Hugging Face's logo

yesj1234
/
enko_mbartLarge_36p_tokenize_run1

Transformers
PyTorch
English
Korean
mbart
text2text-generation
Generated from Trainer
Model card Files
xet
 Community
yesj1234 commited on
Commit
8c46a6c
·
1 Parent(s): 6d177f9

Upload folder using huggingface_hub

Browse files
Files changed (46) hide show
  1. .gitattributes +3 -0
  2. README.md +81 -0
  3. all_results.json +22 -0
  4. checkpoint-50000/config.json +59 -0
  5. checkpoint-50000/generation_config.json +12 -0
  6. checkpoint-50000/optimizer.pt +3 -0
  7. checkpoint-50000/pytorch_model.bin +3 -0
  8. checkpoint-50000/rng_state_0.pth +3 -0
  9. checkpoint-50000/rng_state_1.pth +3 -0
  10. checkpoint-50000/rng_state_2.pth +3 -0
  11. checkpoint-50000/rng_state_3.pth +3 -0
  12. checkpoint-50000/scheduler.pt +3 -0
  13. checkpoint-50000/sentencepiece.bpe.model +3 -0
  14. checkpoint-50000/special_tokens_map.json +69 -0
  15. checkpoint-50000/tokenizer.json +3 -0
  16. checkpoint-50000/tokenizer_config.json +528 -0
  17. checkpoint-50000/trainer_state.json +719 -0
  18. checkpoint-50000/training_args.bin +3 -0
  19. checkpoint-65000/config.json +59 -0
  20. checkpoint-65000/generation_config.json +12 -0
  21. checkpoint-65000/optimizer.pt +3 -0
  22. checkpoint-65000/pytorch_model.bin +3 -0
  23. checkpoint-65000/rng_state_0.pth +3 -0
  24. checkpoint-65000/rng_state_1.pth +3 -0
  25. checkpoint-65000/rng_state_2.pth +3 -0
  26. checkpoint-65000/rng_state_3.pth +3 -0
  27. checkpoint-65000/scheduler.pt +3 -0
  28. checkpoint-65000/sentencepiece.bpe.model +3 -0
  29. checkpoint-65000/special_tokens_map.json +69 -0
  30. checkpoint-65000/tokenizer.json +3 -0
  31. checkpoint-65000/tokenizer_config.json +528 -0
  32. checkpoint-65000/trainer_state.json +929 -0
  33. checkpoint-65000/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 +938 -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-50000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-65000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
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: enko_mbartLarge_36p_tokenize_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
+ # enko_mbartLarge_36p_tokenize_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: 1.1249
23
+ - Bleu: 38.8566
24
+ - Gen Len: 16.4716
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 5e-05
44
+ - train_batch_size: 4
45
+ - eval_batch_size: 4
46
+ - seed: 42
47
+ - distributed_type: multi-GPU
48
+ - num_devices: 4
49
+ - gradient_accumulation_steps: 2
50
+ - total_train_batch_size: 32
51
+ - total_eval_batch_size: 16
52
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
+ - lr_scheduler_type: linear
54
+ - lr_scheduler_warmup_steps: 500
55
+ - num_epochs: 10
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
60
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
61
+ | 1.3157 | 0.46 | 5000 | 1.2895 | 34.4176 | 16.4931 |
62
+ | 1.2575 | 0.93 | 10000 | 1.2279 | 35.0029 | 16.8009 |
63
+ | 1.1578 | 1.39 | 15000 | 1.1733 | 36.9282 | 16.5838 |
64
+ | 1.0885 | 1.86 | 20000 | 1.1464 | 37.6913 | 16.6649 |
65
+ | 1.0451 | 2.32 | 25000 | 1.1437 | 37.7875 | 16.5188 |
66
+ | 1.0465 | 2.79 | 30000 | 1.1425 | 37.895 | 16.4987 |
67
+ | 1.0156 | 3.25 | 35000 | 1.1464 | 37.8434 | 16.5515 |
68
+ | 0.9893 | 3.72 | 40000 | 1.1544 | 37.358 | 16.6096 |
69
+ | 0.8779 | 4.18 | 45000 | 1.1419 | 38.1772 | 16.457 |
70
+ | 0.8565 | 4.65 | 50000 | 1.1249 | 38.8455 | 16.4749 |
71
+ | 0.7293 | 5.11 | 55000 | 1.1566 | 38.4853 | 16.3462 |
72
+ | 0.7294 | 5.57 | 60000 | 1.1824 | 37.8822 | 16.3295 |
73
+ | 0.7254 | 6.04 | 65000 | 1.2153 | 37.3612 | 16.381 |
74
+
75
+
76
+ ### Framework versions
77
+
78
+ - Transformers 4.34.1
79
+ - Pytorch 2.1.0+cu121
80
+ - Datasets 2.14.6
81
+ - Tokenizers 0.14.1
all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.04,
3
+ "eval_bleu": 38.8566,
4
+ "eval_gen_len": 16.4716,
5
+ "eval_loss": 1.1248719692230225,
6
+ "eval_runtime": 1292.612,
7
+ "eval_samples": 21605,
8
+ "eval_samples_per_second": 16.714,
9
+ "eval_steps_per_second": 1.045,
10
+ "predict_bleu": 38.9274,
11
+ "predict_gen_len": 16.5004,
12
+ "predict_loss": 1.1190268993377686,
13
+ "predict_runtime": 1297.778,
14
+ "predict_samples": 21606,
15
+ "predict_samples_per_second": 16.648,
16
+ "predict_steps_per_second": 1.041,
17
+ "train_loss": 1.0097502070500302,
18
+ "train_runtime": 65202.0758,
19
+ "train_samples": 172202,
20
+ "train_samples_per_second": 26.411,
21
+ "train_steps_per_second": 1.651
22
+ }
checkpoint-50000/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-50000/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-50000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa8cb181fd498d79e7f47678dfc0ce08b39f250ae7ae972b6df5e75e68bab9db
3
+ size 4887473903
checkpoint-50000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddcb9c9754bc4c2074c390655306feefb3edb3766101b16f114e8bca711b448e
3
+ size 2444694490
checkpoint-50000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d5b72c7705691f8f4f3e2d9cea877218a21d0ffe19995aa22e5c56ab66e71fd
3
+ size 15024
checkpoint-50000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc29778a9639fa97ef4371817f55d366e6983a4050832d0bfde8005ad2cdbf3e
3
+ size 15024
checkpoint-50000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99e8a1fcf2827bce7a472cc400a6e446ef04905a80586217a70316276eba953d
3
+ size 15024
checkpoint-50000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7f8a85b69d2279fdac138b22681032178706d857f40d109da26bb32f3d99f3a
3
+ size 15024
checkpoint-50000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30e2eda5c27cc771ccfc8bcd3e7c8d830bb4b798fc2d859ece7182edb34807d1
3
+ size 1064
checkpoint-50000/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-50000/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-50000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c575bfc0f1e48abab95d19b3641d88b702fb559ab79e21f99d2893f304a8e96d
3
+ size 17110043
checkpoint-50000/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": "en_XX",
525
+ "tgt_lang": "ko_KR",
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
checkpoint-50000/trainer_state.json ADDED
@@ -0,0 +1,719 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 38.8455,
3
+ "best_model_checkpoint": "./enko_mbartLarge_36p_tokenize_run1/checkpoint-50000",
4
+ "epoch": 4.6455449224194,
5
+ "eval_steps": 5000,
6
+ "global_step": 50000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05,
13
+ "learning_rate": 5e-05,
14
+ "loss": 1.9707,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.09,
19
+ "learning_rate": 4.9766638663306266e-05,
20
+ "loss": 1.5932,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.14,
25
+ "learning_rate": 4.953327732661253e-05,
26
+ "loss": 1.4429,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.19,
31
+ "learning_rate": 4.929991598991879e-05,
32
+ "loss": 1.4161,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.23,
37
+ "learning_rate": 4.9066554653225056e-05,
38
+ "loss": 1.386,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.28,
43
+ "learning_rate": 4.883319331653132e-05,
44
+ "loss": 1.3715,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.33,
49
+ "learning_rate": 4.859983197983758e-05,
50
+ "loss": 1.3461,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.37,
55
+ "learning_rate": 4.8366470643143846e-05,
56
+ "loss": 1.3319,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.42,
61
+ "learning_rate": 4.813310930645011e-05,
62
+ "loss": 1.3196,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.46,
67
+ "learning_rate": 4.789974796975637e-05,
68
+ "loss": 1.3157,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.46,
73
+ "eval_bleu": 34.4176,
74
+ "eval_gen_len": 16.4931,
75
+ "eval_loss": 1.2895288467407227,
76
+ "eval_runtime": 1334.0511,
77
+ "eval_samples_per_second": 16.195,
78
+ "eval_steps_per_second": 1.013,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 0.51,
83
+ "learning_rate": 4.7666386633062636e-05,
84
+ "loss": 1.2994,
85
+ "step": 5500
86
+ },
87
+ {
88
+ "epoch": 0.56,
89
+ "learning_rate": 4.74330252963689e-05,
90
+ "loss": 1.2914,
91
+ "step": 6000
92
+ },
93
+ {
94
+ "epoch": 0.6,
95
+ "learning_rate": 4.719966395967516e-05,
96
+ "loss": 1.2989,
97
+ "step": 6500
98
