Hugging Face's logo

yesj1234
/
mbart-mmt_mid2_ko-en

Text2Text Generation
Transformers
PyTorch
Korean
English
mbart
Generated from Trainer
Inference Endpoints
Model card Files Community
yesj1234 commited on
Commit
38816df
•
1 Parent(s): 2fbe2d5

Upload folder using huggingface_hub

Browse files
Files changed (33) hide show
  1. .gitattributes +2 -0
  2. README.md +83 -0
  3. added_tokens.json +59 -0
  4. all_results.json +22 -0
  5. checkpoint-22000/added_tokens.json +59 -0
  6. checkpoint-22000/config.json +59 -0
  7. checkpoint-22000/generation_config.json +12 -0
  8. checkpoint-22000/optimizer.pt +3 -0
  9. checkpoint-22000/pytorch_model.bin +3 -0
  10. checkpoint-22000/rng_state_0.pth +3 -0
  11. checkpoint-22000/rng_state_1.pth +3 -0
  12. checkpoint-22000/rng_state_2.pth +3 -0
  13. checkpoint-22000/rng_state_3.pth +3 -0
  14. checkpoint-22000/scheduler.pt +3 -0
  15. checkpoint-22000/sentencepiece.bpe.model +3 -0
  16. checkpoint-22000/special_tokens_map.json +63 -0
  17. checkpoint-22000/tokenizer.json +3 -0
  18. checkpoint-22000/tokenizer_config.json +528 -0
  19. checkpoint-22000/trainer_state.json +393 -0
  20. checkpoint-22000/training_args.bin +3 -0
  21. config.json +59 -0
  22. eval_results.json +10 -0
  23. generated_predictions.txt +0 -0
  24. generation_config.json +12 -0
  25. predict_results.json +9 -0
  26. pytorch_model.bin +3 -0
  27. sentencepiece.bpe.model +3 -0
  28. special_tokens_map.json +63 -0
  29. tokenizer.json +3 -0
  30. tokenizer_config.json +528 -0
  31. train_results.json +8 -0
  32. trainer_state.json +538 -0
  33. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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-22000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ 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_mid2
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_mid2
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: 1.3246
23
+ - Bleu: 22.9623
24
+ - Gen Len: 18.7197
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: cosine
54
+ - lr_scheduler_warmup_steps: 1000
55
+ - num_epochs: 40
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
60
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
61
+ | 1.5377 | 0.23 | 2000 | 1.6122 | 17.2009 | 18.7106 |
62
+ | 1.3891 | 0.46 | 4000 | 1.5059 | 19.3345 | 18.7688 |
63
+ | 1.2812 | 0.7 | 6000 | 1.4348 | 20.6032 | 18.9022 |
64
+ | 1.2374 | 0.93 | 8000 | 1.4035 | 21.2391 | 18.8434 |
65
+ | 1.1734 | 1.16 | 10000 | 1.4039 | 21.304 | 18.9964 |
66
+ | 1.1531 | 1.39 | 12000 | 1.3694 | 21.9087 | 18.8573 |
67
+ | 1.1158 | 1.62 | 14000 | 1.3574 | 22.004 | 18.5485 |
68
+ | 1.0941 | 1.86 | 16000 | 1.3457 | 21.9785 | 18.7119 |
69
+ | 0.9809 | 2.09 | 18000 | 1.3495 | 22.7983 | 18.8011 |
70
+ | 0.9834 | 2.32 | 20000 | 1.3429 | 22.5654 | 18.9416 |
71
+ | 0.9981 | 2.55 | 22000 | 1.3246 | 22.9493 | 18.7364 |
72
+ | 1.0074 | 2.78 | 24000 | 1.3539 | 22.3874 | 18.4428 |
73
+ | 0.9752 | 3.02 | 26000 | 1.3587 | 22.1907 | 18.8139 |
74
+ | 0.8858 | 3.25 | 28000 | 1.3457 | 22.82 | 18.8021 |
75
+ | 0.8895 | 3.48 | 30000 | 1.3603 | 22.1575 | 18.5638 |
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": 22.9623,
4
+ "eval_gen_len": 18.7197,
5
+ "eval_loss": 1.324600100517273,
6
+ "eval_runtime": 1142.3157,
7
+ "eval_samples": 17237,
8
+ "eval_samples_per_second": 15.09,
9
+ "eval_steps_per_second": 0.944,
10
+ "predict_bleu": 21.2781,
11
+ "predict_gen_len": 16.8303,
12
+ "predict_loss": 1.5452861785888672,
