yesj1234 commited on
Commit
6ab071f
1 Parent(s): 2109ee7

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +4 -0
  2. README.md +75 -0
  3. all_results.json +22 -0
  4. checkpoint-32000/config.json +59 -0
  5. checkpoint-32000/generation_config.json +12 -0
  6. checkpoint-32000/optimizer.pt +3 -0
  7. checkpoint-32000/pytorch_model.bin +3 -0
  8. checkpoint-32000/rng_state_0.pth +3 -0
  9. checkpoint-32000/rng_state_1.pth +3 -0
  10. checkpoint-32000/rng_state_2.pth +3 -0
  11. checkpoint-32000/rng_state_3.pth +3 -0
  12. checkpoint-32000/scheduler.pt +3 -0
  13. checkpoint-32000/sentencepiece.bpe.model +3 -0
  14. checkpoint-32000/special_tokens_map.json +69 -0
  15. checkpoint-32000/tokenizer.json +3 -0
  16. checkpoint-32000/tokenizer_config.json +528 -0
  17. checkpoint-32000/trainer_state.json +443 -0
  18. checkpoint-32000/training_args.bin +3 -0
  19. checkpoint-56000/config.json +59 -0
  20. checkpoint-56000/generation_config.json +12 -0
  21. checkpoint-56000/optimizer.pt +3 -0
  22. checkpoint-56000/pytorch_model.bin +3 -0
  23. checkpoint-56000/rng_state_0.pth +3 -0
  24. checkpoint-56000/rng_state_1.pth +3 -0
  25. checkpoint-56000/rng_state_2.pth +3 -0
  26. checkpoint-56000/rng_state_3.pth +3 -0
  27. checkpoint-56000/scheduler.pt +3 -0
  28. checkpoint-56000/sentencepiece.bpe.model +3 -0
  29. checkpoint-56000/special_tokens_map.json +69 -0
  30. checkpoint-56000/tokenizer.json +3 -0
  31. checkpoint-56000/tokenizer_config.json +528 -0
  32. checkpoint-56000/trainer_state.json +761 -0
  33. checkpoint-56000/training_args.bin +3 -0
  34. checkpoint-64000/config.json +59 -0
  35. checkpoint-64000/generation_config.json +12 -0
  36. checkpoint-64000/optimizer.pt +3 -0
  37. checkpoint-64000/pytorch_model.bin +3 -0
  38. checkpoint-64000/rng_state_0.pth +3 -0
  39. checkpoint-64000/rng_state_1.pth +3 -0
  40. checkpoint-64000/rng_state_2.pth +3 -0
  41. checkpoint-64000/rng_state_3.pth +3 -0
  42. checkpoint-64000/scheduler.pt +3 -0
  43. checkpoint-64000/sentencepiece.bpe.model +3 -0
  44. checkpoint-64000/special_tokens_map.json +69 -0
  45. checkpoint-64000/tokenizer.json +3 -0
  46. checkpoint-64000/tokenizer_config.json +528 -0
  47. checkpoint-64000/trainer_state.json +867 -0
  48. checkpoint-64000/training_args.bin +3 -0
  49. config.json +59 -0
  50. eval_results.json +10 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ 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-32000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-56000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-64000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ko
4
+ - ja
5
+ base_model: facebook/mbart-large-50-many-to-many-mmt
6
+ tags:
7
+ - generated_from_trainer
8
+ metrics:
9
+ - bleu
10
+ model-index:
11
+ - name: koja_mbartLarge_55p_run1
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
+ # koja_mbartLarge_55p_run1
19
+
20
+ This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on an unknown dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.9008
23
+ - Bleu: 8.9861
24
+ - Gen Len: 17.9149
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
+ - num_epochs: 10
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
59
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
60
+ | 1.0254 | 0.48 | 8000 | 1.0065 | 7.1252 | 18.5403 |
61
+ | 0.9374 | 0.97 | 16000 | 0.9200 | 8.2047 | 18.2091 |
62
+ | 0.7429 | 1.45 | 24000 | 0.9086 | 8.4622 | 17.9606 |
63
+ | 0.7039 | 1.93 | 32000 | 0.9008 | 8.9198 | 17.8841 |
64
+ | 0.5616 | 2.42 | 40000 | 0.9210 | 8.7938 | 17.78 |
65
+ | 0.5355 | 2.9 | 48000 | 0.9400 | 8.6506 | 17.9146 |
66
+ | 0.4194 | 3.38 | 56000 | 1.0054 | 8.4235 | 17.6759 |
67
+ | 0.3852 | 3.86 | 64000 | 1.0154 | 8.5886 | 17.7885 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - Transformers 4.34.1
73
+ - Pytorch 2.1.0+cu121
74
+ - Datasets 2.14.6
75
+ - Tokenizers 0.14.1
all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.86,
3
+ "eval_bleu": 8.9861,
4
+ "eval_gen_len": 17.9149,
5
+ "eval_loss": 0.9008079171180725,
6
+ "eval_runtime": 1886.4166,
7
+ "eval_samples": 33118,
8
+ "eval_samples_per_second": 17.556,
9
+ "eval_steps_per_second": 1.097,
10
+ "predict_bleu": 8.4331,
11
+ "predict_gen_len": 17.8764,
12
+ "predict_loss": 0.8994398713111877,
13
+ "predict_runtime": 1874.5901,
14
+ "predict_samples": 33119,
15
+ "predict_samples_per_second": 17.667,
16
+ "predict_steps_per_second": 1.104,
17
+ "train_loss": 0.7053718340396881,
18
+ "train_runtime": 90544.7613,
19
+ "train_samples": 264951,
20
+ "train_samples_per_second": 29.262,
21
+ "train_steps_per_second": 1.829
22
+ }
checkpoint-32000/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": true,
8
+ "architectures": [
9
+ "MBartForConditionalGeneration"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 1024,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 4096,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 12,
20
+ "decoder_start_token_id": 2,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 2,
28
+ "forced_bos_token_id": 250012,
29
+ "forced_eos_token_id": 2,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "max_length": 200,
44
+ "max_position_embeddings": 1024,
45
+ "model_type": "mbart",
46
+ "normalize_before": true,
47
+ "normalize_embedding": true,
48
+ "num_beams": 5,
49
+ "num_hidden_layers": 12,
50
+ "output_past": true,
51
+ "pad_token_id": 1,
52
+ "scale_embedding": true,
53
+ "static_position_embeddings": false,
54
+ "tokenizer_class": "MBart50Tokenizer",
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.34.1",
57
+ "use_cache": true,
58
+ "vocab_size": 250054
59
+ }
checkpoint-32000/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "forced_bos_token_id": 250012,
7
+ "forced_eos_token_id": 2,
8
+ "max_length": 200,
9
+ "num_beams": 5,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.34.1"
12
+ }
checkpoint-32000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bc37e31c85752658da38e35b4760aa76f87d13e284fa0eedf65fd8d124a6867
3
+ size 4887473903
checkpoint-32000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2b3273e3a63fa37a46f15d97f4fac2f92a73af23505051155f792bd1b9da2e0
3
+ size 2444694490
checkpoint-32000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e4356e9fa1b2e179d4e4a31f616d16f8bb53ac7a814437f0d27a275745b7ac0
3
+ size 15024
checkpoint-32000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67f9c0608d49cfafb905479647bb872b9af9665024bfe1ff6748bcff2986ceb1
3
+ size 15024
checkpoint-32000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d361df7da358983eb63d358012d8fe4b037166ecae9680cebc75c05557e2abd9
3
+ size 15024
checkpoint-32000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30b3b055ad75a01b5c037786d8024b7c11d8ebdd8ebcb5c5c0a66cb5c7a7f42f
3
+ size 15024
checkpoint-32000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aed56fb4d961407e21110ec0a6d47975e854fab7c8e97fca0537318b2a4916ce
3
+ size 1064
checkpoint-32000/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-32000/special_tokens_map.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN",
28
+ "af_ZA",
29
+ "az_AZ",
30
+ "bn_IN",
31
+ "fa_IR",
32
+ "he_IL",
33
+ "hr_HR",
34
+ "id_ID",
35
+ "ka_GE",
36
+ "km_KH",
37
+ "mk_MK",
38
+ "ml_IN",
39
+ "mn_MN",
40
+ "mr_IN",
41
+ "pl_PL",
42
+ "ps_AF",
43
+ "pt_XX",
44
+ "sv_SE",
45
+ "sw_KE",
46
+ "ta_IN",
47
+ "te_IN",
48
+ "th_TH",
49
+ "tl_XX",
50
+ "uk_UA",
51
+ "ur_PK",
52
+ "xh_ZA",
53
+ "gl_ES",
54
+ "sl_SI"
55
+ ],
56
+ "bos_token": "<s>",
57
+ "cls_token": "<s>",
58
+ "eos_token": "</s>",
59
+ "mask_token": {
60
+ "content": "<mask>",
61
+ "lstrip": true,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ "pad_token": "<pad>",
67
+ "sep_token": "</s>",
68
+ "unk_token": "<unk>"
69
+ }
checkpoint-32000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fc2a9a463953c664738ef8571ed97361b8de258b2aca93c0214a89676a73379
3
+ size 17110043
checkpoint-32000/tokenizer_config.json ADDED
@@ -0,0 +1,528 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "ar_AR",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "250002": {
44
+ "content": "cs_CZ",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "250003": {
52
+ "content": "de_DE",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "250004": {
60
+ "content": "en_XX",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "250005": {
68
+ "content": "es_XX",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "250006": {
76
+ "content": "et_EE",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "250007": {
84
+ "content": "fi_FI",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "250008": {
92
+ "content": "fr_XX",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "250009": {
100
+ "content": "gu_IN",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "250010": {
108
+ "content": "hi_IN",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "250011": {
116
+ "content": "it_IT",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "250012": {
124
+ "content": "ja_XX",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "250013": {
132
+ "content": "kk_KZ",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "250014": {
140
+ "content": "ko_KR",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "250015": {
148
+ "content": "lt_LT",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "250016": {
156
+ "content": "lv_LV",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "250017": {
164
+ "content": "my_MM",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "250018": {
172
+ "content": "ne_NP",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "250019": {
180
+ "content": "nl_XX",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "250020": {
188
+ "content": "ro_RO",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "250021": {
196
+ "content": "ru_RU",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "250022": {
204
+ "content": "si_LK",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "250023": {
