yesj1234 commited on
Commit
50d86e6
·
1 Parent(s): 7fe46ff

Upload folder using huggingface_hub

Browse files
Files changed (49) hide show
  1. .gitattributes +3 -0
  2. README.md +86 -0
  3. added_tokens.json +59 -0
  4. all_results.json +22 -0
  5. checkpoint-60000/added_tokens.json +59 -0
  6. checkpoint-60000/config.json +59 -0
  7. checkpoint-60000/generation_config.json +12 -0
  8. checkpoint-60000/optimizer.pt +3 -0
  9. checkpoint-60000/pytorch_model.bin +3 -0
  10. checkpoint-60000/rng_state_0.pth +3 -0
  11. checkpoint-60000/rng_state_1.pth +3 -0
  12. checkpoint-60000/rng_state_2.pth +3 -0
  13. checkpoint-60000/rng_state_3.pth +3 -0
  14. checkpoint-60000/scheduler.pt +3 -0
  15. checkpoint-60000/sentencepiece.bpe.model +3 -0
  16. checkpoint-60000/special_tokens_map.json +63 -0
  17. checkpoint-60000/tokenizer.json +3 -0
  18. checkpoint-60000/tokenizer_config.json +528 -0
  19. checkpoint-60000/trainer_state.json +889 -0
  20. checkpoint-60000/training_args.bin +3 -0
  21. checkpoint-76000/added_tokens.json +59 -0
  22. checkpoint-76000/config.json +59 -0
  23. checkpoint-76000/generation_config.json +12 -0
  24. checkpoint-76000/optimizer.pt +3 -0
  25. checkpoint-76000/pytorch_model.bin +3 -0
  26. checkpoint-76000/rng_state_0.pth +3 -0
  27. checkpoint-76000/rng_state_1.pth +3 -0
  28. checkpoint-76000/rng_state_2.pth +3 -0
  29. checkpoint-76000/rng_state_3.pth +3 -0
  30. checkpoint-76000/scheduler.pt +3 -0
  31. checkpoint-76000/sentencepiece.bpe.model +3 -0
  32. checkpoint-76000/special_tokens_map.json +63 -0
  33. checkpoint-76000/tokenizer.json +3 -0
  34. checkpoint-76000/tokenizer_config.json +528 -0
  35. checkpoint-76000/trainer_state.json +1121 -0
  36. checkpoint-76000/training_args.bin +3 -0
  37. config.json +59 -0
  38. eval_results.json +10 -0
  39. generated_predictions.txt +0 -0
  40. generation_config.json +12 -0
  41. predict_results.json +9 -0
  42. pytorch_model.bin +3 -0
  43. sentencepiece.bpe.model +3 -0
  44. special_tokens_map.json +63 -0
  45. tokenizer.json +3 -0
  46. tokenizer_config.json +528 -0
  47. train_results.json +8 -0
  48. trainer_state.json +1130 -0
  49. 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-60000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-76000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ko
4
+ - en
5
+ base_model: facebook/mbart-large-50-many-to-many-mmt
6
+ tags:
7
+ - generated_from_trainer
8
+ metrics:
9
+ - bleu
10
+ model-index:
11
+ - name: ko-en_mbartLarge_exp20p_linear_alpha
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # ko-en_mbartLarge_exp20p_linear_alpha
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: 1.1682
23
+ - Bleu: 29.1144
24
+ - Gen Len: 18.5459
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: 5.5e-05
44
+ - train_batch_size: 4
45
+ - eval_batch_size: 4
46
+ - seed: 42
47
+ - distributed_type: multi-GPU
48
+ - num_devices: 4
49
+ - gradient_accumulation_steps: 2
50
+ - total_train_batch_size: 32
51
+ - total_eval_batch_size: 16
52
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
+ - lr_scheduler_type: linear
54
+ - num_epochs: 40
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
59
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
60
+ | 1.404 | 0.46 | 4000 | 1.3738 | 22.5375 | 18.6852 |
61
+ | 1.2629 | 0.93 | 8000 | 1.2458 | 25.3741 | 18.7797 |
62
+ | 1.1951 | 1.39 | 12000 | 1.2067 | 26.1281 | 18.6597 |
63
+ | 1.1317 | 1.86 | 16000 | 1.1768 | 26.5384 | 19.2055 |
64
+ | 0.9906 | 2.32 | 20000 | 1.1363 | 28.2459 | 18.7269 |
65
+ | 0.9894 | 2.78 | 24000 | 1.1239 | 28.5124 | 18.6882 |
66
+ | 0.8965 | 3.25 | 28000 | 1.1278 | 28.5335 | 18.4917 |
67
+ | 0.9138 | 3.71 | 32000 | 1.1216 | 28.8189 | 18.7873 |
68
+ | 0.8272 | 4.18 | 36000 | 1.1468 | 28.332 | 18.6516 |
69
+ | 0.8753 | 4.64 | 40000 | 1.1345 | 28.2695 | 18.4919 |
