187378,
72
+ "eval_runtime": 1131.9789,
73
+ "eval_samples_per_second": 15.227,
74
+ "eval_steps_per_second": 0.952,
75
+ "step": 3000
76
+ },
77
+ {
78
+ "epoch": 0.81,
79
+ "learning_rate": 4.6478046489786336e-05,
80
+ "loss": 1.2587,
81
+ "step": 3500
82
+ },
83
+ {
84
+ "epoch": 0.93,
85
+ "learning_rate": 4.589105423808406e-05,
86
+ "loss": 1.251,
87
+ "step": 4000
88
+ },
89
+ {
90
+ "epoch": 0.93,
91
+ "eval_bleu": 25.2975,
92
+ "eval_gen_len": 19.0918,
93
+ "eval_loss": 1.2229138612747192,
94
+ "eval_runtime": 1120.4864,
95
+ "eval_samples_per_second": 15.383,
96
+ "eval_steps_per_second": 0.962,
97
+ "step": 4000
98
+ },
99
+ {
100
+ "epoch": 1.04,
101
+ "learning_rate": 4.530406198638178e-05,
102
+ "loss": 1.135,
103
+ "step": 4500
104
+ },
105
+ {
106
+ "epoch": 1.16,
107
+ "learning_rate": 4.47170697346795e-05,
108
+ "loss": 0.9843,
109
+ "step": 5000
110
+ },
111
+ {
112
+ "epoch": 1.16,
113
+ "eval_bleu": 25.609,
114
+ "eval_gen_len": 18.7589,
115
+ "eval_loss": 1.2308591604232788,
116
+ "eval_runtime": 1118.1785,
117
+ "eval_samples_per_second": 15.415,
118
+ "eval_steps_per_second": 0.964,
119
+ "step": 5000
120
+ },
121
+ {
122
+ "epoch": 1.28,
123
+ "learning_rate": 4.413007748297723e-05,
124
+ "loss": 0.9916,
125
+ "step": 5500
126
+ },
127
+ {
128
+ "epoch": 1.39,
129
+ "learning_rate": 4.354308523127495e-05,
130
+ "loss": 0.9874,
131
+ "step": 6000
132
+ },
133
+ {
134
+ "epoch": 1.39,
135
+ "eval_bleu": 26.1792,
136
+ "eval_gen_len": 18.8287,
137
+ "eval_loss": 1.2100664377212524,
138
+ "eval_runtime": 1093.6874,
139
+ "eval_samples_per_second": 15.76,
140
+ "eval_steps_per_second": 0.986,
141
+ "step": 6000
142
+ },
143
+ {
144
+ "epoch": 1.51,
145
+ "learning_rate": 4.295609297957267e-05,
146
+ "loss": 0.9931,
147
+ "step": 6500
148
+ },
149
+ {
150
+ "epoch": 1.62,
151
+ "learning_rate": 4.2369100727870395e-05,
152
+ "loss": 0.9838,
153
+ "step": 7000
154
+ },
155
+ {
156
+ "epoch": 1.62,
157
+ "eval_bleu": 26.024,
158
+ "eval_gen_len": 18.4025,
159
+ "eval_loss": 1.2053465843200684,
160
+ "eval_runtime": 1074.6707,
161
+ "eval_samples_per_second": 16.039,
162
+ "eval_steps_per_second": 1.003,
163
+ "step": 7000
164
+ },
165
+ {
166
+ "epoch": 1.74,
167
+ "learning_rate": 4.178210847616812e-05,
168
+ "loss": 0.9931,
169
+ "step": 7500
170
+ },
171
+ {
172
+ "epoch": 1.86,
173
+ "learning_rate": 4.1195116224465844e-05,
174
+ "loss": 0.9927,
175
+ "step": 8000
176
+ },
177
+ {
178
+ "epoch": 1.86,
179
+ "eval_bleu": 26.3148,
180
+ "eval_gen_len": 19.09,
181
+ "eval_loss": 1.1906589269638062,
182
+ "eval_runtime": 1112.0878,
183
+ "eval_samples_per_second": 15.5,
184
+ "eval_steps_per_second": 0.969,
185
+ "step": 8000
186
+ },
187
+ {
188
+ "epoch": 1.97,
189
+ "learning_rate": 4.060812397276356e-05,
190
+ "loss": 0.9921,
191
+ "step": 8500
192
+ },
193
+ {
194
+ "epoch": 2.09,
195
+ "learning_rate": 4.0021131721061286e-05,
196
+ "loss": 0.7835,
197
+ "step": 9000
198
+ },
199
+ {
200
+ "epoch": 2.09,
201
+ "eval_bleu": 26.5613,
202
+ "eval_gen_len": 18.7196,
203
+ "eval_loss": 1.2300479412078857,
204
+ "eval_runtime": 1083.4234,
205
+ "eval_samples_per_second": 15.91,
206
+ "eval_steps_per_second": 0.995,
207
+ "step": 9000
208
+ },
209
+ {
210
+ "epoch": 2.2,
211
+ "learning_rate": 3.9434139469359004e-05,
212
+ "loss": 0.7268,
213
+ "step": 9500
214
+ },
215
+ {
216
+ "epoch": 2.32,
217
+ "learning_rate": 3.884714721765673e-05,
218
+ "loss": 0.7437,
219
+ "step": 10000
220
+ },