+ },
99
+ {
100
+ "epoch": 0.65,
101
+ "learning_rate": 4.6966302622981427e-05,
102
+ "loss": 1.2784,
103
+ "step": 7000
104
+ },
105
+ {
106
+ "epoch": 0.7,
107
+ "learning_rate": 4.673294128628769e-05,
108
+ "loss": 1.2662,
109
+ "step": 7500
110
+ },
111
+ {
112
+ "epoch": 0.74,
113
+ "learning_rate": 4.649957994959395e-05,
114
+ "loss": 1.2529,
115
+ "step": 8000
116
+ },
117
+ {
118
+ "epoch": 0.79,
119
+ "learning_rate": 4.626621861290022e-05,
120
+ "loss": 1.2614,
121
+ "step": 8500
122
+ },
123
+ {
124
+ "epoch": 0.84,
125
+ "learning_rate": 4.603285727620648e-05,
126
+ "loss": 1.2564,
127
+ "step": 9000
128
+ },
129
+ {
130
+ "epoch": 0.88,
131
+ "learning_rate": 4.5799495939512744e-05,
132
+ "loss": 1.2435,
133
+ "step": 9500
134
+ },
135
+ {
136
+ "epoch": 0.93,
137
+ "learning_rate": 4.556613460281901e-05,
138
+ "loss": 1.2575,
139
+ "step": 10000
140
+ },
141
+ {
142
+ "epoch": 0.93,
143
+ "eval_bleu": 35.0029,
144
+ "eval_gen_len": 16.8009,
145
+ "eval_loss": 1.2279398441314697,
146
+ "eval_runtime": 1342.4865,
147
+ "eval_samples_per_second": 16.093,
148
+ "eval_steps_per_second": 1.006,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 0.98,
153
+ "learning_rate": 4.533277326612527e-05,
154
+ "loss": 1.2473,
155
+ "step": 10500
156
+ },
157
+ {
158
+ "epoch": 1.02,
159
+ "learning_rate": 4.5099411929431534e-05,
160
+ "loss": 1.2544,
161
+ "step": 11000
162
+ },
163
+ {
164
+ "epoch": 1.07,
165
+ "learning_rate": 4.48660505927378e-05,
166
+ "loss": 1.207,
167
+ "step": 11500
168
+ },
169
+ {
170
+ "epoch": 1.11,
171
+ "learning_rate": 4.463268925604406e-05,
172
+ "loss": 1.1671,
173
+ "step": 12000
174
+ },
175
+ {
176
+ "epoch": 1.16,
177
+ "learning_rate": 4.4399327919350324e-05,
178
+ "loss": 1.1709,
179
+ "step": 12500
180
+ },
181
+ {
182
+ "epoch": 1.21,
183
+ "learning_rate": 4.416596658265659e-05,
184
+ "loss": 1.165,
185
+ "step": 13000
186
+ },
187
+ {
188
+ "epoch": 1.25,
189
+ "learning_rate": 4.393260524596285e-05,
190
+ "loss": 1.1727,
191
+ "step": 13500
192
+ },
193
+ {
194
+ "epoch": 1.3,
195
+ "learning_rate": 4.3699243909269114e-05,
196
+ "loss": 1.17,
197
+ "step": 14000
198
+ },
199
+ {
200
+ "epoch": 1.35,
201
+ "learning_rate": 4.346588257257538e-05,
202
+ "loss": 1.1465,
203
+ "step": 14500
204
+ },
205
+ {
206
+ "epoch": 1.39,
207
+ "learning_rate": 4.323252123588164e-05,
208
+ "loss": 1.1578,
209
+ "step": 15000
210
+ },
211
+ {
212
+ "epoch": 1.39,
213
+ "eval_bleu": 36.9282,
214
+ "eval_gen_len": 16.5838,
215
+ "eval_loss": 1.1733436584472656,
216
+ "eval_runtime": 1318.0972,
217
+ "eval_samples_per_second": 16.391,
218
+ "eval_steps_per_second": 1.025,
219
+ "step": 15000
220
+ },
221
+ {
222
+ "epoch": 1.44,
223
+ "learning_rate": 4.2999159899187904e-05,
224
+ "loss": 1.1582,
225
+ "step": 15500
226
+ },
227
+ {
228
+ "epoch": 1.49,
229
+ "learning_rate": 4.276579856249417e-05,
230
+ "loss": 1.1495,
231
+ "step": 16000
232
+ },
233
+ {
234
+ "epoch": 1.53,
235
+ "learning_rate": 4.253243722580043e-05,
236
+ "loss": 1.1349,
237
+ "step": 16500
238
+ },
239
+ {
240
+ "epoch": 1.58,
241
+ "learning_rate": 4.2299075889106695e-05,
242
+ "loss": 1.1443,
243
+ "step": 17000
244
+ },
245
+ {
246
+ "epoch": 1.63,
247
+ "learning_rate": 4.206571455241296e-05,
248
+ "loss": 1.1326,
249
+ "step": 17500
250
+ },
251
+ {
252
+ "epoch": 1.67,
253
+ "learning_rate": 4.183235321571922e-05,
254
+ "loss": 1.1425,
255
+ "step": 18000
256
+ },
257
+ {
258
+ "epoch": 1.72,
259
+ "learning_rate": 4.1598991879025485e-05,
260
+ "loss": 1.1196,
261
+ "step": 18500
262
+ },
263
+ {
264
+ "epoch": 1.77,
265
+ "learning_rate": 4.136563054233175e-05,
266
+ "loss": 1.1272,
267
+ "step": 19000
268
+ },
269
+ {
270
+ "epoch": 1.81,
271
+ "learning_rate": 4.113226920563801e-05,
272
+ "loss": 1.1186,
273
+ "step": 19500
274
+ },
275
+ {
276
+ "epoch": 1.86,
277
+ "learning_rate": 4.0898907868944275e-05,
278
+ "loss": 1.0885,
279
+ "step": 20000
280
+ },
281
+ {
282
+ "epoch": 1.86,
283
+ "eval_bleu": 37.6913,
284
+ "eval_gen_len": 16.6649,
285
+ "eval_loss": 1.1464108228683472,
286
+ "eval_runtime": 1319.4192,
287
+ "eval_samples_per_second": 16.375,
288
+ "eval_steps_per_second": 1.024,
289
+ "step": 20000
290
+ },
291
+ {
292
+ "epoch": 1.9,
293
+ "learning_rate": 4.066554653225054e-05,
294
+ "loss": 1.0541,
295
+ "step": 20500
296
+ },
297
+ {
298
+ "epoch": 1.95,
299
+ "learning_rate": 4.04321851955568e-05,
300
+ "loss": 1.0473,
301
+ "step": 21000
302
+ },
303
+ {
304
+ "epoch": 2.0,
305
+ "learning_rate": 4.0198823858863065e-05,
306
+ "loss": 1.0511,
307
+ "step": 21500
308
+ },
309
+ {
310
+ "epoch": 2.04,
311
+ "learning_rate": 3.996546252216933e-05,
312
+ "loss": 1.0647,
313
+ "step": 22000
314
+ },
315
+ {
316
+ "epoch": 2.09,
317
+ "learning_rate": 3.973210118547559e-05,
318
+ "loss": 1.0747,
319
+ "step": 22500
320
+ },
321
+ {
322
+ "epoch": 2.14,
323
+ "learning_rate": 3.9498739848781855e-05,
324
+ "loss": 1.044,
325
+ "step": 23000
326
+ },
327
+ {
328
+ "epoch": 2.18,
329
+ "learning_rate": 3.926537851208812e-05,
330
+ "loss": 1.052,
331
+ "step": 23500
332
+ },
333
+ {
334
+ "epoch": 2.23,
335
+ "learning_rate": 3.903201717539438e-05,
336
+ "loss": 1.0624,
337
+ "step": 24000
338
+ },
339
+ {
340
+ "epoch": 2.28,
341
+ "learning_rate": 3.8798655838700645e-05,
342
+ "loss": 1.0493,
343
+ "step": 24500
344
+ },
345
+ {
346
+ "epoch": 2.32,
347
+ "learning_rate": 3.856529450200691e-05,
348
+ "loss": 1.0451,
349
+ "step": 25000
350
+ },
351
+ {
352
+ "epoch": 2.32,
353
+ "eval_bleu": 37.7875,
354
+ "eval_gen_len": 16.5188,
355
+ "eval_loss": 1.1437026262283325,
356
+ "eval_runtime": 1315.5301,
357
+ "eval_samples_per_second": 16.423,
358
+ "eval_steps_per_second": 1.027,
359
+ "step": 25000
360
+ },
361
+ {
362
+ "epoch": 2.37,
363
+ "learning_rate": 3.833193316531317e-05,
364
+ "loss": 1.054,
365
+ "step": 25500
366
+ },
367
+ {
368
+ "epoch": 2.42,
369
+ "learning_rate": 3.8098571828619436e-05,
370
+ "loss": 1.0726,
371
+ "step": 26000
372
+ },
373
+ {
374
+ "epoch": 2.46,
375
+ "learning_rate": 3.78652104919257e-05,
376
+ "loss": 1.032,
377
+ "step": 26500
378
+ },
379
+ {
380
+ "epoch": 2.51,
381
+ "learning_rate": 3.763184915523196e-05,
382
+ "loss": 0.9733,
383
+ "step": 27000
384
+ },
385
+ {
386
+ "epoch": 2.56,
387
+ "learning_rate": 3.7398487818538226e-05,
388
+ "loss": 0.9602,
389
+ "step": 27500
390
+ },
391
+ {
392
+ "epoch": 2.6,
393
+ "learning_rate": 3.716512648184449e-05,
394
+ "loss": 0.9606,
395
+ "step": 28000
396
+ },
397
+ {
398
+ "epoch": 2.65,
399
+ "learning_rate": 3.693176514515075e-05,
400
+ "loss": 0.9968,
401
+ "step": 28500
402
+ },
403
+ {
404
+ "epoch": 2.69,
405
+ "learning_rate": 3.6698403808457016e-05,
406
+ "loss": 1.036,
407
+ "step": 29000
408
+ },
409
+ {
410
+ "epoch": 2.74,
411
+ "learning_rate": 3.646504247176328e-05,
412
+ "loss": 1.0285,
413
+ "step": 29500
414
+ },
415
+ {
416
+ "epoch": 2.79,
417
+ "learning_rate": 3.623168113506954e-05,
418
+ "loss": 1.0465,
419
+ "step": 30000
420
+ },
421
+ {
422
+ "epoch": 2.79,
423
+ "eval_bleu": 37.895,
424
+ "eval_gen_len": 16.4987,
425
+ "eval_loss": 1.1424869298934937,
426
+ "eval_runtime": 1301.3337,
427
+ "eval_samples_per_second": 16.602,
428
+ "eval_steps_per_second": 1.038,
429
+ "step": 30000
430
+ },
431
+ {
432
+ "epoch": 2.83,
433
+ "learning_rate": 3.5998319798375806e-05,
434
+ "loss": 1.0458,
435
+ "step": 30500
436
+ },
437
+ {
438
+ "epoch": 2.88,
439
+ "learning_rate": 3.576495846168207e-05,
440
+ "loss": 0.9843,
441
+ "step": 31000
442
+ },
443
+ {
444
+ "epoch": 2.93,
445
+ "learning_rate": 3.553159712498833e-05,
446
+ "loss": 0.9826,
447
+ "step": 31500
448
+ },
449
+ {
450
+ "epoch": 2.97,
451
+ "learning_rate": 3.5298235788294596e-05,
452
+ "loss": 0.9817,
453
+ "step": 32000
454
+ },
455
+ {
456
+ "epoch": 3.02,
457
+ "learning_rate": 3.506487445160086e-05,
458
+ "loss": 0.9911,
459
+ "step": 32500
460
+ },
461
+ {
462
+ "epoch": 3.07,
463
+ "learning_rate": 3.483151311490712e-05,
464
+ "loss": 1.0227,
465
+ "step": 33000
466
+ },
467
+ {
468
+ "epoch": 3.11,
469
+ "learning_rate": 3.459815177821339e-05,
470
+ "loss": 1.0126,
471
+ "step": 33500
472
+ },
473
+ {
474
+ "epoch": 3.16,
475
+ "learning_rate": 3.436479044151965e-05,
476
+ "loss": 1.0125,