212
+ "content": "tr_TR",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "250024": {
220
+ "content": "vi_VN",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "250025": {
228
+ "content": "zh_CN",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "250026": {
236
+ "content": "af_ZA",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "250027": {
244
+ "content": "az_AZ",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "250028": {
252
+ "content": "bn_IN",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "250029": {
260
+ "content": "fa_IR",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "250030": {
268
+ "content": "he_IL",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "250031": {
276
+ "content": "hr_HR",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "250032": {
284
+ "content": "id_ID",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "250033": {
292
+ "content": "ka_GE",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "250034": {
300
+ "content": "km_KH",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "250035": {
308
+ "content": "mk_MK",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "250036": {
316
+ "content": "ml_IN",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "250037": {
324
+ "content": "mn_MN",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "250038": {
332
+ "content": "mr_IN",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "250039": {
340
+ "content": "pl_PL",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "250040": {
348
+ "content": "ps_AF",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "250041": {
356
+ "content": "pt_XX",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "250042": {
364
+ "content": "sv_SE",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "250043": {
372
+ "content": "sw_KE",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "250044": {
380
+ "content": "ta_IN",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "250045": {
388
+ "content": "te_IN",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "250046": {
396
+ "content": "th_TH",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "250047": {
404
+ "content": "tl_XX",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "250048": {
412
+ "content": "uk_UA",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "250049": {
420
+ "content": "ur_PK",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "250050": {
428
+ "content": "xh_ZA",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "250051": {
436
+ "content": "gl_ES",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "250052": {
444
+ "content": "sl_SI",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "250053": {
452
+ "content": "<mask>",
453
+ "lstrip": true,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ }
459
+ },
460
+ "additional_special_tokens": [
461
+ "ar_AR",
462
+ "cs_CZ",
463
+ "de_DE",
464
+ "en_XX",
465
+ "es_XX",
466
+ "et_EE",
467
+ "fi_FI",
468
+ "fr_XX",
469
+ "gu_IN",
470
+ "hi_IN",
471
+ "it_IT",
472
+ "ja_XX",
473
+ "kk_KZ",
474
+ "ko_KR",
475
+ "lt_LT",
476
+ "lv_LV",
477
+ "my_MM",
478
+ "ne_NP",
479
+ "nl_XX",
480
+ "ro_RO",
481
+ "ru_RU",
482
+ "si_LK",
483
+ "tr_TR",
484
+ "vi_VN",
485
+ "zh_CN",
486
+ "af_ZA",
487
+ "az_AZ",
488
+ "bn_IN",
489
+ "fa_IR",
490
+ "he_IL",
491
+ "hr_HR",
492
+ "id_ID",
493
+ "ka_GE",
494
+ "km_KH",
495
+ "mk_MK",
496
+ "ml_IN",
497
+ "mn_MN",
498
+ "mr_IN",
499
+ "pl_PL",
500
+ "ps_AF",
501
+ "pt_XX",
502
+ "sv_SE",
503
+ "sw_KE",
504
+ "ta_IN",
505
+ "te_IN",
506
+ "th_TH",
507
+ "tl_XX",
508
+ "uk_UA",
509
+ "ur_PK",
510
+ "xh_ZA",
511
+ "gl_ES",
512
+ "sl_SI"
513
+ ],
514
+ "bos_token": "<s>",
515
+ "clean_up_tokenization_spaces": true,
516
+ "cls_token": "<s>",
517
+ "eos_token": "</s>",
518
+ "language_codes": "ML50",
519
+ "mask_token": "<mask>",
520
+ "model_max_length": 1000000000000000019884624838656,
521
+ "pad_token": "<pad>",
522
+ "sep_token": "</s>",
523
+ "sp_model_kwargs": {},
524
+ "src_lang": "ko_KR",
525
+ "tgt_lang": "ja_XX",
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
checkpoint-32000/trainer_state.json ADDED
@@ -0,0 +1,443 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9008079171180725,
3
+ "best_model_checkpoint": "./koja_mbartLarge_55p_run1/checkpoint-32000",
4
+ "epoch": 1.9324254959388871,
5
+ "eval_steps": 8000,
6
+ "global_step": 32000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 4.9849024699559153e-05,
14
+ "loss": 1.5854,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.06,
19
+ "learning_rate": 4.9698049399118304e-05,
20
+ "loss": 1.3951,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.09,
25
+ "learning_rate": 4.954707409867746e-05,
26
+ "loss": 1.2938,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.12,
31
+ "learning_rate": 4.939609879823661e-05,
32
+ "loss": 1.2482,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.15,
37
+ "learning_rate": 4.9245123497795764e-05,
38
+ "loss": 1.2122,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.18,
43
+ "learning_rate": 4.9094148197354915e-05,
44
+ "loss": 1.178,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.21,
49
+ "learning_rate": 4.8943172896914066e-05,
50
+ "loss": 1.1483,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.24,
55
+ "learning_rate": 4.8792197596473224e-05,
56
+ "loss": 1.1408,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.27,
61
+ "learning_rate": 4.8641222296032375e-05,
62
+ "loss": 1.1053,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.3,
67
+ "learning_rate": 4.8490246995591526e-05,
68
+ "loss": 1.0876,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.33,
73
+ "learning_rate": 4.833927169515067e-05,
74
+ "loss": 1.0745,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 0.36,
79
+ "learning_rate": 4.818829639470983e-05,
80
+ "loss": 1.0707,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 0.39,
85
+ "learning_rate": 4.803732109426898e-05,
86
+ "loss": 1.0664,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 0.42,
91
+ "learning_rate": 4.788634579382813e-05,
92
+ "loss": 1.0426,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 0.45,
97
+ "learning_rate": 4.773537049338728e-05,
98
+ "loss": 1.0357,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 0.48,
103
+ "learning_rate": 4.758439519294643e-05,
104
+ "loss": 1.0254,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 0.48,
109
+ "eval_bleu": 7.1252,
110
+ "eval_gen_len": 18.5403,
111
+ "eval_loss": 1.0065276622772217,
112
+ "eval_runtime": 2330.5491,
113
+ "eval_samples_per_second": 14.21,
114
+ "eval_steps_per_second": 0.888,
115
+ "step": 8000
116
+ },
117
+ {
118
+ "epoch": 0.51,
119
+ "learning_rate": 4.743341989250559e-05,
120
+ "loss": 1.0195,
121
+ "step": 8500
122
+ },
123
+ {
124
+ "epoch": 0.54,
125
+ "learning_rate": 4.728244459206474e-05,
126
+ "loss": 1.0094,
127
+ "step": 9000
128
+ },
129
+ {
130
+ "epoch": 0.57,
131
+ "learning_rate": 4.713146929162389e-05,
132
+ "loss": 0.9984,
133
+ "step": 9500
134
+ },
135
+ {
136
+ "epoch": 0.6,
137
+ "learning_rate": 4.698049399118304e-05,
138
+ "loss": 0.9693,
139
+ "step": 10000
140
+ },
141
+ {
142
+ "epoch": 0.63,
143
+ "learning_rate": 4.6829518690742194e-05,
144
+ "loss": 0.9945,
145
+ "step": 10500
146
+ },
147
+ {
148
+ "epoch": 0.66,
149
+ "learning_rate": 4.667854339030135e-05,
150
+ "loss": 0.989,
151
+ "step": 11000
152
+ },
153
+ {
154
+ "epoch": 0.69,
155
+ "learning_rate": 4.65275680898605e-05,
156
+ "loss": 0.9907,
157
+ "step": 11500
158
+ },
159
+ {
160
+ "epoch": 0.72,
161
+ "learning_rate": 4.6376592789419654e-05,
162
+ "loss": 0.97,
163
+ "step": 12000
164
+ },
165
+ {
166
+ "epoch": 0.75,
167
+ "learning_rate": 4.6225617488978805e-05,
168
+ "loss": 0.9642,
169
+ "step": 12500
170
+ },
171
+ {
172
+ "epoch": 0.79,
173
+ "learning_rate": 4.6074642188537956e-05,
174
+ "loss": 0.9615,
175
+ "step": 13000
176
+ },
177
+ {
178
+ "epoch": 0.82,
179
+ "learning_rate": 4.5923666888097114e-05,
180
+ "loss": 0.9485,
181
+ "step": 13500
182
+ },
183
+ {
184
+ "epoch": 0.85,
185
+ "learning_rate": 4.5772691587656265e-05,
186
+ "loss": 0.9492,
187
+ "step": 14000
188
+ },
189
+ {
190
+ "epoch": 0.88,
191
+ "learning_rate": 4.5621716287215416e-05,
192
+ "loss": 0.9568,
193
+ "step": 14500
194
+ },
195
+ {
196
+ "epoch": 0.91,
197
+ "learning_rate": 4.547074098677457e-05,
198
+ "loss": 0.9507,
199
+ "step": 15000
200
+ },
201
+ {
202
+ "epoch": 0.94,
203
+ "learning_rate": 4.531976568633372e-05,
204
+ "loss": 0.9437,
205
+ "step": 15500
206
+ },
207
+ {
208
+ "epoch": 0.97,
209
+ "learning_rate": 4.516879038589287e-05,
210
+ "loss": 0.9374,
211
+ "step": 16000
212
+ },
213
+ {
214
+ "epoch": 0.97,
215
+ "eval_bleu": 8.2047,
216
+ "eval_gen_len": 18.2091,
217
+ "eval_loss": 0.9199957847595215,
218
+ "eval_runtime": 2175.6016,
219
+ "eval_samples_per_second": 15.222,
220
+ "eval_steps_per_second": 0.951,
221
+ "step": 16000
222
+ },
223
+ {
224
+ "epoch": 1.0,
225
+ "learning_rate": 4.501781508545202e-05,
226
+ "loss": 0.9266,
227
+ "step": 16500
228
+ },
229
+ {
230
+ "epoch": 1.03,
231
+ "learning_rate": 4.486683978501117e-05,
232
+ "loss": 0.8505,
233
+ "step": 17000
234
+ },
235
+ {
236
+ "epoch": 1.06,
237
+ "learning_rate": 4.471586448457032e-05,
238
+ "loss": 0.8316,
239
+ "step": 17500
240
+ },
241
+ {
242
+ "epoch": 1.09,
243
+ "learning_rate": 4.456488918412948e-05,
244
+ "loss": 0.8079,
245
+ "step": 18000
246
+ },
247
+ {
248
+ "epoch": 1.12,
249
+ "learning_rate": 4.441391388368863e-05,
250
+ "loss": 0.7993,
251
+ "step": 18500
252
+ },
253
+ {
254
+ "epoch": 1.15,
255
+ "learning_rate": 4.426293858324778e-05,
256
+ "loss": 0.7984,
257
+ "step": 19000
258
+ },
259
+ {
260
+ "epoch": 1.18,
261
+ "learning_rate": 4.411196328280693e-05,
262
+ "loss": 0.789,
263
+ "step": 19500
264
+ },
265
+ {
266
+ "epoch": 1.21,
267
+ "learning_rate": 4.3960987982366084e-05,
268
+ "loss": 0.7766,
269
+ "step": 20000
270
+ },
271
+ {