13
+ "predict_runtime": 1073.4319,
14
+ "predict_samples": 17237,
15
+ "predict_samples_per_second": 16.058,
16
+ "predict_steps_per_second": 1.004,
17
+ "train_loss": 1.1391656209309895,
18
+ "train_runtime": 38922.7808,
19
+ "train_samples": 137900,
20
+ "train_samples_per_second": 141.716,
21
+ "train_steps_per_second": 8.858
22
+ }
checkpoint-22000/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-22000/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-22000/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-22000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:175ac48d4373ed89679983ed799cceec9e97bd59f7f412595ea5dfc55053a03f
3
+ size 4887473903
checkpoint-22000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca9586f3cb9b524ab156afc1902175304725a37aea1ceb902310060466bd0049
3
+ size 2444694490
checkpoint-22000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7458e4ba8e7392cb26fc0a52846ad1a36c90859a1721bc5113df820794fc3418
3
+ size 15024
checkpoint-22000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73165c9d5e3f414a77ec50dac2ca3c491ea742b54aaebea61f617c86acca1e9f
3
+ size 15024
checkpoint-22000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32066ea8b89d77bc7b0944ef40e63a0d998650b77b17f8e16a85923957e399a0
3
+ size 15024
checkpoint-22000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:286addb5df8bbff75ba0b87293a59d9cbbb3b1f7399a9a8e2d200c1c0e915b4f
3
+ size 15024
checkpoint-22000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:854fa98c8fbff4acd3cd58f1b921eb1d3a0ce38afa26535888b15d6180b57197
3
+ size 1064
checkpoint-22000/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-22000/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-22000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3a71a6430f26d8667787032844b9efe0d820460f1eb2e56a96b5f171813bc1a
3
+ size 17109939
checkpoint-22000/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-22000/trainer_state.json ADDED
@@ -0,0 +1,393 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 22.9493,
3
+ "best_model_checkpoint": "./ko-en_mbartLarge_mid2/checkpoint-22000",
4
+ "epoch": 2.552500290056851,
5
+ "eval_steps": 2000,
6
+ "global_step": 22000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.06,
13
+ "learning_rate": 2.5e-05,
14
+ "loss": 1.9104,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.12,
19
+ "learning_rate": 5e-05,
20
+ "loss": 1.7744,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.17,
25
+ "learning_rate": 4.99997390013085e-05,
26
+ "loss": 1.6281,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.23,
31
+ "learning_rate": 4.9998956010683606e-05,
32
+ "loss": 1.5377,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.23,
37
+ "eval_bleu": 17.2009,
38
+ "eval_gen_len": 18.7106,
39
+ "eval_loss": 1.6122242212295532,
40
+ "eval_runtime": 1145.0919,
41
+ "eval_samples_per_second": 15.053,
42
+ "eval_steps_per_second": 0.941,
43
+ "step": 2000
44
+ },
45
+ {
46
+ "epoch": 0.29,
47
+ "learning_rate": 4.9997651044474085e-05,
48
+ "loss": 1.4666,
49
+ "step": 2500
50
+ },
51
+ {
52
+ "epoch": 0.35,
53
+ "learning_rate": 4.999582412992751e-05,
54
+ "loss": 1.4294,
55
+ "step": 3000
56
+ },
57
+ {
58
+ "epoch": 0.41,
59
+ "learning_rate": 4.999347530518964e-05,
60
+ "loss": 1.3956,
61
+ "step": 3500
62
+ },
63
+ {
64
+ "epoch": 0.46,
65
+ "learning_rate": 4.999060461930371e-05,
66
+ "loss": 1.3891,
67
+ "step": 4000
68
+ },
69
+ {
70
+ "epoch": 0.46,
71