477
+ "step": 34000
478
+ },
479
+ {
480
+ "epoch": 3.21,
481
+ "learning_rate": 3.4131429104825913e-05,
482
+ "loss": 1.0224,
483
+ "step": 34500
484
+ },
485
+ {
486
+ "epoch": 3.25,
487
+ "learning_rate": 3.389806776813218e-05,
488
+ "loss": 1.0156,
489
+ "step": 35000
490
+ },
491
+ {
492
+ "epoch": 3.25,
493
+ "eval_bleu": 37.8434,
494
+ "eval_gen_len": 16.5515,
495
+ "eval_loss": 1.1464043855667114,
496
+ "eval_runtime": 1324.0443,
497
+ "eval_samples_per_second": 16.317,
498
+ "eval_steps_per_second": 1.02,
499
+ "step": 35000
500
+ },
501
+ {
502
+ "epoch": 3.3,
503
+ "learning_rate": 3.366470643143844e-05,
504
+ "loss": 1.009,
505
+ "step": 35500
506
+ },
507
+ {
508
+ "epoch": 3.34,
509
+ "learning_rate": 3.3431345094744704e-05,
510
+ "loss": 0.964,
511
+ "step": 36000
512
+ },
513
+ {
514
+ "epoch": 3.39,
515
+ "learning_rate": 3.319798375805097e-05,
516
+ "loss": 0.9596,
517
+ "step": 36500
518
+ },
519
+ {
520
+ "epoch": 3.44,
521
+ "learning_rate": 3.296462242135723e-05,
522
+ "loss": 0.9587,
523
+ "step": 37000
524
+ },
525
+ {
526
+ "epoch": 3.48,
527
+ "learning_rate": 3.2731261084663494e-05,
528
+ "loss": 0.9024,
529
+ "step": 37500
530
+ },
531
+ {
532
+ "epoch": 3.53,
533
+ "learning_rate": 3.249789974796976e-05,
534
+ "loss": 0.9277,
535
+ "step": 38000
536
+ },
537
+ {
538
+ "epoch": 3.58,
539
+ "learning_rate": 3.226453841127603e-05,
540
+ "loss": 0.9486,
541
+ "step": 38500
542
+ },
543
+ {
544
+ "epoch": 3.62,
545
+ "learning_rate": 3.2031177074582284e-05,
546
+ "loss": 0.9543,
547
+ "step": 39000
548
+ },
549
+ {
550
+ "epoch": 3.67,
551
+ "learning_rate": 3.179781573788855e-05,
552
+ "loss": 1.0035,
553
+ "step": 39500
554
+ },
555
+ {
556
+ "epoch": 3.72,
557
+ "learning_rate": 3.156445440119481e-05,
558
+ "loss": 0.9893,
559
+ "step": 40000
560
+ },
561
+ {
562
+ "epoch": 3.72,
563
+ "eval_bleu": 37.358,
564
+ "eval_gen_len": 16.6096,
565
+ "eval_loss": 1.1543793678283691,
566
+ "eval_runtime": 1317.3643,
567
+ "eval_samples_per_second": 16.4,
568
+ "eval_steps_per_second": 1.026,
569
+ "step": 40000
570
+ },
571
+ {
572
+ "epoch": 3.76,
573
+ "learning_rate": 3.1331093064501074e-05,
574
+ "loss": 0.9877,
575
+ "step": 40500
576
+ },
577
+ {
578
+ "epoch": 3.81,
579
+ "learning_rate": 3.109773172780734e-05,
580
+ "loss": 0.9901,
581
+ "step": 41000
582
+ },
583
+ {
584
+ "epoch": 3.86,
585
+ "learning_rate": 3.08643703911136e-05,
586
+ "loss": 0.9699,
587
+ "step": 41500
588
+ },
589
+ {
590
+ "epoch": 3.9,
591
+ "learning_rate": 3.0631009054419864e-05,
592
+ "loss": 0.9425,
593
+ "step": 42000
594
+ },
595
+ {
596
+ "epoch": 3.95,
597
+ "learning_rate": 3.039764771772613e-05,
598
+ "loss": 0.9494,
599
+ "step": 42500
600
+ },
601
+ {
602
+ "epoch": 4.0,
603
+ "learning_rate": 3.016428638103239e-05,
604
+ "loss": 0.9508,
605
+ "step": 43000
606
+ },
607
+ {
608
+ "epoch": 4.04,
609
+ "learning_rate": 2.9930925044338655e-05,
610
+ "loss": 0.9409,
611
+ "step": 43500
612
+ },
613
+ {
614
+ "epoch": 4.09,
615
+ "learning_rate": 2.969756370764492e-05,
616
+ "loss": 0.9012,
617
+ "step": 44000
618
+ },
619
+ {
620
+ "epoch": 4.13,
621
+ "learning_rate": 2.946420237095118e-05,
622
+ "loss": 0.8723,
623
+ "step": 44500
624
+ },
625
+ {
626
+ "epoch": 4.18,
627
+ "learning_rate": 2.9230841034257445e-05,
628
+ "loss": 0.8779,
629
+ "step": 45000
630
+ },
631
+ {
632
+ "epoch": 4.18,
633
+ "eval_bleu": 38.1772,
634
+ "eval_gen_len": 16.457,
635
+ "eval_loss": 1.1419273614883423,
636
+ "eval_runtime": 1300.9539,
637
+ "eval_samples_per_second": 16.607,
638
+ "eval_steps_per_second": 1.038,
639
+ "step": 45000
640
+ },
641
+ {
642
+ "epoch": 4.23,
643
+ "learning_rate": 2.8997479697563705e-05,
644
+ "loss": 0.8922,
645
+ "step": 45500
646
+ },
647
+ {
648
+ "epoch": 4.27,
649
+ "learning_rate": 2.8764118360869975e-05,
650
+ "loss": 0.8749,
651
+ "step": 46000
652
+ },
653
+ {
654
+ "epoch": 4.32,
655
+ "learning_rate": 2.8530757024176235e-05,
656
+ "loss": 0.8625,
657
+ "step": 46500
658
+ },
659
+ {
660
+ "epoch": 4.37,
661
+ "learning_rate": 2.82973956874825e-05,
662
+ "loss": 0.8248,
663
+ "step": 47000
664
+ },
665
+ {
666
+ "epoch": 4.41,
667
+ "learning_rate": 2.8064034350788765e-05,
668
+ "loss": 0.8554,
669
+ "step": 47500
670
+ },
671
+ {
672
+ "epoch": 4.46,
673
+ "learning_rate": 2.7830673014095025e-05,
674
+ "loss": 0.8822,
675
+ "step": 48000
676
+ },
677
+ {
678
+ "epoch": 4.51,
679
+ "learning_rate": 2.759731167740129e-05,
680
+ "loss": 0.7873,
681
+ "step": 48500
682
+ },
683
+ {
684
+ "epoch": 4.55,
685
+ "learning_rate": 2.7363950340707552e-05,
686
+ "loss": 0.8181,
687
+ "step": 49000
688
+ },
689
+ {
690
+ "epoch": 4.6,
691
+ "learning_rate": 2.713058900401382e-05,
692
+ "loss": 0.8259,
693
+ "step": 49500
694
+ },
695
+ {
696
+ "epoch": 4.65,
697
+ "learning_rate": 2.689722766732008e-05,
698
+ "loss": 0.8565,
699
+ "step": 50000
700
+ },
701
+ {
702
+ "epoch": 4.65,
703
+ "eval_bleu": 38.8455,
704
+ "eval_gen_len": 16.4749,
705
+ "eval_loss": 1.1248719692230225,
706
+ "eval_runtime": 1294.4037,
707
+ "eval_samples_per_second": 16.691,
708
+ "eval_steps_per_second": 1.044,
709
+ "step": 50000
710
+ }
711
+ ],
712
+ "logging_steps": 500,
713
+ "max_steps": 107630,
714
+ "num_train_epochs": 10,
715
+ "save_steps": 5000,
716
+ "total_flos": 1.7339465326143734e+18,
717
+ "trial_name": null,
718
+ "trial_params": null
719
+ }
checkpoint-50000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5537df5d9b28eceb75a3afd4a4db4d0e3b695076e108e4c2d3ee734e37ad90f
3
+ size 4728
checkpoint-65000/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-65000/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-65000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09e17062fae52472394a86347673bd3a01bc8a159d2a8e35808337175e72b579
3
+ size 4887473903
checkpoint-65000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08c7a1e3d710a0854fdc7acb651df30c8c12c5d07673ed8fb4273e83aa2b4618
3
+ size 2444694490
checkpoint-65000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc9f27b7ed69a998c39f5a03a878da5418ff51a0b53f63d5698666dfac0f6068
3
+ size 15024
checkpoint-65000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c64d5d876f5f3cd9bcc8ac13be8fd5a9909fcebda97dc97406e077234babeb5f
3
+ size 15024
checkpoint-65000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f4dfa6536086fb0b6a3cedd9f04bf7e1c0641495ca6ddbfb9a68d82ea60f193
3
+ size 15024
checkpoint-65000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6a024fb07f5d68d480985ee47b80c753fb9d681f032347615b5eff75286f471
3
+ size 15024
checkpoint-65000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:230f4e9a5b2bec07c54a4951ea39f15bff1e253bcced7bffbe05879b2e028423
3
+ size 1064
checkpoint-65000/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-65000/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-65000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c575bfc0f1e48abab95d19b3641d88b702fb559ab79e21f99d2893f304a8e96d
3
+ size 17110043
checkpoint-65000/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": "en_XX",
525
+ "tgt_lang": "ko_KR",
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
checkpoint-65000/trainer_state.json ADDED
@@ -0,0 +1,929 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 38.8455,
3
+ "best_model_checkpoint": "./enko_mbartLarge_36p_tokenize_run1/checkpoint-50000",
4
+ "epoch": 6.0392083991452195,
5
+ "eval_steps": 5000,
6
+ "global_step": 65000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05,
13
+ "learning_rate": 5e-05,
14
+ "loss": 1.9707,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.09,
19
+ "learning_rate": 4.9766638663306266e-05,
20
+ "loss": 1.5932,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.14,
25
+ "learning_rate": 4.953327732661253e-05,
26
+ "loss": 1.4429,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.19,
31
+ "learning_rate": 4.929991598991879e-05,
32
+ "loss": 1.4161,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.23,
37
+ "learning_rate": 4.9066554653225056e-05,
38
+ "loss": 1.386,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.28,
43
+ "learning_rate": 4.883319331653132e-05,
44
+ "loss": 1.3715,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.33,
49
+ "learning_rate": 4.859983197983758e-05,
50