272
+ "epoch": 1.24,
273
+ "learning_rate": 4.381001268192524e-05,
274
+ "loss": 0.7798,
275
+ "step": 20500
276
+ },
277
+ {
278
+ "epoch": 1.27,
279
+ "learning_rate": 4.365903738148439e-05,
280
+ "loss": 0.7717,
281
+ "step": 21000
282
+ },
283
+ {
284
+ "epoch": 1.3,
285
+ "learning_rate": 4.3508062081043544e-05,
286
+ "loss": 0.7581,
287
+ "step": 21500
288
+ },
289
+ {
290
+ "epoch": 1.33,
291
+ "learning_rate": 4.3357086780602695e-05,
292
+ "loss": 0.7531,
293
+ "step": 22000
294
+ },
295
+ {
296
+ "epoch": 1.36,
297
+ "learning_rate": 4.3206111480161846e-05,
298
+ "loss": 0.7578,
299
+ "step": 22500
300
+ },
301
+ {
302
+ "epoch": 1.39,
303
+ "learning_rate": 4.3055136179721003e-05,
304
+ "loss": 0.7528,
305
+ "step": 23000
306
+ },
307
+ {
308
+ "epoch": 1.42,
309
+ "learning_rate": 4.2904160879280154e-05,
310
+ "loss": 0.7479,
311
+ "step": 23500
312
+ },
313
+ {
314
+ "epoch": 1.45,
315
+ "learning_rate": 4.2753185578839306e-05,
316
+ "loss": 0.7429,
317
+ "step": 24000
318
+ },
319
+ {
320
+ "epoch": 1.45,
321
+ "eval_bleu": 8.4622,
322
+ "eval_gen_len": 17.9606,
323
+ "eval_loss": 0.9085537791252136,
324
+ "eval_runtime": 2144.5036,
325
+ "eval_samples_per_second": 15.443,
326
+ "eval_steps_per_second": 0.965,
327
+ "step": 24000
328
+ },
329
+ {
330
+ "epoch": 1.48,
331
+ "learning_rate": 4.2602210278398457e-05,
332
+ "loss": 0.7292,
333
+ "step": 24500
334
+ },
335
+ {
336
+ "epoch": 1.51,
337
+ "learning_rate": 4.245123497795761e-05,
338
+ "loss": 0.7363,
339
+ "step": 25000
340
+ },
341
+ {
342
+ "epoch": 1.54,
343
+ "learning_rate": 4.2300259677516765e-05,
344
+ "loss": 0.7261,
345
+ "step": 25500
346
+ },
347
+ {
348
+ "epoch": 1.57,
349
+ "learning_rate": 4.2149284377075916e-05,
350
+ "loss": 0.7214,
351
+ "step": 26000
352
+ },
353
+ {
354
+ "epoch": 1.6,
355
+ "learning_rate": 4.199830907663506e-05,
356
+ "loss": 0.7077,
357
+ "step": 26500
358
+ },
359
+ {
360
+ "epoch": 1.63,
361
+ "learning_rate": 4.184733377619421e-05,
362
+ "loss": 0.724,
363
+ "step": 27000
364
+ },
365
+ {
366
+ "epoch": 1.66,
367
+ "learning_rate": 4.169635847575337e-05,
368
+ "loss": 0.7286,
369
+ "step": 27500
370
+ },
371
+ {
372
+ "epoch": 1.69,
373
+ "learning_rate": 4.154538317531252e-05,
374
+ "loss": 0.7224,
375
+ "step": 28000
376
+ },
377
+ {
378
+ "epoch": 1.72,
379
+ "learning_rate": 4.139440787487167e-05,
380
+ "loss": 0.7194,
381
+ "step": 28500
382
+ },
383
+ {
384
+ "epoch": 1.75,
385
+ "learning_rate": 4.124343257443082e-05,
386
+ "loss": 0.7095,
387
+ "step": 29000
388
+ },
389
+ {
390
+ "epoch": 1.78,
391
+ "learning_rate": 4.1092457273989973e-05,
392
+ "loss": 0.7065,
393
+ "step": 29500
394
+ },
395
+ {
396
+ "epoch": 1.81,
397
+ "learning_rate": 4.094148197354913e-05,
398
+ "loss": 0.7012,
399
+ "step": 30000
400
+ },
401
+ {
402
+ "epoch": 1.84,
403
+ "learning_rate": 4.079050667310828e-05,
404
+ "loss": 0.7045,
405
+ "step": 30500
406
+ },
407
+ {
408
+ "epoch": 1.87,
409
+ "learning_rate": 4.063953137266743e-05,
410
+ "loss": 0.7099,
411
+ "step": 31000
412
+ },
413
+ {
414
+ "epoch": 1.9,
415
+ "learning_rate": 4.0488556072226584e-05,
416
+ "loss": 0.7084,
417
+ "step": 31500
418
+ },
419
+ {
420
+ "epoch": 1.93,
421
+ "learning_rate": 4.0337580771785735e-05,
422
+ "loss": 0.7039,
423
+ "step": 32000
424
+ },
425
+ {
426
+ "epoch": 1.93,
427
+ "eval_bleu": 8.9198,
428
+ "eval_gen_len": 17.8841,
429
+ "eval_loss": 0.9008079171180725,
430
+ "eval_runtime": 2125.9264,
431
+ "eval_samples_per_second": 15.578,
432
+ "eval_steps_per_second": 0.974,
433
+ "step": 32000
434
+ }
435
+ ],
436
+ "logging_steps": 500,
437
+ "max_steps": 165590,
438
+ "num_train_epochs": 10,
439
+ "save_steps": 8000,
440
+ "total_flos": 1.1096744631436575e+18,
441
+ "trial_name": null,
442
+ "trial_params": null
443
+ }
checkpoint-32000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2375b9520792a916e970310a134c4b72d4500b7fe94384774f1d61421a8a22ea
3
+ size 4728
checkpoint-56000/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": true,
8
+ "architectures": [
9
+ "MBartForConditionalGeneration"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 1024,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 4096,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 12,
20
+ "decoder_start_token_id": 2,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 2,
28
+ "forced_bos_token_id": 250012,
29
+ "forced_eos_token_id": 2,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "max_length": 200,
44
+ "max_position_embeddings": 1024,
45
+ "model_type": "mbart",
46
+ "normalize_before": true,
47
+ "normalize_embedding": true,
48
+ "num_beams": 5,
49
+ "num_hidden_layers": 12,
50
+ "output_past": true,
51
+ "pad_token_id": 1,
52
+ "scale_embedding": true,
53
+ "static_position_embeddings": false,
54
+ "tokenizer_class": "MBart50Tokenizer",
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.34.1",
57
+ "use_cache": true,
58
+ "vocab_size": 250054
59
+ }
checkpoint-56000/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "forced_bos_token_id": 250012,
7
+ "forced_eos_token_id": 2,
8
+ "max_length": 200,
9
+ "num_beams": 5,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.34.1"
12
+ }
checkpoint-56000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:503d5674510ab702284b2b559dfdcffaa01a26bc901cc2c3030f59d963219d12
3
+ size 4887473903
checkpoint-56000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a73f8f749858bcc0593d9caa6d671e9003fcb3f0885aa50268ca23a51af1574
3
+ size 2444694490
checkpoint-56000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faac7745c793c2b478e563dcf7d6a0238c751e0cb18dcb1c129e77227faeeae6
3
+ size 15024
checkpoint-56000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23be16af2716bab362d4e4ca587fe4e1bef6489ac8dff893542617881c5530bb
3
+ size 15024
checkpoint-56000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:696500ad13bc838b4b9188d84a0285f677847522e9d12edc13521de631989045
3
+ size 15024
checkpoint-56000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdfe1e6b34bd504acf9a8b85ab3529d648bc0ae66d504cd10d13400f8ae80a32
3
+ size 15024
checkpoint-56000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:141a0d5eb630d7dbfe6e7a3f513a9428b39d4b0bb8fa9c0c6bfec5e126d12cfa
3
+ size 1064
checkpoint-56000/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-56000/special_tokens_map.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN",
28
+ "af_ZA",
29
+ "az_AZ",
30
+ "bn_IN",
31
+ "fa_IR",
32
+ "he_IL",
33
+ "hr_HR",
34
+ "id_ID",
35
+ "ka_GE",
36
+ "km_KH",
37
+ "mk_MK",
38
+ "ml_IN",
39
+ "mn_MN",
40
+ "mr_IN",
41
+ "pl_PL",
42
+ "ps_AF",
43
+ "pt_XX",
44
+ "sv_SE",
45
+ "sw_KE",
46
+ "ta_IN",
47
+ "te_IN",
48
+ "th_TH",
49
+ "tl_XX",
50
+ "uk_UA",
51
+ "ur_PK",
52
+ "xh_ZA",
53
+ "gl_ES",
54
+ "sl_SI"
55
+ ],
56
+ "bos_token": "<s>",
57
+ "cls_token": "<s>",
58
+ "eos_token": "</s>",
59
+ "mask_token": {
60
+ "content": "<mask>",
61
+ "lstrip": true,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ "pad_token": "<pad>",
67
+ "sep_token": "</s>",
68
+ "unk_token": "<unk>"
69
+ }
checkpoint-56000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fc2a9a463953c664738ef8571ed97361b8de258b2aca93c0214a89676a73379
3
+ size 17110043
checkpoint-56000/tokenizer_config.json ADDED
@@ -0,0 +1,528 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "ar_AR",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "250002": {
44
+ "content": "cs_CZ",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "250003": {
52
+ "content": "de_DE",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "250004": {
60
+ "content": "en_XX",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "250005": {
68
+ "content": "es_XX",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "250006": {
76
+ "content": "et_EE",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "250007": {
84
+ "content": "fi_FI",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "250008": {
92
+ "content": "fr_XX",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "250009": {
100
+ "content": "gu_IN",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "250010": {
108
+ "content": "hi_IN",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "250011": {
116
+ "content": "it_IT",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "250012": {
124
+ "content": "ja_XX",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "250013": {
132
+ "content": "kk_KZ",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "250014": {
140
+ "content": "ko_KR",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "250015": {
148
+ "content": "lt_LT",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "250016": {
156
+ "content": "lv_LV",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "250017": {
164
+ "content": "my_MM",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "250018": {
172
+ "content": "ne_NP",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "250019": {
180
+ "content": "nl_XX",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "250020": {
188
+ "content": "ro_RO",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "250021": {
196
+ "content": "ru_RU",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "250022": {
204
+ "content": "si_LK",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "250023": {
212
+ "content": "tr_TR",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "250024": {
220
+ "content": "vi_VN",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "250025": {
228
+ "content": "zh_CN",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "250026": {
236
+ "content": "af_ZA",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "250027": {
244
+ "content": "az_AZ",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "250028": {
252
+ "content": "bn_IN",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "250029": {
260
+ "content": "fa_IR",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "250030": {
268