+ "eval_bleu": 19.3345,
72
+ "eval_gen_len": 18.7688,
73
+ "eval_loss": 1.5059210062026978,
74
+ "eval_runtime": 1145.5496,
75
+ "eval_samples_per_second": 15.047,
76
+ "eval_steps_per_second": 0.941,
77
+ "step": 4000
78
+ },
79
+ {
80
+ "epoch": 0.52,
81
+ "learning_rate": 4.998721213220933e-05,
82
+ "loss": 1.3651,
83
+ "step": 4500
84
+ },
85
+ {
86
+ "epoch": 0.58,
87
+ "learning_rate": 4.9983297914741276e-05,
88
+ "loss": 1.3337,
89
+ "step": 5000
90
+ },
91
+ {
92
+ "epoch": 0.64,
93
+ "learning_rate": 4.9978862048628e-05,
94
+ "loss": 1.3017,
95
+ "step": 5500
96
+ },
97
+ {
98
+ "epoch": 0.7,
99
+ "learning_rate": 4.997390462648993e-05,
100
+ "loss": 1.2812,
101
+ "step": 6000
102
+ },
103
+ {
104
+ "epoch": 0.7,
105
+ "eval_bleu": 20.6032,
106
+ "eval_gen_len": 18.9022,
107
+ "eval_loss": 1.4347867965698242,
108
+ "eval_runtime": 1144.9766,
109
+ "eval_samples_per_second": 15.054,
110
+ "eval_steps_per_second": 0.942,
111
+ "step": 6000
112
+ },
113
+ {
114
+ "epoch": 0.75,
115
+ "learning_rate": 4.996842575183751e-05,
116
+ "loss": 1.2664,
117
+ "step": 6500
118
+ },
119
+ {
120
+ "epoch": 0.81,
121
+ "learning_rate": 4.996242553906908e-05,
122
+ "loss": 1.2599,
123
+ "step": 7000
124
+ },
125
+ {
126
+ "epoch": 0.87,
127
+ "learning_rate": 4.9955904113468444e-05,
128
+ "loss": 1.2513,
129
+ "step": 7500
130
+ },
131
+ {
132
+ "epoch": 0.93,
133
+ "learning_rate": 4.994886161120229e-05,
134
+ "loss": 1.2374,
135
+ "step": 8000
136
+ },
137
+ {
138
+ "epoch": 0.93,
139
+ "eval_bleu": 21.2391,
140
+ "eval_gen_len": 18.8434,
141
+ "eval_loss": 1.4034597873687744,
142
+ "eval_runtime": 1156.93,
143
+ "eval_samples_per_second": 14.899,
144
+ "eval_steps_per_second": 0.932,
145
+ "step": 8000
146
+ },
147
+ {
148
+ "epoch": 0.99,
149
+ "learning_rate": 4.994129817931734e-05,
150
+ "loss": 1.2306,
151
+ "step": 8500
152
+ },
153
+ {
154
+ "epoch": 1.04,
155
+ "learning_rate": 4.993321397573724e-05,
156
+ "loss": 1.1716,
157
+ "step": 9000
158
+ },
159
+ {
160
+ "epoch": 1.1,
161
+ "learning_rate": 4.9924609169259325e-05,
162
+ "loss": 1.1718,
163
+ "step": 9500
164
+ },
165
+ {
166
+ "epoch": 1.16,
167
+ "learning_rate": 4.991548393955104e-05,
168
+ "loss": 1.1734,
169
+ "step": 10000
170
+ },
171
+ {
172
+ "epoch": 1.16,
173
+ "eval_bleu": 21.304,
174
+ "eval_gen_len": 18.9964,
175
+ "eval_loss": 1.4039467573165894,
176
+ "eval_runtime": 1152.4015,
177
+ "eval_samples_per_second": 14.957,
178
+ "eval_steps_per_second": 0.935,
179
+ "step": 10000
180
+ },
181
+ {
182
+ "epoch": 1.22,
183
+ "learning_rate": 4.990583847714626e-05,
184
+ "loss": 1.1702,
185
+ "step": 10500
186
+ },
187
+ {
188
+ "epoch": 1.28,
189
+ "learning_rate": 4.9895672983441194e-05,
190
+ "loss": 1.1688,
191
+ "step": 11000
192
+ },
193
+ {
194
+ "epoch": 1.33,
195
+ "learning_rate": 4.988498767069031e-05,
196
+ "loss": 1.1581,
197
+ "step": 11500
198
+ },
199
+ {
200
+ "epoch": 1.39,
201
+ "learning_rate": 4.98737827620018e-05,
202
+ "loss": 1.1531,
203
+ "step": 12000
204
+ },
205
+ {
206
+ "epoch": 1.39,
207
+ "eval_bleu": 21.9087,
208
+ "eval_gen_len": 18.8573,
209
+ "eval_loss": 1.3693655729293823,
210
+ "eval_runtime": 1145.8261,
211
+ "eval_samples_per_second": 15.043,
212
+ "eval_steps_per_second": 0.941,
213
+ "step": 12000
214
+ },
215
+ {
216
+ "epoch": 1.45,
217
+ "learning_rate": 4.9862058491333e-05,
218
+ "loss": 1.1184,
219
+ "step": 12500
220
+ },
221
+ {
222
+ "epoch": 1.51,
223
+ "learning_rate": 4.984981510348545e-05,