+ "loss": 1.3461,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.37,
55
+ "learning_rate": 4.8366470643143846e-05,
56
+ "loss": 1.3319,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.42,
61
+ "learning_rate": 4.813310930645011e-05,
62
+ "loss": 1.3196,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.46,
67
+ "learning_rate": 4.789974796975637e-05,
68
+ "loss": 1.3157,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.46,
73
+ "eval_bleu": 34.4176,
74
+ "eval_gen_len": 16.4931,
75
+ "eval_loss": 1.2895288467407227,
76
+ "eval_runtime": 1334.0511,
77
+ "eval_samples_per_second": 16.195,
78
+ "eval_steps_per_second": 1.013,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 0.51,
83
+ "learning_rate": 4.7666386633062636e-05,
84
+ "loss": 1.2994,
85
+ "step": 5500
86
+ },
87
+ {
88
+ "epoch": 0.56,
89
+ "learning_rate": 4.74330252963689e-05,
90
+ "loss": 1.2914,
91
+ "step": 6000
92
+ },
93
+ {
94
+ "epoch": 0.6,
95
+ "learning_rate": 4.719966395967516e-05,
96
+ "loss": 1.2989,
97
+ "step": 6500
98
+ },
99
+ {
100
+ "epoch": 0.65,
101
+ "learning_rate": 4.6966302622981427e-05,
102
+ "loss": 1.2784,
103
+ "step": 7000
104
+ },
105
+ {
106
+ "epoch": 0.7,
107
+ "learning_rate": 4.673294128628769e-05,
108
+ "loss": 1.2662,
109
+ "step": 7500
110
+ },
111
+ {
112
+ "epoch": 0.74,
113
+ "learning_rate": 4.649957994959395e-05,
114
+ "loss": 1.2529,
115
+ "step": 8000
116
+ },
117
+ {
118
+ "epoch": 0.79,
119
+ "learning_rate": 4.626621861290022e-05,
120
+ "loss": 1.2614,
121
+ "step": 8500
122
+ },
123
+ {
124
+ "epoch": 0.84,
125
+ "learning_rate": 4.603285727620648e-05,
126
+ "loss": 1.2564,
127
+ "step": 9000
128
+ },
129
+ {
130
+ "epoch": 0.88,
131
+ "learning_rate": 4.5799495939512744e-05,
132
+ "loss": 1.2435,
133
+ "step": 9500
134
+ },
135
+ {
136
+ "epoch": 0.93,
137
+ "learning_rate": 4.556613460281901e-05,
138
+ "loss": 1.2575,
139
+ "step": 10000
140
+ },
141
+ {
142
+ "epoch": 0.93,
143
+ "eval_bleu": 35.0029,
144
+ "eval_gen_len": 16.8009,
145
+ "eval_loss": 1.2279398441314697,
146
+ "eval_runtime": 1342.4865,
147
+ "eval_samples_per_second": 16.093,
148
+ "eval_steps_per_second": 1.006,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 0.98,
153
+ "learning_rate": 4.533277326612527e-05,
154
+ "loss": 1.2473,
155
+ "step": 10500
156
+ },
157
+ {
158
+ "epoch": 1.02,
159
+ "learning_rate": 4.5099411929431534e-05,
160
+ "loss": 1.2544,
161
+ "step": 11000
162
+ },
163
+ {
164
+ "epoch": 1.07,
165
+ "learning_rate": 4.48660505927378e-05,
166
+ "loss": 1.207,
167
+ "step": 11500
168
+ },
169
+ {
170
+ "epoch": 1.11,
171
+ "learning_rate": 4.463268925604406e-05,
172
+ "loss": 1.1671,
173
+ "step": 12000
174
+ },
175
+ {
176
+ "epoch": 1.16,
177
+ "learning_rate": 4.4399327919350324e-05,
178
+ "loss": 1.1709,
179
+ "step": 12500
180
+ },
181
+ {
182
+ "epoch": 1.21,
183
+ "learning_rate": 4.416596658265659e-05,
184
+ "loss": 1.165,
185
+ "step": 13000
186
+ },
187
+ {
188
+ "epoch": 1.25,
189
+ "learning_rate": 4.393260524596285e-05,
190
+ "loss": 1.1727,
191
+ "step": 13500
192
+ },
193
+ {
194
+ "epoch": 1.3,
195
+ "learning_rate": 4.3699243909269114e-05,
196
+ "loss": 1.17,
197
+ "step": 14000
198
+ },
199
+ {
200
+ "epoch": 1.35,
201
+ "learning_rate": 4.346588257257538e-05,
202
+ "loss": 1.1465,
203
+ "step": 14500
204
+ },
205
+ {
206
+ "epoch": 1.39,
207
+ "learning_rate": 4.323252123588164e-05,
208
+ "loss": 1.1578,
209
+ "step": 15000
210
+ },
211
+ {
212
+ "epoch": 1.39,
213
+ "eval_bleu": 36.9282,
214
+ "eval_gen_len": 16.5838,
215
+ "eval_loss": 1.1733436584472656,
216
+ "eval_runtime": 1318.0972,
217
+ "eval_samples_per_second": 16.391,
218
+ "eval_steps_per_second": 1.025,
219
+ "step": 15000
220
+ },
221
+ {
222
+ "epoch": 1.44,
223
+ "learning_rate": 4.2999159899187904e-05,
224
+ "loss": 1.1582,
225
+ "step": 15500
226
+ },
227
+ {
228
+ "epoch": 1.49,
229
+ "learning_rate": 4.276579856249417e-05,
230
+ "loss": 1.1495,
231
+ "step": 16000
232
+ },
233
+ {
234
+ "epoch": 1.53,
235
+ "learning_rate": 4.253243722580043e-05,
236
+ "loss": 1.1349,
237
+ "step": 16500
238
+ },
239
+ {
240
+ "epoch": 1.58,
241
+ "learning_rate": 4.2299075889106695e-05,
242
+ "loss": 1.1443,
243
+ "step": 17000
244
+ },
245
+ {
246
+ "epoch": 1.63,
247
+ "learning_rate": 4.206571455241296e-05,
248
+ "loss": 1.1326,
249
+ "step": 17500
250
+ },
251
+ {
252
+ "epoch": 1.67,
253
+ "learning_rate": 4.183235321571922e-05,
254
+ "loss": 1.1425,
255
+ "step": 18000
256
+ },
257
+ {
258
+ "epoch": 1.72,
259
+ "learning_rate": 4.1598991879025485e-05,
260
+ "loss": 1.1196,
261
+ "step": 18500
262
+ },
263
+ {
264
+ "epoch": 1.77,
265
+ "learning_rate": 4.136563054233175e-05,
266
+ "loss": 1.1272,
267
+ "step": 19000
268
+ },
269
+ {
270
+ "epoch": 1.81,
271
+ "learning_rate": 4.113226920563801e-05,
272
+ "loss": 1.1186,
273
+ "step": 19500
274
+ },
275
+ {
276
+ "epoch": 1.86,
277
+ "learning_rate": 4.0898907868944275e-05,
278
+ "loss": 1.0885,
279
+ "step": 20000
280
+ },
281
+ {
282
+ "epoch": 1.86,
283
+ "eval_bleu": 37.6913,
284
+ "eval_gen_len": 16.6649,
285
+ "eval_loss": 1.1464108228683472,
286
+ "eval_runtime": 1319.4192,
287
+ "eval_samples_per_second": 16.375,
288
+ "eval_steps_per_second": 1.024,
289
+ "step": 20000
290
+ },
291
+ {
292
+ "epoch": 1.9,
293
+ "learning_rate": 4.066554653225054e-05,
294
+ "loss": 1.0541,
295
+ "step": 20500
296
+ },
297
+ {
298
+ "epoch": 1.95,
299
+ "learning_rate": 4.04321851955568e-05,
300
+ "loss": 1.0473,
301
+ "step": 21000
302
+ },
303
+ {
304
+ "epoch": 2.0,
305
+ "learning_rate": 4.0198823858863065e-05,
306
+ "loss": 1.0511,
307
+ "step": 21500
308
+ },
309
+ {
310
+ "epoch": 2.04,
311
+ "learning_rate": 3.996546252216933e-05,
312
+ "loss": 1.0647,
313
+ "step": 22000
314
+ },
315
+ {
316
+ "epoch": 2.09,
317
+ "learning_rate": 3.973210118547559e-05,
318
+ "loss": 1.0747,
319
+ "step": 22500
320
+ },
321
+ {
322
+ "epoch": 2.14,
323
+ "learning_rate": 3.9498739848781855e-05,
324
+ "loss": 1.044,
325
+ "step": 23000
326
+ },
327
+ {
328
+ "epoch": 2.18,
329
+ "learning_rate": 3.926537851208812e-05,
330
+ "loss": 1.052,
331
+ "step": 23500
332
+ },
333
+ {
334
+ "epoch": 2.23,
335
+ "learning_rate": 3.903201717539438e-05,
336
+ "loss": 1.0624,
337
+ "step": 24000
338
+ },
339
+ {
340
+ "epoch": 2.28,
341
+ "learning_rate": 3.8798655838700645e-05,
342
+ "loss": 1.0493,
343
+ "step": 24500
344
+ },
345
+ {
346
+ "epoch": 2.32,
347
+ "learning_rate": 3.856529450200691e-05,
348
+ "loss": 1.0451,
349
+ "step": 25000
350
+ },
351
+ {
352
+ "epoch": 2.32,
353
+ "eval_bleu": 37.7875,
354
+ "eval_gen_len": 16.5188,
355
+ "eval_loss": 1.1437026262283325,
356
+ "eval_runtime": 1315.5301,
357
+ "eval_samples_per_second": 16.423,
358
+ "eval_steps_per_second": 1.027,
359
+ "step": 25000
360
+ },
361
+ {
362
+ "epoch": 2.37,
363
+ "learning_rate": 3.833193316531317e-05,
364
+ "loss": 1.054,
365
+ "step": 25500
366
+ },
367
+ {
368
+ "epoch": 2.42,
369
+ "learning_rate": 3.8098571828619436e-05,
370
+ "loss": 1.0726,
371
+ "step": 26000
372
+ },
373
+ {
374
+ "epoch": 2.46,
375
+ "learning_rate": 3.78652104919257e-05,
376
+ "loss": 1.032,
377
+ "step": 26500
378
+ },
379
+ {
380
+ "epoch": 2.51,
381
+ "learning_rate": 3.763184915523196e-05,
382
+ "loss": 0.9733,
383
+ "step": 27000
384
+ },
385
+ {
386
+ "epoch": 2.56,
387
+ "learning_rate": 3.7398487818538226e-05,
388
+ "loss": 0.9602,
389
+ "step": 27500
390
+ },
391
+ {
392
+ "epoch": 2.6,
393
+ "learning_rate": 3.716512648184449e-05,
394
+ "loss": 0.9606,
395
+ "step": 28000
396
+ },
397
+ {
398
+ "epoch": 2.65,
399
+ "learning_rate": 3.693176514515075e-05,
400
+ "loss": 0.9968,
401
+ "step": 28500
402
+ },
403
+ {
404
+ "epoch": 2.69,
405
+ "learning_rate": 3.6698403808457016e-05,
406
+ "loss": 1.036,
407
+ "step": 29000
408
+ },
409
+ {
410
+ "epoch": 2.74,
411
+ "learning_rate": 3.646504247176328e-05,
412
+ "loss": 1.0285,
413
+ "step": 29500
414
+ },
415
+ {
416
+ "epoch": 2.79,
417
+ "learning_rate": 3.623168113506954e-05,
418
+ "loss": 1.0465,
419
+ "step": 30000
420
+ },
421
+ {
422
+ "epoch": 2.79,
423
+ "eval_bleu": 37.895,
424
+ "eval_gen_len": 16.4987,
425
+ "eval_loss": 1.1424869298934937,
426
+ "eval_runtime": 1301.3337,
427
+ "eval_samples_per_second": 16.602,
428
+ "eval_steps_per_second": 1.038,