+ "content": "he_IL",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "250031": {
276
+ "content": "hr_HR",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "250032": {
284
+ "content": "id_ID",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "250033": {
292
+ "content": "ka_GE",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "250034": {
300
+ "content": "km_KH",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "250035": {
308
+ "content": "mk_MK",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "250036": {
316
+ "content": "ml_IN",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "250037": {
324
+ "content": "mn_MN",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "250038": {
332
+ "content": "mr_IN",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "250039": {
340
+ "content": "pl_PL",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "250040": {
348
+ "content": "ps_AF",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "250041": {
356
+ "content": "pt_XX",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "250042": {
364
+ "content": "sv_SE",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "250043": {
372
+ "content": "sw_KE",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "250044": {
380
+ "content": "ta_IN",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "250045": {
388
+ "content": "te_IN",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "250046": {
396
+ "content": "th_TH",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "250047": {
404
+ "content": "tl_XX",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "250048": {
412
+ "content": "uk_UA",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "250049": {
420
+ "content": "ur_PK",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "250050": {
428
+ "content": "xh_ZA",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "250051": {
436
+ "content": "gl_ES",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "250052": {
444
+ "content": "sl_SI",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "250053": {
452
+ "content": "<mask>",
453
+ "lstrip": true,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ }
459
+ },
460
+ "additional_special_tokens": [
461
+ "ar_AR",
462
+ "cs_CZ",
463
+ "de_DE",
464
+ "en_XX",
465
+ "es_XX",
466
+ "et_EE",
467
+ "fi_FI",
468
+ "fr_XX",
469
+ "gu_IN",
470
+ "hi_IN",
471
+ "it_IT",
472
+ "ja_XX",
473
+ "kk_KZ",
474
+ "ko_KR",
475
+ "lt_LT",
476
+ "lv_LV",
477
+ "my_MM",
478
+ "ne_NP",
479
+ "nl_XX",
480
+ "ro_RO",
481
+ "ru_RU",
482
+ "si_LK",
483
+ "tr_TR",
484
+ "vi_VN",
485
+ "zh_CN",
486
+ "af_ZA",
487
+ "az_AZ",
488
+ "bn_IN",
489
+ "fa_IR",
490
+ "he_IL",
491
+ "hr_HR",
492
+ "id_ID",
493
+ "ka_GE",
494
+ "km_KH",
495
+ "mk_MK",
496
+ "ml_IN",
497
+ "mn_MN",
498
+ "mr_IN",
499
+ "pl_PL",
500
+ "ps_AF",
501
+ "pt_XX",
502
+ "sv_SE",
503
+ "sw_KE",
504
+ "ta_IN",
505
+ "te_IN",
506
+ "th_TH",
507
+ "tl_XX",
508
+ "uk_UA",
509
+ "ur_PK",
510
+ "xh_ZA",
511
+ "gl_ES",
512
+ "sl_SI"
513
+ ],
514
+ "bos_token": "<s>",
515
+ "clean_up_tokenization_spaces": true,
516
+ "cls_token": "<s>",
517
+ "eos_token": "</s>",
518
+ "language_codes": "ML50",
519
+ "mask_token": "<mask>",
520
+ "model_max_length": 1000000000000000019884624838656,
521
+ "pad_token": "<pad>",
522
+ "sep_token": "</s>",
523
+ "sp_model_kwargs": {},
524
+ "src_lang": "ko_KR",
525
+ "tgt_lang": "ja_XX",
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
checkpoint-56000/trainer_state.json ADDED
@@ -0,0 +1,761 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9008079171180725,
3
+ "best_model_checkpoint": "./koja_mbartLarge_55p_run1/checkpoint-32000",
4
+ "epoch": 3.381744617893052,
5
+ "eval_steps": 8000,
6
+ "global_step": 56000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 4.9849024699559153e-05,
14
+ "loss": 1.5854,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.06,
19
+ "learning_rate": 4.9698049399118304e-05,
20
+ "loss": 1.3951,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.09,
25
+ "learning_rate": 4.954707409867746e-05,
26
+ "loss": 1.2938,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.12,
31
+ "learning_rate": 4.939609879823661e-05,
32
+ "loss": 1.2482,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.15,
37
+ "learning_rate": 4.9245123497795764e-05,
38
+ "loss": 1.2122,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.18,
43
+ "learning_rate": 4.9094148197354915e-05,
44
+ "loss": 1.178,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.21,
49
+ "learning_rate": 4.8943172896914066e-05,
50
+ "loss": 1.1483,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.24,
55
+ "learning_rate": 4.8792197596473224e-05,
56
+ "loss": 1.1408,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.27,
61
+ "learning_rate": 4.8641222296032375e-05,
62
+ "loss": 1.1053,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.3,
67
+ "learning_rate": 4.8490246995591526e-05,
68
+ "loss": 1.0876,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.33,
73
+ "learning_rate": 4.833927169515067e-05,
74
+ "loss": 1.0745,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 0.36,
79
+ "learning_rate": 4.818829639470983e-05,
80
+ "loss": 1.0707,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 0.39,
85
+ "learning_rate": 4.803732109426898e-05,
86
+ "loss": 1.0664,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 0.42,
91
+ "learning_rate": 4.788634579382813e-05,
92
+ "loss": 1.0426,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 0.45,
97
+ "learning_rate": 4.773537049338728e-05,
98
+ "loss": 1.0357,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 0.48,
103
+ "learning_rate": 4.758439519294643e-05,
104
+ "loss": 1.0254,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 0.48,
109
+ "eval_bleu": 7.1252,
110
+ "eval_gen_len": 18.5403,
111
+ "eval_loss": 1.0065276622772217,
112
+ "eval_runtime": 2330.5491,
113
+ "eval_samples_per_second": 14.21,
114
+ "eval_steps_per_second": 0.888,
115
+ "step": 8000
116
+ },
117
+ {
118
+ "epoch": 0.51,
119
+ "learning_rate": 4.743341989250559e-05,
120
+ "loss": 1.0195,
121
+ "step": 8500
122
+ },
123
+ {
124
+ "epoch": 0.54,
125
+ "learning_rate": 4.728244459206474e-05,
126
+ "loss": 1.0094,
127
+ "step": 9000
128
+ },
129
+ {
130
+ "epoch": 0.57,
131
+ "learning_rate": 4.713146929162389e-05,
132
+ "loss": 0.9984,
133
+ "step": 9500
134
+ },
135
+ {
136
+ "epoch": 0.6,
137
+ "learning_rate": 4.698049399118304e-05,
138
+ "loss": 0.9693,
139
+ "step": 10000
140
+ },
141
+ {
142
+ "epoch": 0.63,
143
+ "learning_rate": 4.6829518690742194e-05,
144
+ "loss": 0.9945,
145
+ "step": 10500
146
+ },
147
+ {
148
+ "epoch": 0.66,
149
+ "learning_rate": 4.667854339030135e-05,
150
+ "loss": 0.989,
151
+ "step": 11000
152
+ },
153
+ {
154
+ "epoch": 0.69,
155
+ "learning_rate": 4.65275680898605e-05,
156
+ "loss": 0.9907,
157
+ "step": 11500
158
+ },
159
+ {
160
+ "epoch": 0.72,
161
+ "learning_rate": 4.6376592789419654e-05,
162
+ "loss": 0.97,
163
+ "step": 12000
164
+ },
165
+ {
166
+ "epoch": 0.75,
167
+ "learning_rate": 4.6225617488978805e-05,
168
+ "loss": 0.9642,
169
+ "step": 12500
170
+ },
171
+ {
172
+ "epoch": 0.79,
173
+ "learning_rate": 4.6074642188537956e-05,
174
+ "loss": 0.9615,
175
+ "step": 13000
176
+ },
177
+ {
178
+ "epoch": 0.82,
179
+ "learning_rate": 4.5923666888097114e-05,
180
+ "loss": 0.9485,
181
+ "step": 13500
182
+ },
183
+ {
184
+ "epoch": 0.85,
185
+ "learning_rate": 4.5772691587656265e-05,
186
+ "loss": 0.9492,
187
+ "step": 14000
188
+ },
189
+ {
190
+ "epoch": 0.88,
191
+ "learning_rate": 4.5621716287215416e-05,
192
+ "loss": 0.9568,
193
+ "step": 14500
194
+ },
195
+ {
196
+ "epoch": 0.91,
197
+ "learning_rate": 4.547074098677457e-05,
198
+ "loss": 0.9507,
199
+ "step": 15000
200
+ },
201
+ {
202
+ "epoch": 0.94,
203
+ "learning_rate": 4.531976568633372e-05,
204
+ "loss": 0.9437,
205
+ "step": 15500
206
+ },
207
+ {
208
+ "epoch": 0.97,
209
+ "learning_rate": 4.516879038589287e-05,
210
+ "loss": 0.9374,
211
+ "step": 16000
212
+ },
213
+ {
214
+ "epoch": 0.97,
215
+ "eval_bleu": 8.2047,
216
+ "eval_gen_len": 18.2091,
217
+ "eval_loss": 0.9199957847595215,
218
+ "eval_runtime": 2175.6016,
219
+ "eval_samples_per_second": 15.222,
220
+ "eval_steps_per_second": 0.951,
221
+ "step": 16000
222
+ },
223
+ {
224
+ "epoch": 1.0,
225
+ "learning_rate": 4.501781508545202e-05,
226
+ "loss": 0.9266,
227
+ "step": 16500
228
+ },
229
+ {
230
+ "epoch": 1.03,
231
+ "learning_rate": 4.486683978501117e-05,
232
+ "loss": 0.8505,
233
+ "step": 17000
234
+ },
235
+ {
236
+ "epoch": 1.06,
237
+ "learning_rate": 4.471586448457032e-05,
238
+ "loss": 0.8316,
239
+ "step": 17500
240
+ },
241
+ {
242
+ "epoch": 1.09,
243
+ "learning_rate": 4.456488918412948e-05,
244
+ "loss": 0.8079,
245
+ "step": 18000
246
+ },
247
+ {
248
+ "epoch": 1.12,
249
+ "learning_rate": 4.441391388368863e-05,
250
+ "loss": 0.7993,
251
+ "step": 18500
252
+ },
253
+ {
254
+ "epoch": 1.15,
255
+ "learning_rate": 4.426293858324778e-05,
256
+ "loss": 0.7984,
257
+ "step": 19000
258
+ },
259
+ {
260
+ "epoch": 1.18,
261
+ "learning_rate": 4.411196328280693e-05,
262
+ "loss": 0.789,
263
+ "step": 19500
264
+ },
265
+ {
266
+ "epoch": 1.21,
267
+ "learning_rate": 4.3960987982366084e-05,
268
+ "loss": 0.7766,
269
+ "step": 20000
270
+ },
271
+ {
272
+ "epoch": 1.24,
273
+ "learning_rate": 4.381001268192524e-05,
274
+ "loss": 0.7798,
275
+ "step": 20500
276
+ },
277
+ {
278
+ "epoch": 1.27,
279
+ "learning_rate": 4.365903738148439e-05,
280
+ "loss": 0.7717,
281
+ "step": 21000
282
+ },
283
+ {
284
+ "epoch": 1.3,
285
+ "learning_rate": 4.3508062081043544e-05,
286
+ "loss": 0.7581,
287
+ "step": 21500
288
+ },
289
+ {
290
+ "epoch": 1.33,
291
+ "learning_rate": 4.3357086780602695e-05,
292
+ "loss": 0.7531,
293
+ "step": 22000
294
+ },
295
+ {
296
+ "epoch": 1.36,
297
+ "learning_rate": 4.3206111480161846e-05,
298
+ "loss": 0.7578,
299
+ "step": 22500
300
+ },
301
+ {
302
+ "epoch": 1.39,
303
