yesj1234 commited on
Commit
8a1aeec
1 Parent(s): 3495674

Upload folder using huggingface_hub

Browse files
Files changed (46) hide show
  1. .gitattributes +3 -0
  2. README.md +80 -0
  3. all_results.json +22 -0
  4. checkpoint-17600/config.json +59 -0
  5. checkpoint-17600/generation_config.json +12 -0
  6. checkpoint-17600/optimizer.pt +3 -0
  7. checkpoint-17600/pytorch_model.bin +3 -0
  8. checkpoint-17600/rng_state_0.pth +3 -0
  9. checkpoint-17600/rng_state_1.pth +3 -0
  10. checkpoint-17600/rng_state_2.pth +3 -0
  11. checkpoint-17600/rng_state_3.pth +3 -0
  12. checkpoint-17600/scheduler.pt +3 -0
  13. checkpoint-17600/sentencepiece.bpe.model +3 -0
  14. checkpoint-17600/special_tokens_map.json +69 -0
  15. checkpoint-17600/tokenizer.json +3 -0
  16. checkpoint-17600/tokenizer_config.json +528 -0
  17. checkpoint-17600/trainer_state.json +339 -0
  18. checkpoint-17600/training_args.bin +3 -0
  19. checkpoint-19200/config.json +59 -0
  20. checkpoint-19200/generation_config.json +12 -0
  21. checkpoint-19200/optimizer.pt +3 -0
  22. checkpoint-19200/pytorch_model.bin +3 -0
  23. checkpoint-19200/rng_state_0.pth +3 -0
  24. checkpoint-19200/rng_state_1.pth +3 -0
  25. checkpoint-19200/rng_state_2.pth +3 -0
  26. checkpoint-19200/rng_state_3.pth +3 -0
  27. checkpoint-19200/scheduler.pt +3 -0
  28. checkpoint-19200/sentencepiece.bpe.model +3 -0
  29. checkpoint-19200/special_tokens_map.json +69 -0
  30. checkpoint-19200/tokenizer.json +3 -0
  31. checkpoint-19200/tokenizer_config.json +528 -0
  32. checkpoint-19200/trainer_state.json +367 -0
  33. checkpoint-19200/training_args.bin +3 -0
  34. config.json +59 -0
  35. eval_results.json +10 -0
  36. generated_predictions.txt +0 -0
  37. generation_config.json +12 -0
  38. predict_results.json +9 -0
  39. pytorch_model.bin +3 -0
  40. sentencepiece.bpe.model +3 -0
  41. special_tokens_map.json +69 -0
  42. tokenizer.json +3 -0
  43. tokenizer_config.json +528 -0
  44. train_results.json +8 -0
  45. trainer_state.json +376 -0
  46. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-17600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-19200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ja
4
+ - ko
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: jako_13p_tokenie_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
+ # jako_13p_tokenie_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: 1.3560
23
+ - Bleu: 50.2114
24
+ - Gen Len: 18.2159
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 5e-05
44
+ - train_batch_size: 4
45
+ - eval_batch_size: 4
46
+ - seed: 42
47
+ - distributed_type: multi-GPU
48
+ - num_devices: 4
49
+ - gradient_accumulation_steps: 2
50
+ - total_train_batch_size: 32
51
+ - total_eval_batch_size: 16
52
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
+ - lr_scheduler_type: linear
54
+ - lr_scheduler_warmup_steps: 200
55
+ - num_epochs: 10
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
60
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
61
+ | 1.2125 | 0.83 | 1600 | 1.1356 | 44.2732 | 18.9394 |
62
+ | 0.8519 | 1.66 | 3200 | 1.0618 | 47.1622 | 18.3936 |
63
+ | 0.6394 | 2.49 | 4800 | 1.0923 | 47.7818 | 18.3397 |
64
+ | 0.532 | 3.32 | 6400 | 1.1294 | 48.4283 | 18.3375 |
65
+ | 0.3543 | 4.15 | 8000 | 1.1765 | 47.7916 | 18.4422 |
66
+ | 0.2569 | 4.99 | 9600 | 1.2103 | 48.1268 | 18.5385 |
67
+ | 0.1732 | 5.82 | 11200 | 1.2549 | 48.9329 | 18.2085 |
68
+ | 0.1228 | 6.65 | 12800 | 1.3022 | 49.0248 | 18.2133 |
69
+ | 0.0937 | 7.48 | 14400 | 1.3179 | 49.3503 | 18.1673 |
70
+ | 0.0627 | 8.31 | 16000 | 1.3409 | 49.5551 | 18.2672 |
71
+ | 0.0558 | 9.14 | 17600 | 1.3545 | 49.7808 | 18.2815 |
72
+ | 0.0442 | 9.97 | 19200 | 1.3560 | 50.2114 | 18.2159 |
73
+
74
+
75
+ ### Framework versions
76
+
77
+ - Transformers 4.34.1
78
+ - Pytorch 2.1.0+cu121
79
+ - Datasets 2.14.6
80
+ - Tokenizers 0.14.1
all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_bleu": 50.2114,
4
+ "eval_gen_len": 18.2159,
5
+ "eval_loss": 1.3559678792953491,
6
+ "eval_runtime": 502.2392,
7
+ "eval_samples": 7701,
8
+ "eval_samples_per_second": 15.333,
9
+ "eval_steps_per_second": 0.96,
10
+ "predict_bleu": 50.1532,
11
+ "predict_gen_len": 18.221,
12
+ "predict_loss": 1.3584160804748535,
13
+ "predict_runtime": 503.6712,
14
+ "predict_samples": 7701,
15
+ "predict_samples_per_second": 15.29,
16