429
+ "step": 30000
430
+ },
431
+ {
432
+ "epoch": 2.83,
433
+ "learning_rate": 3.5998319798375806e-05,
434
+ "loss": 1.0458,
435
+ "step": 30500
436
+ },
437
+ {
438
+ "epoch": 2.88,
439
+ "learning_rate": 3.576495846168207e-05,
440
+ "loss": 0.9843,
441
+ "step": 31000
442
+ },
443
+ {
444
+ "epoch": 2.93,
445
+ "learning_rate": 3.553159712498833e-05,
446
+ "loss": 0.9826,
447
+ "step": 31500
448
+ },
449
+ {
450
+ "epoch": 2.97,
451
+ "learning_rate": 3.5298235788294596e-05,
452
+ "loss": 0.9817,
453
+ "step": 32000
454
+ },
455
+ {
456
+ "epoch": 3.02,
457
+ "learning_rate": 3.506487445160086e-05,
458
+ "loss": 0.9911,
459
+ "step": 32500
460
+ },
461
+ {
462
+ "epoch": 3.07,
463
+ "learning_rate": 3.483151311490712e-05,
464
+ "loss": 1.0227,
465
+ "step": 33000
466
+ },
467
+ {
468
+ "epoch": 3.11,
469
+ "learning_rate": 3.459815177821339e-05,
470
+ "loss": 1.0126,
471
+ "step": 33500
472
+ },
473
+ {
474
+ "epoch": 3.16,
475
+ "learning_rate": 3.436479044151965e-05,
476
+ "loss": 1.0125,
477
+ "step": 34000
478
+ },
479
+ {
480
+ "epoch": 3.21,
481
+ "learning_rate": 3.4131429104825913e-05,
482
+ "loss": 1.0224,
483
+ "step": 34500
484
+ },
485
+ {
486
+ "epoch": 3.25,
487
+ "learning_rate": 3.389806776813218e-05,
488
+ "loss": 1.0156,
489
+ "step": 35000
490
+ },
491
+ {
492
+ "epoch": 3.25,
493
+ "eval_bleu": 37.8434,
494
+ "eval_gen_len": 16.5515,
495
+ "eval_loss": 1.1464043855667114,
496
+ "eval_runtime": 1324.0443,
497
+ "eval_samples_per_second": 16.317,
498
+ "eval_steps_per_second": 1.02,
499
+ "step": 35000
500
+ },
501
+ {
502
+ "epoch": 3.3,
503
+ "learning_rate": 3.366470643143844e-05,
504
+ "loss": 1.009,
505
+ "step": 35500
506
+ },
507
+ {
508
+ "epoch": 3.34,
509
+ "learning_rate": 3.3431345094744704e-05,
510
+ "loss": 0.964,
511
+ "step": 36000
512
+ },
513
+ {
514
+ "epoch": 3.39,
515
+ "learning_rate": 3.319798375805097e-05,
516
+ "loss": 0.9596,
517
+ "step": 36500
518
+ },
519
+ {
520
+ "epoch": 3.44,
521
+ "learning_rate": 3.296462242135723e-05,
522
+ "loss": 0.9587,
523
+ "step": 37000
524
+ },
525
+ {
526
+ "epoch": 3.48,
527
+ "learning_rate": 3.2731261084663494e-05,
528
+ "loss": 0.9024,
529
+ "step": 37500
530
+ },
531
+ {
532
+ "epoch": 3.53,
533
+ "learning_rate": 3.249789974796976e-05,
534
+ "loss": 0.9277,
535
+ "step": 38000
536
+ },
537
+ {
538
+ "epoch": 3.58,
539
+ "learning_rate": 3.226453841127603e-05,
540
+ "loss": 0.9486,
541
+ "step": 38500
542
+ },
543
+ {
544
+ "epoch": 3.62,
545
+ "learning_rate": 3.2031177074582284e-05,
546
+ "loss": 0.9543,
547
+ "step": 39000
548
+ },
549
+ {
550
+ "epoch": 3.67,
551
+ "learning_rate": 3.179781573788855e-05,
552
+ "loss": 1.0035,
553
+ "step": 39500
554
+ },
555
+ {
556
+ "epoch": 3.72,
557
+ "learning_rate": 3.156445440119481e-05,
558
+ "loss": 0.9893,
559
+ "step": 40000
560
+ },
561
+ {
562
+ "epoch": 3.72,
563
+ "eval_bleu": 37.358,
564
+ "eval_gen_len": 16.6096,
565
+ "eval_loss": 1.1543793678283691,
566
+ "eval_runtime": 1317.3643,
567
+ "eval_samples_per_second": 16.4,
568
+ "eval_steps_per_second": 1.026,
569
+ "step": 40000
570
+ },
571
+ {
572
+ "epoch": 3.76,
573
+ "learning_rate": 3.1331093064501074e-05,
574
+ "loss": 0.9877,
575
+ "step": 40500
576
+ },
577
+ {
578
+ "epoch": 3.81,
579
+ "learning_rate": 3.109773172780734e-05,
580
+ "loss": 0.9901,
581
+ "step": 41000
582
+ },
583
+ {
584
+ "epoch": 3.86,
585
+ "learning_rate": 3.08643703911136e-05,
586
+ "loss": 0.9699,
587
+ "step": 41500
588
+ },
589
+ {
590
+ "epoch": 3.9,
591
+ "learning_rate": 3.0631009054419864e-05,
592
+ "loss": 0.9425,
593
+ "step": 42000
594
+ },
595
+ {
596
+ "epoch": 3.95,
597
+ "learning_rate": 3.039764771772613e-05,
598
+ "loss": 0.9494,
599
+ "step": 42500
600
+ },
601
+ {
602
+ "epoch": 4.0,
603
+ "learning_rate": 3.016428638103239e-05,
604
+ "loss": 0.9508,
605
+ "step": 43000
606
+ },
607
+ {
608
+ "epoch": 4.04,
609
+ "learning_rate": 2.9930925044338655e-05,
610
+ "loss": 0.9409,
611
+ "step": 43500
612
+ },
613
+ {
614
+ "epoch": 4.09,
615
+ "learning_rate": 2.969756370764492e-05,
616
+ "loss": 0.9012,
617
+ "step": 44000
618
+ },
619
+ {
620
+ "epoch": 4.13,
621
+ "learning_rate": 2.946420237095118e-05,
622
+ "loss": 0.8723,
623
+ "step": 44500
624
+ },
625
+ {
626
+ "epoch": 4.18,
627
+ "learning_rate": 2.9230841034257445e-05,
628
+ "loss": 0.8779,
629
+ "step": 45000
630
+ },
631
+ {
632
+ "epoch": 4.18,
633
+ "eval_bleu": 38.1772,
634
+ "eval_gen_len": 16.457,
635
+ "eval_loss": 1.1419273614883423,
636
+ "eval_runtime": 1300.9539,
637
+ "eval_samples_per_second": 16.607,
638
+ "eval_steps_per_second": 1.038,
639
+ "step": 45000
640
+ },
641
+ {
642
+ "epoch": 4.23,
643
+ "learning_rate": 2.8997479697563705e-05,
644
+ "loss": 0.8922,
645
+ "step": 45500
646
+ },
647
+ {
648
+ "epoch": 4.27,
649
+ "learning_rate": 2.8764118360869975e-05,
650
+ "loss": 0.8749,
651
+ "step": 46000
652
+ },
653
+ {
654
+ "epoch": 4.32,
655
+ "learning_rate": 2.8530757024176235e-05,
656
+ "loss": 0.8625,
657
+ "step": 46500
658
+ },
659
+ {
660
+ "epoch": 4.37,
661
+ "learning_rate": 2.82973956874825e-05,
662
+ "loss": 0.8248,
663
+ "step": 47000
664
+ },
665
+ {
666
+ "epoch": 4.41,
667
+ "learning_rate": 2.8064034350788765e-05,
668
+ "loss": 0.8554,
669
+ "step": 47500
670
+ },
671
+ {
672
+ "epoch": 4.46,
673
+ "learning_rate": 2.7830673014095025e-05,
674
+ "loss": 0.8822,
675
+ "step": 48000
676
+ },
677
+ {
678
+ "epoch": 4.51,
679
+ "learning_rate": 2.759731167740129e-05,
680
+ "loss": 0.7873,
681
+ "step": 48500
682
+ },
683
+ {
684
+ "epoch": 4.55,
685
+ "learning_rate": 2.7363950340707552e-05,
686
+ "loss": 0.8181,
687
+ "step": 49000
688
+ },
689
+ {
690
+ "epoch": 4.6,
691
+ "learning_rate": 2.713058900401382e-05,
692
+ "loss": 0.8259,
693
+ "step": 49500
694
+ },
695
+ {
696
+ "epoch": 4.65,
697
+ "learning_rate": 2.689722766732008e-05,
698
+ "loss": 0.8565,
699
+ "step": 50000
700
+ },
701
+ {
702
+ "epoch": 4.65,
703
+ "eval_bleu": 38.8455,
704
+ "eval_gen_len": 16.4749,
705
+ "eval_loss": 1.1248719692230225,
706
+ "eval_runtime": 1294.4037,
707
+ "eval_samples_per_second": 16.691,
708
+ "eval_steps_per_second": 1.044,
709
+ "step": 50000
710
+ },
711
+ {
712
+ "epoch": 4.69,
713
+ "learning_rate": 2.6663866330626342e-05,
714
+ "loss": 0.9321,
715
+ "step": 50500
716
+ },
717
+ {
718
+ "epoch": 4.74,
719
+ "learning_rate": 2.643050499393261e-05,
720
+ "loss": 0.8021,
721
+ "step": 51000
722
+ },
723
+ {
724
+ "epoch": 4.78,
725
+ "learning_rate": 2.6197143657238872e-05,
726
+ "loss": 0.7701,
727
+ "step": 51500
728
+ },
729
+ {
730
+ "epoch": 4.83,
731
+ "learning_rate": 2.5963782320545132e-05,
732
+ "loss": 0.7838,
733
+ "step": 52000
734
+ },
735
+ {
736
+ "epoch": 4.88,
737
+ "learning_rate": 2.5730420983851396e-05,
738
+ "loss": 0.7467,
739
+ "step": 52500
740
+ },
741
+ {
742
+ "epoch": 4.92,
743
+ "learning_rate": 2.5497059647157663e-05,
744
+ "loss": 0.7778,
745
+ "step": 53000
746
+ },
747
+ {
748
+ "epoch": 4.97,
749
+ "learning_rate": 2.5263698310463923e-05,
750
+ "loss": 0.7451,
751
+ "step": 53500
752
+ },
753
+ {
754
+ "epoch": 5.02,
755
+ "learning_rate": 2.5030336973770186e-05,
756
+ "loss": 0.7485,
757
+ "step": 54000
758
+ },
759
+ {
760
+ "epoch": 5.06,
761
+ "learning_rate": 2.479697563707645e-05,
762
+ "loss": 0.7287,
763
+ "step": 54500
764
+ },
765
+ {
766
+ "epoch": 5.11,
767
+ "learning_rate": 2.4563614300382716e-05,
768
+ "loss": 0.7293,
769
+ "step": 55000
770
+ },
771
+ {
772
+ "epoch": 5.11,
773
+ "eval_bleu": 38.4853,
774
+ "eval_gen_len": 16.3462,
775
+ "eval_loss": 1.1566184759140015,
776
+ "eval_runtime": 1302.7449,
777
+ "eval_samples_per_second": 16.584,
778
+ "eval_steps_per_second": 1.037,
779
+ "step": 55000
780
+ },
781
+ {
782
+ "epoch": 5.16,
783
+ "learning_rate": 2.4330252963688976e-05,
784
+ "loss": 0.7792,
785
+ "step": 55500
786
+ },
787
+ {
788
+ "epoch": 5.2,
789
+ "learning_rate": 2.409689162699524e-05,
790
+ "loss": 0.7879,
791
+ "step": 56000
792
+ },
793
+ {
794
+ "epoch": 5.25,
795
+ "learning_rate": 2.3863530290301503e-05,
796
+ "loss": 0.7784,
797
+ "step": 56500
798
+ },
799
+ {
800
+ "epoch": 5.3,
801
+ "learning_rate": 2.3630168953607766e-05,
802
+ "loss": 0.7922,
803
+ "step": 57000
804
+ },
805
+ {
806
+ "epoch": 5.34,
807