221
+ {
222
+ "epoch": 2.32,
223
+ "eval_bleu": 26.8232,
224
+ "eval_gen_len": 18.6513,
225
+ "eval_loss": 1.2358065843582153,
226
+ "eval_runtime": 1078.4504,
227
+ "eval_samples_per_second": 15.983,
228
+ "eval_steps_per_second": 1.0,
229
+ "step": 10000
230
+ },
231
+ {
232
+ "epoch": 2.44,
233
+ "learning_rate": 3.826015496595445e-05,
234
+ "loss": 0.7532,
235
+ "step": 10500
236
+ },
237
+ {
238
+ "epoch": 2.55,
239
+ "learning_rate": 3.767316271425218e-05,
240
+ "loss": 0.7585,
241
+ "step": 11000
242
+ },
243
+ {
244
+ "epoch": 2.55,
245
+ "eval_bleu": 26.9203,
246
+ "eval_gen_len": 18.7513,
247
+ "eval_loss": 1.2291104793548584,
248
+ "eval_runtime": 1083.6296,
249
+ "eval_samples_per_second": 15.907,
250
+ "eval_steps_per_second": 0.995,
251
+ "step": 11000
252
+ },
253
+ {
254
+ "epoch": 2.67,
255
+ "learning_rate": 3.7086170462549895e-05,
256
+ "loss": 0.7627,
257
+ "step": 11500
258
+ },
259
+ {
260
+ "epoch": 2.78,
261
+ "learning_rate": 3.649917821084762e-05,
262
+ "loss": 0.7631,
263
+ "step": 12000
264
+ },
265
+ {
266
+ "epoch": 2.78,
267
+ "eval_bleu": 26.8668,
268
+ "eval_gen_len": 18.5441,
269
+ "eval_loss": 1.217042088508606,
270
+ "eval_runtime": 1079.6719,
271
+ "eval_samples_per_second": 15.965,
272
+ "eval_steps_per_second": 0.998,
273
+ "step": 12000
274
+ },
275
+ {
276
+ "epoch": 2.9,
277
+ "learning_rate": 3.591218595914534e-05,
278
+ "loss": 0.772,
279
+ "step": 12500
280
+ },
281
+ {
282
+ "epoch": 3.02,
283
+ "learning_rate": 3.532519370744307e-05,
284
+ "loss": 0.7428,
285
+ "step": 13000
286
+ },
287
+ {
288
+ "epoch": 3.02,
289
+ "eval_bleu": 26.2506,
290
+ "eval_gen_len": 18.6959,
291
+ "eval_loss": 1.3271690607070923,
292
+ "eval_runtime": 1081.5187,
293
+ "eval_samples_per_second": 15.938,
294
+ "eval_steps_per_second": 0.997,
295
+ "step": 13000
296
+ },
297
+ {
298
+ "epoch": 3.13,
299
+ "learning_rate": 3.473820145574079e-05,
300
+ "loss": 0.5342,
301
+ "step": 13500
302
+ },
303
+ {
304
+ "epoch": 3.25,
305
+ "learning_rate": 3.415120920403851e-05,
306
+ "loss": 0.5502,
307
+ "step": 14000
308
+ },
309
+ {
310
+ "epoch": 3.25,
311
+ "eval_bleu": 26.419,
312
+ "eval_gen_len": 18.6722,
313
+ "eval_loss": 1.3392120599746704,
314
+ "eval_runtime": 1080.7472,
315
+ "eval_samples_per_second": 15.949,
316
+ "eval_steps_per_second": 0.997,
317
+ "step": 14000
318
+ },
319
+ {
320
+ "epoch": 3.36,
321
+ "learning_rate": 3.356421695233623e-05,
322
+ "loss": 0.5541,
323
+ "step": 14500
324
+ },
325
+ {
326
+ "epoch": 3.48,
327
+ "learning_rate": 3.2977224700633954e-05,
328
+ "loss": 0.5577,
329
+ "step": 15000
330
+ },
331
+ {
332
+ "epoch": 3.48,
333
+ "eval_bleu": 26.1621,
334
+ "eval_gen_len": 18.7036,
335
+ "eval_loss": 1.320376992225647,
336
+ "eval_runtime": 1082.8765,
337
+ "eval_samples_per_second": 15.918,
338
+ "eval_steps_per_second": 0.995,
339
+ "step": 15000
340
+ },
341
+ {
342
+ "epoch": 3.48,
343
+ "step": 15000,
344
+ "total_flos": 1.04022228860928e+18,
345
+ "train_loss": 0.9628536214192709,
346
+ "train_runtime": 41969.1276,
347
+ "train_samples_per_second": 32.857,
348
+ "train_steps_per_second": 1.027
349
+ }
350
+ ],
351
+ "logging_steps": 500,
352
+ "max_steps": 43090,
353
+ "num_train_epochs": 10,
354
+ "save_steps": 1000,
355
+ "total_flos": 1.04022228860928e+18,
356
+ "trial_name": null,
357
+ "trial_params": null
358
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91607c7bfad43ad04ea3fed68b9ccfcd999071a12acc321f89b877d6c7150cbc
3
+ size 4728