yesj1234 commited on
Commit
e818adf
1 Parent(s): 44043f6

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 +73 -0
  3. all_results.json +22 -0
  4. checkpoint-22708/config.json +59 -0
  5. checkpoint-22708/generation_config.json +12 -0
  6. checkpoint-22708/optimizer.pt +3 -0
  7. checkpoint-22708/pytorch_model.bin +3 -0
  8. checkpoint-22708/rng_state_0.pth +3 -0
  9. checkpoint-22708/rng_state_1.pth +3 -0
  10. checkpoint-22708/rng_state_2.pth +3 -0
  11. checkpoint-22708/rng_state_3.pth +3 -0
  12. checkpoint-22708/scheduler.pt +3 -0
  13. checkpoint-22708/sentencepiece.bpe.model +3 -0
  14. checkpoint-22708/special_tokens_map.json +69 -0
  15. checkpoint-22708/tokenizer.json +3 -0
  16. checkpoint-22708/tokenizer_config.json +528 -0
  17. checkpoint-22708/trainer_state.json +309 -0
  18. checkpoint-22708/training_args.bin +3 -0
  19. checkpoint-56770/config.json +59 -0
  20. checkpoint-56770/generation_config.json +12 -0
  21. checkpoint-56770/optimizer.pt +3 -0
  22. checkpoint-56770/pytorch_model.bin +3 -0
  23. checkpoint-56770/rng_state_0.pth +3 -0
  24. checkpoint-56770/rng_state_1.pth +3 -0
  25. checkpoint-56770/rng_state_2.pth +3 -0
  26. checkpoint-56770/rng_state_3.pth +3 -0
  27. checkpoint-56770/scheduler.pt +3 -0
  28. checkpoint-56770/sentencepiece.bpe.model +3 -0
  29. checkpoint-56770/special_tokens_map.json +69 -0
  30. checkpoint-56770/tokenizer.json +3 -0
  31. checkpoint-56770/tokenizer_config.json +528 -0
  32. checkpoint-56770/trainer_state.json +747 -0
  33. checkpoint-56770/training_args.bin +3 -0
  34. checkpoint-68124/config.json +59 -0
  35. checkpoint-68124/generation_config.json +12 -0
  36. checkpoint-68124/optimizer.pt +3 -0
  37. checkpoint-68124/pytorch_model.bin +3 -0
  38. checkpoint-68124/rng_state_0.pth +3 -0
  39. checkpoint-68124/rng_state_1.pth +3 -0
  40. checkpoint-68124/rng_state_2.pth +3 -0
  41. checkpoint-68124/rng_state_3.pth +3 -0
  42. checkpoint-68124/scheduler.pt +3 -0
  43. checkpoint-68124/sentencepiece.bpe.model +3 -0
  44. checkpoint-68124/special_tokens_map.json +69 -0
  45. checkpoint-68124/tokenizer.json +3 -0
  46. checkpoint-68124/tokenizer_config.json +528 -0
  47. checkpoint-68124/trainer_state.json +895 -0
  48. checkpoint-68124/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-22708/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-56770/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-68124/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: mbartLarge_koja_mid2_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
+ # mbartLarge_koja_mid2_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: 1.1251
23
+ - Bleu: 30.7351
24
+ - Gen Len: 18.1559
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
+ | 1.1823 | 1.0 | 11354 | 1.1695 | 29.4501 | 18.8118 |
61
+ | 0.9207 | 2.0 | 22708 | 1.1251 | 30.842 | 18.0892 |
62
+ | 0.7127 | 3.0 | 34062 | 1.1687 | 31.2642 | 18.1188 |
63
+ | 0.5406 | 4.0 | 45416 | 1.2619 | 30.9531 | 17.9958 |
64
+ | 0.4027 | 5.0 | 56770 | 1.3789 | 30.7923 | 18.0582 |
65
+ | 0.286 | 6.0 | 68124 | 1.4784 | 30.9393 | 18.1183 |
66
+
67
+
68
+ ### Framework versions
69
+
70
+ - Transformers 4.34.1
71
+ - Pytorch 2.1.0+cu121
72
+ - Datasets 2.14.6
73
+ - Tokenizers 0.14.1
all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.0,
3
+ "eval_bleu": 30.7351,
4
+ "eval_gen_len": 18.1559,
5
+ "eval_loss": 1.1251049041748047,
6
+ "eval_runtime": 1367.4753,
7
+ "eval_samples": 22707,
8
+ "eval_samples_per_second": 16.605,
9
+ "eval_steps_per_second": 1.038,
10
+ "predict_bleu": 30.2762,
11
+ "predict_gen_len": 18.1178,
12
+ "predict_loss": 1.1167916059494019,
13
+ "predict_runtime": 1359.8349,
14
+ "predict_samples": 22707,
15
+ "predict_samples_per_second": 16.698,
16
+ "predict_steps_per_second": 1.044,
17
+ "train_loss": 0.7323888317612346,
18
+ "train_runtime": 87093.7472,
19
+ "train_samples": 181661,
20
+ "train_samples_per_second": 20.858,
21
+ "train_steps_per_second": 1.304
22
+ }
checkpoint-22708/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-22708/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-22708/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7f259e06d682d02804756a323d31695aa78946a124c5985f124213eafc1bd0a
3
+ size 4887473903
checkpoint-22708/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38cca4711d49275274bdb2051e8192a69feb86ab3af1a6f8a87d012006bfd312
3
+ size 2444694490
checkpoint-22708/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:144abaa2500fc08e72d553b6980a0f9a4031ca6b5db42a79d9c8474361a9a38b
3
+ size 15024
checkpoint-22708/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d96ed7ed40bcff76153cafc32dec1d57131d3fe9a95b3ece933585f4bf7e5972
3
+ size 15024
checkpoint-22708/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fd0320f8433fa49b581a0cdecf727b9da68373526aedfd6827d9535a2decb0d
3
+ size 15024
checkpoint-22708/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6505c5a0317b59bc35c4f3c690ecd518a56ab512bd51187a7a60ee126211be6f
3
+ size 15024
checkpoint-22708/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98b9e9546f78cb2f67934e1d5f68b8a5d57bc647d90e5426d767601e5ca4c549
3
+ size 1064
checkpoint-22708/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-22708/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-22708/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fc2a9a463953c664738ef8571ed97361b8de258b2aca93c0214a89676a73379
3
+ size 17110043
checkpoint-22708/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-22708/trainer_state.json ADDED
@@ -0,0 +1,309 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.1251049041748047,
3
+ "best_model_checkpoint": "./mbartLarge_koja_mid2_run1/checkpoint-22708",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 22708,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04,
13
+ "learning_rate": 4.977981328166285e-05,
14
+ "loss": 1.9241,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.09,
19
+ "learning_rate": 4.95596265633257e-05,
20
+ "loss": 1.6494,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.13,
25
+ "learning_rate": 4.933943984498855e-05,
26
+ "loss": 1.5434,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.18,
31
+ "learning_rate": 4.91192531266514e-05,
32
+ "loss": 1.4836,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.22,
37
+ "learning_rate": 4.889906640831425e-05,
38
+ "loss": 1.4499,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.26,
43