224
+ "loss": 1.1171,
225
+ "step": 13000
226
+ },
227
+ {
228
+ "epoch": 1.57,
229
+ "learning_rate": 4.9837052854099804e-05,
230
+ "loss": 1.1149,
231
+ "step": 13500
232
+ },
233
+ {
234
+ "epoch": 1.62,
235
+ "learning_rate": 4.9823772009650496e-05,
236
+ "loss": 1.1158,
237
+ "step": 14000
238
+ },
239
+ {
240
+ "epoch": 1.62,
241
+ "eval_bleu": 22.004,
242
+ "eval_gen_len": 18.5485,
243
+ "eval_loss": 1.357371211051941,
244
+ "eval_runtime": 1130.4228,
245
+ "eval_samples_per_second": 15.248,
246
+ "eval_steps_per_second": 0.954,
247
+ "step": 14000
248
+ },
249
+ {
250
+ "epoch": 1.68,
251
+ "learning_rate": 4.980997284744017e-05,
252
+ "loss": 1.1163,
253
+ "step": 14500
254
+ },
255
+ {
256
+ "epoch": 1.74,
257
+ "learning_rate": 4.979565565559388e-05,
258
+ "loss": 1.1147,
259
+ "step": 15000
260
+ },
261
+ {
262
+ "epoch": 1.8,
263
+ "learning_rate": 4.97808207330531e-05,
264
+ "loss": 1.0988,
265
+ "step": 15500
266
+ },
267
+ {
268
+ "epoch": 1.86,
269
+ "learning_rate": 4.9765468389569455e-05,
270
+ "loss": 1.0941,
271
+ "step": 16000
272
+ },
273
+ {
274
+ "epoch": 1.86,
275
+ "eval_bleu": 21.9785,
276
+ "eval_gen_len": 18.7119,
277
+ "eval_loss": 1.3456674814224243,
278
+ "eval_runtime": 1148.5287,
279
+ "eval_samples_per_second": 15.008,
280
+ "eval_steps_per_second": 0.939,
281
+ "step": 16000
282
+ },
283
+ {
284
+ "epoch": 1.91,
285
+ "learning_rate": 4.9749598945698276e-05,
286
+ "loss": 1.1112,
287
+ "step": 16500
288
+ },
289
+ {
290
+ "epoch": 1.97,
291
+ "learning_rate": 4.973321273279189e-05,
292
+ "loss": 1.1,
293
+ "step": 17000
294
+ },
295
+ {
296
+ "epoch": 2.03,
297
+ "learning_rate": 4.97163100929927e-05,
298
+ "loss": 1.0405,
299
+ "step": 17500
300
+ },
301
+ {
302
+ "epoch": 2.09,
303
+ "learning_rate": 4.9698891379226064e-05,
304
+ "loss": 0.9809,
305
+ "step": 18000
306
+ },
307
+ {
308
+ "epoch": 2.09,
309
+ "eval_bleu": 22.7983,
310
+ "eval_gen_len": 18.8011,
311
+ "eval_loss": 1.3494887351989746,
312
+ "eval_runtime": 1139.125,
313
+ "eval_samples_per_second": 15.132,
314
+ "eval_steps_per_second": 0.946,
315
+ "step": 18000
316
+ },
317
+ {
318
+ "epoch": 2.15,
319
+ "learning_rate": 4.9680956955192896e-05,
320
+ "loss": 0.9747,
321
+ "step": 18500
322
+ },
323
+ {
324
+ "epoch": 2.2,
325
+ "learning_rate": 4.966250719536209e-05,
326
+ "loss": 0.9933,
327
+ "step": 19000
328
+ },
329
+ {
330
+ "epoch": 2.26,
331
+ "learning_rate": 4.964354248496271e-05,
332
+ "loss": 0.9972,
333
+ "step": 19500
334
+ },
335
+ {
336
+ "epoch": 2.32,
337
+ "learning_rate": 4.962406321997592e-05,
338
+ "loss": 0.9834,
339
+ "step": 20000
340
+ },
341
+ {
342
+ "epoch": 2.32,
343
+ "eval_bleu": 22.5654,
344
+ "eval_gen_len": 18.9416,
345
+ "eval_loss": 1.3429056406021118,
346
+ "eval_runtime": 1149.8703,
347
+ "eval_samples_per_second": 14.99,
348
+ "eval_steps_per_second": 0.937,
349
+ "step": 20000
350
+ },
351
+ {
352
+ "epoch": 2.38,
353
+ "learning_rate": 4.960406980712672e-05,
354
+ "loss": 0.9855,
355
+ "step": 20500
356
+ },
357
+ {
358
+ "epoch": 2.44,
359
+ "learning_rate": 4.9583562663875496e-05,
360
+ "loss": 0.9939,
361
+ "step": 21000
362
+ },
363
+ {
364
+ "epoch": 2.49,
365
+ "learning_rate": 4.956254221840925e-05,
366
+ "loss": 0.985,
367
+ "step": 21500
368
+ },
369
+ {
370
+ "epoch": 2.55,
371
+ "learning_rate": 4.9541008909632674e-05,
372
+ "loss": 0.9981,
373
+ "step": 22000
374
+ },
375
+ {
376
+ "epoch": 2.55,
377
+ "eval_bleu": 22.9493,