+ "learning_rate": 4.3055136179721003e-05,
304
+ "loss": 0.7528,
305
+ "step": 23000
306
+ },
307
+ {
308
+ "epoch": 1.42,
309
+ "learning_rate": 4.2904160879280154e-05,
310
+ "loss": 0.7479,
311
+ "step": 23500
312
+ },
313
+ {
314
+ "epoch": 1.45,
315
+ "learning_rate": 4.2753185578839306e-05,
316
+ "loss": 0.7429,
317
+ "step": 24000
318
+ },
319
+ {
320
+ "epoch": 1.45,
321
+ "eval_bleu": 8.4622,
322
+ "eval_gen_len": 17.9606,
323
+ "eval_loss": 0.9085537791252136,
324
+ "eval_runtime": 2144.5036,
325
+ "eval_samples_per_second": 15.443,
326
+ "eval_steps_per_second": 0.965,
327
+ "step": 24000
328
+ },
329
+ {
330
+ "epoch": 1.48,
331
+ "learning_rate": 4.2602210278398457e-05,
332
+ "loss": 0.7292,
333
+ "step": 24500
334
+ },
335
+ {
336
+ "epoch": 1.51,
337
+ "learning_rate": 4.245123497795761e-05,
338
+ "loss": 0.7363,
339
+ "step": 25000
340
+ },
341
+ {
342
+ "epoch": 1.54,
343
+ "learning_rate": 4.2300259677516765e-05,
344
+ "loss": 0.7261,
345
+ "step": 25500
346
+ },
347
+ {
348
+ "epoch": 1.57,
349
+ "learning_rate": 4.2149284377075916e-05,
350
+ "loss": 0.7214,
351
+ "step": 26000
352
+ },
353
+ {
354
+ "epoch": 1.6,
355
+ "learning_rate": 4.199830907663506e-05,
356
+ "loss": 0.7077,
357
+ "step": 26500
358
+ },
359
+ {
360
+ "epoch": 1.63,
361
+ "learning_rate": 4.184733377619421e-05,
362
+ "loss": 0.724,
363
+ "step": 27000
364
+ },
365
+ {
366
+ "epoch": 1.66,
367
+ "learning_rate": 4.169635847575337e-05,
368
+ "loss": 0.7286,
369
+ "step": 27500
370
+ },
371
+ {
372
+ "epoch": 1.69,
373
+ "learning_rate": 4.154538317531252e-05,
374
+ "loss": 0.7224,
375
+ "step": 28000
376
+ },
377
+ {
378
+ "epoch": 1.72,
379
+ "learning_rate": 4.139440787487167e-05,
380
+ "loss": 0.7194,
381
+ "step": 28500
382
+ },
383
+ {
384
+ "epoch": 1.75,
385
+ "learning_rate": 4.124343257443082e-05,
386
+ "loss": 0.7095,
387
+ "step": 29000
388
+ },
389
+ {
390
+ "epoch": 1.78,
391
+ "learning_rate": 4.1092457273989973e-05,
392
+ "loss": 0.7065,
393
+ "step": 29500
394
+ },
395
+ {
396
+ "epoch": 1.81,
397
+ "learning_rate": 4.094148197354913e-05,
398
+ "loss": 0.7012,
399
+ "step": 30000
400
+ },
401
+ {
402
+ "epoch": 1.84,
403
+ "learning_rate": 4.079050667310828e-05,
404
+ "loss": 0.7045,
405
+ "step": 30500
406
+ },
407
+ {
408
+ "epoch": 1.87,
409
+ "learning_rate": 4.063953137266743e-05,
410
+ "loss": 0.7099,
411
+ "step": 31000
412
+ },
413
+ {
414
+ "epoch": 1.9,
415
+ "learning_rate": 4.0488556072226584e-05,
416
+ "loss": 0.7084,
417
+ "step": 31500
418
+ },
419
+ {
420
+ "epoch": 1.93,
421
+ "learning_rate": 4.0337580771785735e-05,
422
+ "loss": 0.7039,
423
+ "step": 32000
424
+ },
425
+ {
426
+ "epoch": 1.93,
427
+ "eval_bleu": 8.9198,
428
+ "eval_gen_len": 17.8841,
429
+ "eval_loss": 0.9008079171180725,
430
+ "eval_runtime": 2125.9264,
431
+ "eval_samples_per_second": 15.578,
432
+ "eval_steps_per_second": 0.974,
433
+ "step": 32000
434
+ },
435
+ {
436
+ "epoch": 1.96,
437
+ "learning_rate": 4.018660547134489e-05,
438
+ "loss": 0.7029,
439
+ "step": 32500
440
+ },
441
+ {
442
+ "epoch": 1.99,
443
+ "learning_rate": 4.0035630170904044e-05,
444
+ "loss": 0.6983,
445
+ "step": 33000
446
+ },
447
+ {
448
+ "epoch": 2.02,
449
+ "learning_rate": 3.9884654870463195e-05,
450
+ "loss": 0.6503,
451
+ "step": 33500
452
+ },
453
+ {
454
+ "epoch": 2.05,
455
+ "learning_rate": 3.9733679570022346e-05,
456
+ "loss": 0.6191,
457
+ "step": 34000
458
+ },
459
+ {
460
+ "epoch": 2.08,
461
+ "learning_rate": 3.95827042695815e-05,
462
+ "loss": 0.605,
463
+ "step": 34500
464
+ },
465
+ {
466
+ "epoch": 2.11,
467
+ "learning_rate": 3.9431728969140655e-05,
468
+ "loss": 0.6035,
469
+ "step": 35000
470
+ },
471
+ {
472
+ "epoch": 2.14,
473
+ "learning_rate": 3.9280753668699806e-05,
474
+ "loss": 0.6008,
475
+ "step": 35500
476
+ },
477
+ {
478
+ "epoch": 2.17,
479
+ "learning_rate": 3.912977836825896e-05,
480
+ "loss": 0.5947,
481
+ "step": 36000
482
+ },
483
+ {
484
+ "epoch": 2.2,
485
+ "learning_rate": 3.897880306781811e-05,
486
+ "loss": 0.5812,
487
+ "step": 36500
488
+ },
489
+ {
490
+ "epoch": 2.23,
491
+ "learning_rate": 3.882782776737726e-05,
492
+ "loss": 0.587,
493
+ "step": 37000
494
+ },
495
+ {
496
+ "epoch": 2.26,
497
+ "learning_rate": 3.867685246693641e-05,
498
+ "loss": 0.5857,
499
+ "step": 37500
500
+ },
501
+ {
502
+ "epoch": 2.29,
503
+ "learning_rate": 3.852587716649556e-05,
504
+ "loss": 0.5659,
505
+ "step": 38000
506
+ },
507
+ {
508
+ "epoch": 2.32,
509
+ "learning_rate": 3.837490186605471e-05,
510
+ "loss": 0.5702,
511
+ "step": 38500
512
+ },
513
+ {
514
+ "epoch": 2.36,
515
+ "learning_rate": 3.822392656561386e-05,
516
+ "loss": 0.5651,
517
+ "step": 39000
518
+ },
519
+ {
520
+ "epoch": 2.39,
521
+ "learning_rate": 3.807295126517302e-05,
522
+ "loss": 0.5691,
523
+ "step": 39500
524
+ },
525
+ {
526
+ "epoch": 2.42,
527
+ "learning_rate": 3.792197596473217e-05,
528
+ "loss": 0.5616,
529
+ "step": 40000
530
+ },
531
+ {
532
+ "epoch": 2.42,
533
+ "eval_bleu": 8.7938,
534
+ "eval_gen_len": 17.78,
535
+ "eval_loss": 0.9209699630737305,
536
+ "eval_runtime": 2116.9975,
537
+ "eval_samples_per_second": 15.644,
538
+ "eval_steps_per_second": 0.978,
539
+ "step": 40000
540
+ },
541
+ {
542
+ "epoch": 2.45,
543
+ "learning_rate": 3.777100066429132e-05,
544
+ "loss": 0.5552,
545
+ "step": 40500
546
+ },
547
+ {
548
+ "epoch": 2.48,
549
+ "learning_rate": 3.7620025363850474e-05,
550
+ "loss": 0.5461,
551
+ "step": 41000
552
+ },
553
+ {
554
+ "epoch": 2.51,
555
+ "learning_rate": 3.7469050063409625e-05,
556
+ "loss": 0.5546,
557
+ "step": 41500
558
+ },
559
+ {
560
+ "epoch": 2.54,
561
+ "learning_rate": 3.731807476296878e-05,
562
+ "loss": 0.5383,
563
+ "step": 42000
564
+ },
565
+ {
566
+ "epoch": 2.57,
567
+ "learning_rate": 3.7167099462527934e-05,
568
+ "loss": 0.5452,
569
+ "step": 42500
570
+ },
571
+ {
572
+ "epoch": 2.6,
573
+ "learning_rate": 3.7016124162087085e-05,
574
+ "loss": 0.5318,
575
+ "step": 43000
576
+ },
577
+ {
578
+ "epoch": 2.63,
579
+ "learning_rate": 3.6865148861646236e-05,
580
+ "loss": 0.5407,
581
+ "step": 43500
582
+ },
583
+ {
584
+ "epoch": 2.66,
585
+ "learning_rate": 3.671417356120539e-05,
586
+ "loss": 0.549,
587
+ "step": 44000
588
+ },
589
+ {
590
+ "epoch": 2.69,
591
+ "learning_rate": 3.6563198260764545e-05,
592
+ "loss": 0.5384,
593
+ "step": 44500
594
+ },
595
+ {
596
+ "epoch": 2.72,
597
+ "learning_rate": 3.6412222960323696e-05,
598
+ "loss": 0.5441,
599
+ "step": 45000
600
+ },
601
+ {
602
+ "epoch": 2.75,
603
+ "learning_rate": 3.626124765988285e-05,
604
+ "loss": 0.5317,
605
+ "step": 45500
606
+ },
607
+ {
608
+ "epoch": 2.78,
609
+ "learning_rate": 3.6110272359442e-05,
610
+ "loss": 0.5352,
611
+ "step": 46000
612
+ },
613
+ {
614
+ "epoch": 2.81,
615
+ "learning_rate": 3.595929705900115e-05,
616
+ "loss": 0.5248,
617
+ "step": 46500
618
+ },
619
+ {
620
+ "epoch": 2.84,
621
+ "learning_rate": 3.5808321758560307e-05,
622
+ "loss": 0.5309,
623
+ "step": 47000
624
+ },
625
+ {
626
+ "epoch": 2.87,
627
+ "learning_rate": 3.565734645811946e-05,
628
+ "loss": 0.5296,
629
+ "step": 47500
630
+ },
631
+ {
632
+ "epoch": 2.9,
633
+ "learning_rate": 3.55063711576786e-05,
634
+ "loss": 0.5355,
635
+ "step": 48000
636
+ },
637
+ {
638
+ "epoch": 2.9,
639
+ "eval_bleu": 8.6506,
640
+ "eval_gen_len": 17.9146,
641
+ "eval_loss": 0.9399827122688293,
642
+ "eval_runtime": 2117.673,
643
+ "eval_samples_per_second": 15.639,
644
+ "eval_steps_per_second": 0.977,
645
+ "step": 48000
646
+ },
647
+ {
648
+ "epoch": 2.93,
649
+ "learning_rate": 3.535539585723775e-05,
650
+ "loss": 0.5262,
651
+ "step": 48500
652
+ },
653
+ {
654
+ "epoch": 2.96,
655
+ "learning_rate": 3.520442055679691e-05,
656
+ "loss": 0.5247,
657
+ "step": 49000
658
+ },
659
+ {
660
+ "epoch": 2.99,
661
+ "learning_rate": 3.505344525635606e-05,
662
+ "loss": 0.5315,
663
+ "step": 49500
664
+ },
665
+ {
666
+ "epoch": 3.02,
667
+ "learning_rate": 3.490246995591521e-05,
668
+ "loss": 0.4932,
669
+ "step": 50000
670
+ },
671
+ {
672
+ "epoch": 3.05,
673
+ "learning_rate": 3.4751494655474364e-05,
674
+ "loss": 0.4595,
675
+ "step": 50500
676
+ },
677
+ {
678
+ "epoch": 3.08,
679
+ "learning_rate": 3.4600519355033515e-05,
680
+ "loss": 0.45,
681
+ "step": 51000
682
+ },
683
+ {
684
+ "epoch": 3.11,
685
+ "learning_rate": 3.444954405459267e-05,
686
+ "loss": 0.4477,
687
+ "step": 51500
688
+ },
689
+ {
690
+ "epoch": 3.14,
691
+ "learning_rate": 3.4298568754151824e-05,
692
+ "loss": 0.4423,
693
+ "step": 52000
694
+ },
695
+ {
696
+ "epoch": 3.17,
697
+ "learning_rate": 3.4147593453710975e-05,
698
+ "loss": 0.435,
699
+ "step": 52500
700
+ },
701
+ {
702
+ "epoch": 3.2,
703
+ "learning_rate": 3.3996618153270126e-05,
704
+ "loss": 0.4345,
705
+ "step": 53000
706
+ },
707
+ {
708
+ "epoch": 3.23,
709
+ "learning_rate": 3.3845642852829277e-05,
710
+ "loss": 0.4337,
711
+ "step": 53500
712
+ },
713
+ {
714
+ "epoch": 3.26,
715
+ "learning_rate": 3.3694667552388434e-05,
716
+ "loss": 0.4295,
717
+ "step": 54000
718
+ },
719
+ {
720
+ "epoch": 3.29,
721
+ "learning_rate": 3.3543692251947585e-05,
722
+ "loss": 0.4143,
723
+ "step": 54500
724
+ },
725
+ {
726
+ "epoch": 3.32,
727
+ "learning_rate": 3.3392716951506736e-05,
728
+ "loss": 0.4203,
729
+ "step": 55000
730
+ },
731
+ {
732
+ "epoch": 3.35,
733
+ "learning_rate": 3.324174165106589e-05,
734
+ "loss": 0.4164,
735
+ "step": 55500
736
+ },
737
+ {
738
+ "epoch": 3.38,
739
+ "learning_rate": 3.309076635062504e-05,
740
+ "loss": 0.4194,
741
+ "step": 56000
742
+ },
743
+ {
744
+ "epoch": 3.38,
745
+ "eval_bleu": 8.4235,
746
+ "eval_gen_len": 17.6759,
747
+ "eval_loss": 1.0053656101226807,
748
+ "eval_runtime": 2100.231,
749
+ "eval_samples_per_second": 15.769,
750
+ "eval_steps_per_second": 0.986,
751
+ "step": 56000
752
+ }
753
+ ],
754
+ "logging_steps": 500,
755
+ "max_steps": 165590,
756
+ "num_train_epochs": 10,
757
+ "save_steps": 8000,
758
+ "total_flos": 1.9418522940310815e+18,
759
+ "trial_name": null,