+ "learning_rate": 4.86788796899771e-05,
44
+ "loss": 1.3934,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.31,
49
+ "learning_rate": 4.845869297163995e-05,
50
+ "loss": 1.3857,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.35,
55
+ "learning_rate": 4.82385062533028e-05,
56
+ "loss": 1.3396,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.4,
61
+ "learning_rate": 4.801831953496565e-05,
62
+ "loss": 1.3322,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.44,
67
+ "learning_rate": 4.77981328166285e-05,
68
+ "loss": 1.3106,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.48,
73
+ "learning_rate": 4.757794609829135e-05,
74
+ "loss": 1.2924,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 0.53,
79
+ "learning_rate": 4.73577593799542e-05,
80
+ "loss": 1.2834,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 0.57,
85
+ "learning_rate": 4.713757266161705e-05,
86
+ "loss": 1.2791,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 0.62,
91
+ "learning_rate": 4.69173859432799e-05,
92
+ "loss": 1.255,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 0.66,
97
+ "learning_rate": 4.669719922494275e-05,
98
+ "loss": 1.2573,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 0.7,
103
+ "learning_rate": 4.64770125066056e-05,
104
+ "loss": 1.2382,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 0.75,
109
+ "learning_rate": 4.625682578826845e-05,
110
+ "loss": 1.223,
111
+ "step": 8500
112
+ },
113
+ {
114
+ "epoch": 0.79,
115
+ "learning_rate": 4.6036639069931303e-05,
116
+ "loss": 1.2145,
117
+ "step": 9000
118
+ },
119
+ {
120
+ "epoch": 0.84,
121
+ "learning_rate": 4.5816452351594153e-05,
122
+ "loss": 1.219,
123
+ "step": 9500
124
+ },
125
+ {
126
+ "epoch": 0.88,
127
+ "learning_rate": 4.5596265633257004e-05,
128
+ "loss": 1.2125,
129
+ "step": 10000
130
+ },
131
+ {
132
+ "epoch": 0.92,
133
+ "learning_rate": 4.5376078914919854e-05,
134
+ "loss": 1.1996,
135
+ "step": 10500
136
+ },
137
+ {
138
+ "epoch": 0.97,
139
+ "learning_rate": 4.5155892196582704e-05,
140
+ "loss": 1.1823,
141
+ "step": 11000
142
+ },
143
+ {
144
+ "epoch": 1.0,
145
+ "eval_bleu": 29.4501,
146
+ "eval_gen_len": 18.8118,
147
+ "eval_loss": 1.1695398092269897,
148
+ "eval_runtime": 1716.1373,
149
+ "eval_samples_per_second": 13.231,
150
+ "eval_steps_per_second": 0.827,
151
+ "step": 11354
152
+ },
153
+ {
154
+ "epoch": 1.01,
155
+ "learning_rate": 4.4935705478245554e-05,
156
+ "loss": 1.1596,
157
+ "step": 11500
158
+ },
159
+ {
160
+ "epoch": 1.06,
161
+ "learning_rate": 4.4715518759908404e-05,
162
+ "loss": 1.0777,
163
+ "step": 12000
164
+ },
165
+ {
166
+ "epoch": 1.1,
167
+ "learning_rate": 4.4495332041571254e-05,
168
+ "loss": 1.0658,
169
+ "step": 12500
170
+ },
171
+ {
172
+ "epoch": 1.14,
173
+ "learning_rate": 4.427514532323411e-05,
174
+ "loss": 1.0296,
175
+ "step": 13000
176
+ },
177
+ {
178
+ "epoch": 1.19,
179
+ "learning_rate": 4.4054958604896954e-05,
180
+ "loss": 1.0269,
181
+ "step": 13500
182
+ },
183
+ {
184
+ "epoch": 1.23,
185
+ "learning_rate": 4.3834771886559804e-05,
186
+ "loss": 1.0192,
187
+ "step": 14000
188
+ },
189
+ {
190
+ "epoch": 1.28,
191
+ "learning_rate": 4.3614585168222654e-05,
192
+ "loss": 0.9946,
193
+ "step": 14500
194
+ },
195
+ {
196
+ "epoch": 1.32,
197
+ "learning_rate": 4.3394398449885504e-05,
198
+ "loss": 0.9996,
199
+ "step": 15000
200
+ },
201
+ {
202
+ "epoch": 1.37,
203
+ "learning_rate": 4.3174211731548354e-05,
204
+ "loss": 0.975,
205
+ "step": 15500
206
+ },
207
+ {
208
+ "epoch": 1.41,
209
+ "learning_rate": 4.295402501321121e-05,
210
+ "loss": 0.9874,
211
+ "step": 16000
212
+ },
213
+ {
214
+ "epoch": 1.45,
215
+ "learning_rate": 4.2733838294874054e-05,
216
+ "loss": 0.9683,
217
+ "step": 16500
218
+ },
219
+ {
220
+ "epoch": 1.5,
221
+ "learning_rate": 4.2513651576536904e-05,
222
+ "loss": 0.9675,
223
+ "step": 17000
224
+ },
225
+ {
226
+ "epoch": 1.54,
227
+ "learning_rate": 4.2293464858199754e-05,
228
+ "loss": 0.969,
229
+ "step": 17500
230
+ },
231
+ {
232
+ "epoch": 1.59,
233
+ "learning_rate": 4.2073278139862604e-05,
234
+ "loss": 0.9548,
235
+ "step": 18000
236
+ },
237
+ {
238
+ "epoch": 1.63,
239
+ "learning_rate": 4.1853091421525454e-05,
240
+ "loss": 0.9563,
241
+ "step": 18500
242
+ },
243
+ {
244
+ "epoch": 1.67,
245
+ "learning_rate": 4.163290470318831e-05,
246
+ "loss": 0.9536,
247
+ "step": 19000
248
+ },
249
+ {
250
+ "epoch": 1.72,
251
+ "learning_rate": 4.1412717984851155e-05,
252
+ "loss": 0.941,
253
+ "step": 19500
254
+ },
255
+ {
256
+ "epoch": 1.76,
257
+ "learning_rate": 4.1192531266514005e-05,
258
+ "loss": 0.9285,
259
+ "step": 20000
260
+ },
261
+ {
262
+ "epoch": 1.81,
263
+ "learning_rate": 4.0972344548176855e-05,
264
+ "loss": 0.9303,
265
+ "step": 20500
266
+ },
267
+ {
268
+ "epoch": 1.85,
269
+ "learning_rate": 4.0752157829839705e-05,
270
+ "loss": 0.9428,
271
+ "step": 21000
272
+ },
273
+ {
274
+ "epoch": 1.89,
275
+ "learning_rate": 4.0531971111502555e-05,
276
+ "loss": 0.9359,
277
+ "step": 21500
278
+ },
279
+ {
280
+ "epoch": 1.94,
281
+ "learning_rate": 4.031178439316541e-05,
282
+ "loss": 0.9302,
283
+ "step": 22000
284
+ },
285
+ {
286
+ "epoch": 1.98,
287
+ "learning_rate": 4.0091597674828255e-05,
288
+ "loss": 0.9207,
289
+ "step": 22500
290
+ },
291
+ {
292
+ "epoch": 2.0,
293
+ "eval_bleu": 30.842,
294
+ "eval_gen_len": 18.0892,
295
+ "eval_loss": 1.1251049041748047,
296
+ "eval_runtime": 1535.7063,
297
+ "eval_samples_per_second": 14.786,
298
+ "eval_steps_per_second": 0.925,
299
+ "step": 22708
300
+ }
301
+ ],
302
+ "logging_steps": 500,
303
+ "max_steps": 113540,
304
+ "num_train_epochs": 10,
305
+ "save_steps": 500,
306
+ "total_flos": 7.874829468219474e+17,
307
+ "trial_name": null,
308
+ "trial_params": null
309
+ }
checkpoint-22708/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9db9168480a6c0a1a80baf9aa7bf4344735c517df328c25f6d3bd3a09bdcb88
3
+ size 4728
checkpoint-56770/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-56770/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-56770/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec671f9b6adf657947534ab036d17b96adec70e0911c65c40a8cdbd5220f3800
3
+ size 4887473903
checkpoint-56770/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c1378c5cbd1e953947b4698ee68d7c20c1c38daec0436202d9ad987fbf8fc07
3
+ size 2444694490
checkpoint-56770/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a15d133a658da31f7f4a096e824c6e92867b1d4cfa3937fb9ca675521a9dd2d