378
+ "eval_gen_len": 18.7364,
379
+ "eval_loss": 1.324600100517273,
380
+ "eval_runtime": 1150.1819,
381
+ "eval_samples_per_second": 14.986,
382
+ "eval_steps_per_second": 0.937,
383
+ "step": 22000
384
+ }
385
+ ],
386
+ "logging_steps": 500,
387
+ "max_steps": 344760,
388
+ "num_train_epochs": 40,
389
+ "save_steps": 2000,
390
+ "total_flos": 7.629337002738975e+17,
391
+ "trial_name": null,
392
+ "trial_params": null
393
+ }
checkpoint-22000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a54dead05f063b9ad8e5ddbf2dd516b8f77c845284745a38ea36aba119e79c80
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": 22.9623,
4
+ "eval_gen_len": 18.7197,
5
+ "eval_loss": 1.324600100517273,
6
+ "eval_runtime": 1142.3157,
7
+ "eval_samples": 17237,
8
+ "eval_samples_per_second": 15.09,
9
+ "eval_steps_per_second": 0.944
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": 21.2781,
3
+ "predict_gen_len": 16.8303,
4
+ "predict_loss": 1.5452861785888672,
5
+ "predict_runtime": 1073.4319,
6
+ "predict_samples": 17237,
7
+ "predict_samples_per_second": 16.058,
8
+ "predict_steps_per_second": 1.004
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca9586f3cb9b524ab156afc1902175304725a37aea1ceb902310060466bd0049
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": 1.1391656209309895,
4
+ "train_runtime": 38922.7808,
5
+ "train_samples": 137900,
6
+ "train_samples_per_second": 141.716,
7
+ "train_steps_per_second": 8.858
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,538 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 22.9493,
3
+ "best_model_checkpoint": "./ko-en_mbartLarge_mid2/checkpoint-22000",
4
+ "epoch": 3.4806822137138878,
5
+ "eval_steps": 2000,
6
+ "global_step": 30000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.06,
13
+ "learning_rate": 2.5e-05,
14
+ "loss": 1.9104,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.12,
19
+ "learning_rate": 5e-05,
20
+ "loss": 1.7744,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.17,
25
+ "learning_rate": 4.99997390013085e-05,
26
+ "loss": 1.6281,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.23,
31
+ "learning_rate": 4.9998956010683606e-05,
32
+ "loss": 1.5377,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.23,
37
+ "eval_bleu": 17.2009,
38
+ "eval_gen_len": 18.7106,
39
+ "eval_loss": 1.6122242212295532,
40
+ "eval_runtime": 1145.0919,
41
+ "eval_samples_per_second": 15.053,
42
+ "eval_steps_per_second": 0.941,
43
+ "step": 2000
44
+ },
45
+ {
46
+ "epoch": 0.29,
47
+ "learning_rate": 4.9997651044474085e-05,
48
+ "loss": 1.4666,
49
+ "step": 2500
50
+ },
51
+ {
52
+ "epoch": 0.35,
53
+ "learning_rate": 4.999582412992751e-05,
54
+ "loss": 1.4294,
55
+ "step": 3000
56
+ },
57
+ {
58
+ "epoch": 0.41,
59
+ "learning_rate": 4.999347530518964e-05,
60
+ "loss": 1.3956,
61
+ "step": 3500
62
+ },
63
+ {
64
+ "epoch": 0.46,
65
+ "learning_rate": 4.999060461930371e-05,
66
+ "loss": 1.3891,
67
+ "step": 4000
68
+ },
69
+ {
70
+ "epoch": 0.46,
71
+ "eval_bleu": 19.3345,
72
+ "eval_gen_len": 18.7688,
73
+ "eval_loss": 1.5059210062026978,
74
+ "eval_runtime": 1145.5496,
75
+ "eval_samples_per_second": 15.047,
76
+ "eval_steps_per_second": 0.941,
77
+ "step": 4000
78
+ },
79
+ {
80
+ "epoch": 0.52,
81
+ "learning_rate": 4.998721213220933e-05,
82
+ "loss": 1.3651,
83
+ "step": 4500
84
+ },
85
+ {
86
+ "epoch": 0.58,
87
+ "learning_rate": 4.9983297914741276e-05,
88
+ "loss": 1.3337,
89
+ "step": 5000
90
+ },