760
+ "trial_params": null
761
+ }
checkpoint-56000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2375b9520792a916e970310a134c4b72d4500b7fe94384774f1d61421a8a22ea
3
+ size 4728
checkpoint-64000/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": true,
8
+ "architectures": [
9
+ "MBartForConditionalGeneration"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 1024,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 4096,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 12,
20
+ "decoder_start_token_id": 2,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 2,
28
+ "forced_bos_token_id": 250012,
29
+ "forced_eos_token_id": 2,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "max_length": 200,
44
+ "max_position_embeddings": 1024,
45
+ "model_type": "mbart",
46
+ "normalize_before": true,
47
+ "normalize_embedding": true,
48
+ "num_beams": 5,
49
+ "num_hidden_layers": 12,
50
+ "output_past": true,
51
+ "pad_token_id": 1,
52
+ "scale_embedding": true,
53
+ "static_position_embeddings": false,
54
+ "tokenizer_class": "MBart50Tokenizer",
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.34.1",
57
+ "use_cache": true,
58
+ "vocab_size": 250054
59
+ }
checkpoint-64000/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "forced_bos_token_id": 250012,
7
+ "forced_eos_token_id": 2,
8
+ "max_length": 200,
9
+ "num_beams": 5,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.34.1"
12
+ }
checkpoint-64000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7790cd5b034aebb39c5aff05f2beea8ff9c8121e9372a646db4a474cf7918c7a
3
+ size 4887473903
checkpoint-64000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c751859c451328ac0e9715dd97ecd63d9fd750607f153f24b996e6b61db144ab
3
+ size 2444694490
checkpoint-64000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fed4d444e7c6333f4b6049ef0b6f71e595ca7060962b2e05ce807df46a62fc5
3
+ size 15024
checkpoint-64000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39dee38ac86d1da3fc7201d1cca665831c739158d6b6d71257b30880ddffc68e
3
+ size 15024
checkpoint-64000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02b7366bbae7ecf22a38e43d36dfb3b2d195214f9335337853ee472d60f36237
3
+ size 15024
checkpoint-64000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c2a77882c36b95e5186211ccba4ca2b66392d3c227b64ce8488c5be447b060b
3
+ size 15024
checkpoint-64000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3c4ac76ca444c3f1fc121023c04e7a22a648c34500094f0ba3fbf15dbe2b78a
3
+ size 1064
checkpoint-64000/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-64000/special_tokens_map.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN",
28
+ "af_ZA",
29
+ "az_AZ",
30
+ "bn_IN",
31
+ "fa_IR",
32
+ "he_IL",
33
+ "hr_HR",
34
+ "id_ID",
35
+ "ka_GE",
36
+ "km_KH",
37
+ "mk_MK",
38
+ "ml_IN",
39
+ "mn_MN",
40
+ "mr_IN",
41
+ "pl_PL",
42
+ "ps_AF",
43
+ "pt_XX",
44
+ "sv_SE",
45
+ "sw_KE",
46
+ "ta_IN",
47
+ "te_IN",
48
+ "th_TH",
49
+ "tl_XX",
50
+ "uk_UA",
51
+ "ur_PK",
52
+ "xh_ZA",
53
+ "gl_ES",
54
+ "sl_SI"
55
+ ],
56
+ "bos_token": "<s>",
57
+ "cls_token": "<s>",
58
+ "eos_token": "</s>",
59
+ "mask_token": {
60
+ "content": "<mask>",
61
+ "lstrip": true,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ "pad_token": "<pad>",
67
+ "sep_token": "</s>",
68
+ "unk_token": "<unk>"
69
+ }
checkpoint-64000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fc2a9a463953c664738ef8571ed97361b8de258b2aca93c0214a89676a73379
3
+ size 17110043
checkpoint-64000/tokenizer_config.json ADDED
@@ -0,0 +1,528 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "ar_AR",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "250002": {
44
+ "content": "cs_CZ",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "250003": {
52
+ "content": "de_DE",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "250004": {
60
+ "content": "en_XX",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "250005": {
68
+ "content": "es_XX",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "250006": {
76
+ "content": "et_EE",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "250007": {
84
+ "content": "fi_FI",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "250008": {
92
+ "content": "fr_XX",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "250009": {
100
+ "content": "gu_IN",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "250010": {
108
+ "content": "hi_IN",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "250011": {
116
+ "content": "it_IT",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "250012": {
124
+ "content": "ja_XX",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "250013": {
132
+ "content": "kk_KZ",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "250014": {
140
+ "content": "ko_KR",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "250015": {
148
+ "content": "lt_LT",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "250016": {
156
+ "content": "lv_LV",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "250017": {
164
+ "content": "my_MM",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "250018": {
172
+ "content": "ne_NP",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "250019": {
180
+ "content": "nl_XX",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "250020": {
188
+ "content": "ro_RO",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "250021": {
196
+ "content": "ru_RU",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "250022": {
204
+ "content": "si_LK",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "250023": {
212
+ "content": "tr_TR",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "250024": {
220
+ "content": "vi_VN",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "250025": {
228
+ "content": "zh_CN",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "250026": {
236
+ "content": "af_ZA",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "250027": {
244
+ "content": "az_AZ",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "250028": {
252
+ "content": "bn_IN",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "250029": {
260
+ "content": "fa_IR",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "250030": {
268
+ "content": "he_IL",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "250031": {
276
+ "content": "hr_HR",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "250032": {
284
+ "content": "id_ID",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "250033": {
292
+ "content": "ka_GE",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "250034": {
300
+ "content": "km_KH",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "250035": {
308
+ "content": "mk_MK",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "250036": {
316
+ "content": "ml_IN",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "250037": {
324
+ "content": "mn_MN",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "250038": {
332
+ "content": "mr_IN",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "250039": {
340
+ "content": "pl_PL",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "250040": {
348
+ "content": "ps_AF",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "250041": {
356
+ "content": "pt_XX",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "250042": {
364
+ "content": "sv_SE",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "250043": {
372
+ "content": "sw_KE",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "250044": {
380
+ "content": "ta_IN",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "250045": {
388
+ "content": "te_IN",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "250046": {
396
+ "content": "th_TH",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "250047": {
404
+ "content": "tl_XX",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "250048": {
412
+ "content": "uk_UA",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "250049": {
420
+ "content": "ur_PK",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "250050": {
428
+ "content": "xh_ZA",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "250051": {
436
+ "content": "gl_ES",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "250052": {
444
+ "content": "sl_SI",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "250053": {
452
+ "content": "<mask>",
453
+ "lstrip": true,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ }
459
+ },
460
+ "additional_special_tokens": [
461
+ "ar_AR",
462
+ "cs_CZ",
463
+ "de_DE",
464
+ "en_XX",
465
+ "es_XX",
466
+ "et_EE",
467
+ "fi_FI",
468
+ "fr_XX",
469
+ "gu_IN",
470
+ "hi_IN",
471
+ "it_IT",
472
+ "ja_XX",
473
+ "kk_KZ",
474
+ "ko_KR",
475
+ "lt_LT",
476
+ "lv_LV",
477
+ "my_MM",
478
+ "ne_NP",
479
+ "nl_XX",
480
+ "ro_RO",
481
+ "ru_RU",
482
+ "si_LK",
483
+ "tr_TR",
484
+ "vi_VN",
485
+ "zh_CN",
486
+ "af_ZA",
487
+ "az_AZ",
488
+ "bn_IN",
489
+ "fa_IR",
490
+ "he_IL",
491
+ "hr_HR",
492
+ "id_ID",
493
+ "ka_GE",
494
+ "km_KH",
495
+ "mk_MK",
496
+ "ml_IN",
497
+ "mn_MN",
498
+ "mr_IN",
499
+ "pl_PL",
500
+ "ps_AF",
501
+ "pt_XX",
502
+ "sv_SE",
503
+ "sw_KE",
504
+ "ta_IN",
505
+ "te_IN",
506
+ "th_TH",
507
+ "tl_XX",
508
+ "uk_UA",
509
+ "ur_PK",
510
+ "xh_ZA",
511
+ "gl_ES",
512
+ "sl_SI"
513
+ ],
514
+ "bos_token": "<s>",
515
+ "clean_up_tokenization_spaces": true,
516
+ "cls_token": "<s>",
517
+ "eos_token": "</s>",
518
+ "language_codes": "ML50",
519
+ "mask_token": "<mask>",
520
+ "model_max_length": 1000000000000000019884624838656,
521
+ "pad_token": "<pad>",
522
+ "sep_token": "</s>",
523
+ "sp_model_kwargs": {},
524
+ "src_lang": "ko_KR",
525
+ "tgt_lang": "ja_XX",
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
checkpoint-64000/trainer_state.json ADDED
@@ -0,0 +1,867 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9008079171180725,
3
+ "best_model_checkpoint": "./koja_mbartLarge_55p_run1/checkpoint-32000",
4
+ "epoch": 3.8648509918777743,
5
+ "eval_steps": 8000,
6
+ "global_step": 64000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 4.9849024699559153e-05,