3
+ size 15024
checkpoint-56770/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd44e58072aa35bbc11bf5a50d9cf7e027612baa5b5c7829c92714dca4b387dc
3
+ size 15024
checkpoint-56770/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60d1918d0402a7c92691b2348301f678f63a9640fa75a2de8403f47faba2144
3
+ size 15024
checkpoint-56770/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e49d600dc2b3715e36d947333e54e9956575ab57f404254b11957697a8b64c27
3
+ size 15024
checkpoint-56770/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dbdd8bbc1f69e07c96a6fb36413467831131151ec3b4960bce1f24256e32e35
3
+ size 1064
checkpoint-56770/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-56770/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-56770/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fc2a9a463953c664738ef8571ed97361b8de258b2aca93c0214a89676a73379
3
+ size 17110043
checkpoint-56770/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-56770/trainer_state.json ADDED
@@ -0,0 +1,747 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.1251049041748047,
3
+ "best_model_checkpoint": "./mbartLarge_koja_mid2_run1/checkpoint-22708",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 56770,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04,
13
+ "learning_rate": 4.977981328166285e-05,
14
+ "loss": 1.9241,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.09,
19
+ "learning_rate": 4.95596265633257e-05,
20
+ "loss": 1.6494,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.13,
25
+ "learning_rate": 4.933943984498855e-05,
26
+ "loss": 1.5434,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.18,
31
+ "learning_rate": 4.91192531266514e-05,
32
+ "loss": 1.4836,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.22,
37
+ "learning_rate": 4.889906640831425e-05,
38
+ "loss": 1.4499,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.26,
43
+ "learning_rate": 4.86788796899771e-05,
44
+ "loss": 1.3934,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.31,
49
+ "learning_rate": 4.845869297163995e-05,
50
+ "loss": 1.3857,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.35,
55
+ "learning_rate": 4.82385062533028e-05,
56
+ "loss": 1.3396,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.4,
61
+ "learning_rate": 4.801831953496565e-05,
62
+ "loss": 1.3322,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.44,
67
+ "learning_rate": 4.77981328166285e-05,
68
+ "loss": 1.3106,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.48,
73
+ "learning_rate": 4.757794609829135e-05,
74
+ "loss": 1.2924,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 0.53,
79
+ "learning_rate": 4.73577593799542e-05,
80
+ "loss": 1.2834,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 0.57,
85
+ "learning_rate": 4.713757266161705e-05,
86
+ "loss": 1.2791,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 0.62,
91
+ "learning_rate": 4.69173859432799e-05,
92
+ "loss": 1.255,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 0.66,
97
+ "learning_rate": 4.669719922494275e-05,
98
+ "loss": 1.2573,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 0.7,
103
+ "learning_rate": 4.64770125066056e-05,
104
+ "loss": 1.2382,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 0.75,
109
+ "learning_rate": 4.625682578826845e-05,
110
+ "loss": 1.223,
111
+ "step": 8500
112
+ },
113
+ {
114
+ "epoch": 0.79,
115
+ "learning_rate": 4.6036639069931303e-05,
116
+ "loss": 1.2145,
117
+ "step": 9000
118
+ },
119
+ {
120
+ "epoch": 0.84,
121
+ "learning_rate": 4.5816452351594153e-05,
122
+ "loss": 1.219,
123
+ "step": 9500
124
+ },
125
+ {
126
+ "epoch": 0.88,
127
+ "learning_rate": 4.5596265633257004e-05,
128
+ "loss": 1.2125,
129
+ "step": 10000
130
+ },
131
+ {
132
+ "epoch": 0.92,
133
+ "learning_rate": 4.5376078914919854e-05,
134
+ "loss": 1.1996,
135
+ "step": 10500
136
+ },
137
+ {
138
+ "epoch": 0.97,
139
+ "learning_rate": 4.5155892196582704e-05,
140
+ "loss": 1.1823,
141
+ "step": 11000
142
+ },
143
+ {
144
+ "epoch": 1.0,
145
+ "eval_bleu": 29.4501,
146
+ "eval_gen_len": 18.8118,
147
+ "eval_loss": 1.1695398092269897,
148
+ "eval_runtime": 1716.1373,
149
+ "eval_samples_per_second": 13.231,
150
+ "eval_steps_per_second": 0.827,
151
+ "step": 11354
152
+ },
153
+ {
154
+ "epoch": 1.01,
155
+ "learning_rate": 4.4935705478245554e-05,
156
+ "loss": 1.1596,
157
+ "step": 11500
158
+ },
159
+ {
160
+ "epoch": 1.06,
161
+ "learning_rate": 4.4715518759908404e-05,
162
+ "loss": 1.0777,
163
+ "step": 12000
164
+ },
165
+ {
166
+ "epoch": 1.1,
167
+ "learning_rate": 4.4495332041571254e-05,
168
+ "loss": 1.0658,
169
+ "step": 12500
170
+ },
171
+ {
172
+ "epoch": 1.14,
173
+ "learning_rate": 4.427514532323411e-05,
174
+ "loss": 1.0296,
175
+ "step": 13000
176
+ },
177
+ {
178
+ "epoch": 1.19,
179
+ "learning_rate": 4.4054958604896954e-05,
180
+ "loss": 1.0269,
181
+ "step": 13500
182
+ },
183
+ {
184
+ "epoch": 1.23,
185
+ "learning_rate": 4.3834771886559804e-05,
186
+ "loss": 1.0192,
187
+ "step": 14000
188
+ },
189
+ {
190
+ "epoch": 1.28,
191
+ "learning_rate": 4.3614585168222654e-05,
192
+ "loss": 0.9946,
193
+ "step": 14500
194
+ },
195
+ {
196
+ "epoch": 1.32,
197
+ "learning_rate": 4.3394398449885504e-05,
198
+ "loss": 0.9996,
199
+ "step": 15000
200
+ },
201
+ {
202
+ "epoch": 1.37,
203
+ "learning_rate": 4.3174211731548354e-05,
204
+ "loss": 0.975,
205
+ "step": 15500
206
+ },
207
+ {
208
+ "epoch": 1.41,
209
+ "learning_rate": 4.295402501321121e-05,
210
+ "loss": 0.9874,
211
+ "step": 16000
212
+ },
213
+ {
214
+ "epoch": 1.45,
215
+ "learning_rate": 4.2733838294874054e-05,
216
+ "loss": 0.9683,
217
+ "step": 16500
218
+ },
219
+ {
220
+ "epoch": 1.5,
221
+ "learning_rate": 4.2513651576536904e-05,
222
+ "loss": 0.9675,
223
+ "step": 17000
224
+ },
225
+ {
226
+ "epoch": 1.54,
227
+ "learning_rate": 4.2293464858199754e-05,
228
+ "loss": 0.969,
229
+ "step": 17500
230
+ },
231
+ {
232
+ "epoch": 1.59,
233
+ "learning_rate": 4.2073278139862604e-05,
234
+ "loss": 0.9548,
235
+ "step": 18000
236
+ },
237
+ {
238
+ "epoch": 1.63,
239
+ "learning_rate": 4.1853091421525454e-05,
240
+ "loss": 0.9563,
241
+ "step": 18500
242
+ },
243
+ {
244
+ "epoch": 1.67,
245
+ "learning_rate": 4.163290470318831e-05,
246
+ "loss": 0.9536,
247
+ "step": 19000
248
+ },
249
+ {
250
+ "epoch": 1.72,
251
+ "learning_rate": 4.1412717984851155e-05,
252
+ "loss": 0.941,