+ "predict_steps_per_second": 0.957,
17
+ "train_loss": 0.4018082245665711,
18
+ "train_runtime": 39148.2976,
19
+ "train_samples": 61615,
20
+ "train_samples_per_second": 15.739,
21
+ "train_steps_per_second": 0.492
22
+ }
checkpoint-17600/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": 250014,
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-17600/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": 250014,
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-17600/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fcea03a041bc8e44852070f702f2921bed48821e9d9ede15a584427a5a656af
3
+ size 4887473903
checkpoint-17600/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ba1051375a482af6b647dd85a54b4138d13e645763165b39fce78af8e40568a
3
+ size 2444694490
checkpoint-17600/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b40b30b93e428e6a2a7c484daf4b767e6058f549d52d9af59d575bf80a91fd83
3
+ size 15024
checkpoint-17600/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04aff38bfe71203718af81862fbd12821d9b1aee50481bbe16399e89b1d50b90
3
+ size 15024
checkpoint-17600/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a498071b9a55c9d8af526a5fcd93546cda8ceca57eba3b6ce66cd81d698ca90
3
+ size 15024
checkpoint-17600/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eb8449010125604e5946d9d6fff718784280983d6b46b089a35e6a7fa220b14
3
+ size 15024
checkpoint-17600/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:266c1e1ec588323daa75967f5acbbbee3ac5e7cca2e0924b13206536e27f44d3
3
+ size 1064
checkpoint-17600/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-17600/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-17600/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bdb5ec99ce8fb69d8205cc7d3612cef589a885d910c331c73bd5fe10e1d9847
3
+ size 17110043
checkpoint-17600/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": "ja_XX",
525
+ "tgt_lang": "ko_KR",
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
checkpoint-17600/trainer_state.json ADDED
@@ -0,0 +1,339 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 49.7808,
3
+ "best_model_checkpoint": "./jako_13p_tokenie_run1/checkpoint-17600",
4
+ "epoch": 9.140482991430797,
5
+ "eval_steps": 1600,
6
+ "global_step": 17600,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.26,
13
+ "learning_rate": 4.9212598425196856e-05,
14
+ "loss": 1.7571,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.52,
19
+ "learning_rate": 4.79002624671916e-05,
20
+ "loss": 1.3294,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.78,
25
+ "learning_rate": 4.6587926509186354e-05,
26
+ "loss": 1.2125,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.83,
31
+ "eval_bleu": 44.2732,
32
+ "eval_gen_len": 18.9394,
33
+ "eval_loss": 1.1356315612792969,
34
+ "eval_runtime": 557.6241,
35
+ "eval_samples_per_second": 13.81,
36
+ "eval_steps_per_second": 0.864,
37
+ "step": 1600
38
+ },
39
+ {
40
+ "epoch": 1.04,
41
+ "learning_rate": 4.52755905511811e-05,
42
+ "loss": 1.1386,
43
+ "step": 2000
44
+ },
45
+ {
46
+ "epoch": 1.3,
47
+ "learning_rate": 4.396325459317586e-05,
48
+ "loss": 0.9283,
49
+ "step": 2500
50
+ },
51
+ {
52
+ "epoch": 1.56,
53
+ "learning_rate": 4.2650918635170604e-05,
54
+ "loss": 0.8519,
55
+ "step": 3000
56
+ },
57
+ {
58
+ "epoch": 1.66,
59
+ "eval_bleu": 47.1622,
60
+ "eval_gen_len": 18.3936,
61
+ "eval_loss": 1.061800241470337,
62
+ "eval_runtime": 524.2089,
63
+ "eval_samples_per_second": 14.691,
64
+ "eval_steps_per_second": 0.919,
65
+ "step": 3200
66
+ },
67
+ {
68
+ "epoch": 1.82,
69
+ "learning_rate": 4.133858267716536e-05,
70
+ "loss": 0.8109,
71
+ "step": 3500
72
+ },
73
+ {
74
+ "epoch": 2.08,
75
+ "learning_rate": 4.00262467191601e-05,
76
+ "loss": 0.7727,
77
+ "step": 4000
78
+ },
79
+ {
80
+ "epoch": 2.34,
81
+ "learning_rate": 3.871391076115486e-05,
82
+ "loss": 0.6394,
83
+ "step": 4500
84
+ },
85
+ {
86
+ "epoch": 2.49,
87
+ "eval_bleu": 47.7818,
88
+ "eval_gen_len": 18.3397,
89
+ "eval_loss": 1.0923182964324951,
90
+ "eval_runtime": 516.7936,
91
+ "eval_samples_per_second": 14.902,
92
+ "eval_steps_per_second": 0.933,
93
+ "step": 4800
94
+ },
95
+ {
96
+ "epoch": 2.6,
97
+ "learning_rate": 3.740157480314961e-05,
98
+ "loss": 0.5875,
99
+ "step": 5000
100
+ },
101
+ {
102
+ "epoch": 2.86,
103
+ "learning_rate": 3.608923884514436e-05,
104
+ "loss": 0.5625,
105
+ "step": 5500