14
+ "loss": 1.5854,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.06,
19
+ "learning_rate": 4.9698049399118304e-05,
20
+ "loss": 1.3951,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.09,
25
+ "learning_rate": 4.954707409867746e-05,
26
+ "loss": 1.2938,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.12,
31
+ "learning_rate": 4.939609879823661e-05,
32
+ "loss": 1.2482,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.15,
37
+ "learning_rate": 4.9245123497795764e-05,
38
+ "loss": 1.2122,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.18,
43
+ "learning_rate": 4.9094148197354915e-05,
44
+ "loss": 1.178,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.21,
49
+ "learning_rate": 4.8943172896914066e-05,
50
+ "loss": 1.1483,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.24,
55
+ "learning_rate": 4.8792197596473224e-05,
56
+ "loss": 1.1408,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.27,
61
+ "learning_rate": 4.8641222296032375e-05,
62
+ "loss": 1.1053,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.3,
67
+ "learning_rate": 4.8490246995591526e-05,
68
+ "loss": 1.0876,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.33,
73
+ "learning_rate": 4.833927169515067e-05,
74
+ "loss": 1.0745,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 0.36,
79
+ "learning_rate": 4.818829639470983e-05,
80
+ "loss": 1.0707,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 0.39,
85
+ "learning_rate": 4.803732109426898e-05,
86
+ "loss": 1.0664,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 0.42,
91
+ "learning_rate": 4.788634579382813e-05,
92
+ "loss": 1.0426,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 0.45,
97
+ "learning_rate": 4.773537049338728e-05,
98
+ "loss": 1.0357,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 0.48,
103
+ "learning_rate": 4.758439519294643e-05,
104
+ "loss": 1.0254,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 0.48,
109
+ "eval_bleu": 7.1252,
110
+ "eval_gen_len": 18.5403,
111
+ "eval_loss": 1.0065276622772217,
112
+ "eval_runtime": 2330.5491,
113
+ "eval_samples_per_second": 14.21,
114
+ "eval_steps_per_second": 0.888,
115
+ "step": 8000
116
+ },
117
+ {
118
+ "epoch": 0.51,
119
+ "learning_rate": 4.743341989250559e-05,
120
+ "loss": 1.0195,
121
+ "step": 8500
122
+ },
123
+ {
124
+ "epoch": 0.54,
125
+ "learning_rate": 4.728244459206474e-05,
126
+ "loss": 1.0094,
127
+ "step": 9000
128
+ },
129
+ {
130
+ "epoch": 0.57,
131
+ "learning_rate": 4.713146929162389e-05,
132
+ "loss": 0.9984,
133
+ "step": 9500
134
+ },
135
+ {
136
+ "epoch": 0.6,
137
+ "learning_rate": 4.698049399118304e-05,
138
+ "loss": 0.9693,
139
+ "step": 10000
140
+ },
141
+ {
142
+ "epoch": 0.63,
143
+ "learning_rate": 4.6829518690742194e-05,
144
+ "loss": 0.9945,
145
+ "step": 10500
146
+ },
147
+ {
148
+ "epoch": 0.66,
149
+ "learning_rate": 4.667854339030135e-05,
150
+ "loss": 0.989,
151
+ "step": 11000
152
+ },
153
+ {
154
+ "epoch": 0.69,
155
+ "learning_rate": 4.65275680898605e-05,
156
+ "loss": 0.9907,
157
+ "step": 11500
158
+ },
159
+ {
160
+ "epoch": 0.72,
161
+ "learning_rate": 4.6376592789419654e-05,
162
+ "loss": 0.97,
163
+ "step": 12000
164
+ },
165
+ {
166
+ "epoch": 0.75,
167
+ "learning_rate": 4.6225617488978805e-05,
168
+ "loss": 0.9642,
169
+ "step": 12500
170
+ },
171
+ {
172
+ "epoch": 0.79,
173
+ "learning_rate": 4.6074642188537956e-05,
174
+ "loss": 0.9615,
175
+ "step": 13000
176
+ },
177
+ {
178
+ "epoch": 0.82,
179
+ "learning_rate": 4.5923666888097114e-05,
180
+ "loss": 0.9485,
181
+ "step": 13500
182
+ },
183
+ {
184
+ "epoch": 0.85,
185
+ "learning_rate": 4.5772691587656265e-05,
186
+ "loss": 0.9492,
187
+ "step": 14000
188
+ },
189
+ {
190
+ "epoch": 0.88,
191
+ "learning_rate": 4.5621716287215416e-05,
192
+ "loss": 0.9568,
193
+ "step": 14500
194
+ },
195
+ {
196
+ "epoch": 0.91,
197
+ "learning_rate": 4.547074098677457e-05,
198
+ "loss": 0.9507,
199
+ "step": 15000
200
+ },
201
+ {
202
+ "epoch": 0.94,
203
+ "learning_rate": 4.531976568633372e-05,
204
+ "loss": 0.9437,
205
+ "step": 15500
206
+ },
207
+ {
208
+ "epoch": 0.97,
209
+ "learning_rate": 4.516879038589287e-05,
210
+ "loss": 0.9374,
211
+ "step": 16000
212
+ },
213
+ {
214
+ "epoch": 0.97,
215
+ "eval_bleu": 8.2047,
216
+ "eval_gen_len": 18.2091,
217
+ "eval_loss": 0.9199957847595215,
218
+ "eval_runtime": 2175.6016,
219
+ "eval_samples_per_second": 15.222,
220
+ "eval_steps_per_second": 0.951,
221
+ "step": 16000
222
+ },
223
+ {
224
+ "epoch": 1.0,
225
+ "learning_rate": 4.501781508545202e-05,
226
+ "loss": 0.9266,
227
+ "step": 16500
228
+ },
229
+ {
230
+ "epoch": 1.03,
231
+ "learning_rate": 4.486683978501117e-05,
232
+ "loss": 0.8505,
233
+ "step": 17000
234
+ },
235
+ {
236
+ "epoch": 1.06,
237
+ "learning_rate": 4.471586448457032e-05,
238
+ "loss": 0.8316,
239
+ "step": 17500
240
+ },
241
+ {
242
+ "epoch": 1.09,
243
+ "learning_rate": 4.456488918412948e-05,
244
+ "loss": 0.8079,
245
+ "step": 18000
246
+ },
247
+ {
248
+ "epoch": 1.12,
249
+ "learning_rate": 4.441391388368863e-05,
250
+ "loss": 0.7993,
251
+ "step": 18500
252
+ },
253
+ {
254
+ "epoch": 1.15,
255
+ "learning_rate": 4.426293858324778e-05,
256
+ "loss": 0.7984,
257
+ "step": 19000
258
+ },
259
+ {
260
+ "epoch": 1.18,
261
+ "learning_rate": 4.411196328280693e-05,
262
+ "loss": 0.789,
263
+ "step": 19500
264
+ },
265
+ {
266
+ "epoch": 1.21,
267
+ "learning_rate": 4.3960987982366084e-05,
268
+ "loss": 0.7766,
269
+ "step": 20000
270
+ },
271
+ {
272
+ "epoch": 1.24,
273
+ "learning_rate": 4.381001268192524e-05,
274
+ "loss": 0.7798,
275
+ "step": 20500
276
+ },
277
+ {
278
+ "epoch": 1.27,
279
+ "learning_rate": 4.365903738148439e-05,
280
+ "loss": 0.7717,
281
+ "step": 21000
282
+ },
283
+ {
284
+ "epoch": 1.3,
285
+ "learning_rate": 4.3508062081043544e-05,
286
+ "loss": 0.7581,
287
+ "step": 21500
288
+ },
289
+ {
290
+ "epoch": 1.33,
291
+ "learning_rate": 4.3357086780602695e-05,
292
+ "loss": 0.7531,
293
+ "step": 22000
294
+ },
295
+ {
296
+ "epoch": 1.36,
297
+ "learning_rate": 4.3206111480161846e-05,
298
+ "loss": 0.7578,
299
+ "step": 22500
300
+ },
301
+ {
302
+ "epoch": 1.39,
303
+ "learning_rate": 4.3055136179721003e-05,
304
+ "loss": 0.7528,
305
+ "step": 23000
306
+ },
307
+ {
308
+ "epoch": 1.42,
309
+ "learning_rate": 4.2904160879280154e-05,
310
+ "loss": 0.7479,
311
+ "step": 23500
312
+ },
313
+ {
314
+ "epoch": 1.45,
315
+ "learning_rate": 4.2753185578839306e-05,
316
+ "loss": 0.7429,
317
+ "step": 24000
318
+ },
319
+ {
320
+ "epoch": 1.45,
321
+ "eval_bleu": 8.4622,
322
+ "eval_gen_len": 17.9606,
323
+ "eval_loss": 0.9085537791252136,
324
+ "eval_runtime": 2144.5036,
325
+ "eval_samples_per_second": 15.443,
326
+ "eval_steps_per_second": 0.965,
327
+ "step": 24000
328
+ },
329
+ {
330
+ "epoch": 1.48,
331
+ "learning_rate": 4.2602210278398457e-05,
332
+ "loss": 0.7292,
333
+ "step": 24500
334
+ },
335
+ {
336
+ "epoch": 1.51,
337
+ "learning_rate": 4.245123497795761e-05,
338
+ "loss": 0.7363,
339
+ "step": 25000
340
+ },
341
+ {
342
+ "epoch": 1.54,
343
+ "learning_rate": 4.2300259677516765e-05,
344
+ "loss": 0.7261,
345
+ "step": 25500
346
+ },
347
+ {
348
+ "epoch": 1.57,
349
+ "learning_rate": 4.2149284377075916e-05,
350
+ "loss": 0.7214,
351
+ "step": 26000
352
+ },
353
+ {
354
+ "epoch": 1.6,
355
+ "learning_rate": 4.199830907663506e-05,
356
+ "loss": 0.7077,
357
+ "step": 26500
358
+ },
359
+ {
360
+ "epoch": 1.63,
361
+ "learning_rate": 4.184733377619421e-05,
362
+ "loss": 0.724,
363
+ "step": 27000
364
+ },
365
+ {
366
+ "epoch": 1.66,
367
+ "learning_rate": 4.169635847575337e-05,
368
+ "loss": 0.7286,
369
+ "step": 27500
370
+ },
371
+ {
372
+ "epoch": 1.69,
373
+ "learning_rate": 4.154538317531252e-05,
374
+ "loss": 0.7224,
375
+ "step": 28000
376
+ },
377
+ {
378
+ "epoch": 1.72,
379
+ "learning_rate": 4.139440787487167e-05,
380
+ "loss": 0.7194,
381
+ "step": 28500
382
+ },
383
+ {
384
+ "epoch": 1.75,
385
+ "learning_rate": 4.124343257443082e-05,
386
+ "loss": 0.7095,
387
+ "step": 29000
388
+ },
389
+ {
390
+ "epoch": 1.78,
391
+ "learning_rate": 4.1092457273989973e-05,
392
+ "loss": 0.7065,
393
+ "step": 29500
394
+ },
395
+ {
396
+ "epoch": 1.81,
397
+ "learning_rate": 4.094148197354913e-05,
398
+ "loss": 0.7012,
399
+ "step": 30000
400
+ },
401
+ {
402
+ "epoch": 1.84,
403
+ "learning_rate": 4.079050667310828e-05,
404
+ "loss": 0.7045,
405
+ "step": 30500
406
+ },
407
+ {
408
+ "epoch": 1.87,
409
+ "learning_rate": 4.063953137266743e-05,
410
+ "loss": 0.7099,
411
+ "step": 31000
412
+ },
413
+ {
414
+ "epoch": 1.9,
415
+ "learning_rate": 4.0488556072226584e-05,
416
+ "loss": 0.7084,
417
+ "step": 31500
418
+ },
419
+ {
420
+ "epoch": 1.93,
421
+ "learning_rate": 4.0337580771785735e-05,
422
+ "loss": 0.7039,
423
+ "step": 32000
424
+ },
425
+ {
426
+ "epoch": 1.93,
427
+ "eval_bleu": 8.9198,
428
+ "eval_gen_len": 17.8841,
429
+ "eval_loss": 0.9008079171180725,
430
+ "eval_runtime": 2125.9264,
431
+ "eval_samples_per_second": 15.578,
432
+ "eval_steps_per_second": 0.974,
433
+ "step": 32000
434
+ },
435
+ {
436
+ "epoch": 1.96,
437
+ "learning_rate": 4.018660547134489e-05,
438
+ "loss": 0.7029,
439
+ "step": 32500
440
+ },
441
+ {
442
+ "epoch": 1.99,
443
+ "learning_rate": 4.0035630170904044e-05,
444
+ "loss": 0.6983,
445
+ "step": 33000
446
+ },
447
+ {
448
+ "epoch": 2.02,
449
+ "learning_rate": 3.9884654870463195e-05,
450
+ "loss": 0.6503,
451
+ "step": 33500
452
+ },
453
+ {
454
+ "epoch": 2.05,
455
+ "learning_rate": 3.9733679570022346e-05,
456
+ "loss": 0.6191,
457
+ "step": 34000
458
+ },
459
+ {
460
+ "epoch": 2.08,
461
+ "learning_rate": 3.95827042695815e-05,
462
+ "loss": 0.605,
463
+ "step": 34500
464
+ },
465
+ {
466
+ "epoch": 2.11,
467
+ "learning_rate": 3.9431728969140655e-05,
468
+ "loss": 0.6035,
469
+ "step": 35000
470
+ },
471
+ {
472
+ "epoch": 2.14,
473
+ "learning_rate": 3.9280753668699806e-05,
474
+ "loss": 0.6008,
475