253
+ "step": 19500
254
+ },
255
+ {
256
+ "epoch": 1.76,
257
+ "learning_rate": 4.1192531266514005e-05,
258
+ "loss": 0.9285,
259
+ "step": 20000
260
+ },
261
+ {
262
+ "epoch": 1.81,
263
+ "learning_rate": 4.0972344548176855e-05,
264
+ "loss": 0.9303,
265
+ "step": 20500
266
+ },
267
+ {
268
+ "epoch": 1.85,
269
+ "learning_rate": 4.0752157829839705e-05,
270
+ "loss": 0.9428,
271
+ "step": 21000
272
+ },
273
+ {
274
+ "epoch": 1.89,
275
+ "learning_rate": 4.0531971111502555e-05,
276
+ "loss": 0.9359,
277
+ "step": 21500
278
+ },
279
+ {
280
+ "epoch": 1.94,
281
+ "learning_rate": 4.031178439316541e-05,
282
+ "loss": 0.9302,
283
+ "step": 22000
284
+ },
285
+ {
286
+ "epoch": 1.98,
287
+ "learning_rate": 4.0091597674828255e-05,
288
+ "loss": 0.9207,
289
+ "step": 22500
290
+ },
291
+ {
292
+ "epoch": 2.0,
293
+ "eval_bleu": 30.842,
294
+ "eval_gen_len": 18.0892,
295
+ "eval_loss": 1.1251049041748047,
296
+ "eval_runtime": 1535.7063,
297
+ "eval_samples_per_second": 14.786,
298
+ "eval_steps_per_second": 0.925,
299
+ "step": 22708
300
+ },
301
+ {
302
+ "epoch": 2.03,
303
+ "learning_rate": 3.9871410956491105e-05,
304
+ "loss": 0.8788,
305
+ "step": 23000
306
+ },
307
+ {
308
+ "epoch": 2.07,
309
+ "learning_rate": 3.9651224238153955e-05,
310
+ "loss": 0.8367,
311
+ "step": 23500
312
+ },
313
+ {
314
+ "epoch": 2.11,
315
+ "learning_rate": 3.9431037519816805e-05,
316
+ "loss": 0.8196,
317
+ "step": 24000
318
+ },
319
+ {
320
+ "epoch": 2.16,
321
+ "learning_rate": 3.921085080147966e-05,
322
+ "loss": 0.7967,
323
+ "step": 24500
324
+ },
325
+ {
326
+ "epoch": 2.2,
327
+ "learning_rate": 3.8990664083142505e-05,
328
+ "loss": 0.7956,
329
+ "step": 25000
330
+ },
331
+ {
332
+ "epoch": 2.25,
333
+ "learning_rate": 3.8770477364805355e-05,
334
+ "loss": 0.7843,
335
+ "step": 25500
336
+ },
337
+ {
338
+ "epoch": 2.29,
339
+ "learning_rate": 3.8550290646468205e-05,
340
+ "loss": 0.7767,
341
+ "step": 26000
342
+ },
343
+ {
344
+ "epoch": 2.33,
345
+ "learning_rate": 3.8330103928131055e-05,
346
+ "loss": 0.7668,
347
+ "step": 26500
348
+ },
349
+ {
350
+ "epoch": 2.38,
351
+ "learning_rate": 3.8109917209793905e-05,
352
+ "loss": 0.754,
353
+ "step": 27000
354
+ },
355
+ {
356
+ "epoch": 2.42,
357
+ "learning_rate": 3.788973049145676e-05,
358
+ "loss": 0.7671,
359
+ "step": 27500
360
+ },
361
+ {
362
+ "epoch": 2.47,
363
+ "learning_rate": 3.7669543773119605e-05,
364
+ "loss": 0.7569,
365
+ "step": 28000
366
+ },
367
+ {
368
+ "epoch": 2.51,
369
+ "learning_rate": 3.7449357054782456e-05,
370
+ "loss": 0.7553,
371
+ "step": 28500
372
+ },
373
+ {
374
+ "epoch": 2.55,
375
+ "learning_rate": 3.7229170336445306e-05,
376
+ "loss": 0.7526,
377
+ "step": 29000
378
+ },
379
+ {
380
+ "epoch": 2.6,
381
+ "learning_rate": 3.7008983618108156e-05,
382
+ "loss": 0.7427,
383
+ "step": 29500
384
+ },
385
+ {
386
+ "epoch": 2.64,
387
+ "learning_rate": 3.6788796899771006e-05,
388
+ "loss": 0.7407,
389
+ "step": 30000
390
+ },
391
+ {
392
+ "epoch": 2.69,
393
+ "learning_rate": 3.656861018143386e-05,
394
+ "loss": 0.7418,
395
+ "step": 30500
396
+ },
397
+ {
398
+ "epoch": 2.73,
399
+ "learning_rate": 3.6348423463096706e-05,
400
+ "loss": 0.7301,
401
+ "step": 31000
402
+ },
403
+ {
404
+ "epoch": 2.77,
405
+ "learning_rate": 3.6128236744759556e-05,
406
+ "loss": 0.7218,
407
+ "step": 31500
408
+ },
409
+ {
410
+ "epoch": 2.82,
411
+ "learning_rate": 3.5908050026422406e-05,
412
+ "loss": 0.7232,
413
+ "step": 32000
414
+ },
415
+ {
416
+ "epoch": 2.86,
417
+ "learning_rate": 3.5687863308085256e-05,
418
+ "loss": 0.7375,
419
+ "step": 32500
420
+ },
421
+ {
422
+ "epoch": 2.91,
423
+ "learning_rate": 3.5467676589748106e-05,
424
+ "loss": 0.7261,
425
+ "step": 33000
426
+ },
427
+ {
428
+ "epoch": 2.95,
429
+ "learning_rate": 3.524748987141096e-05,
430
+ "loss": 0.7197,
431
+ "step": 33500
432
+ },
433
+ {
434
+ "epoch": 2.99,
435
+ "learning_rate": 3.5027303153073806e-05,
436
+ "loss": 0.7127,
437
+ "step": 34000
438
+ },
439
+ {
440
+ "epoch": 3.0,
441
+ "eval_bleu": 31.2642,
442
+ "eval_gen_len": 18.1188,
443
+ "eval_loss": 1.168749451637268,
444
+ "eval_runtime": 1511.0096,
445
+ "eval_samples_per_second": 15.028,
446
+ "eval_steps_per_second": 0.94,
447
+ "step": 34062
448
+ },
449
+ {
450
+ "epoch": 3.04,
451
+ "learning_rate": 3.4807116434736656e-05,
452
+ "loss": 0.6673,
453
+ "step": 34500
454
+ },
455
+ {
456
+ "epoch": 3.08,
457
+ "learning_rate": 3.4586929716399506e-05,
458
+ "loss": 0.6346,
459
+ "step": 35000
460
+ },
461
+ {
462
+ "epoch": 3.13,
463
+ "learning_rate": 3.4366742998062356e-05,
464
+ "loss": 0.6203,
465
+ "step": 35500
466
+ },
467
+ {
468
+ "epoch": 3.17,
469
+ "learning_rate": 3.4146556279725206e-05,
470
+ "loss": 0.605,
471
+ "step": 36000
472
+ },
473
+ {
474
+ "epoch": 3.21,
475
+ "learning_rate": 3.392636956138806e-05,
476
+ "loss": 0.5996,
477
+ "step": 36500
478
+ },
479
+ {
480
+ "epoch": 3.26,
481
+ "learning_rate": 3.3706182843050906e-05,
482
+ "loss": 0.5942,
483
+ "step": 37000
484
+ },
485
+ {
486
+ "epoch": 3.3,
487
+ "learning_rate": 3.3485996124713757e-05,
488
+ "loss": 0.5911,
489
+ "step": 37500
490
+ },
491
+ {
492
+ "epoch": 3.35,
493
+ "learning_rate": 3.3265809406376607e-05,
494
+ "loss": 0.5741,
495
+ "step": 38000
496
+ },
497
+ {
498
+ "epoch": 3.39,
499
+ "learning_rate": 3.304562268803946e-05,
500
+ "loss": 0.5807,
501
+ "step": 38500
502
+ },
503
+ {
504
+ "epoch": 3.43,
505
+ "learning_rate": 3.2825435969702313e-05,
506
+ "loss": 0.5777,
507
+ "step": 39000
508
+ },
509
+ {
510
+ "epoch": 3.48,
511
+ "learning_rate": 3.2605249251365164e-05,
512
+ "loss": 0.5823,
513
+ "step": 39500
514
+ },
515
+ {
516
+ "epoch": 3.52,
517
+ "learning_rate": 3.238506253302801e-05,
518
+ "loss": 0.5698,
519
+ "step": 40000
520
+ },
521
+ {
522
+ "epoch": 3.57,
523
+ "learning_rate": 3.216487581469086e-05,
524
+ "loss": 0.5727,
525
+ "step": 40500
526
+ },
527
+ {
528
+ "epoch": 3.61,
529
+ "learning_rate": 3.194468909635371e-05,
530
+ "loss": 0.5648,
531
+ "step": 41000
532
+ },
533
+ {
534
+ "epoch": 3.66,
535
+ "learning_rate": 3.172450237801656e-05,
536
+ "loss": 0.5641,
537
+ "step": 41500
538
+ },
539
+ {
540
+ "epoch": 3.7,
541
+ "learning_rate": 3.1504315659679414e-05,
542
+ "loss": 0.559,
543
+ "step": 42000
544
+ },
545
+ {
546
+ "epoch": 3.74,
547
+ "learning_rate": 3.1284128941342264e-05,
548
+ "loss": 0.5487,
549
+ "step": 42500
550
+ },
551
+ {
552