+ "learning_rate": 2.3396807616914033e-05,
808
+ "loss": 0.7878,
809
+ "step": 57500
810
+ },
811
+ {
812
+ "epoch": 5.39,
813
+ "learning_rate": 2.3163446280220293e-05,
814
+ "loss": 0.7396,
815
+ "step": 58000
816
+ },
817
+ {
818
+ "epoch": 5.44,
819
+ "learning_rate": 2.293008494352656e-05,
820
+ "loss": 0.7602,
821
+ "step": 58500
822
+ },
823
+ {
824
+ "epoch": 5.48,
825
+ "learning_rate": 2.269672360683282e-05,
826
+ "loss": 0.7061,
827
+ "step": 59000
828
+ },
829
+ {
830
+ "epoch": 5.53,
831
+ "learning_rate": 2.2463362270139087e-05,
832
+ "loss": 0.6956,
833
+ "step": 59500
834
+ },
835
+ {
836
+ "epoch": 5.57,
837
+ "learning_rate": 2.2230000933445347e-05,
838
+ "loss": 0.7294,
839
+ "step": 60000
840
+ },
841
+ {
842
+ "epoch": 5.57,
843
+ "eval_bleu": 37.8822,
844
+ "eval_gen_len": 16.3295,
845
+ "eval_loss": 1.1824171543121338,
846
+ "eval_runtime": 1289.8042,
847
+ "eval_samples_per_second": 16.751,
848
+ "eval_steps_per_second": 1.047,
849
+ "step": 60000
850
+ },
851
+ {
852
+ "epoch": 5.62,
853
+ "learning_rate": 2.199663959675161e-05,
854
+ "loss": 0.7407,
855
+ "step": 60500
856
+ },
857
+ {
858
+ "epoch": 5.67,
859
+ "learning_rate": 2.1763278260057874e-05,
860
+ "loss": 0.8116,
861
+ "step": 61000
862
+ },
863
+ {
864
+ "epoch": 5.71,
865
+ "learning_rate": 2.1529916923364137e-05,
866
+ "loss": 0.8055,
867
+ "step": 61500
868
+ },
869
+ {
870
+ "epoch": 5.76,
871
+ "learning_rate": 2.1296555586670404e-05,
872
+ "loss": 0.7065,
873
+ "step": 62000
874
+ },
875
+ {
876
+ "epoch": 5.81,
877
+ "learning_rate": 2.1063194249976664e-05,
878
+ "loss": 0.688,
879
+ "step": 62500
880
+ },
881
+ {
882
+ "epoch": 5.85,
883
+ "learning_rate": 2.082983291328293e-05,
884
+ "loss": 0.6955,
885
+ "step": 63000
886
+ },
887
+ {
888
+ "epoch": 5.9,
889
+ "learning_rate": 2.059647157658919e-05,
890
+ "loss": 0.6782,
891
+ "step": 63500
892
+ },
893
+ {
894
+ "epoch": 5.95,
895
+ "learning_rate": 2.0363110239895454e-05,
896
+ "loss": 0.7089,
897
+ "step": 64000
898
+ },
899
+ {
900
+ "epoch": 5.99,
901
+ "learning_rate": 2.0129748903201717e-05,
902
+ "loss": 0.7563,
903
+ "step": 64500
904
+ },
905
+ {
906
+ "epoch": 6.04,
907
+ "learning_rate": 1.989638756650798e-05,
908
+ "loss": 0.7254,
909
+ "step": 65000
910
+ },
911
+ {
912
+ "epoch": 6.04,
913
+ "eval_bleu": 37.3612,
914
+ "eval_gen_len": 16.381,
915
+ "eval_loss": 1.2153156995773315,
916
+ "eval_runtime": 1293.9687,
917
+ "eval_samples_per_second": 16.697,
918
+ "eval_steps_per_second": 1.044,
919
+ "step": 65000
920
+ }
921
+ ],
922
+ "logging_steps": 500,
923
+ "max_steps": 107630,
924
+ "num_train_epochs": 10,
925
+ "save_steps": 5000,
926
+ "total_flos": 2.2540576769190134e+18,
927
+ "trial_name": null,
928
+ "trial_params": null
929
+ }
checkpoint-65000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5537df5d9b28eceb75a3afd4a4db4d0e3b695076e108e4c2d3ee734e37ad90f
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": 6.04,
3
+ "eval_bleu": 38.8566,
4
+ "eval_gen_len": 16.4716,
5
+ "eval_loss": 1.1248719692230225,
6
+ "eval_runtime": 1292.612,
7
+ "eval_samples": 21605,
8
+ "eval_samples_per_second": 16.714,
9
+ "eval_steps_per_second": 1.045
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": 38.9274,
3
+ "predict_gen_len": 16.5004,
4
+ "predict_loss": 1.1190268993377686,
5
+ "predict_runtime": 1297.778,
6
+ "predict_samples": 21606,
7
+ "predict_samples_per_second": 16.648,
8
+ "predict_steps_per_second": 1.041
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddcb9c9754bc4c2074c390655306feefb3edb3766101b16f114e8bca711b448e
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:c575bfc0f1e48abab95d19b3641d88b702fb559ab79e21f99d2893f304a8e96d
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": "en_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": 6.04,
3
+ "train_loss": 1.0097502070500302,
4
+ "train_runtime": 65202.0758,
5
+ "train_samples": 172202,
6
+ "train_samples_per_second": 26.411,
7
+ "train_steps_per_second": 1.651
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,938 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 38.8455,
3
+ "best_model_checkpoint": "./enko_mbartLarge_36p_tokenize_run1/checkpoint-50000",
4
+ "epoch": 6.0392083991452195,
5
+ "eval_steps": 5000,
6
+ "global_step": 65000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05,
13
+ "learning_rate": 5e-05,
14
+ "loss": 1.9707,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.09,
19
+ "learning_rate": 4.9766638663306266e-05,
20
+ "loss": 1.5932,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.14,
25
+ "learning_rate": 4.953327732661253e-05,
26
+ "loss": 1.4429,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.19,
31
+ "learning_rate": 4.929991598991879e-05,
32
+ "loss": 1.4161,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.23,
37
+ "learning_rate": 4.9066554653225056e-05,
38
+ "loss": 1.386,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.28,
43
+ "learning_rate": 4.883319331653132e-05,
44
+ "loss": 1.3715,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.33,
49
+ "learning_rate": 4.859983197983758e-05,
50
+ "loss": 1.3461,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.37,
55
+ "learning_rate": 4.8366470643143846e-05,
56
+ "loss": 1.3319,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.42,
61
+ "learning_rate": 4.813310930645011e-05,
62
+ "loss": 1.3196,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.46,
67
+ "learning_rate": 4.789974796975637e-05,
68
+ "loss": 1.3157,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.46,
73
+ "eval_bleu": 34.4176,
74
+ "eval_gen_len": 16.4931,
75
+ "eval_loss": 1.2895288467407227,
76
+ "eval_runtime": 1334.0511,
77
+ "eval_samples_per_second": 16.195,
78
+ "eval_steps_per_second": 1.013,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 0.51,
83
+ "learning_rate": 4.7666386633062636e-05,
84
+ "loss": 1.2994,
85
+ "step": 5500
86
+ },
87
+ {
88
+ "epoch": 0.56,
89
+ "learning_rate": 4.74330252963689e-05,
90
+ "loss": 1.2914,
91
+ "step": 6000
92
+ },
93
+ {
94
+ "epoch": 0.6,
95
+ "learning_rate": 4.719966395967516e-05,
96
+ "loss": 1.2989,
97
+ "step": 6500
98
+ },
99
+ {
100
+ "epoch": 0.65,
101
+ "learning_rate": 4.6966302622981427e-05,
102
+ "loss": 1.2784,
103
+ "step": 7000
104
+ },
105
+ {
106
+ "epoch": 0.7,
107
+ "learning_rate": 4.673294128628769e-05,
108
+ "loss": 1.2662,
109
+ "step": 7500
110
+ },
111
+ {
112
+ "epoch": 0.74,
113
+ "learning_rate": 4.649957994959395e-05,
114
+ "loss": 1.2529,
115
+ "step": 8000
116
+ },
117
+ {
118
+ "epoch": 0.79,
119
+ "learning_rate": 4.626621861290022e-05,
120
+ "loss": 1.2614,
121
+ "step": 8500
122
+ },
123
+ {
124
+ "epoch": 0.84,
125
+ "learning_rate": 4.603285727620648e-05,
126
+ "loss": 1.2564,
127
+ "step": 9000
128
+ },
129
+ {
130
+ "epoch": 0.88,
131
+ "learning_rate": 4.5799495939512744e-05,
132
+ "loss": 1.2435,
133
+ "step": 9500
134
+ },
135
+ {
136
+ "epoch": 0.93,
137
+ "learning_rate": 4.556613460281901e-05,
138
+ "loss": 1.2575,
139
+ "step": 10000
140
+ },
141
+ {
142
+ "epoch": 0.93,
143
+ "eval_bleu": 35.0029,
144
+ "eval_gen_len": 16.8009,
145
+ "eval_loss": 1.2279398441314697,
146
+ "eval_runtime": 1342.4865,
147
+ "eval_samples_per_second": 16.093,
148
+ "eval_steps_per_second": 1.006,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 0.98,
153
+ "learning_rate": 4.533277326612527e-05,
154
+ "loss": 1.2473,
155
+ "step": 10500
156
+ },
157
+ {
158
+ "epoch": 1.02,
159
+ "learning_rate": 4.5099411929431534e-05,
160
+ "loss": 1.2544,
161
+ "step": 11000
162
+ },
163
+ {
164
+ "epoch": 1.07,
165
+ "learning_rate": 4.48660505927378e-05,
166
+ "loss": 1.207,
167
+ "step": 11500
168
+ },
169
+ {
170
+ "epoch": 1.11,
171
+ "learning_rate": 4.463268925604406e-05,
172
+ "loss": 1.1671,
173
+ "step": 12000
174
+ },
175
+ {
176
+ "epoch": 1.16,
177
+ "learning_rate": 4.4399327919350324e-05,
178
+ "loss": 1.1709,
179
+ "step": 12500
180
+ },
181
+ {
182
+ "epoch": 1.21,
183
+ "learning_rate": 4.416596658265659e-05,
184
+ "loss": 1.165,
185
+ "step": 13000
186
+ },
187
+ {
188
+ "epoch": 1.25,
189
+ "learning_rate": 4.393260524596285e-05,
190
+ "loss": 1.1727,
191
+ "step": 13500
192
+ },
193
+ {
194
+ "epoch": 1.3,
195
+ "learning_rate": 4.3699243909269114e-05,
196