70
+ | 0.6855 | 5.11 | 44000 | 1.1542 | 28.7913 | 18.7596 |
71
+ | 0.7088 | 5.57 | 48000 | 1.1531 | 29.0865 | 18.6626 |
72
+ | 0.6738 | 6.03 | 52000 | 1.1906 | 28.0235 | 18.4243 |
73
+ | 0.6763 | 6.5 | 56000 | 1.1941 | 28.1501 | 18.6932 |
74
+ | 0.6594 | 6.96 | 60000 | 1.1682 | 29.1144 | 18.5459 |
75
+ | 0.5971 | 7.43 | 64000 | 1.2449 | 27.9464 | 18.4482 |
76
+ | 0.5935 | 7.89 | 68000 | 1.2156 | 28.6034 | 18.5967 |
77
+ | 0.5383 | 8.35 | 72000 | 1.2927 | 27.891 | 18.6539 |
78
+ | 0.6022 | 8.82 | 76000 | 1.2831 | 27.7624 | 18.5558 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - Transformers 4.34.0
84
+ - Pytorch 2.1.0+cu121
85
+ - Datasets 2.14.5
86
+ - Tokenizers 0.14.1
added_tokens.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<mask>": 250053,
4
+ "<pad>": 1,
5
+ "<s>": 0,
6
+ "<unk>": 3,
7
+ "af_ZA": 250026,
8
+ "ar_AR": 250001,
9
+ "az_AZ": 250027,
10
+ "bn_IN": 250028,
11
+ "cs_CZ": 250002,
12
+ "de_DE": 250003,
13
+ "en_XX": 250004,
14
+ "es_XX": 250005,
15
+ "et_EE": 250006,
16
+ "fa_IR": 250029,
17
+ "fi_FI": 250007,
18
+ "fr_XX": 250008,
19
+ "gl_ES": 250051,
20
+ "gu_IN": 250009,
21
+ "he_IL": 250030,
22
+ "hi_IN": 250010,
23
+ "hr_HR": 250031,
24
+ "id_ID": 250032,
25
+ "it_IT": 250011,
26
+ "ja_XX": 250012,
27
+ "ka_GE": 250033,
28
+ "kk_KZ": 250013,
29
+ "km_KH": 250034,
30
+ "ko_KR": 250014,
31
+ "lt_LT": 250015,
32
+ "lv_LV": 250016,
33
+ "mk_MK": 250035,
34
+ "ml_IN": 250036,
35
+ "mn_MN": 250037,
36
+ "mr_IN": 250038,
37
+ "my_MM": 250017,
38
+ "ne_NP": 250018,
39
+ "nl_XX": 250019,
40
+ "pl_PL": 250039,
41
+ "ps_AF": 250040,
42
+ "pt_XX": 250041,
43
+ "ro_RO": 250020,
44
+ "ru_RU": 250021,
45
+ "si_LK": 250022,
46
+ "sl_SI": 250052,
47
+ "sv_SE": 250042,
48
+ "sw_KE": 250043,
49
+ "ta_IN": 250044,
50
+ "te_IN": 250045,
51
+ "th_TH": 250046,
52
+ "tl_XX": 250047,
53
+ "tr_TR": 250023,
54
+ "uk_UA": 250048,
55
+ "ur_PK": 250049,
56
+ "vi_VN": 250024,
57
+ "xh_ZA": 250050,
58
+ "zh_CN": 250025
59
+ }
all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 8.82,
3
+ "eval_bleu": 29.1144,
4
+ "eval_gen_len": 18.5459,
5
+ "eval_loss": 1.1682050228118896,
6
+ "eval_runtime": 1138.2217,
7
+ "eval_samples": 17237,
8
+ "eval_samples_per_second": 15.144,
9
+ "eval_steps_per_second": 0.947,
10
+ "predict_bleu": 29.2336,
11
+ "predict_gen_len": 18.5319,
12
+ "predict_loss": 1.1511610746383667,
13
+ "predict_runtime": 1143.8858,
14
+ "predict_samples": 17237,
15
+ "predict_samples_per_second": 15.069,
16
+ "predict_steps_per_second": 0.942,
17
+ "train_loss": 0.8847039678473222,
18
+ "train_runtime": 77092.0129,
19
+ "train_samples": 137900,
20
+ "train_samples_per_second": 71.551,
21
+ "train_steps_per_second": 4.472
22
+ }
checkpoint-60000/added_tokens.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<mask>": 250053,
4
+ "<pad>": 1,
5
+ "<s>": 0,
6
+ "<unk>": 3,
7
+ "af_ZA": 250026,
8
+ "ar_AR": 250001,
9
+ "az_AZ": 250027,
10
+ "bn_IN": 250028,
11
+ "cs_CZ": 250002,
12
+ "de_DE": 250003,
13
+ "en_XX": 250004,
14
+ "es_XX": 250005,
15
+ "et_EE": 250006,
16
+ "fa_IR": 250029,
17
+ "fi_FI": 250007,
18
+ "fr_XX": 250008,
19
+ "gl_ES": 250051,
20
+ "gu_IN": 250009,
21
+ "he_IL": 250030,
22
+ "hi_IN": 250010,
23
+ "hr_HR": 250031,
24
+ "id_ID": 250032,
25
+ "it_IT": 250011,
26
+ "ja_XX": 250012,
27
+ "ka_GE": 250033,
28
+ "kk_KZ": 250013,
29
+ "km_KH": 250034,
30
+ "ko_KR": 250014,
31
+ "lt_LT": 250015,
32
+ "lv_LV": 250016,
33
+ "mk_MK": 250035,
34
+ "ml_IN": 250036,
35
+ "mn_MN": 250037,
36
+ "mr_IN": 250038,
37
+ "my_MM": 250017,
38
+ "ne_NP": 250018,
39
+ "nl_XX": 250019,
40
+ "pl_PL": 250039,
41
+ "ps_AF": 250040,
42
+ "pt_XX": 250041,
43
+ "ro_RO": 250020,
44
+ "ru_RU": 250021,
45
+ "si_LK": 250022,
46
+ "sl_SI": 250052,
47
+ "sv_SE": 250042,
48
+ "sw_KE": 250043,
49
+ "ta_IN": 250044,
50
+ "te_IN": 250045,
51