+ "epoch": 3.79,
553
+ "learning_rate": 3.106394222300511e-05,
554
+ "loss": 0.5521,
555
+ "step": 43000
556
+ },
557
+ {
558
+ "epoch": 3.83,
559
+ "learning_rate": 3.084375550466796e-05,
560
+ "loss": 0.5509,
561
+ "step": 43500
562
+ },
563
+ {
564
+ "epoch": 3.88,
565
+ "learning_rate": 3.062356878633081e-05,
566
+ "loss": 0.5557,
567
+ "step": 44000
568
+ },
569
+ {
570
+ "epoch": 3.92,
571
+ "learning_rate": 3.0403382067993657e-05,
572
+ "loss": 0.551,
573
+ "step": 44500
574
+ },
575
+ {
576
+ "epoch": 3.96,
577
+ "learning_rate": 3.018319534965651e-05,
578
+ "loss": 0.5406,
579
+ "step": 45000
580
+ },
581
+ {
582
+ "epoch": 4.0,
583
+ "eval_bleu": 30.9531,
584
+ "eval_gen_len": 17.9958,
585
+ "eval_loss": 1.2618861198425293,
586
+ "eval_runtime": 1469.856,
587
+ "eval_samples_per_second": 15.448,
588
+ "eval_steps_per_second": 0.966,
589
+ "step": 45416
590
+ },
591
+ {
592
+ "epoch": 4.01,
593
+ "learning_rate": 2.996300863131936e-05,
594
+ "loss": 0.5371,
595
+ "step": 45500
596
+ },
597
+ {
598
+ "epoch": 4.05,
599
+ "learning_rate": 2.974282191298221e-05,
600
+ "loss": 0.4843,
601
+ "step": 46000
602
+ },
603
+ {
604
+ "epoch": 4.1,
605
+ "learning_rate": 2.952263519464506e-05,
606
+ "loss": 0.4779,
607
+ "step": 46500
608
+ },
609
+ {
610
+ "epoch": 4.14,
611
+ "learning_rate": 2.9302448476307908e-05,
612
+ "loss": 0.4551,
613
+ "step": 47000
614
+ },
615
+ {
616
+ "epoch": 4.18,
617
+ "learning_rate": 2.9082261757970758e-05,
618
+ "loss": 0.4512,
619
+ "step": 47500
620
+ },
621
+ {
622
+ "epoch": 4.23,
623
+ "learning_rate": 2.886207503963361e-05,
624
+ "loss": 0.4464,
625
+ "step": 48000
626
+ },
627
+ {
628
+ "epoch": 4.27,
629
+ "learning_rate": 2.864188832129646e-05,
630
+ "loss": 0.4317,
631
+ "step": 48500
632
+ },
633
+ {
634
+ "epoch": 4.32,
635
+ "learning_rate": 2.842170160295931e-05,
636
+ "loss": 0.4392,
637
+ "step": 49000
638
+ },
639
+ {
640
+ "epoch": 4.36,
641
+ "learning_rate": 2.820151488462216e-05,
642
+ "loss": 0.4232,
643
+ "step": 49500
644
+ },
645
+ {
646
+ "epoch": 4.4,
647
+ "learning_rate": 2.7981328166285008e-05,
648
+ "loss": 0.4341,
649
+ "step": 50000
650
+ },
651
+ {
652
+ "epoch": 4.45,
653
+ "learning_rate": 2.7761141447947865e-05,
654
+ "loss": 0.4245,
655
+ "step": 50500
656
+ },
657
+ {
658
+ "epoch": 4.49,
659
+ "learning_rate": 2.754095472961071e-05,
660
+ "loss": 0.4266,
661
+ "step": 51000
662
+ },
663
+ {
664
+ "epoch": 4.54,
665
+ "learning_rate": 2.732076801127356e-05,
666
+ "loss": 0.4199,
667
+ "step": 51500
668
+ },
669
+ {
670
+ "epoch": 4.58,
671
+ "learning_rate": 2.710058129293641e-05,
672
+ "loss": 0.4266,
673
+ "step": 52000
674
+ },
675
+ {
676
+ "epoch": 4.62,
677
+ "learning_rate": 2.688039457459926e-05,
678
+ "loss": 0.4191,
679
+ "step": 52500
680
+ },
681
+ {
682
+ "epoch": 4.67,
683
+ "learning_rate": 2.6660207856262108e-05,
684
+ "loss": 0.4155,
685
+ "step": 53000
686
+ },
687
+ {
688
+ "epoch": 4.71,
689
+ "learning_rate": 2.6440021137924965e-05,
690
+ "loss": 0.4058,
691
+ "step": 53500
692
+ },
693
+ {
694
+ "epoch": 4.76,
695
+ "learning_rate": 2.6219834419587812e-05,
696
+ "loss": 0.4079,
697
+ "step": 54000
698
+ },
699
+ {
700
+ "epoch": 4.8,
701
+ "learning_rate": 2.5999647701250662e-05,
702
+ "loss": 0.4041,
703
+ "step": 54500
704
+ },
705
+ {
706
+ "epoch": 4.84,
707
+ "learning_rate": 2.5779460982913512e-05,
708
+ "loss": 0.4099,
709
+ "step": 55000
710
+ },
711
+ {
712
+ "epoch": 4.89,
713
+ "learning_rate": 2.5559274264576362e-05,
714
+ "loss": 0.4107,
715
+ "step": 55500
716
+ },
717
+ {
718
+ "epoch": 4.93,
719
+ "learning_rate": 2.533908754623921e-05,
720
+ "loss": 0.4016,
721
+ "step": 56000
722
+ },
723
+ {
724
+ "epoch": 4.98,
725
+ "learning_rate": 2.5118900827902065e-05,
726
+ "loss": 0.4027,
727
+ "step": 56500
728
+ },
729
+ {
730
+ "epoch": 5.0,
731
+ "eval_bleu": 30.7923,
732
+ "eval_gen_len": 18.0582,
733
+ "eval_loss": 1.3788937330245972,
734
+ "eval_runtime": 1470.5701,
735
+ "eval_samples_per_second": 15.441,
736
+ "eval_steps_per_second": 0.966,
737
+ "step": 56770
738
+ }
739
+ ],
740
+ "logging_steps": 500,
741
+ "max_steps": 113540,
742
+ "num_train_epochs": 10,
743
+ "save_steps": 500,
744
+ "total_flos": 1.968551332235182e+18,
745
+ "trial_name": null,
746
+ "trial_params": null
747
+ }
checkpoint-56770/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9db9168480a6c0a1a80baf9aa7bf4344735c517df328c25f6d3bd3a09bdcb88
3
+ size 4728
checkpoint-68124/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-68124/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-68124/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5815afc92bed096795c585993d5204770ff8a88b341f3278a3a05e1269b2155
3
+ size 4887473903
checkpoint-68124/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b24cd055182d47f2a5db95c21e24fbf23576c255178f516be211b1f76795c4b
3
+ size 2444694490
checkpoint-68124/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bb0786a42adcc8c8566e6dad695b737f9a1b738819c9c6b2491648dd0de1cb6
3
+ size 15024
checkpoint-68124/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbb881931c8a529374ce28277b96e8c599c9ccbb93d118a64a74c792bb63e3cd
3
+ size 15024
checkpoint-68124/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ce99eff5797affe2bb8411e2d5c01b819439e962a110394d1d45cf993a74a06
3
+ size 15024
checkpoint-68124/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1216beca6837987fe170f65369eecebf0987deda8cb332f245258c8494becf50
3
+ size 15024
checkpoint-68124/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aa1a57d10a2e6558a7ce32d004b21600b62858c8f786eadb0bb93fbc4c903a7
3
+ size 1064
checkpoint-68124/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-68124/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-68124/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fc2a9a463953c664738ef8571ed97361b8de258b2aca93c0214a89676a73379
3
+ size 17110043
checkpoint-68124/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-68124/trainer_state.json ADDED
@@ -0,0 +1,895 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.1251049041748047,
3
+ "best_model_checkpoint": "./mbartLarge_koja_mid2_run1/checkpoint-22708",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 68124,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04,
13
+ "learning_rate": 4.977981328166285e-05,
14
+ "loss": 1.9241,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.09,
19
+ "learning_rate": 4.95596265633257e-05,