106
+ },
107
+ {
108
+ "epoch": 3.12,
109
+ "learning_rate": 3.4776902887139105e-05,
110
+ "loss": 0.532,
111
+ "step": 6000
112
+ },
113
+ {
114
+ "epoch": 3.32,
115
+ "eval_bleu": 48.4283,
116
+ "eval_gen_len": 18.3375,
117
+ "eval_loss": 1.1293830871582031,
118
+ "eval_runtime": 519.3842,
119
+ "eval_samples_per_second": 14.827,
120
+ "eval_steps_per_second": 0.928,
121
+ "step": 6400
122
+ },
123
+ {
124
+ "epoch": 3.38,
125
+ "learning_rate": 3.3464566929133864e-05,
126
+ "loss": 0.4299,
127
+ "step": 6500
128
+ },
129
+ {
130
+ "epoch": 3.64,
131
+ "learning_rate": 3.215223097112861e-05,
132
+ "loss": 0.3984,
133
+ "step": 7000
134
+ },
135
+ {
136
+ "epoch": 3.9,
137
+ "learning_rate": 3.083989501312336e-05,
138
+ "loss": 0.3857,
139
+ "step": 7500
140
+ },
141
+ {
142
+ "epoch": 4.15,
143
+ "learning_rate": 2.952755905511811e-05,
144
+ "loss": 0.3543,
145
+ "step": 8000
146
+ },
147
+ {
148
+ "epoch": 4.15,
149
+ "eval_bleu": 47.7916,
150
+ "eval_gen_len": 18.4422,
151
+ "eval_loss": 1.176469087600708,
152
+ "eval_runtime": 519.0077,
153
+ "eval_samples_per_second": 14.838,
154
+ "eval_steps_per_second": 0.929,
155
+ "step": 8000
156
+ },
157
+ {
158
+ "epoch": 4.41,
159
+ "learning_rate": 2.8215223097112863e-05,
160
+ "loss": 0.2836,
161
+ "step": 8500
162
+ },
163
+ {
164
+ "epoch": 4.67,
165
+ "learning_rate": 2.6902887139107612e-05,
166
+ "loss": 0.2648,
167
+ "step": 9000
168
+ },
169
+ {
170
+ "epoch": 4.93,
171
+ "learning_rate": 2.5590551181102364e-05,
172
+ "loss": 0.2569,
173
+ "step": 9500
174
+ },
175
+ {
176
+ "epoch": 4.99,
177
+ "eval_bleu": 48.1268,
178
+ "eval_gen_len": 18.5385,
179
+ "eval_loss": 1.2102879285812378,
180
+ "eval_runtime": 526.7602,
181
+ "eval_samples_per_second": 14.62,
182
+ "eval_steps_per_second": 0.915,
183
+ "step": 9600
184
+ },
185
+ {
186
+ "epoch": 5.19,
187
+ "learning_rate": 2.4278215223097113e-05,
188
+ "loss": 0.2268,
189
+ "step": 10000
190
+ },
191
+ {
192
+ "epoch": 5.45,
193
+ "learning_rate": 2.2965879265091865e-05,
194
+ "loss": 0.1854,
195
+ "step": 10500
196
+ },
197
+ {
198
+ "epoch": 5.71,
199
+ "learning_rate": 2.1653543307086614e-05,
200
+ "loss": 0.1732,
201
+ "step": 11000
202
+ },
203
+ {
204
+ "epoch": 5.82,
205
+ "eval_bleu": 48.9329,
206
+ "eval_gen_len": 18.2085,
207
+ "eval_loss": 1.25494384765625,
208
+ "eval_runtime": 505.0437,
209
+ "eval_samples_per_second": 15.248,
210
+ "eval_steps_per_second": 0.954,
211
+ "step": 11200
212
+ },
213
+ {
214
+ "epoch": 5.97,
215
+ "learning_rate": 2.0341207349081366e-05,
216
+ "loss": 0.1693,
217
+ "step": 11500
218
+ },
219
+ {
220
+ "epoch": 6.23,
221
+ "learning_rate": 1.9028871391076115e-05,
222
+ "loss": 0.1453,
223
+ "step": 12000
224
+ },
225
+ {
226
+ "epoch": 6.49,
227
+ "learning_rate": 1.7716535433070868e-05,
228
+ "loss": 0.1228,
229
+ "step": 12500
230
+ },
231
+ {
232
+ "epoch": 6.65,
233
+ "eval_bleu": 49.0248,
234
+ "eval_gen_len": 18.2133,
235
+ "eval_loss": 1.3022269010543823,
236
+ "eval_runtime": 504.7977,
237
+ "eval_samples_per_second": 15.256,
238
+ "eval_steps_per_second": 0.955,
239
+ "step": 12800
240
+ },
241
+ {
242
+ "epoch": 6.75,
243
+ "learning_rate": 1.6404199475065617e-05,
244
+ "loss": 0.1158,
245
+ "step": 13000
246
+ },
247
+ {
248
+ "epoch": 7.01,
249
+ "learning_rate": 1.5091863517060367e-05,
250
+ "loss": 0.1144,
251
+ "step": 13500
252
+ },
253
+ {
254
+ "epoch": 7.27,
255
+ "learning_rate": 1.377952755905512e-05,
256
+ "loss": 0.0937,
257
+ "step": 14000
258
+ },
259
+ {
260
+ "epoch": 7.48,
261
+ "eval_bleu": 49.3503,
262
+ "eval_gen_len": 18.1673,
263
+ "eval_loss": 1.317897081375122,
264
+ "eval_runtime": 503.3739,
265
+ "eval_samples_per_second": 15.299,
266
+ "eval_steps_per_second": 0.958,
267
+ "step": 14400
268
+ },
269
+ {
270
+ "epoch": 7.53,
271
+ "learning_rate": 1.246719160104987e-05,
272
+ "loss": 0.0829,
273
+ "step": 14500
274
+ },
275
+ {
276
+ "epoch": 7.79,
277
+ "learning_rate": 1.115485564304462e-05,
278
+ "loss": 0.0783,
279
+ "step": 15000
280
+ },
281
+ {
282
+ "epoch": 8.05,
283
+ "learning_rate": 9.842519685039371e-06,
284
+ "loss": 0.0779,
285
+ "step": 15500
286
+ },
287
+ {
288
+ "epoch": 8.31,
289
+ "learning_rate": 8.530183727034122e-06,
290
+ "loss": 0.0627,
291
+ "step": 16000
292
+ },
293
+ {
294
+ "epoch": 8.31,
295
+ "eval_bleu": 49.5551,
296
+ "eval_gen_len": 18.2672,
297