+ "th_TH": 250046,
52
+ "tl_XX": 250047,
53
+ "tr_TR": 250023,
54
+ "uk_UA": 250048,
55
+ "ur_PK": 250049,
56
+ "vi_VN": 250024,
57
+ "xh_ZA": 250050,
58
+ "zh_CN": 250025
59
+ }
checkpoint-60000/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": true,
8
+ "architectures": [
9
+ "MBartForConditionalGeneration"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 1024,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 4096,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 12,
20
+ "decoder_start_token_id": 2,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 2,
28
+ "forced_bos_token_id": 250004,
29
+ "forced_eos_token_id": 2,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "max_length": 200,
44
+ "max_position_embeddings": 1024,
45
+ "model_type": "mbart",
46
+ "normalize_before": true,
47
+ "normalize_embedding": true,
48
+ "num_beams": 5,
49
+ "num_hidden_layers": 12,
50
+ "output_past": true,
51
+ "pad_token_id": 1,
52
+ "scale_embedding": true,
53
+ "static_position_embeddings": false,
54
+ "tokenizer_class": "MBart50Tokenizer",
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.34.0",
57
+ "use_cache": true,
58
+ "vocab_size": 250054
59
+ }
checkpoint-60000/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "forced_bos_token_id": 250004,
7
+ "forced_eos_token_id": 2,
8
+ "max_length": 200,
9
+ "num_beams": 5,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.34.0"
12
+ }
checkpoint-60000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f1a29ebb712467f96461895e6d4be0a8a0a3819259d2d2b18bc5a02709b7705
3
+ size 4887473903
checkpoint-60000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a465d06942b45eaada7790ed77f43e70b8bab3ac5e5a6ed682cb0ce1351e6b79
3
+ size 2444694490
checkpoint-60000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddd94a2f98f6527dd829619b426e00b09b72105a0a50d515ad8d341fab3fceb5
3
+ size 15024
checkpoint-60000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe09369bb01e96cdf251292ed1c8b4dade1f5afafdb2b7628f0901e9f095492d
3
+ size 15024
checkpoint-60000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7b4a869926519f11b2aea1ca9405011f6166d6011d8d0e07552017032a4a9ba
3
+ size 15024
checkpoint-60000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fc25d38f561ccfa43435d6ef5519c390bc343538761ad6217b5f954a0db7f01
3
+ size 15024
checkpoint-60000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eadf47d6eb93e4927739e5598674dfd299acf75824e4eeaa19d4793dcfdd39f9
3
+ size 1064
checkpoint-60000/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-60000/special_tokens_map.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN",
28
+ "af_ZA",
29
+ "az_AZ",
30
+ "bn_IN",
31
+ "fa_IR",
32
+ "he_IL",
33
+ "hr_HR",
34
+ "id_ID",
35
+ "ka_GE",
36
+ "km_KH",
37
+ "mk_MK",
38
+ "ml_IN",
39
+ "mn_MN",
40
+ "mr_IN",
41
+ "pl_PL",
42
+ "ps_AF",
43
+ "pt_XX",
44
+ "sv_SE",
45
+ "sw_KE",
46
+ "ta_IN",
47
+ "te_IN",
48
+ "th_TH",
49
+ "tl_XX",
50
+ "uk_UA",
51
+ "ur_PK",
52
+ "xh_ZA",
53
+ "gl_ES",
54
+ "sl_SI"
55
+ ],
56
+ "bos_token": "<s>",
57
+ "cls_token": "<s>",
58
+ "eos_token": "</s>",
59
+ "mask_token": "<mask>",
60
+ "pad_token": "<pad>",
61
+ "sep_token": "</s>",
62
+ "unk_token": "<unk>"
63
+ }
checkpoint-60000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3a71a6430f26d8667787032844b9efe0d820460f1eb2e56a96b5f171813bc1a
3
+ size 17109939
checkpoint-60000/tokenizer_config.json ADDED
@@ -0,0 +1,528 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "ar_AR",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "250002": {
44
+ "content": "cs_CZ",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "250003": {
52
+ "content": "de_DE",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "250004": {
60
+ "content": "en_XX",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "250005": {
68