+ "step": 35500
476
+ },
477
+ {
478
+ "epoch": 2.17,
479
+ "learning_rate": 3.912977836825896e-05,
480
+ "loss": 0.5947,
481
+ "step": 36000
482
+ },
483
+ {
484
+ "epoch": 2.2,
485
+ "learning_rate": 3.897880306781811e-05,
486
+ "loss": 0.5812,
487
+ "step": 36500
488
+ },
489
+ {
490
+ "epoch": 2.23,
491
+ "learning_rate": 3.882782776737726e-05,
492
+ "loss": 0.587,
493
+ "step": 37000
494
+ },
495
+ {
496
+ "epoch": 2.26,
497
+ "learning_rate": 3.867685246693641e-05,
498
+ "loss": 0.5857,
499
+ "step": 37500
500
+ },
501
+ {
502
+ "epoch": 2.29,
503
+ "learning_rate": 3.852587716649556e-05,
504
+ "loss": 0.5659,
505
+ "step": 38000
506
+ },
507
+ {
508
+ "epoch": 2.32,
509
+ "learning_rate": 3.837490186605471e-05,
510
+ "loss": 0.5702,
511
+ "step": 38500
512
+ },
513
+ {
514
+ "epoch": 2.36,
515
+ "learning_rate": 3.822392656561386e-05,
516
+ "loss": 0.5651,
517
+ "step": 39000
518
+ },
519
+ {
520
+ "epoch": 2.39,
521
+ "learning_rate": 3.807295126517302e-05,
522
+ "loss": 0.5691,
523
+ "step": 39500
524
+ },
525
+ {
526
+ "epoch": 2.42,
527
+ "learning_rate": 3.792197596473217e-05,
528
+ "loss": 0.5616,
529
+ "step": 40000
530
+ },
531
+ {
532
+ "epoch": 2.42,
533
+ "eval_bleu": 8.7938,
534
+ "eval_gen_len": 17.78,
535
+ "eval_loss": 0.9209699630737305,
536
+ "eval_runtime": 2116.9975,
537
+ "eval_samples_per_second": 15.644,
538
+ "eval_steps_per_second": 0.978,
539
+ "step": 40000
540
+ },
541
+ {
542
+ "epoch": 2.45,
543
+ "learning_rate": 3.777100066429132e-05,
544
+ "loss": 0.5552,
545
+ "step": 40500
546
+ },
547
+ {
548
+ "epoch": 2.48,
549
+ "learning_rate": 3.7620025363850474e-05,
550
+ "loss": 0.5461,
551
+ "step": 41000
552
+ },
553
+ {
554
+ "epoch": 2.51,
555
+ "learning_rate": 3.7469050063409625e-05,
556
+ "loss": 0.5546,
557
+ "step": 41500
558
+ },
559
+ {
560
+ "epoch": 2.54,
561
+ "learning_rate": 3.731807476296878e-05,
562
+ "loss": 0.5383,
563
+ "step": 42000
564
+ },
565
+ {
566
+ "epoch": 2.57,
567
+ "learning_rate": 3.7167099462527934e-05,
568
+ "loss": 0.5452,
569
+ "step": 42500
570
+ },
571
+ {
572
+ "epoch": 2.6,
573
+ "learning_rate": 3.7016124162087085e-05,
574
+ "loss": 0.5318,
575
+ "step": 43000
576
+ },
577
+ {
578
+ "epoch": 2.63,
579
+ "learning_rate": 3.6865148861646236e-05,
580
+ "loss": 0.5407,
581
+ "step": 43500
582
+ },
583
+ {
584
+ "epoch": 2.66,
585
+ "learning_rate": 3.671417356120539e-05,
586
+ "loss": 0.549,
587
+ "step": 44000
588
+ },
589
+ {
590
+ "epoch": 2.69,
591
+ "learning_rate": 3.6563198260764545e-05,
592
+ "loss": 0.5384,
593
+ "step": 44500
594
+ },
595
+ {
596
+ "epoch": 2.72,
597
+ "learning_rate": 3.6412222960323696e-05,
598
+ "loss": 0.5441,
599
+ "step": 45000
600
+ },
601
+ {
602
+ "epoch": 2.75,
603
+ "learning_rate": 3.626124765988285e-05,
604
+ "loss": 0.5317,
605
+ "step": 45500
606
+ },
607
+ {
608
+ "epoch": 2.78,
609
+ "learning_rate": 3.6110272359442e-05,
610
+ "loss": 0.5352,
611
+ "step": 46000
612
+ },
613
+ {
614
+ "epoch": 2.81,
615
+ "learning_rate": 3.595929705900115e-05,
616
+ "loss": 0.5248,
617
+ "step": 46500
618
+ },
619
+ {
620
+ "epoch": 2.84,
621
+ "learning_rate": 3.5808321758560307e-05,
622
+ "loss": 0.5309,
623
+ "step": 47000
624
+ },
625
+ {
626
+ "epoch": 2.87,
627
+ "learning_rate": 3.565734645811946e-05,
628
+ "loss": 0.5296,
629
+ "step": 47500
630
+ },
631
+ {
632
+ "epoch": 2.9,
633
+ "learning_rate": 3.55063711576786e-05,
634
+ "loss": 0.5355,
635
+ "step": 48000
636
+ },
637
+ {
638
+ "epoch": 2.9,
639
+ "eval_bleu": 8.6506,
640
+ "eval_gen_len": 17.9146,
641
+ "eval_loss": 0.9399827122688293,
642
+ "eval_runtime": 2117.673,
643
+ "eval_samples_per_second": 15.639,
644
+ "eval_steps_per_second": 0.977,
645
+ "step": 48000
646
+ },
647
+ {
648
+ "epoch": 2.93,
649
+ "learning_rate": 3.535539585723775e-05,
650
+ "loss": 0.5262,
651
+ "step": 48500
652
+ },
653
+ {
654
+ "epoch": 2.96,
655
+ "learning_rate": 3.520442055679691e-05,
656
+ "loss": 0.5247,
657
+ "step": 49000
658
+ },
659
+ {
660
+ "epoch": 2.99,
661
+ "learning_rate": 3.505344525635606e-05,
662
+ "loss": 0.5315,
663
+ "step": 49500
664
+ },
665
+ {
666
+ "epoch": 3.02,
667
+ "learning_rate": 3.490246995591521e-05,
668
+ "loss": 0.4932,
669
+ "step": 50000
670
+ },
671
+ {
672
+ "epoch": 3.05,
673
+ "learning_rate": 3.4751494655474364e-05,
674
+ "loss": 0.4595,
675
+ "step": 50500
676
+ },
677
+ {
678
+ "epoch": 3.08,
679
+ "learning_rate": 3.4600519355033515e-05,
680
+ "loss": 0.45,
681
+ "step": 51000
682
+ },
683
+ {
684
+ "epoch": 3.11,
685
+ "learning_rate": 3.444954405459267e-05,
686
+ "loss": 0.4477,
687
+ "step": 51500
688
+ },
689
+ {
690
+ "epoch": 3.14,
691
+ "learning_rate": 3.4298568754151824e-05,
692
+ "loss": 0.4423,
693
+ "step": 52000
694
+ },
695
+ {
696
+ "epoch": 3.17,
697
+ "learning_rate": 3.4147593453710975e-05,
698
+ "loss": 0.435,
699
+ "step": 52500
700
+ },
701
+ {
702
+ "epoch": 3.2,
703
+ "learning_rate": 3.3996618153270126e-05,
704
+ "loss": 0.4345,
705
+ "step": 53000
706
+ },
707
+ {
708
+ "epoch": 3.23,
709
+ "learning_rate": 3.3845642852829277e-05,
710
+ "loss": 0.4337,
711
+ "step": 53500
712
+ },
713
+ {
714
+ "epoch": 3.26,
715
+ "learning_rate": 3.3694667552388434e-05,
716
+ "loss": 0.4295,
717
+ "step": 54000
718
+ },
719
+ {
720
+ "epoch": 3.29,
721
+ "learning_rate": 3.3543692251947585e-05,
722
+ "loss": 0.4143,
723
+ "step": 54500
724
+ },
725
+ {
726
+ "epoch": 3.32,
727
+ "learning_rate": 3.3392716951506736e-05,
728
+ "loss": 0.4203,
729
+ "step": 55000
730
+ },
731
+ {
732
+ "epoch": 3.35,
733
+ "learning_rate": 3.324174165106589e-05,
734
+ "loss": 0.4164,
735
+ "step": 55500
736
+ },
737
+ {
738
+ "epoch": 3.38,
739
+ "learning_rate": 3.309076635062504e-05,
740
+ "loss": 0.4194,
741
+ "step": 56000
742
+ },
743
+ {
744
+ "epoch": 3.38,
745
+ "eval_bleu": 8.4235,
746
+ "eval_gen_len": 17.6759,
747
+ "eval_loss": 1.0053656101226807,
748
+ "eval_runtime": 2100.231,
749
+ "eval_samples_per_second": 15.769,
750
+ "eval_steps_per_second": 0.986,
751
+ "step": 56000
752
+ },
753
+ {
754
+ "epoch": 3.41,
755
+ "learning_rate": 3.2939791050184196e-05,
756
+ "loss": 0.4132,
757
+ "step": 56500
758
+ },
759
+ {
760
+ "epoch": 3.44,
761
+ "learning_rate": 3.278881574974335e-05,
762
+ "loss": 0.4118,
763
+ "step": 57000
764
+ },
765
+ {
766
+ "epoch": 3.47,
767
+ "learning_rate": 3.26378404493025e-05,
768
+ "loss": 0.3997,
769
+ "step": 57500
770
+ },
771
+ {
772
+ "epoch": 3.5,
773
+ "learning_rate": 3.248686514886165e-05,
774
+ "loss": 0.4088,
775
+ "step": 58000
776
+ },
777
+ {
778
+ "epoch": 3.53,
779
+ "learning_rate": 3.23358898484208e-05,
780
+ "loss": 0.3937,
781
+ "step": 58500
782
+ },
783
+ {
784
+ "epoch": 3.56,
785
+ "learning_rate": 3.218491454797995e-05,
786
+ "loss": 0.4001,
787
+ "step": 59000
788
+ },
789
+ {
790
+ "epoch": 3.59,
791
+ "learning_rate": 3.20339392475391e-05,
792
+ "loss": 0.3933,
793
+ "step": 59500
794
+ },
795
+ {
796
+ "epoch": 3.62,
797
+ "learning_rate": 3.1882963947098253e-05,
798
+ "loss": 0.3973,
799
+ "step": 60000
800
+ },
801
+ {
802
+ "epoch": 3.65,
803
+ "learning_rate": 3.1731988646657404e-05,
804
+ "loss": 0.4039,
805
+ "step": 60500
806
+ },
807
+ {
808
+ "epoch": 3.68,
809
+ "learning_rate": 3.158101334621656e-05,
810
+ "loss": 0.3913,
811
+ "step": 61000
812
+ },
813
+ {
814
+ "epoch": 3.71,
815
+ "learning_rate": 3.143003804577571e-05,
816
+ "loss": 0.3998,
817
+ "step": 61500
818
+ },
819
+ {
820
+ "epoch": 3.74,
821
+ "learning_rate": 3.1279062745334864e-05,
822
+ "loss": 0.392,
823
+ "step": 62000
824
+ },
825
+ {
826
+ "epoch": 3.77,
827
+ "learning_rate": 3.1128087444894015e-05,
828
+ "loss": 0.3931,
829
+ "step": 62500
830
+ },
831
+ {
832
+ "epoch": 3.8,
833
+ "learning_rate": 3.0977112144453166e-05,
834
+ "loss": 0.3859,
835
+ "step": 63000
836
+ },
837
+ {
838
+ "epoch": 3.83,
839
+ "learning_rate": 3.0826136844012324e-05,
840
+ "loss": 0.3826,
841
+ "step": 63500
842
+ },
843
+ {
844
+ "epoch": 3.86,
845
+ "learning_rate": 3.0675161543571475e-05,
846
+ "loss": 0.3852,
847
+ "step": 64000
848
+ },
849
+ {
850
+ "epoch": 3.86,
851
+ "eval_bleu": 8.5886,
852
+ "eval_gen_len": 17.7885,
853
+ "eval_loss": 1.0153683423995972,
854
+ "eval_runtime": 2110.3892,
855
+ "eval_samples_per_second": 15.693,
856
+ "eval_steps_per_second": 0.981,
857
+ "step": 64000
858
+ }
859
+ ],
860
+ "logging_steps": 500,
861
+ "max_steps": 165590,
862
+ "num_train_epochs": 10,
863
+ "save_steps": 8000,
864
+ "total_flos": 2.2192449043268895e+18,
865
+ "trial_name": null,
866
+ "trial_params": null
867
+ }
checkpoint-64000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2375b9520792a916e970310a134c4b72d4500b7fe94384774f1d61421a8a22ea
3
+ size 4728
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": true,
8
+ "architectures": [
9
+ "MBartForConditionalGeneration"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 1024,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 4096,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 12,
20
+ "decoder_start_token_id": 2,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 2,
28
+ "forced_bos_token_id": 250012,
29
+ "forced_eos_token_id": 2,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "max_length": 200,
44
+ "max_position_embeddings": 1024,
45
+ "model_type": "mbart",
46
+ "normalize_before": true,
47
+ "normalize_embedding": true,
48
+ "num_beams": 5,
49
+ "num_hidden_layers": 12,
50
+ "output_past": true,
51
+ "pad_token_id": 1,
52
+ "scale_embedding": true,
53
+ "static_position_embeddings": false,
54
+ "tokenizer_class": "MBart50Tokenizer",
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.34.1",
57
+ "use_cache": true,
58
+ "vocab_size": 250054
59
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.86,
3
+ "eval_bleu": 8.9861,
4
+ "eval_gen_len": 17.9149,
5
+ "eval_loss": 0.9008079171180725,
6
+ "eval_runtime": 1886.4166,
7
+ "eval_samples": 33118,
8
+ "eval_samples_per_second": 17.556,
9
+ "eval_steps_per_second": 1.097
10
+ }