+ "eval_loss": 1.3408894538879395,
298
+ "eval_runtime": 506.5726,
299
+ "eval_samples_per_second": 15.202,
300
+ "eval_steps_per_second": 0.951,
301
+ "step": 16000
302
+ },
303
+ {
304
+ "epoch": 8.57,
305
+ "learning_rate": 7.2178477690288725e-06,
306
+ "loss": 0.0579,
307
+ "step": 16500
308
+ },
309
+ {
310
+ "epoch": 8.83,
311
+ "learning_rate": 5.905511811023622e-06,
312
+ "loss": 0.0551,
313
+ "step": 17000
314
+ },
315
+ {
316
+ "epoch": 9.09,
317
+ "learning_rate": 4.593175853018373e-06,
318
+ "loss": 0.0558,
319
+ "step": 17500
320
+ },
321
+ {
322
+ "epoch": 9.14,
323
+ "eval_bleu": 49.7808,
324
+ "eval_gen_len": 18.2815,
325
+ "eval_loss": 1.3544921875,
326
+ "eval_runtime": 505.3645,
327
+ "eval_samples_per_second": 15.239,
328
+ "eval_steps_per_second": 0.954,
329
+ "step": 17600
330
+ }
331
+ ],
332
+ "logging_steps": 500,
333
+ "max_steps": 19250,
334
+ "num_train_epochs": 10,
335
+ "save_steps": 1600,
336
+ "total_flos": 1.2205274853015552e+18,
337
+ "trial_name": null,
338
+ "trial_params": null
339
+ }
checkpoint-17600/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ba345dbcbd4da315f08522c539a6a76b333ac4e076317f3a4045568bf9d97d9
3
+ size 4728
checkpoint-19200/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": 250014,
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-19200/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": 250014,
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-19200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5dcd17ec9c1794eba70d72a0eaaff8e638ce752e107fe8abcd27fc2d1da0904
3
+ size 4887473903
checkpoint-19200/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6ac31b67727a096c4319bc3cb30cbdf92a93b2f1917b4942cfb0e6a8c6ab1a9
3
+ size 2444694490
checkpoint-19200/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37e404e7e1b97e3e674086b4ea27ad30f27468a65fa92265bab96f1d1dc60660
3
+ size 15024
checkpoint-19200/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05aa666503d6e4bb2ba2c5ce201516a97704cd5e2b993bbe2983d2445c3a453f
3
+ size 15024
checkpoint-19200/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fca124887cfc9eff1c149de2ab19225890cb11ca7ae22e96a41013cb6a4cb9a
3
+ size 15024
checkpoint-19200/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bec949f5170dd6deb1b2faa8a05cdef20c678f762905e00ebe6fa1d1ef4e94f9
3
+ size 15024
checkpoint-19200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a76abd7dd61b6daca463faacc3f3c6a6bef01eda511c3b10df295a33a91e569f
3
+ size 1064
checkpoint-19200/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-19200/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-19200/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bdb5ec99ce8fb69d8205cc7d3612cef589a885d910c331c73bd5fe10e1d9847
3
+ size 17110043
checkpoint-19200/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": "ja_XX",
525
+ "tgt_lang": "ko_KR",
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
checkpoint-19200/trainer_state.json ADDED
@@ -0,0 +1,367 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 50.2114,
3
+ "best_model_checkpoint": "./jako_13p_tokenie_run1/checkpoint-19200",
4
+ "epoch": 9.971435990651779,
5
+ "eval_steps": 1600,
6
+ "global_step": 19200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.26,
13
+ "learning_rate": 4.9212598425196856e-05,
14
+ "loss": 1.7571,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.52,
19
+ "learning_rate": 4.79002624671916e-05,
20
+ "loss": 1.3294,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.78,
25
+ "learning_rate": 4.6587926509186354e-05,
26
+ "loss": 1.2125,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.83,
31
+ "eval_bleu": 44.2732,
32
+ "eval_gen_len": 18.9394,
33
+ "eval_loss": 1.1356315612792969,
34
+ "eval_runtime": 557.6241,
35
+ "eval_samples_per_second": 13.81,
36
+ "eval_steps_per_second": 0.864,
37
+ "step": 1600
38
+ },
39
+ {
40
+ "epoch": 1.04,
41
+ "learning_rate": 4.52755905511811e-05,
42
+ "loss": 1.1386,
43
+ "step": 2000
44
+ },
45
+ {
46
+ "epoch": 1.3,
47
+ "learning_rate": 4.396325459317586e-05,
48
+ "loss": 0.9283,
49
+ "step": 2500
50
+ },
51
+ {
52
+ "epoch": 1.56,
53
+ "learning_rate": 4.2650918635170604e-05,
54
+ "loss": 0.8519,
55
+ "step": 3000
56
+ },
57
+ {
58
+ "epoch": 1.66,
59
+ "eval_bleu": 47.1622,
60
+ "eval_gen_len": 18.3936,
61
+ "eval_loss": 1.061800241470337,
62
+ "eval_runtime": 524.2089,