20
+ "loss": 1.6494,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.13,
25
+ "learning_rate": 4.933943984498855e-05,
26
+ "loss": 1.5434,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.18,
31
+ "learning_rate": 4.91192531266514e-05,
32
+ "loss": 1.4836,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.22,
37
+ "learning_rate": 4.889906640831425e-05,
38
+ "loss": 1.4499,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.26,
43
+ "learning_rate": 4.86788796899771e-05,
44
+ "loss": 1.3934,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.31,
49
+ "learning_rate": 4.845869297163995e-05,
50
+ "loss": 1.3857,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.35,
55
+ "learning_rate": 4.82385062533028e-05,
56
+ "loss": 1.3396,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.4,
61
+ "learning_rate": 4.801831953496565e-05,
62
+ "loss": 1.3322,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.44,
67
+ "learning_rate": 4.77981328166285e-05,
68
+ "loss": 1.3106,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.48,
73
+ "learning_rate": 4.757794609829135e-05,
74
+ "loss": 1.2924,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 0.53,
79
+ "learning_rate": 4.73577593799542e-05,
80
+ "loss": 1.2834,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 0.57,
85
+ "learning_rate": 4.713757266161705e-05,
86
+ "loss": 1.2791,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 0.62,
91
+ "learning_rate": 4.69173859432799e-05,
92
+ "loss": 1.255,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 0.66,
97
+ "learning_rate": 4.669719922494275e-05,
98
+ "loss": 1.2573,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 0.7,
103
+ "learning_rate": 4.64770125066056e-05,
104
+ "loss": 1.2382,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 0.75,
109
+ "learning_rate": 4.625682578826845e-05,
110
+ "loss": 1.223,
111
+ "step": 8500
112
+ },
113
+ {
114
+ "epoch": 0.79,
115
+ "learning_rate": 4.6036639069931303e-05,
116
+ "loss": 1.2145,
117
+ "step": 9000
118
+ },
119
+ {
120
+ "epoch": 0.84,
121
+ "learning_rate": 4.5816452351594153e-05,
122
+ "loss": 1.219,
123
+ "step": 9500
124
+ },
125
+ {
126
+ "epoch": 0.88,
127
+ "learning_rate": 4.5596265633257004e-05,
128
+ "loss": 1.2125,
129
+ "step": 10000
130
+ },
131
+ {
132
+ "epoch": 0.92,
133
+ "learning_rate": 4.5376078914919854e-05,
134
+ "loss": 1.1996,
135
+ "step": 10500
136
+ },
137
+ {
138
+ "epoch": 0.97,
139
+ "learning_rate": 4.5155892196582704e-05,
140
+ "loss": 1.1823,
141
+ "step": 11000
142
+ },
143
+ {
144
+ "epoch": 1.0,
145
+ "eval_bleu": 29.4501,
146
+ "eval_gen_len": 18.8118,
147
+ "eval_loss": 1.1695398092269897,
148
+ "eval_runtime": 1716.1373,
149
+ "eval_samples_per_second": 13.231,
150
+ "eval_steps_per_second": 0.827,
151
+ "step": 11354
152
+ },
153
+ {
154
+ "epoch": 1.01,
155
+ "learning_rate": 4.4935705478245554e-05,
156
+ "loss": 1.1596,
157
+ "step": 11500
158
+ },
159
+ {
160
+ "epoch": 1.06,
161
+ "learning_rate": 4.4715518759908404e-05,
162
+ "loss": 1.0777,
163
+ "step": 12000
164
+ },
165
+ {
166
+ "epoch": 1.1,
167
+ "learning_rate": 4.4495332041571254e-05,
168
+ "loss": 1.0658,
169
+ "step": 12500
170
+ },
171
+ {
172
+ "epoch": 1.14,
173
+ "learning_rate": 4.427514532323411e-05,
174
+ "loss": 1.0296,
175
+ "step": 13000
176
+ },
177
+ {
178
+ "epoch": 1.19,
179
+ "learning_rate": 4.4054958604896954e-05,
180
+ "loss": 1.0269,
181
+ "step": 13500
182
+ },
183
+ {
184
+ "epoch": 1.23,
185
+ "learning_rate": 4.3834771886559804e-05,
186
+ "loss": 1.0192,
187
+ "step": 14000
188
+ },
189
+ {
190
+ "epoch": 1.28,
191
+ "learning_rate": 4.3614585168222654e-05,
192
+ "loss": 0.9946,
193
+ "step": 14500
194
+ },
195
+ {
196
+ "epoch": 1.32,
197
+ "learning_rate": 4.3394398449885504e-05,
198
+ "loss": 0.9996,
199
+ "step": 15000
200
+ },
201
+ {
202
+ "epoch": 1.37,
203
+ "learning_rate": 4.3174211731548354e-05,
204
+ "loss": 0.975,
205
+ "step": 15500
206
+ },
207
+ {
208
+ "epoch": 1.41,
209
+ "learning_rate": 4.295402501321121e-05,
210
+ "loss": 0.9874,
211
+ "step": 16000
212
+ },
213
+ {
214
+ "epoch": 1.45,
215
+ "learning_rate": 4.2733838294874054e-05,
216
+ "loss": 0.9683,
217
+ "step": 16500
218
+ },
219
+ {
220
+ "epoch": 1.5,
221
+ "learning_rate": 4.2513651576536904e-05,
222
+ "loss": 0.9675,
223
+ "step": 17000
224
+ },
225
+ {
226
+ "epoch": 1.54,
227
+ "learning_rate": 4.2293464858199754e-05,
228
+ "loss": 0.969,
229
+ "step": 17500
230
+ },
231
+ {
232
+ "epoch": 1.59,
233
+ "learning_rate": 4.2073278139862604e-05,
234
+ "loss": 0.9548,
235
+ "step": 18000
236
+ },
237
+ {
238
+ "epoch": 1.63,
239
+ "learning_rate": 4.1853091421525454e-05,
240
+ "loss": 0.9563,
241
+ "step": 18500
242
+ },
243
+ {
244
+ "epoch": 1.67,
245
+ "learning_rate": 4.163290470318831e-05,
246
+ "loss": 0.9536,
247
+ "step": 19000
248
+ },
249
+ {
250
+ "epoch": 1.72,
251
+ "learning_rate": 4.1412717984851155e-05,
252
+ "loss": 0.941,
253
+ "step": 19500
254
+ },
255
+ {
256
+ "epoch": 1.76,
257
+ "learning_rate": 4.1192531266514005e-05,
258
+ "loss": 0.9285,
259
+ "step": 20000
260
+ },
261
+ {
262
+ "epoch": 1.81,
263
+ "learning_rate": 4.0972344548176855e-05,
264
+ "loss": 0.9303,
265
+ "step": 20500
266
+ },
267
+ {
268
+ "epoch": 1.85,
269
+ "learning_rate": 4.0752157829839705e-05,
270
+ "loss": 0.9428,
271
+ "step": 21000
272
+ },
273
+ {
274
+ "epoch": 1.89,
275
+ "learning_rate": 4.0531971111502555e-05,
276
+ "loss": 0.9359,
277
+ "step": 21500
278
+ },
279
+ {
280
+ "epoch": 1.94,
281
+ "learning_rate": 4.031178439316541e-05,
282
+ "loss": 0.9302,
283
+ "step": 22000
284
+ },
285
+ {
286
+ "epoch": 1.98,
287
+ "learning_rate": 4.0091597674828255e-05,
288
+ "loss": 0.9207,
289
+ "step": 22500
290
+ },
291
+ {
292
+ "epoch": 2.0,
293
+ "eval_bleu": 30.842,
294
+ "eval_gen_len": 18.0892,
295
+ "eval_loss": 1.1251049041748047,
296
+ "eval_runtime": 1535.7063,
297
+ "eval_samples_per_second": 14.786,
298
+ "eval_steps_per_second": 0.925,
299
+ "step": 22708
300
+ },
301
+ {
302
+ "epoch": 2.03,
303
+ "learning_rate": 3.9871410956491105e-05,
304
+ "loss": 0.8788,
305
+ "step": 23000
306
+ },
307
+ {
308
+ "epoch": 2.07,
309
+ "learning_rate": 3.9651224238153955e-05,
310
+ "loss": 0.8367,
311
+ "step": 23500
312
+ },
313
+ {
314
+ "epoch": 2.11,
315
+ "learning_rate": 3.9431037519816805e-05,
316
+ "loss": 0.8196,
317
+ "step": 24000
318
+ },
319
+ {
320
+ "epoch": 2.16,
321