+ "loss": 1.17,
197
+ "step": 14000
198
+ },
199
+ {
200
+ "epoch": 1.35,
201
+ "learning_rate": 4.346588257257538e-05,
202
+ "loss": 1.1465,
203
+ "step": 14500
204
+ },
205
+ {
206
+ "epoch": 1.39,
207
+ "learning_rate": 4.323252123588164e-05,
208
+ "loss": 1.1578,
209
+ "step": 15000
210
+ },
211
+ {
212
+ "epoch": 1.39,
213
+ "eval_bleu": 36.9282,
214
+ "eval_gen_len": 16.5838,
215
+ "eval_loss": 1.1733436584472656,
216
+ "eval_runtime": 1318.0972,
217
+ "eval_samples_per_second": 16.391,
218
+ "eval_steps_per_second": 1.025,
219
+ "step": 15000
220
+ },
221
+ {
222
+ "epoch": 1.44,
223
+ "learning_rate": 4.2999159899187904e-05,
224
+ "loss": 1.1582,
225
+ "step": 15500
226
+ },
227
+ {
228
+ "epoch": 1.49,
229
+ "learning_rate": 4.276579856249417e-05,
230
+ "loss": 1.1495,
231
+ "step": 16000
232
+ },
233
+ {
234
+ "epoch": 1.53,
235
+ "learning_rate": 4.253243722580043e-05,
236
+ "loss": 1.1349,
237
+ "step": 16500
238
+ },
239
+ {
240
+ "epoch": 1.58,
241
+ "learning_rate": 4.2299075889106695e-05,
242
+ "loss": 1.1443,
243
+ "step": 17000
244
+ },
245
+ {
246
+ "epoch": 1.63,
247
+ "learning_rate": 4.206571455241296e-05,
248
+ "loss": 1.1326,
249
+ "step": 17500
250
+ },
251
+ {
252
+ "epoch": 1.67,
253
+ "learning_rate": 4.183235321571922e-05,
254
+ "loss": 1.1425,
255
+ "step": 18000
256
+ },
257
+ {
258
+ "epoch": 1.72,
259
+ "learning_rate": 4.1598991879025485e-05,
260
+ "loss": 1.1196,
261
+ "step": 18500
262
+ },
263
+ {
264
+ "epoch": 1.77,
265
+ "learning_rate": 4.136563054233175e-05,
266
+ "loss": 1.1272,
267
+ "step": 19000
268
+ },
269
+ {
270
+ "epoch": 1.81,
271
+ "learning_rate": 4.113226920563801e-05,
272
+ "loss": 1.1186,
273
+ "step": 19500
274
+ },
275
+ {
276
+ "epoch": 1.86,
277
+ "learning_rate": 4.0898907868944275e-05,
278
+ "loss": 1.0885,
279
+ "step": 20000
280
+ },
281
+ {
282
+ "epoch": 1.86,
283
+ "eval_bleu": 37.6913,
284
+ "eval_gen_len": 16.6649,
285
+ "eval_loss": 1.1464108228683472,
286
+ "eval_runtime": 1319.4192,
287
+ "eval_samples_per_second": 16.375,
288
+ "eval_steps_per_second": 1.024,
289
+ "step": 20000
290
+ },
291
+ {
292
+ "epoch": 1.9,
293
+ "learning_rate": 4.066554653225054e-05,
294
+ "loss": 1.0541,
295
+ "step": 20500
296
+ },
297
+ {
298
+ "epoch": 1.95,
299
+ "learning_rate": 4.04321851955568e-05,
300
+ "loss": 1.0473,
301
+ "step": 21000
302
+ },
303
+ {
304
+ "epoch": 2.0,
305
+ "learning_rate": 4.0198823858863065e-05,
306
+ "loss": 1.0511,
307
+ "step": 21500
308
+ },
309
+ {
310
+ "epoch": 2.04,
311
+ "learning_rate": 3.996546252216933e-05,
312
+ "loss": 1.0647,
313
+ "step": 22000
314
+ },
315
+ {
316
+ "epoch": 2.09,
317
+ "learning_rate": 3.973210118547559e-05,
318
+ "loss": 1.0747,
319
+ "step": 22500
320
+ },
321
+ {
322
+ "epoch": 2.14,
323
+ "learning_rate": 3.9498739848781855e-05,
324
+ "loss": 1.044,
325
+ "step": 23000
326
+ },
327
+ {
328
+ "epoch": 2.18,
329
+ "learning_rate": 3.926537851208812e-05,
330
+ "loss": 1.052,
331
+ "step": 23500
332
+ },
333
+ {
334
+ "epoch": 2.23,
335
+ "learning_rate": 3.903201717539438e-05,
336
+ "loss": 1.0624,
337
+ "step": 24000
338
+ },
339
+ {
340
+ "epoch": 2.28,
341
+ "learning_rate": 3.8798655838700645e-05,
342
+ "loss": 1.0493,
343
+ "step": 24500
344
+ },
345
+ {
346
+ "epoch": 2.32,
347
+ "learning_rate": 3.856529450200691e-05,
348
+ "loss": 1.0451,
349
+ "step": 25000
350
+ },
351
+ {
352
+ "epoch": 2.32,
353
+ "eval_bleu": 37.7875,
354
+ "eval_gen_len": 16.5188,
355
+ "eval_loss": 1.1437026262283325,
356
+ "eval_runtime": 1315.5301,
357
+ "eval_samples_per_second": 16.423,
358
+ "eval_steps_per_second": 1.027,
359
+ "step": 25000
360
+ },
361
+ {
362
+ "epoch": 2.37,
363
+ "learning_rate": 3.833193316531317e-05,
364
+ "loss": 1.054,
365
+ "step": 25500
366
+ },
367
+ {
368
+ "epoch": 2.42,
369
+ "learning_rate": 3.8098571828619436e-05,
370
+ "loss": 1.0726,
371
+ "step": 26000
372
+ },
373
+ {
374
+ "epoch": 2.46,
375
+ "learning_rate": 3.78652104919257e-05,
376
+ "loss": 1.032,
377
+ "step": 26500
378
+ },
379
+ {
380
+ "epoch": 2.51,
381
+ "learning_rate": 3.763184915523196e-05,
382
+ "loss": 0.9733,
383
+ "step": 27000
384
+ },
385
+ {
386
+ "epoch": 2.56,
387
+ "learning_rate": 3.7398487818538226e-05,
388
+ "loss": 0.9602,
389
+ "step": 27500
390
+ },
391
+ {
392
+ "epoch": 2.6,
393
+ "learning_rate": 3.716512648184449e-05,
394
+ "loss": 0.9606,
395
+ "step": 28000
396
+ },
397
+ {
398
+ "epoch": 2.65,
399
+ "learning_rate": 3.693176514515075e-05,
400
+ "loss": 0.9968,
401
+ "step": 28500
402
+ },
403
+ {
404
+ "epoch": 2.69,
405
+ "learning_rate": 3.6698403808457016e-05,
406
+ "loss": 1.036,
407
+ "step": 29000
408
+ },
409
+ {
410
+ "epoch": 2.74,
411
+ "learning_rate": 3.646504247176328e-05,
412
+ "loss": 1.0285,
413
+ "step": 29500
414
+ },
415
+ {
416
+ "epoch": 2.79,
417
+ "learning_rate": 3.623168113506954e-05,
418
+ "loss": 1.0465,
419
+ "step": 30000
420
+ },
421
+ {
422
+ "epoch": 2.79,
423
+ "eval_bleu": 37.895,
424
+ "eval_gen_len": 16.4987,
425
+ "eval_loss": 1.1424869298934937,
426
+ "eval_runtime": 1301.3337,
427
+ "eval_samples_per_second": 16.602,
428
+ "eval_steps_per_second": 1.038,
429
+ "step": 30000
430
+ },
431
+ {
432
+ "epoch": 2.83,
433
+ "learning_rate": 3.5998319798375806e-05,
434
+ "loss": 1.0458,
435
+ "step": 30500
436
+ },
437
+ {
438
+ "epoch": 2.88,
439
+ "learning_rate": 3.576495846168207e-05,
440
+ "loss": 0.9843,
441
+ "step": 31000
442
+ },
443
+ {
444
+ "epoch": 2.93,
445
+ "learning_rate": 3.553159712498833e-05,
446
+ "loss": 0.9826,
447
+ "step": 31500
448
+ },
449
+ {
450
+ "epoch": 2.97,
451
+ "learning_rate": 3.5298235788294596e-05,
452
+ "loss": 0.9817,
453
+ "step": 32000
454
+ },
455
+ {
456
+ "epoch": 3.02,
457
+ "learning_rate": 3.506487445160086e-05,
458
+ "loss": 0.9911,
459
+ "step": 32500
460
+ },
461
+ {
462
+ "epoch": 3.07,
463
+ "learning_rate": 3.483151311490712e-05,
464
+ "loss": 1.0227,
465
+ "step": 33000
466
+ },
467
+ {
468
+ "epoch": 3.11,
469
+ "learning_rate": 3.459815177821339e-05,
470
+ "loss": 1.0126,
471
+ "step": 33500
472
+ },
473
+ {
474
+ "epoch": 3.16,
475
+ "learning_rate": 3.436479044151965e-05,
476
+ "loss": 1.0125,
477
+ "step": 34000
478
+ },
479
+ {
480
+ "epoch": 3.21,
481
+ "learning_rate": 3.4131429104825913e-05,
482
+ "loss": 1.0224,
483
+ "step": 34500
484
+ },
485
+ {
486
+ "epoch": 3.25,
487
+ "learning_rate": 3.389806776813218e-05,
488
+ "loss": 1.0156,
489
+ "step": 35000
490
+ },
491
+ {
492
+ "epoch": 3.25,
493
+ "eval_bleu": 37.8434,
494
+ "eval_gen_len": 16.5515,
495
+ "eval_loss": 1.1464043855667114,
496
+ "eval_runtime": 1324.0443,
497
+ "eval_samples_per_second": 16.317,
498
+ "eval_steps_per_second": 1.02,
499
+ "step": 35000
500
+ },
501
+ {
502
+ "epoch": 3.3,
503
+ "learning_rate": 3.366470643143844e-05,
504
+ "loss": 1.009,
505
+ "step": 35500
506
+ },
507
+ {
508
+ "epoch": 3.34,
509
+ "learning_rate": 3.3431345094744704e-05,
510
+ "loss": 0.964,
511
+ "step": 36000
512
+ },
513
+ {
514
+ "epoch": 3.39,
515
+ "learning_rate": 3.319798375805097e-05,
516
+ "loss": 0.9596,
517
+ "step": 36500
518
+ },
519
+ {
520
+ "epoch": 3.44,
521
+ "learning_rate": 3.296462242135723e-05,
522
+ "loss": 0.9587,
523
+ "step": 37000
524
+ },
525
+ {
526
+ "epoch": 3.48,
527
+ "learning_rate": 3.2731261084663494e-05,
528
+ "loss": 0.9024,
529
+ "step": 37500
530
+ },
531
+ {
532
+ "epoch": 3.53,
533
+ "learning_rate": 3.249789974796976e-05,
534
+ "loss": 0.9277,
535
+ "step": 38000
536
+ },
537
+ {
538
+ "epoch": 3.58,
539
+ "learning_rate": 3.226453841127603e-05,
540
+ "loss": 0.9486,
541
+ "step": 38500
542
+ },
543
+ {
544
+ "epoch": 3.62,
545
+ "learning_rate": 3.2031177074582284e-05,
546
+ "loss": 0.9543,
547
+ "step": 39000
548
+ },
549
+ {
550
+ "epoch": 3.67,
551
+ "learning_rate": 3.179781573788855e-05,
552
+ "loss": 1.0035,
553
+ "step": 39500
554
+ },
555
+ {
556
+ "epoch": 3.72,
557
+ "learning_rate": 3.156445440119481e-05,
558
+ "loss": 0.9893,
559
+ "step": 40000
560
+ },
561
+ {
562
+ "epoch": 3.72,
563
+ "eval_bleu": 37.358,
564
+ "eval_gen_len": 16.6096,
565
+ "eval_loss": 1.1543793678283691,
566
+ "eval_runtime": 1317.3643,
567
+ "eval_samples_per_second": 16.4,
568
+ "eval_steps_per_second": 1.026,
569
+ "step": 40000
570
+ },
571
+ {
572
+ "epoch": 3.76,
573