63
+ "eval_samples_per_second": 14.691,
64
+ "eval_steps_per_second": 0.919,
65
+ "step": 3200
66
+ },
67
+ {
68
+ "epoch": 1.82,
69
+ "learning_rate": 4.133858267716536e-05,
70
+ "loss": 0.8109,
71
+ "step": 3500
72
+ },
73
+ {
74
+ "epoch": 2.08,
75
+ "learning_rate": 4.00262467191601e-05,
76
+ "loss": 0.7727,
77
+ "step": 4000
78
+ },
79
+ {
80
+ "epoch": 2.34,
81
+ "learning_rate": 3.871391076115486e-05,
82
+ "loss": 0.6394,
83
+ "step": 4500
84
+ },
85
+ {
86
+ "epoch": 2.49,
87
+ "eval_bleu": 47.7818,
88
+ "eval_gen_len": 18.3397,
89
+ "eval_loss": 1.0923182964324951,
90
+ "eval_runtime": 516.7936,
91
+ "eval_samples_per_second": 14.902,
92
+ "eval_steps_per_second": 0.933,
93
+ "step": 4800
94
+ },
95
+ {
96
+ "epoch": 2.6,
97
+ "learning_rate": 3.740157480314961e-05,
98
+ "loss": 0.5875,
99
+ "step": 5000
100
+ },
101
+ {
102
+ "epoch": 2.86,
103
+ "learning_rate": 3.608923884514436e-05,
104
+ "loss": 0.5625,
105
+ "step": 5500
106
+ },
107
+ {
108
+ "epoch": 3.12,
109
+ "learning_rate": 3.4776902887139105e-05,
110
+ "loss": 0.532,
111
+ "step": 6000
112
+ },
113
+ {
114
+ "epoch": 3.32,
115
+ "eval_bleu": 48.4283,
116
+ "eval_gen_len": 18.3375,
117
+ "eval_loss": 1.1293830871582031,
118
+ "eval_runtime": 519.3842,
119
+ "eval_samples_per_second": 14.827,
120
+ "eval_steps_per_second": 0.928,
121
+ "step": 6400
122
+ },
123
+ {
124
+ "epoch": 3.38,
125
+ "learning_rate": 3.3464566929133864e-05,
126
+ "loss": 0.4299,
127
+ "step": 6500
128
+ },
129
+ {
130
+ "epoch": 3.64,
131
+ "learning_rate": 3.215223097112861e-05,
132
+ "loss": 0.3984,
133
+ "step": 7000
134
+ },
135
+ {
136
+ "epoch": 3.9,
137
+ "learning_rate": 3.083989501312336e-05,
138
+ "loss": 0.3857,
139
+ "step": 7500
140
+ },
141
+ {
142
+ "epoch": 4.15,
143
+ "learning_rate": 2.952755905511811e-05,
144
+ "loss": 0.3543,
145
+ "step": 8000
146
+ },
147
+ {
148
+ "epoch": 4.15,
149
+ "eval_bleu": 47.7916,
150
+ "eval_gen_len": 18.4422,
151
+ "eval_loss": 1.176469087600708,
152
+ "eval_runtime": 519.0077,
153
+ "eval_samples_per_second": 14.838,
154
+ "eval_steps_per_second": 0.929,
155
+ "step": 8000
156
+ },
157
+ {
158
+ "epoch": 4.41,
159
+ "learning_rate": 2.8215223097112863e-05,
160
+ "loss": 0.2836,
161
+ "step": 8500
162
+ },
163
+ {
164
+ "epoch": 4.67,
165
+ "learning_rate": 2.6902887139107612e-05,
166
+ "loss": 0.2648,
167
+ "step": 9000
168
+ },
169
+ {
170
+ "epoch": 4.93,
171
+ "learning_rate": 2.5590551181102364e-05,
172
+ "loss": 0.2569,
173
+ "step": 9500
174
+ },
175
+ {
176
+ "epoch": 4.99,
177
+ "eval_bleu": 48.1268,
178
+ "eval_gen_len": 18.5385,
179
+ "eval_loss": 1.2102879285812378,
180
+ "eval_runtime": 526.7602,
181
+ "eval_samples_per_second": 14.62,
182
+ "eval_steps_per_second": 0.915,
183
+ "step": 9600
184
+ },
185
+ {
186
+ "epoch": 5.19,
187
+ "learning_rate": 2.4278215223097113e-05,
188
+ "loss": 0.2268,
189
+ "step": 10000
190
+ },
191
+ {
192
+ "epoch": 5.45,
193
+ "learning_rate": 2.2965879265091865e-05,
194
+ "loss": 0.1854,
195
+ "step": 10500
196
+ },
197
+ {
198
+ "epoch": 5.71,
199
+ "learning_rate": 2.1653543307086614e-05,
200
+ "loss": 0.1732,
201
+ "step": 11000
202
+ },
203
+ {
204
+ "epoch": 5.82,
205
+ "eval_bleu": 48.9329,
206
+ "eval_gen_len": 18.2085,
207
+ "eval_loss": 1.25494384765625,
208
+ "eval_runtime": 505.0437,
209
+ "eval_samples_per_second": 15.248,
210
+ "eval_steps_per_second": 0.954,
211
+ "step": 11200
212
+ },
213
+ {
214
+ "epoch": 5.97,
215
+ "learning_rate": 2.0341207349081366e-05,
216
+ "loss": 0.1693,
217
+ "step": 11500
218
+ },
219
+ {
220
+ "epoch": 6.23,
221
+ "learning_rate": 1.9028871391076115e-05,
222
+ "loss": 0.1453,
223
+ "step": 12000
224
+ },
225
+ {
226
+ "epoch": 6.49,
227
+ "learning_rate": 1.7716535433070868e-05,
228
+ "loss": 0.1228,
229
+ "step": 12500
230
+ },
231
+ {
232
+ "epoch": 6.65,
233
+ "eval_bleu": 49.0248,
234
+ "eval_gen_len": 18.2133,
235
+ "eval_loss": 1.3022269010543823,
236
+ "eval_runtime": 504.7977,
237
+ "eval_samples_per_second": 15.256,
238
+ "eval_steps_per_second": 0.955,
239
+ "step": 12800
240
+ },
241
+ {
242
+ "epoch": 6.75,
243
+ "learning_rate": 1.6404199475065617e-05,
244
+ "loss": 0.1158,
245
+ "step": 13000
246
+ },
247
+ {
248
+ "epoch": 7.01,
249
+ "learning_rate": 1.5091863517060367e-05,
250
+ "loss": 0.1144,
251
+ "step": 13500
252
+ },
253
+ {
254
+ "epoch": 7.27,
255