+ "learning_rate": 3.921085080147966e-05,
322
+ "loss": 0.7967,
323
+ "step": 24500
324
+ },
325
+ {
326
+ "epoch": 2.2,
327
+ "learning_rate": 3.8990664083142505e-05,
328
+ "loss": 0.7956,
329
+ "step": 25000
330
+ },
331
+ {
332
+ "epoch": 2.25,
333
+ "learning_rate": 3.8770477364805355e-05,
334
+ "loss": 0.7843,
335
+ "step": 25500
336
+ },
337
+ {
338
+ "epoch": 2.29,
339
+ "learning_rate": 3.8550290646468205e-05,
340
+ "loss": 0.7767,
341
+ "step": 26000
342
+ },
343
+ {
344
+ "epoch": 2.33,
345
+ "learning_rate": 3.8330103928131055e-05,
346
+ "loss": 0.7668,
347
+ "step": 26500
348
+ },
349
+ {
350
+ "epoch": 2.38,
351
+ "learning_rate": 3.8109917209793905e-05,
352
+ "loss": 0.754,
353
+ "step": 27000
354
+ },
355
+ {
356
+ "epoch": 2.42,
357
+ "learning_rate": 3.788973049145676e-05,
358
+ "loss": 0.7671,
359
+ "step": 27500
360
+ },
361
+ {
362
+ "epoch": 2.47,
363
+ "learning_rate": 3.7669543773119605e-05,
364
+ "loss": 0.7569,
365
+ "step": 28000
366
+ },
367
+ {
368
+ "epoch": 2.51,
369
+ "learning_rate": 3.7449357054782456e-05,
370
+ "loss": 0.7553,
371
+ "step": 28500
372
+ },
373
+ {
374
+ "epoch": 2.55,
375
+ "learning_rate": 3.7229170336445306e-05,
376
+ "loss": 0.7526,
377
+ "step": 29000
378
+ },
379
+ {
380
+ "epoch": 2.6,
381
+ "learning_rate": 3.7008983618108156e-05,
382
+ "loss": 0.7427,
383
+ "step": 29500
384
+ },
385
+ {
386
+ "epoch": 2.64,
387
+ "learning_rate": 3.6788796899771006e-05,
388
+ "loss": 0.7407,
389
+ "step": 30000
390
+ },
391
+ {
392
+ "epoch": 2.69,
393
+ "learning_rate": 3.656861018143386e-05,
394
+ "loss": 0.7418,
395
+ "step": 30500
396
+ },
397
+ {
398
+ "epoch": 2.73,
399
+ "learning_rate": 3.6348423463096706e-05,
400
+ "loss": 0.7301,
401
+ "step": 31000
402
+ },
403
+ {
404
+ "epoch": 2.77,
405
+ "learning_rate": 3.6128236744759556e-05,
406
+ "loss": 0.7218,
407
+ "step": 31500
408
+ },
409
+ {
410
+ "epoch": 2.82,
411
+ "learning_rate": 3.5908050026422406e-05,
412
+ "loss": 0.7232,
413
+ "step": 32000
414
+ },
415
+ {
416
+ "epoch": 2.86,
417
+ "learning_rate": 3.5687863308085256e-05,
418
+ "loss": 0.7375,
419
+ "step": 32500
420
+ },
421
+ {
422
+ "epoch": 2.91,
423
+ "learning_rate": 3.5467676589748106e-05,
424
+ "loss": 0.7261,
425
+ "step": 33000
426
+ },
427
+ {
428
+ "epoch": 2.95,
429
+ "learning_rate": 3.524748987141096e-05,
430
+ "loss": 0.7197,
431
+ "step": 33500
432
+ },
433
+ {
434
+ "epoch": 2.99,
435
+ "learning_rate": 3.5027303153073806e-05,
436
+ "loss": 0.7127,
437
+ "step": 34000
438
+ },
439
+ {
440
+ "epoch": 3.0,
441
+ "eval_bleu": 31.2642,
442
+ "eval_gen_len": 18.1188,
443
+ "eval_loss": 1.168749451637268,
444
+ "eval_runtime": 1511.0096,
445
+ "eval_samples_per_second": 15.028,
446
+ "eval_steps_per_second": 0.94,
447
+ "step": 34062
448
+ },
449
+ {
450
+ "epoch": 3.04,
451
+ "learning_rate": 3.4807116434736656e-05,
452
+ "loss": 0.6673,
453
+ "step": 34500
454
+ },
455
+ {
456
+ "epoch": 3.08,
457
+ "learning_rate": 3.4586929716399506e-05,
458
+ "loss": 0.6346,
459
+ "step": 35000
460
+ },
461
+ {
462
+ "epoch": 3.13,
463
+ "learning_rate": 3.4366742998062356e-05,
464
+ "loss": 0.6203,
465
+ "step": 35500
466
+ },
467
+ {
468
+ "epoch": 3.17,
469
+ "learning_rate": 3.4146556279725206e-05,
470
+ "loss": 0.605,
471
+ "step": 36000
472
+ },
473
+ {
474
+ "epoch": 3.21,
475
+ "learning_rate": 3.392636956138806e-05,
476
+ "loss": 0.5996,
477
+ "step": 36500
478
+ },
479
+ {
480
+ "epoch": 3.26,
481
+ "learning_rate": 3.3706182843050906e-05,
482
+ "loss": 0.5942,
483
+ "step": 37000
484
+ },
485
+ {
486
+ "epoch": 3.3,
487
+ "learning_rate": 3.3485996124713757e-05,
488
+ "loss": 0.5911,
489
+ "step": 37500
490
+ },
491
+ {
492
+ "epoch": 3.35,
493
+ "learning_rate": 3.3265809406376607e-05,
494
+ "loss": 0.5741,
495
+ "step": 38000
496
+ },
497
+ {
498
+ "epoch": 3.39,
499
+ "learning_rate": 3.304562268803946e-05,
500
+ "loss": 0.5807,
501
+ "step": 38500
502
+ },
503
+ {
504
+ "epoch": 3.43,
505
+ "learning_rate": 3.2825435969702313e-05,
506
+ "loss": 0.5777,
507
+ "step": 39000
508
+ },
509
+ {
510
+ "epoch": 3.48,
511
+ "learning_rate": 3.2605249251365164e-05,
512
+ "loss": 0.5823,
513
+ "step": 39500
514
+ },
515
+ {
516
+ "epoch": 3.52,
517
+ "learning_rate": 3.238506253302801e-05,
518
+ "loss": 0.5698,
519
+ "step": 40000
520
+ },
521
+ {
522
+ "epoch": 3.57,
523
+ "learning_rate": 3.216487581469086e-05,
524
+ "loss": 0.5727,
525
+ "step": 40500
526
+ },
527
+ {
528
+ "epoch": 3.61,
529
+ "learning_rate": 3.194468909635371e-05,
530
+ "loss": 0.5648,
531
+ "step": 41000
532
+ },
533
+ {
534
+ "epoch": 3.66,
535
+ "learning_rate": 3.172450237801656e-05,
536
+ "loss": 0.5641,
537
+ "step": 41500
538
+ },
539
+ {
540
+ "epoch": 3.7,
541
+ "learning_rate": 3.1504315659679414e-05,
542
+ "loss": 0.559,
543
+ "step": 42000
544
+ },
545
+ {
546
+ "epoch": 3.74,
547
+ "learning_rate": 3.1284128941342264e-05,
548
+ "loss": 0.5487,
549
+ "step": 42500
550
+ },
551
+ {
552
+ "epoch": 3.79,
553
+ "learning_rate": 3.106394222300511e-05,
554
+ "loss": 0.5521,
555
+ "step": 43000
556
+ },
557
+ {
558
+ "epoch": 3.83,
559
+ "learning_rate": 3.084375550466796e-05,
560
+ "loss": 0.5509,
561
+ "step": 43500
562
+ },
563
+ {
564
+ "epoch": 3.88,
565
+ "learning_rate": 3.062356878633081e-05,
566
+ "loss": 0.5557,
567
+ "step": 44000
568
+ },
569
+ {
570
+ "epoch": 3.92,
571
+ "learning_rate": 3.0403382067993657e-05,
572
+ "loss": 0.551,
573
+ "step": 44500
574
+ },
575
+ {
576
+ "epoch": 3.96,
577
+ "learning_rate": 3.018319534965651e-05,
578
+ "loss": 0.5406,
579
+ "step": 45000
580
+ },
581
+ {
582
+ "epoch": 4.0,
583
+ "eval_bleu": 30.9531,
584
+ "eval_gen_len": 17.9958,
585
+ "eval_loss": 1.2618861198425293,
586
+ "eval_runtime": 1469.856,
587
+ "eval_samples_per_second": 15.448,
588
+ "eval_steps_per_second": 0.966,
589
+ "step": 45416
590
+ },
591
+ {
592
+ "epoch": 4.01,
593
+ "learning_rate": 2.996300863131936e-05,
594
+ "loss": 0.5371,
595
+ "step": 45500
596
+ },
597
+ {
598
+ "epoch": 4.05,
599
+ "learning_rate": 2.974282191298221e-05,
600
+ "loss": 0.4843,
601
+ "step": 46000
602
+ },
603
+ {
604
+ "epoch": 4.1,
605
+ "learning_rate": 2.952263519464506e-05,
606
+ "loss": 0.4779,
607
+ "step": 46500
608
+ },
609
+ {
610
+ "epoch": 4.14,
611
+ "learning_rate": 2.9302448476307908e-05,
612
+ "loss": 0.4551,
613
+ "step": 47000
614
+ },
615
+ {
616
+ "epoch": 4.18,
617
+ "learning_rate": 2.9082261757970758e-05,
618
+ "loss": 0.4512,