+ "learning_rate": 3.1331093064501074e-05,
574
+ "loss": 0.9877,
575
+ "step": 40500
576
+ },
577
+ {
578
+ "epoch": 3.81,
579
+ "learning_rate": 3.109773172780734e-05,
580
+ "loss": 0.9901,
581
+ "step": 41000
582
+ },
583
+ {
584
+ "epoch": 3.86,
585
+ "learning_rate": 3.08643703911136e-05,
586
+ "loss": 0.9699,
587
+ "step": 41500
588
+ },
589
+ {
590
+ "epoch": 3.9,
591
+ "learning_rate": 3.0631009054419864e-05,
592
+ "loss": 0.9425,
593
+ "step": 42000
594
+ },
595
+ {
596
+ "epoch": 3.95,
597
+ "learning_rate": 3.039764771772613e-05,
598
+ "loss": 0.9494,
599
+ "step": 42500
600
+ },
601
+ {
602
+ "epoch": 4.0,
603
+ "learning_rate": 3.016428638103239e-05,
604
+ "loss": 0.9508,
605
+ "step": 43000
606
+ },
607
+ {
608
+ "epoch": 4.04,
609
+ "learning_rate": 2.9930925044338655e-05,
610
+ "loss": 0.9409,
611
+ "step": 43500
612
+ },
613
+ {
614
+ "epoch": 4.09,
615
+ "learning_rate": 2.969756370764492e-05,
616
+ "loss": 0.9012,
617
+ "step": 44000
618
+ },
619
+ {
620
+ "epoch": 4.13,
621
+ "learning_rate": 2.946420237095118e-05,
622
+ "loss": 0.8723,
623
+ "step": 44500
624
+ },
625
+ {
626
+ "epoch": 4.18,
627
+ "learning_rate": 2.9230841034257445e-05,
628
+ "loss": 0.8779,
629
+ "step": 45000
630
+ },
631
+ {
632
+ "epoch": 4.18,
633
+ "eval_bleu": 38.1772,
634
+ "eval_gen_len": 16.457,
635
+ "eval_loss": 1.1419273614883423,
636
+ "eval_runtime": 1300.9539,
637
+ "eval_samples_per_second": 16.607,
638
+ "eval_steps_per_second": 1.038,
639
+ "step": 45000
640
+ },
641
+ {
642
+ "epoch": 4.23,
643
+ "learning_rate": 2.8997479697563705e-05,
644
+ "loss": 0.8922,
645
+ "step": 45500
646
+ },
647
+ {
648
+ "epoch": 4.27,
649
+ "learning_rate": 2.8764118360869975e-05,
650
+ "loss": 0.8749,
651
+ "step": 46000
652
+ },
653
+ {
654
+ "epoch": 4.32,
655
+ "learning_rate": 2.8530757024176235e-05,
656
+ "loss": 0.8625,
657
+ "step": 46500
658
+ },
659
+ {
660
+ "epoch": 4.37,
661
+ "learning_rate": 2.82973956874825e-05,
662
+ "loss": 0.8248,
663
+ "step": 47000
664
+ },
665
+ {
666
+ "epoch": 4.41,
667
+ "learning_rate": 2.8064034350788765e-05,
668
+ "loss": 0.8554,
669
+ "step": 47500
670
+ },
671
+ {
672
+ "epoch": 4.46,
673
+ "learning_rate": 2.7830673014095025e-05,
674
+ "loss": 0.8822,
675
+ "step": 48000
676
+ },
677
+ {
678
+ "epoch": 4.51,
679
+ "learning_rate": 2.759731167740129e-05,
680
+ "loss": 0.7873,
681
+ "step": 48500
682
+ },
683
+ {
684
+ "epoch": 4.55,
685
+ "learning_rate": 2.7363950340707552e-05,
686
+ "loss": 0.8181,
687
+ "step": 49000
688
+ },
689
+ {
690
+ "epoch": 4.6,
691
+ "learning_rate": 2.713058900401382e-05,
692
+ "loss": 0.8259,
693
+ "step": 49500
694
+ },
695
+ {
696
+ "epoch": 4.65,
697
+ "learning_rate": 2.689722766732008e-05,
698
+ "loss": 0.8565,
699
+ "step": 50000
700
+ },
701
+ {
702
+ "epoch": 4.65,
703
+ "eval_bleu": 38.8455,
704
+ "eval_gen_len": 16.4749,
705
+ "eval_loss": 1.1248719692230225,
706
+ "eval_runtime": 1294.4037,
707
+ "eval_samples_per_second": 16.691,
708
+ "eval_steps_per_second": 1.044,
709
+ "step": 50000
710
+ },
711
+ {
712
+ "epoch": 4.69,
713
+ "learning_rate": 2.6663866330626342e-05,
714
+ "loss": 0.9321,
715
+ "step": 50500
716
+ },
717
+ {
718
+ "epoch": 4.74,
719
+ "learning_rate": 2.643050499393261e-05,
720
+ "loss": 0.8021,
721
+ "step": 51000
722
+ },
723
+ {
724
+ "epoch": 4.78,
725
+ "learning_rate": 2.6197143657238872e-05,
726
+ "loss": 0.7701,
727
+ "step": 51500
728
+ },
729
+ {
730
+ "epoch": 4.83,
731
+ "learning_rate": 2.5963782320545132e-05,
732
+ "loss": 0.7838,
733
+ "step": 52000
734
+ },
735
+ {
736
+ "epoch": 4.88,
737
+ "learning_rate": 2.5730420983851396e-05,
738
+ "loss": 0.7467,
739
+ "step": 52500
740
+ },
741
+ {
742
+ "epoch": 4.92,
743
+ "learning_rate": 2.5497059647157663e-05,
744
+ "loss": 0.7778,
745
+ "step": 53000
746
+ },
747
+ {
748
+ "epoch": 4.97,
749
+ "learning_rate": 2.5263698310463923e-05,
750
+ "loss": 0.7451,
751
+ "step": 53500
752
+ },
753
+ {
754
+ "epoch": 5.02,
755
+ "learning_rate": 2.5030336973770186e-05,
756
+ "loss": 0.7485,
757
+ "step": 54000
758
+ },
759
+ {
760
+ "epoch": 5.06,
761
+ "learning_rate": 2.479697563707645e-05,
762
+ "loss": 0.7287,
763
+ "step": 54500
764
+ },
765
+ {
766
+ "epoch": 5.11,
767
+ "learning_rate": 2.4563614300382716e-05,
768
+ "loss": 0.7293,
769
+ "step": 55000
770
+ },
771
+ {
772
+ "epoch": 5.11,
773
+ "eval_bleu": 38.4853,
774
+ "eval_gen_len": 16.3462,
775
+ "eval_loss": 1.1566184759140015,
776
+ "eval_runtime": 1302.7449,
777
+ "eval_samples_per_second": 16.584,
778
+ "eval_steps_per_second": 1.037,
779
+ "step": 55000
780
+ },
781
+ {
782
+ "epoch": 5.16,
783
+ "learning_rate": 2.4330252963688976e-05,
784
+ "loss": 0.7792,
785
+ "step": 55500
786
+ },
787
+ {
788
+ "epoch": 5.2,
789
+ "learning_rate": 2.409689162699524e-05,
790
+ "loss": 0.7879,
791
+ "step": 56000
792
+ },
793
+ {
794
+ "epoch": 5.25,
795
+ "learning_rate": 2.3863530290301503e-05,
796
+ "loss": 0.7784,
797
+ "step": 56500
798
+ },
799
+ {
800
+ "epoch": 5.3,
801
+ "learning_rate": 2.3630168953607766e-05,
802
+ "loss": 0.7922,
803
+ "step": 57000
804
+ },
805
+ {
806
+ "epoch": 5.34,
807
+ "learning_rate": 2.3396807616914033e-05,
808
+ "loss": 0.7878,
809
+ "step": 57500
810
+ },
811
+ {
812
+ "epoch": 5.39,
813
+ "learning_rate": 2.3163446280220293e-05,
814
+ "loss": 0.7396,
815
+ "step": 58000
816
+ },
817
+ {
818
+ "epoch": 5.44,
819
+ "learning_rate": 2.293008494352656e-05,
820
+ "loss": 0.7602,
821
+ "step": 58500
822
+ },
823
+ {
824
+ "epoch": 5.48,
825
+ "learning_rate": 2.269672360683282e-05,
826
+ "loss": 0.7061,
827
+ "step": 59000
828
+ },
829
+ {
830
+ "epoch": 5.53,
831
+ "learning_rate": 2.2463362270139087e-05,
832
+ "loss": 0.6956,
833
+ "step": 59500
834
+ },
835
+ {
836
+ "epoch": 5.57,
837
+ "learning_rate": 2.2230000933445347e-05,
838
+ "loss": 0.7294,
839
+ "step": 60000
840
+ },
841
+ {
842
+ "epoch": 5.57,
843
+ "eval_bleu": 37.8822,
844
+ "eval_gen_len": 16.3295,
845
+ "eval_loss": 1.1824171543121338,
846
+ "eval_runtime": 1289.8042,
847
+ "eval_samples_per_second": 16.751,
848
+ "eval_steps_per_second": 1.047,
849
+ "step": 60000
850
+ },
851
+ {
852
+ "epoch": 5.62,
853
+ "learning_rate": 2.199663959675161e-05,
854
+ "loss": 0.7407,
855
+ "step": 60500
856
+ },
857
+ {
858
+ "epoch": 5.67,
859
+ "learning_rate": 2.1763278260057874e-05,
860
+ "loss": 0.8116,
861
+ "step": 61000
862
+ },
863
+ {
864
+ "epoch": 5.71,
865
+ "learning_rate": 2.1529916923364137e-05,
866
+ "loss": 0.8055,
867
+ "step": 61500
868
+ },
869
+ {
870
+ "epoch": 5.76,
871
+ "learning_rate": 2.1296555586670404e-05,
872
+ "loss": 0.7065,
873
+ "step": 62000
874
+ },
875
+ {
876
+ "epoch": 5.81,
877
+ "learning_rate": 2.1063194249976664e-05,
878
+ "loss": 0.688,
879
+ "step": 62500
880
+ },
881
+ {
882
+ "epoch": 5.85,
883
+ "learning_rate": 2.082983291328293e-05,
884
+ "loss": 0.6955,
885
+ "step": 63000
886
+ },
887
+ {
888
+ "epoch": 5.9,
889
+ "learning_rate": 2.059647157658919e-05,
890
+ "loss": 0.6782,
891
+ "step": 63500
892
+ },
893
+ {
894
+ "epoch": 5.95,
895
+ "learning_rate": 2.0363110239895454e-05,
896
+ "loss": 0.7089,
897
+ "step": 64000
898
+ },
899
+ {
900
+ "epoch": 5.99,
901
+ "learning_rate": 2.0129748903201717e-05,
902
+ "loss": 0.7563,
903
+ "step": 64500
904
+ },
905
+ {
906
+ "epoch": 6.04,
907
+ "learning_rate": 1.989638756650798e-05,
908
+ "loss": 0.7254,
909
+ "step": 65000
910
+ },
911
+ {
912
+ "epoch": 6.04,
913
+ "eval_bleu": 37.3612,
914
+ "eval_gen_len": 16.381,
915
+ "eval_loss": 1.2153156995773315,
916
+ "eval_runtime": 1293.9687,
917
+ "eval_samples_per_second": 16.697,
918
+ "eval_steps_per_second": 1.044,
919
+ "step": 65000
920
+ },
921
+ {
922
+ "epoch": 6.04,
923
+ "step": 65000,
924
+ "total_flos": 2.2540576769190134e+18,
925
+ "train_loss": 1.0097502070500302,
926
+ "train_runtime": 65202.0758,
927
+ "train_samples_per_second": 26.411,
928
+ "train_steps_per_second": 1.651
929
+ }
930
+ ],
931
+ "logging_steps": 500,
932
+ "max_steps": 107630,
933
+ "num_train_epochs": 10,
934
+ "save_steps": 5000,
935
+ "total_flos": 2.2540576769190134e+18,
936
+ "trial_name": null,
937
+ "trial_params": null
938
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5537df5d9b28eceb75a3afd4a4db4d0e3b695076e108e4c2d3ee734e37ad90f
3
+ size 4728