+ "content": "es_XX",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "250006": {
76
+ "content": "et_EE",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "250007": {
84
+ "content": "fi_FI",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "250008": {
92
+ "content": "fr_XX",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "250009": {
100
+ "content": "gu_IN",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "250010": {
108
+ "content": "hi_IN",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "250011": {
116
+ "content": "it_IT",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "250012": {
124
+ "content": "ja_XX",
125
+ "lstrip": true,
126
+ "normalized": false,
127
+ "rstrip": true,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "250013": {
132
+ "content": "kk_KZ",
133
+ "lstrip": true,
134
+ "normalized": false,
135
+ "rstrip": true,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "250014": {
140
+ "content": "ko_KR",
141
+ "lstrip": true,
142
+ "normalized": false,
143
+ "rstrip": true,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "250015": {
148
+ "content": "lt_LT",
149
+ "lstrip": true,
150
+ "normalized": false,
151
+ "rstrip": true,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "250016": {
156
+ "content": "lv_LV",
157
+ "lstrip": true,
158
+ "normalized": false,
159
+ "rstrip": true,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "250017": {
164
+ "content": "my_MM",
165
+ "lstrip": true,
166
+ "normalized": false,
167
+ "rstrip": true,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "250018": {
172
+ "content": "ne_NP",
173
+ "lstrip": true,
174
+ "normalized": false,
175
+ "rstrip": true,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "250019": {
180
+ "content": "nl_XX",
181
+ "lstrip": true,
182
+ "normalized": false,
183
+ "rstrip": true,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "250020": {
188
+ "content": "ro_RO",
189
+ "lstrip": true,
190
+ "normalized": false,
191
+ "rstrip": true,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "250021": {
196
+ "content": "ru_RU",
197
+ "lstrip": true,
198
+ "normalized": false,
199
+ "rstrip": true,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "250022": {
204
+ "content": "si_LK",
205
+ "lstrip": true,
206
+ "normalized": false,
207
+ "rstrip": true,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "250023": {
212
+ "content": "tr_TR",
213
+ "lstrip": true,
214
+ "normalized": false,
215
+ "rstrip": true,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "250024": {
220
+ "content": "vi_VN",
221
+ "lstrip": true,
222
+ "normalized": false,
223
+ "rstrip": true,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "250025": {
228
+ "content": "zh_CN",
229
+ "lstrip": true,
230
+ "normalized": false,
231
+ "rstrip": true,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "250026": {
236
+ "content": "af_ZA",
237
+ "lstrip": true,
238
+ "normalized": false,
239
+ "rstrip": true,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "250027": {
244
+ "content": "az_AZ",
245
+ "lstrip": true,
246
+ "normalized": false,
247
+ "rstrip": true,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "250028": {
252
+ "content": "bn_IN",
253
+ "lstrip": true,
254
+ "normalized": false,
255
+ "rstrip": true,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "250029": {
260
+ "content": "fa_IR",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": true,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "250030": {
268
+ "content": "he_IL",
269
+ "lstrip": true,
270
+ "normalized": false,
271
+ "rstrip": true,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "250031": {
276
+ "content": "hr_HR",
277
+ "lstrip": true,
278
+ "normalized": false,
279
+ "rstrip": true,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "250032": {
284