+ "learning_rate": 1.377952755905512e-05,
256
+ "loss": 0.0937,
257
+ "step": 14000
258
+ },
259
+ {
260
+ "epoch": 7.48,
261
+ "eval_bleu": 49.3503,
262
+ "eval_gen_len": 18.1673,
263
+ "eval_loss": 1.317897081375122,
264
+ "eval_runtime": 503.3739,
265
+ "eval_samples_per_second": 15.299,
266
+ "eval_steps_per_second": 0.958,
267
+ "step": 14400
268
+ },
269
+ {
270
+ "epoch": 7.53,
271
+ "learning_rate": 1.246719160104987e-05,
272
+ "loss": 0.0829,
273
+ "step": 14500
274
+ },
275
+ {
276
+ "epoch": 7.79,
277
+ "learning_rate": 1.115485564304462e-05,
278
+ "loss": 0.0783,
279
+ "step": 15000
280
+ },
281
+ {
282
+ "epoch": 8.05,
283
+ "learning_rate": 9.842519685039371e-06,
284
+ "loss": 0.0779,
285
+ "step": 15500
286
+ },
287
+ {
288
+ "epoch": 8.31,
289
+ "learning_rate": 8.530183727034122e-06,
290
+ "loss": 0.0627,
291
+ "step": 16000
292
+ },
293
+ {
294
+ "epoch": 8.31,
295
+ "eval_bleu": 49.5551,
296
+ "eval_gen_len": 18.2672,
297
+ "eval_loss": 1.3408894538879395,
298
+ "eval_runtime": 506.5726,
299
+ "eval_samples_per_second": 15.202,
300
+ "eval_steps_per_second": 0.951,
301
+ "step": 16000
302
+ },
303
+ {
304
+ "epoch": 8.57,
305
+ "learning_rate": 7.2178477690288725e-06,
306
+ "loss": 0.0579,
307
+ "step": 16500
308
+ },
309
+ {
310
+ "epoch": 8.83,
311
+ "learning_rate": 5.905511811023622e-06,
312
+ "loss": 0.0551,
313
+ "step": 17000
314
+ },
315
+ {
316
+ "epoch": 9.09,
317
+ "learning_rate": 4.593175853018373e-06,
318
+ "loss": 0.0558,
319
+ "step": 17500
320
+ },
321
+ {
322
+ "epoch": 9.14,
323
+ "eval_bleu": 49.7808,
324
+ "eval_gen_len": 18.2815,
325
+ "eval_loss": 1.3544921875,
326
+ "eval_runtime": 505.3645,
327
+ "eval_samples_per_second": 15.239,
328
+ "eval_steps_per_second": 0.954,
329
+ "step": 17600
330
+ },
331
+ {
332
+ "epoch": 9.35,
333
+ "learning_rate": 3.2808398950131235e-06,
334
+ "loss": 0.0456,
335
+ "step": 18000
336
+ },
337
+ {
338
+ "epoch": 9.61,
339
+ "learning_rate": 1.968503937007874e-06,
340
+ "loss": 0.0433,
341
+ "step": 18500
342
+ },
343
+ {
344
+ "epoch": 9.87,
345
+ "learning_rate": 6.561679790026247e-07,
346
+ "loss": 0.0442,
347
+ "step": 19000
348
+ },
349
+ {
350
+ "epoch": 9.97,
351
+ "eval_bleu": 50.2114,
352
+ "eval_gen_len": 18.2159,
353
+ "eval_loss": 1.3559678792953491,
354
+ "eval_runtime": 503.7841,
355
+ "eval_samples_per_second": 15.286,
356
+ "eval_steps_per_second": 0.957,
357
+ "step": 19200
358
+ }
359
+ ],
360
+ "logging_steps": 500,
361
+ "max_steps": 19250,
362
+ "num_train_epochs": 10,
363
+ "save_steps": 1600,
364
+ "total_flos": 1.3314845294198784e+18,
365
+ "trial_name": null,
366
+ "trial_params": null
367
+ }
checkpoint-19200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ba345dbcbd4da315f08522c539a6a76b333ac4e076317f3a4045568bf9d97d9
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": 250014,
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": 10.0,
3
+ "eval_bleu": 50.2114,
4
+ "eval_gen_len": 18.2159,
5
+ "eval_loss": 1.3559678792953491,
6
+ "eval_runtime": 502.2392,
7
+ "eval_samples": 7701,
8
+ "eval_samples_per_second": 15.333,
9
+ "eval_steps_per_second": 0.96
10
+ }
generated_predictions.txt ADDED
The diff for this file is too large to render. See raw diff
 
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "forced_bos_token_id": 250014,
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
+ }
predict_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "predict_bleu": 50.1532,
3
+ "predict_gen_len": 18.221,
4
+ "predict_loss": 1.3584160804748535,
5
+ "predict_runtime": 503.6712,
6
+ "predict_samples": 7701,
7
+ "predict_samples_per_second": 15.29,
8
+ "predict_steps_per_second": 0.957
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6ac31b67727a096c4319bc3cb30cbdf92a93b2f1917b4942cfb0e6a8c6ab1a9
3
+ size 2444694490
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bdb5ec99ce8fb69d8205cc7d3612cef589a885d910c331c73bd5fe10e1d9847
3
+ size 17110043
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": "ja_XX",
525
+ "tgt_lang": "ko_KR",
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_loss": 0.4018082245665711,
4
+ "train_runtime": 39148.2976,
5
+ "train_samples": 61615,
6
+ "train_samples_per_second": 15.739,
7
+ "train_steps_per_second": 0.492
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,376 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 50.2114,