91
+ {
92
+ "epoch": 0.64,
93
+ "learning_rate": 4.9978862048628e-05,
94
+ "loss": 1.3017,
95
+ "step": 5500
96
+ },
97
+ {
98
+ "epoch": 0.7,
99
+ "learning_rate": 4.997390462648993e-05,
100
+ "loss": 1.2812,
101
+ "step": 6000
102
+ },
103
+ {
104
+ "epoch": 0.7,
105
+ "eval_bleu": 20.6032,
106
+ "eval_gen_len": 18.9022,
107
+ "eval_loss": 1.4347867965698242,
108
+ "eval_runtime": 1144.9766,
109
+ "eval_samples_per_second": 15.054,
110
+ "eval_steps_per_second": 0.942,
111
+ "step": 6000
112
+ },
113
+ {
114
+ "epoch": 0.75,
115
+ "learning_rate": 4.996842575183751e-05,
116
+ "loss": 1.2664,
117
+ "step": 6500
118
+ },
119
+ {
120
+ "epoch": 0.81,
121
+ "learning_rate": 4.996242553906908e-05,
122
+ "loss": 1.2599,
123
+ "step": 7000
124
+ },
125
+ {
126
+ "epoch": 0.87,
127
+ "learning_rate": 4.9955904113468444e-05,
128
+ "loss": 1.2513,
129
+ "step": 7500
130
+ },
131
+ {
132
+ "epoch": 0.93,
133
+ "learning_rate": 4.994886161120229e-05,
134
+ "loss": 1.2374,
135
+ "step": 8000
136
+ },
137
+ {
138
+ "epoch": 0.93,
139
+ "eval_bleu": 21.2391,
140
+ "eval_gen_len": 18.8434,
141
+ "eval_loss": 1.4034597873687744,
142
+ "eval_runtime": 1156.93,
143
+ "eval_samples_per_second": 14.899,
144
+ "eval_steps_per_second": 0.932,
145
+ "step": 8000
146
+ },
147
+ {
148
+ "epoch": 0.99,
149
+ "learning_rate": 4.994129817931734e-05,
150
+ "loss": 1.2306,
151
+ "step": 8500
152
+ },
153
+ {
154
+ "epoch": 1.04,
155
+ "learning_rate": 4.993321397573724e-05,
156
+ "loss": 1.1716,
157
+ "step": 9000
158
+ },
159
+ {
160
+ "epoch": 1.1,
161
+ "learning_rate": 4.9924609169259325e-05,
162
+ "loss": 1.1718,
163
+ "step": 9500
164
+ },
165
+ {
166
+ "epoch": 1.16,
167
+ "learning_rate": 4.991548393955104e-05,
168
+ "loss": 1.1734,
169
+ "step": 10000
170
+ },
171
+ {
172
+ "epoch": 1.16,
173
+ "eval_bleu": 21.304,
174
+ "eval_gen_len": 18.9964,
175
+ "eval_loss": 1.4039467573165894,
176
+ "eval_runtime": 1152.4015,
177
+ "eval_samples_per_second": 14.957,
178
+ "eval_steps_per_second": 0.935,
179
+ "step": 10000
180
+ },
181
+ {
182
+ "epoch": 1.22,
183
+ "learning_rate": 4.990583847714626e-05,
184
+ "loss": 1.1702,
185
+ "step": 10500
186
+ },
187
+ {
188
+ "epoch": 1.28,
189
+ "learning_rate": 4.9895672983441194e-05,
190
+ "loss": 1.1688,
191
+ "step": 11000
192
+ },
193
+ {
194
+ "epoch": 1.33,
195
+ "learning_rate": 4.988498767069031e-05,
196
+ "loss": 1.1581,
197
+ "step": 11500
198
+ },
199
+ {
200
+ "epoch": 1.39,
201
+ "learning_rate": 4.98737827620018e-05,
202
+ "loss": 1.1531,
203
+ "step": 12000
204
+ },
205
+ {
206
+ "epoch": 1.39,
207
+ "eval_bleu": 21.9087,
208
+ "eval_gen_len": 18.8573,
209
+ "eval_loss": 1.3693655729293823,
210
+ "eval_runtime": 1145.8261,
211
+ "eval_samples_per_second": 15.043,
212
+ "eval_steps_per_second": 0.941,
213
+ "step": 12000
214
+ },
215
+ {
216
+ "epoch": 1.45,
217
+ "learning_rate": 4.9862058491333e-05,
218
+ "loss": 1.1184,
219
+ "step": 12500
220
+ },
221
+ {
222
+ "epoch": 1.51,
223
+ "learning_rate": 4.984981510348545e-05,
224
+ "loss": 1.1171,
225
+ "step": 13000
226
+ },
227
+ {
228
+ "epoch": 1.57,
229
+ "learning_rate": 4.9837052854099804e-05,
230
+ "loss": 1.1149,
231
+ "step": 13500
232
+ },
233
+ {
234
+ "epoch": 1.62,
235
+ "learning_rate": 4.9823772009650496e-05,
236
+ "loss": 1.1158,
237
+ "step": 14000
238
+ },
239
+ {
240
+ "epoch": 1.62,
241
+ "eval_bleu": 22.004,
242
+ "eval_gen_len": 18.5485,
243
+ "eval_loss": 1.357371211051941,
244