619
+ "step": 47500
620
+ },
621
+ {
622
+ "epoch": 4.23,
623
+ "learning_rate": 2.886207503963361e-05,
624
+ "loss": 0.4464,
625
+ "step": 48000
626
+ },
627
+ {
628
+ "epoch": 4.27,
629
+ "learning_rate": 2.864188832129646e-05,
630
+ "loss": 0.4317,
631
+ "step": 48500
632
+ },
633
+ {
634
+ "epoch": 4.32,
635
+ "learning_rate": 2.842170160295931e-05,
636
+ "loss": 0.4392,
637
+ "step": 49000
638
+ },
639
+ {
640
+ "epoch": 4.36,
641
+ "learning_rate": 2.820151488462216e-05,
642
+ "loss": 0.4232,
643
+ "step": 49500
644
+ },
645
+ {
646
+ "epoch": 4.4,
647
+ "learning_rate": 2.7981328166285008e-05,
648
+ "loss": 0.4341,
649
+ "step": 50000
650
+ },
651
+ {
652
+ "epoch": 4.45,
653
+ "learning_rate": 2.7761141447947865e-05,
654
+ "loss": 0.4245,
655
+ "step": 50500
656
+ },
657
+ {
658
+ "epoch": 4.49,
659
+ "learning_rate": 2.754095472961071e-05,
660
+ "loss": 0.4266,
661
+ "step": 51000
662
+ },
663
+ {
664
+ "epoch": 4.54,
665
+ "learning_rate": 2.732076801127356e-05,
666
+ "loss": 0.4199,
667
+ "step": 51500
668
+ },
669
+ {
670
+ "epoch": 4.58,
671
+ "learning_rate": 2.710058129293641e-05,
672
+ "loss": 0.4266,
673
+ "step": 52000
674
+ },
675
+ {
676
+ "epoch": 4.62,
677
+ "learning_rate": 2.688039457459926e-05,
678
+ "loss": 0.4191,
679
+ "step": 52500
680
+ },
681
+ {
682
+ "epoch": 4.67,
683
+ "learning_rate": 2.6660207856262108e-05,
684
+ "loss": 0.4155,
685
+ "step": 53000
686
+ },
687
+ {
688
+ "epoch": 4.71,
689
+ "learning_rate": 2.6440021137924965e-05,
690
+ "loss": 0.4058,
691
+ "step": 53500
692
+ },
693
+ {
694
+ "epoch": 4.76,
695
+ "learning_rate": 2.6219834419587812e-05,
696
+ "loss": 0.4079,
697
+ "step": 54000
698
+ },
699
+ {
700
+ "epoch": 4.8,
701
+ "learning_rate": 2.5999647701250662e-05,
702
+ "loss": 0.4041,
703
+ "step": 54500
704
+ },
705
+ {
706
+ "epoch": 4.84,
707
+ "learning_rate": 2.5779460982913512e-05,
708
+ "loss": 0.4099,
709
+ "step": 55000
710
+ },
711
+ {
712
+ "epoch": 4.89,
713
+ "learning_rate": 2.5559274264576362e-05,
714
+ "loss": 0.4107,
715
+ "step": 55500
716
+ },
717
+ {
718
+ "epoch": 4.93,
719
+ "learning_rate": 2.533908754623921e-05,
720
+ "loss": 0.4016,
721
+ "step": 56000
722
+ },
723
+ {
724
+ "epoch": 4.98,
725
+ "learning_rate": 2.5118900827902065e-05,
726
+ "loss": 0.4027,
727
+ "step": 56500
728
+ },
729
+ {
730
+ "epoch": 5.0,
731
+ "eval_bleu": 30.7923,
732
+ "eval_gen_len": 18.0582,
733
+ "eval_loss": 1.3788937330245972,
734
+ "eval_runtime": 1470.5701,
735
+ "eval_samples_per_second": 15.441,
736
+ "eval_steps_per_second": 0.966,
737
+ "step": 56770
738
+ },
739
+ {
740
+ "epoch": 5.02,
741
+ "learning_rate": 2.4898714109564912e-05,
742
+ "loss": 0.3814,
743
+ "step": 57000
744
+ },
745
+ {
746
+ "epoch": 5.06,
747
+ "learning_rate": 2.4678527391227762e-05,
748
+ "loss": 0.3509,
749
+ "step": 57500
750
+ },
751
+ {
752
+ "epoch": 5.11,
753
+ "learning_rate": 2.4458340672890612e-05,
754
+ "loss": 0.3365,
755
+ "step": 58000
756
+ },
757
+ {
758
+ "epoch": 5.15,
759
+ "learning_rate": 2.4238153954553462e-05,
760
+ "loss": 0.3269,
761
+ "step": 58500
762
+ },
763
+ {
764
+ "epoch": 5.2,
765
+ "learning_rate": 2.4017967236216312e-05,
766
+ "loss": 0.3289,
767
+ "step": 59000
768
+ },
769
+ {
770
+ "epoch": 5.24,
771
+ "learning_rate": 2.3797780517879162e-05,
772
+ "loss": 0.3147,
773
+ "step": 59500
774
+ },
775
+ {
776
+ "epoch": 5.28,
777
+ "learning_rate": 2.3577593799542012e-05,
778
+ "loss": 0.3133,
779
+ "step": 60000
780
+ },
781
+ {
782
+ "epoch": 5.33,
783
+ "learning_rate": 2.3357407081204862e-05,
784
+ "loss": 0.3149,
785
+ "step": 60500
786
+ },
787
+ {
788
+ "epoch": 5.37,
789
+ "learning_rate": 2.3137220362867713e-05,
790
+ "loss": 0.3028,
791
+ "step": 61000
792
+ },
793
+ {
794
+ "epoch": 5.42,
795
+ "learning_rate": 2.2917033644530563e-05,
796
+ "loss": 0.313,
797
+ "step": 61500
798
+ },
799
+ {
800
+ "epoch": 5.46,
801
+ "learning_rate": 2.2696846926193413e-05,
802
+ "loss": 0.3081,
803
+ "step": 62000
804
+ },
805
+ {
806
+ "epoch": 5.5,
807
+ "learning_rate": 2.2476660207856263e-05,
808
+ "loss": 0.3068,
809
+ "step": 62500
810
+ },
811
+ {
812
+ "epoch": 5.55,
813
+ "learning_rate": 2.2256473489519113e-05,
814
+ "loss": 0.3054,
815
+ "step": 63000
816
+ },
817
+ {
818
+ "epoch": 5.59,
819
+ "learning_rate": 2.2036286771181963e-05,
820
+ "loss": 0.3015,
821
+ "step": 63500
822
+ },
823
+ {
824
+ "epoch": 5.64,
825
+ "learning_rate": 2.1816100052844813e-05,
826
+ "loss": 0.3043,
827
+ "step": 64000
828
+ },
829
+ {
830
+ "epoch": 5.68,
831
+ "learning_rate": 2.1595913334507663e-05,
832
+ "loss": 0.3009,
833
+ "step": 64500
834
+ },
835
+ {
836
+ "epoch": 5.72,
837
+ "learning_rate": 2.1375726616170513e-05,
838
+ "loss": 0.2964,
839
+ "step": 65000
840
+ },
841
+ {
842
+ "epoch": 5.77,
843
+ "learning_rate": 2.1155539897833363e-05,
844
+ "loss": 0.2883,
845
+ "step": 65500
846
+ },
847
+ {
848
+ "epoch": 5.81,
849
+ "learning_rate": 2.0935353179496213e-05,
850
+ "loss": 0.2958,
851
+ "step": 66000
852
+ },
853
+ {
854
+ "epoch": 5.86,
855
+ "learning_rate": 2.0715166461159063e-05,
856
+ "loss": 0.2985,
857
+ "step": 66500
858
+ },
859
+ {
860
+ "epoch": 5.9,
861
+ "learning_rate": 2.0494979742821913e-05,
862
+ "loss": 0.2975,
863
+ "step": 67000
864
+ },
865
+ {
866
+ "epoch": 5.95,
867
+ "learning_rate": 2.0274793024484763e-05,
868
+ "loss": 0.288,
869
+ "step": 67500
870
+ },
871
+ {
872
+ "epoch": 5.99,
873
+ "learning_rate": 2.0054606306147613e-05,
874
+ "loss": 0.286,
875
+ "step": 68000
876
+ },
877
+ {
878
+ "epoch": 6.0,
879
+ "eval_bleu": 30.9393,
880
+ "eval_gen_len": 18.1183,
881
+ "eval_loss": 1.4784362316131592,
882
+ "eval_runtime": 1467.697,
883
+ "eval_samples_per_second": 15.471,
884
+ "eval_steps_per_second": 0.968,
885
+ "step": 68124
886
+ }
887
+ ],
888
+ "logging_steps": 500,
889
+ "max_steps": 113540,
890
+ "num_train_epochs": 10,
891
+ "save_steps": 500,
892
+ "total_flos": 2.3622407943975076e+18,
893
+ "trial_name": null,
894
+ "trial_params": null
895
+ }
checkpoint-68124/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9db9168480a6c0a1a80baf9aa7bf4344735c517df328c25f6d3bd3a09bdcb88
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": 6.0,
3
+ "eval_bleu": 30.7351,
4
+ "eval_gen_len": 18.1559,
5
+ "eval_loss": 1.1251049041748047,
6
+ "eval_runtime": 1367.4753,
7
+ "eval_samples": 22707,
8
+ "eval_samples_per_second": 16.605,
9
+ "eval_steps_per_second": 1.038
10
+ }