3
+ "best_model_checkpoint": "./jako_13p_tokenie_run1/checkpoint-19200",
4
+ "epoch": 9.997403271877435,
5
+ "eval_steps": 1600,
6
+ "global_step": 19250,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.26,
13
+ "learning_rate": 4.9212598425196856e-05,
14
+ "loss": 1.7571,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.52,
19
+ "learning_rate": 4.79002624671916e-05,
20
+ "loss": 1.3294,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.78,
25
+ "learning_rate": 4.6587926509186354e-05,
26
+ "loss": 1.2125,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.83,
31
+ "eval_bleu": 44.2732,
32
+ "eval_gen_len": 18.9394,
33
+ "eval_loss": 1.1356315612792969,
34
+ "eval_runtime": 557.6241,
35
+ "eval_samples_per_second": 13.81,
36
+ "eval_steps_per_second": 0.864,
37
+ "step": 1600
38
+ },
39
+ {
40
+ "epoch": 1.04,
41
+ "learning_rate": 4.52755905511811e-05,
42
+ "loss": 1.1386,
43
+ "step": 2000
44
+ },
45
+ {
46
+ "epoch": 1.3,
47
+ "learning_rate": 4.396325459317586e-05,
48
+ "loss": 0.9283,
49
+ "step": 2500
50
+ },
51
+ {
52
+ "epoch": 1.56,
53
+ "learning_rate": 4.2650918635170604e-05,
54
+ "loss": 0.8519,
55
+ "step": 3000
56
+ },
57
+ {
58
+ "epoch": 1.66,
59
+ "eval_bleu": 47.1622,
60
+ "eval_gen_len": 18.3936,
61
+ "eval_loss": 1.061800241470337,
62
+ "eval_runtime": 524.2089,
63
+ "eval_samples_per_second": 14.691,
64
+ "eval_steps_per_second": 0.919,
65
+ "step": 3200
66
+ },
67
+ {
68
+ "epoch": 1.82,
69
+ "learning_rate": 4.133858267716536e-05,
70
+ "loss": 0.8109,
71
+ "step": 3500
72
+ },
73
+ {
74
+ "epoch": 2.08,
75
+ "learning_rate": 4.00262467191601e-05,
76
+ "loss": 0.7727,
77
+ "step": 4000
78
+ },
79
+ {
80
+ "epoch": 2.34,
81
+ "learning_rate": 3.871391076115486e-05,
82
+ "loss": 0.6394,
83
+ "step": 4500
84
+ },
85
+ {
86
+ "epoch": 2.49,
87
+ "eval_bleu": 47.7818,
88
+ "eval_gen_len": 18.3397,
89
+ "eval_loss": 1.0923182964324951,
90
+ "eval_runtime": 516.7936,
91
+ "eval_samples_per_second": 14.902,
92
+ "eval_steps_per_second": 0.933,
93
+ "step": 4800
94
+ },
95
+ {
96
+ "epoch": 2.6,
97
+ "learning_rate": 3.740157480314961e-05,
98
+ "loss": 0.5875,
99
+ "step": 5000
100
+ },
101
+ {
102
+ "epoch": 2.86,
103
+ "learning_rate": 3.608923884514436e-05,
104
+ "loss": 0.5625,
105
+ "step": 5500
106
+ },
107
+ {
108
+ "epoch": 3.12,
109
+ "learning_rate": 3.4776902887139105e-05,
110
+ "loss": 0.532,
111
+ "step": 6000
112
+ },
113
+ {
114
+ "epoch": 3.32,
115
+ "eval_bleu": 48.4283,
116
+ "eval_gen_len": 18.3375,
117
+ "eval_loss": 1.1293830871582031,
118
+ "eval_runtime": 519.3842,
119
+ "eval_samples_per_second": 14.827,
120
+ "eval_steps_per_second": 0.928,
121
+ "step": 6400
122
+ },
123
+ {
124
+ "epoch": 3.38,
125
+ "learning_rate": 3.3464566929133864e-05,
126
+ "loss": 0.4299,
127
+ "step": 6500
128
+ },
129
+ {
130
+ "epoch": 3.64,
131
+ "learning_rate": 3.215223097112861e-05,
132
+ "loss": 0.3984,
133
+ "step": 7000
134
+ },
135
+ {
136
+ "epoch": 3.9,
137
+ "learning_rate": 3.083989501312336e-05,
138
+ "loss": 0.3857,
139
+ "step": 7500
140
+ },
141
+ {
142
+ "epoch": 4.15,
143
+ "learning_rate": 2.952755905511811e-05,
144
+ "loss": 0.3543,
145
+ "step": 8000
146
+ },
147
+ {
148
+ "epoch": 4.15,
149
+ "eval_bleu": 47.7916,
150
+ "eval_gen_len": 18.4422,
151
+ "eval_loss": 1.176469087600708,
152
+ "eval_runtime": 519.0077,
153
+ "eval_samples_per_second": 14.838,
154
+ "eval_steps_per_second": 0.929,
155
+ "step": 8000
156
+ },
157
+ {
158
+ "epoch": 4.41,
159
+ "learning_rate": 2.8215223097112863e-05,
160
+ "loss": 0.2836,
161
+ "step": 8500
162
+ },
163
+ {
164
+ "epoch": 4.67,
165
+ "learning_rate": 2.6902887139107612e-05,
166
+ "loss": 0.2648,
167
+ "step": 9000
168
+ },
169
+ {
170
+ "epoch": 4.93,
171
+ "learning_rate": 2.5590551181102364e-05,
172
+ "loss": 0.2569,
173
+ "step": 9500
174
+ },
175
+ {
176
+ "epoch": 4.99,
177
+ "eval_bleu": 48.1268,
178
+ "eval_gen_len": 18.5385,
179
+ "eval_loss": 1.2102879285812378,
180
+ "eval_runtime": 526.7602,
181
+ "eval_samples_per_second": 14.62,
182
+ "eval_steps_per_second": 0.915,
183
+ "step": 9600
184
+ },
185
+ {
186
+ "epoch": 5.19,
187
+ "learning_rate": 2.4278215223097113e-05,
188
+ "loss": 0.2268,
189
+ "step": 10000
190
+ },
191
+ {
192
+ "epoch": 5.45,
193
+ "learning_rate": 2.2965879265091865e-05,
194
+ "loss": 0.1854,
195
+ "step": 10500
196
+ },