+ "eval_runtime": 1130.4228,
245
+ "eval_samples_per_second": 15.248,
246
+ "eval_steps_per_second": 0.954,
247
+ "step": 14000
248
+ },
249
+ {
250
+ "epoch": 1.68,
251
+ "learning_rate": 4.980997284744017e-05,
252
+ "loss": 1.1163,
253
+ "step": 14500
254
+ },
255
+ {
256
+ "epoch": 1.74,
257
+ "learning_rate": 4.979565565559388e-05,
258
+ "loss": 1.1147,
259
+ "step": 15000
260
+ },
261
+ {
262
+ "epoch": 1.8,
263
+ "learning_rate": 4.97808207330531e-05,
264
+ "loss": 1.0988,
265
+ "step": 15500
266
+ },
267
+ {
268
+ "epoch": 1.86,
269
+ "learning_rate": 4.9765468389569455e-05,
270
+ "loss": 1.0941,
271
+ "step": 16000
272
+ },
273
+ {
274
+ "epoch": 1.86,
275
+ "eval_bleu": 21.9785,
276
+ "eval_gen_len": 18.7119,
277
+ "eval_loss": 1.3456674814224243,
278
+ "eval_runtime": 1148.5287,
279
+ "eval_samples_per_second": 15.008,
280
+ "eval_steps_per_second": 0.939,
281
+ "step": 16000
282
+ },
283
+ {
284
+ "epoch": 1.91,
285
+ "learning_rate": 4.9749598945698276e-05,
286
+ "loss": 1.1112,
287
+ "step": 16500
288
+ },
289
+ {
290
+ "epoch": 1.97,
291
+ "learning_rate": 4.973321273279189e-05,
292
+ "loss": 1.1,
293
+ "step": 17000
294
+ },
295
+ {
296
+ "epoch": 2.03,
297
+ "learning_rate": 4.97163100929927e-05,
298
+ "loss": 1.0405,
299
+ "step": 17500
300
+ },
301
+ {
302
+ "epoch": 2.09,
303
+ "learning_rate": 4.9698891379226064e-05,
304
+ "loss": 0.9809,
305
+ "step": 18000
306
+ },
307
+ {
308
+ "epoch": 2.09,
309
+ "eval_bleu": 22.7983,
310
+ "eval_gen_len": 18.8011,
311
+ "eval_loss": 1.3494887351989746,
312
+ "eval_runtime": 1139.125,
313
+ "eval_samples_per_second": 15.132,
314
+ "eval_steps_per_second": 0.946,
315
+ "step": 18000
316
+ },
317
+ {
318
+ "epoch": 2.15,
319
+ "learning_rate": 4.9680956955192896e-05,
320
+ "loss": 0.9747,
321
+ "step": 18500
322
+ },
323
+ {
324
+ "epoch": 2.2,
325
+ "learning_rate": 4.966250719536209e-05,
326
+ "loss": 0.9933,
327
+ "step": 19000
328
+ },
329
+ {
330
+ "epoch": 2.26,
331
+ "learning_rate": 4.964354248496271e-05,
332
+ "loss": 0.9972,
333
+ "step": 19500
334
+ },
335
+ {
336
+ "epoch": 2.32,
337
+ "learning_rate": 4.962406321997592e-05,
338
+ "loss": 0.9834,
339
+ "step": 20000
340
+ },
341
+ {
342
+ "epoch": 2.32,
343
+ "eval_bleu": 22.5654,
344
+ "eval_gen_len": 18.9416,
345
+ "eval_loss": 1.3429056406021118,
346
+ "eval_runtime": 1149.8703,
347
+ "eval_samples_per_second": 14.99,
348
+ "eval_steps_per_second": 0.937,
349
+ "step": 20000
350
+ },
351
+ {
352
+ "epoch": 2.38,
353
+ "learning_rate": 4.960406980712672e-05,
354
+ "loss": 0.9855,
355
+ "step": 20500
356
+ },
357
+ {
358
+ "epoch": 2.44,
359
+ "learning_rate": 4.9583562663875496e-05,
360
+ "loss": 0.9939,
361
+ "step": 21000
362
+ },
363
+ {
364
+ "epoch": 2.49,
365
+ "learning_rate": 4.956254221840925e-05,
366
+ "loss": 0.985,
367
+ "step": 21500
368
+ },
369
+ {
370
+ "epoch": 2.55,
371
+ "learning_rate": 4.9541008909632674e-05,
372
+ "loss": 0.9981,
373
+ "step": 22000
374
+ },
375
+ {
376
+ "epoch": 2.55,
377
+ "eval_bleu": 22.9493,
378
+ "eval_gen_len": 18.7364,
379
+ "eval_loss": 1.324600100517273,
380
+ "eval_runtime": 1150.1819,
381
+ "eval_samples_per_second": 14.986,
382
+ "eval_steps_per_second": 0.937,
383
+ "step": 22000
384
+ },
385
+ {
386
+ "epoch": 2.61,
387
+ "learning_rate": 4.951896318715901e-05,
388
+ "loss": 0.995,
389
+ "step": 22500
390
+ },
391
+ {
392
+ "epoch": 2.67,
393
+ "learning_rate": 4.949640551130063e-05,
394
+ "loss": 1.009,
395
+ "step": 23000