197
+ {
198
+ "epoch": 5.71,
199
+ "learning_rate": 2.1653543307086614e-05,
200
+ "loss": 0.1732,
201
+ "step": 11000
202
+ },
203
+ {
204
+ "epoch": 5.82,
205
+ "eval_bleu": 48.9329,
206
+ "eval_gen_len": 18.2085,
207
+ "eval_loss": 1.25494384765625,
208
+ "eval_runtime": 505.0437,
209
+ "eval_samples_per_second": 15.248,
210
+ "eval_steps_per_second": 0.954,
211
+ "step": 11200
212
+ },
213
+ {
214
+ "epoch": 5.97,
215
+ "learning_rate": 2.0341207349081366e-05,
216
+ "loss": 0.1693,
217
+ "step": 11500
218
+ },
219
+ {
220
+ "epoch": 6.23,
221
+ "learning_rate": 1.9028871391076115e-05,
222
+ "loss": 0.1453,
223
+ "step": 12000
224
+ },
225
+ {
226
+ "epoch": 6.49,
227
+ "learning_rate": 1.7716535433070868e-05,
228
+ "loss": 0.1228,
229
+ "step": 12500
230
+ },
231
+ {
232
+ "epoch": 6.65,
233
+ "eval_bleu": 49.0248,
234
+ "eval_gen_len": 18.2133,
235
+ "eval_loss": 1.3022269010543823,
236
+ "eval_runtime": 504.7977,
237
+ "eval_samples_per_second": 15.256,
238
+ "eval_steps_per_second": 0.955,
239
+ "step": 12800
240
+ },
241
+ {
242
+ "epoch": 6.75,
243
+ "learning_rate": 1.6404199475065617e-05,
244
+ "loss": 0.1158,
245
+ "step": 13000
246
+ },
247
+ {
248
+ "epoch": 7.01,
249
+ "learning_rate": 1.5091863517060367e-05,
250
+ "loss": 0.1144,
251
+ "step": 13500
252
+ },
253
+ {
254
+ "epoch": 7.27,
255
+ "learning_rate": 1.377952755905512e-05,
256
+ "loss": 0.0937,
257
+ "step": 14000
258
+ },
259
+ {
260
+ "epoch": 7.48,
261
+ "eval_bleu": 49.3503,
262
+ "eval_gen_len": 18.1673,
263
+ "eval_loss": 1.317897081375122,
264
+ "eval_runtime": 503.3739,
265
+ "eval_samples_per_second": 15.299,
266
+ "eval_steps_per_second": 0.958,
267
+ "step": 14400
268
+ },
269
+ {
270
+ "epoch": 7.53,
271
+ "learning_rate": 1.246719160104987e-05,
272
+ "loss": 0.0829,
273
+ "step": 14500
274
+ },
275
+ {
276
+ "epoch": 7.79,
277
+ "learning_rate": 1.115485564304462e-05,
278
+ "loss": 0.0783,
279
+ "step": 15000
280
+ },
281
+ {
282
+ "epoch": 8.05,
283
+ "learning_rate": 9.842519685039371e-06,
284
+ "loss": 0.0779,
285
+ "step": 15500
286
+ },
287
+ {
288
+ "epoch": 8.31,
289
+ "learning_rate": 8.530183727034122e-06,
290
+ "loss": 0.0627,
291
+ "step": 16000
292
+ },
293
+ {
294
+ "epoch": 8.31,
295
+ "eval_bleu": 49.5551,
296
+ "eval_gen_len": 18.2672,
297
+ "eval_loss": 1.3408894538879395,
298
+ "eval_runtime": 506.5726,
299
+ "eval_samples_per_second": 15.202,
300
+ "eval_steps_per_second": 0.951,
301
+ "step": 16000
302
+ },
303
+ {
304
+ "epoch": 8.57,
305
+ "learning_rate": 7.2178477690288725e-06,
306
+ "loss": 0.0579,
307
+ "step": 16500
308
+ },
309
+ {
310
+ "epoch": 8.83,
311
+ "learning_rate": 5.905511811023622e-06,
312
+ "loss": 0.0551,
313
+ "step": 17000
314
+ },
315
+ {
316
+ "epoch": 9.09,
317
+ "learning_rate": 4.593175853018373e-06,
318
+ "loss": 0.0558,
319
+ "step": 17500
320
+ },
321
+ {
322
+ "epoch": 9.14,
323
+ "eval_bleu": 49.7808,
324
+ "eval_gen_len": 18.2815,
325
+ "eval_loss": 1.3544921875,
326
+ "eval_runtime": 505.3645,
327
+ "eval_samples_per_second": 15.239,
328
+ "eval_steps_per_second": 0.954,
329
+ "step": 17600
330
+ },
331
+ {
332
+ "epoch": 9.35,
333
+ "learning_rate": 3.2808398950131235e-06,
334
+ "loss": 0.0456,
335
+ "step": 18000
336
+ },
337
+ {
338
+ "epoch": 9.61,
339
+ "learning_rate": 1.968503937007874e-06,
340
+ "loss": 0.0433,
341
+ "step": 18500
342
+ },
343
+ {
344
+ "epoch": 9.87,
345
+ "learning_rate": 6.561679790026247e-07,
346
+ "loss": 0.0442,
347
+ "step": 19000
348
+ },
349
+ {
350
+ "epoch": 9.97,
351
+ "eval_bleu": 50.2114,
352
+ "eval_gen_len": 18.2159,
353
+ "eval_loss": 1.3559678792953491,
354
+ "eval_runtime": 503.7841,
355
+ "eval_samples_per_second": 15.286,
356
+ "eval_steps_per_second": 0.957,
357
+ "step": 19200
358
+ },
359
+ {
360
+ "epoch": 10.0,
361
+ "step": 19250,
362
+ "total_flos": 1.334951937048576e+18,
363
+ "train_loss": 0.4018082245665711,
364
+ "train_runtime": 39148.2976,
365
+ "train_samples_per_second": 15.739,
366
+ "train_steps_per_second": 0.492
367
+ }
368
+ ],
369
+ "logging_steps": 500,
370
+ "max_steps": 19250,
371
+ "num_train_epochs": 10,
372
+ "save_steps": 1600,
373
+ "total_flos": 1.334951937048576e+18,
374
+ "trial_name": null,
375
+ "trial_params": null
376
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ba345dbcbd4da315f08522c539a6a76b333ac4e076317f3a4045568bf9d97d9
3
+ size 4728