396
+ },
397
+ {
398
+ "epoch": 2.73,
399
+ "learning_rate": 4.947333635305944e-05,
400
+ "loss": 1.0026,
401
+ "step": 23500
402
+ },
403
+ {
404
+ "epoch": 2.78,
405
+ "learning_rate": 4.9449756194117056e-05,
406
+ "loss": 1.0074,
407
+ "step": 24000
408
+ },
409
+ {
410
+ "epoch": 2.78,
411
+ "eval_bleu": 22.3874,
412
+ "eval_gen_len": 18.4428,
413
+ "eval_loss": 1.35391366481781,
414
+ "eval_runtime": 1139.9064,
415
+ "eval_samples_per_second": 15.121,
416
+ "eval_steps_per_second": 0.946,
417
+ "step": 24000
418
+ },
419
+ {
420
+ "epoch": 2.84,
421
+ "learning_rate": 4.942566552682473e-05,
422
+ "loss": 1.0106,
423
+ "step": 24500
424
+ },
425
+ {
426
+ "epoch": 2.9,
427
+ "learning_rate": 4.940106485419307e-05,
428
+ "loss": 1.0039,
429
+ "step": 25000
430
+ },
431
+ {
432
+ "epoch": 2.96,
433
+ "learning_rate": 4.937595468988155e-05,
434
+ "loss": 0.9942,
435
+ "step": 25500
436
+ },
437
+ {
438
+ "epoch": 3.02,
439
+ "learning_rate": 4.935033555818776e-05,
440
+ "loss": 0.9752,
441
+ "step": 26000
442
+ },
443
+ {
444
+ "epoch": 3.02,
445
+ "eval_bleu": 22.1907,
446
+ "eval_gen_len": 18.8139,
447
+ "eval_loss": 1.3586821556091309,
448
+ "eval_runtime": 1145.6051,
449
+ "eval_samples_per_second": 15.046,
450
+ "eval_steps_per_second": 0.941,
451
+ "step": 26000
452
+ },
453
+ {
454
+ "epoch": 3.07,
455
+ "learning_rate": 4.932420799403651e-05,
456
+ "loss": 0.8804,
457
+ "step": 26500
458
+ },
459
+ {
460
+ "epoch": 3.13,
461
+ "learning_rate": 4.929757254296859e-05,
462
+ "loss": 0.8868,
463
+ "step": 27000
464
+ },
465
+ {
466
+ "epoch": 3.19,
467
+ "learning_rate": 4.9270429761129415e-05,
468
+ "loss": 0.8998,
469
+ "step": 27500
470
+ },
471
+ {
472
+ "epoch": 3.25,
473
+ "learning_rate": 4.924278021525745e-05,
474
+ "loss": 0.8858,
475
+ "step": 28000
476
+ },
477
+ {
478
+ "epoch": 3.25,
479
+ "eval_bleu": 22.82,
480
+ "eval_gen_len": 18.8021,
481
+ "eval_loss": 1.345699667930603,
482
+ "eval_runtime": 1148.7327,
483
+ "eval_samples_per_second": 15.005,
484
+ "eval_steps_per_second": 0.938,
485
+ "step": 28000
486
+ },
487
+ {
488
+ "epoch": 3.31,
489
+ "learning_rate": 4.921462448267232e-05,
490
+ "loss": 0.8772,
491
+ "step": 28500
492
+ },
493
+ {
494
+ "epoch": 3.36,
495
+ "learning_rate": 4.918596315126276e-05,
496
+ "loss": 0.8855,
497
+ "step": 29000
498
+ },
499
+ {
500
+ "epoch": 3.42,
501
+ "learning_rate": 4.9156796819474384e-05,
502
+ "loss": 0.8879,
503
+ "step": 29500
504
+ },
505
+ {
506
+ "epoch": 3.48,
507
+ "learning_rate": 4.912712609629714e-05,
508
+ "loss": 0.8895,
509
+ "step": 30000
510
+ },
511
+ {
512
+ "epoch": 3.48,
513
+ "eval_bleu": 22.1575,
514
+ "eval_gen_len": 18.5638,
515
+ "eval_loss": 1.3602744340896606,
516
+ "eval_runtime": 1137.9681,
517
+ "eval_samples_per_second": 15.147,
518
+ "eval_steps_per_second": 0.947,
519
+ "step": 30000
520
+ },
521
+ {
522
+ "epoch": 3.48,
523
+ "step": 30000,
524
+ "total_flos": 1.0403263105697055e+18,
525
+ "train_loss": 1.1391656209309895,
526
+ "train_runtime": 38922.7808,
527
+ "train_samples_per_second": 141.716,
528
+ "train_steps_per_second": 8.858
529
+ }
530
+ ],
531
+ "logging_steps": 500,
532
+ "max_steps": 344760,
533
+ "num_train_epochs": 40,
534
+ "save_steps": 2000,
535
+ "total_flos": 1.0403263105697055e+18,
536
+ "trial_name": null,
537
+ "trial_params": null
538
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a54dead05f063b9ad8e5ddbf2dd516b8f77c845284745a38ea36aba119e79c80
3
+ size 4728