+ "content": "id_ID",
285
+ "lstrip": true,
286
+ "normalized": false,
287
+ "rstrip": true,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "250033": {
292
+ "content": "ka_GE",
293
+ "lstrip": true,
294
+ "normalized": false,
295
+ "rstrip": true,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "250034": {
300
+ "content": "km_KH",
301
+ "lstrip": true,
302
+ "normalized": false,
303
+ "rstrip": true,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "250035": {
308
+ "content": "mk_MK",
309
+ "lstrip": true,
310
+ "normalized": false,
311
+ "rstrip": true,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "250036": {
316
+ "content": "ml_IN",
317
+ "lstrip": true,
318
+ "normalized": false,
319
+ "rstrip": true,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "250037": {
324
+ "content": "mn_MN",
325
+ "lstrip": true,
326
+ "normalized": false,
327
+ "rstrip": true,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "250038": {
332
+ "content": "mr_IN",
333
+ "lstrip": true,
334
+ "normalized": false,
335
+ "rstrip": true,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "250039": {
340
+ "content": "pl_PL",
341
+ "lstrip": true,
342
+ "normalized": false,
343
+ "rstrip": true,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "250040": {
348
+ "content": "ps_AF",
349
+ "lstrip": true,
350
+ "normalized": false,
351
+ "rstrip": true,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "250041": {
356
+ "content": "pt_XX",
357
+ "lstrip": true,
358
+ "normalized": false,
359
+ "rstrip": true,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "250042": {
364
+ "content": "sv_SE",
365
+ "lstrip": true,
366
+ "normalized": false,
367
+ "rstrip": true,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "250043": {
372
+ "content": "sw_KE",
373
+ "lstrip": true,
374
+ "normalized": false,
375
+ "rstrip": true,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "250044": {
380
+ "content": "ta_IN",
381
+ "lstrip": true,
382
+ "normalized": false,
383
+ "rstrip": true,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "250045": {
388
+ "content": "te_IN",
389
+ "lstrip": true,
390
+ "normalized": false,
391
+ "rstrip": true,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "250046": {
396
+ "content": "th_TH",
397
+ "lstrip": true,
398
+ "normalized": false,
399
+ "rstrip": true,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "250047": {
404
+ "content": "tl_XX",
405
+ "lstrip": true,
406
+ "normalized": false,
407
+ "rstrip": true,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "250048": {
412
+ "content": "uk_UA",
413
+ "lstrip": true,
414
+ "normalized": false,
415
+ "rstrip": true,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "250049": {
420
+ "content": "ur_PK",
421
+ "lstrip": true,
422
+ "normalized": false,
423
+ "rstrip": true,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "250050": {
428
+ "content": "xh_ZA",
429
+ "lstrip": true,
430
+ "normalized": false,
431
+ "rstrip": true,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "250051": {
436
+ "content": "gl_ES",
437
+ "lstrip": true,
438
+ "normalized": false,
439
+ "rstrip": true,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "250052": {
444
+ "content": "sl_SI",
445
+ "lstrip": true,
446
+ "normalized": false,
447
+ "rstrip": true,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "250053": {
452
+ "content": "<mask>",
453
+ "lstrip": true,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ }
459
+ },
460
+ "additional_special_tokens": [
461
+ "ar_AR",
462
+ "cs_CZ",
463
+ "de_DE",
464
+ "en_XX",
465
+ "es_XX",
466
+ "et_EE",
467
+ "fi_FI",
468
+ "fr_XX",
469
+ "gu_IN",
470
+ "hi_IN",
471
+ "it_IT",
472
+ "ja_XX",
473
+ "kk_KZ",
474
+ "ko_KR",
475
+ "lt_LT",
476
+ "lv_LV",
477
+ "my_MM",
478
+ "ne_NP",
479
+ "nl_XX",
480
+ "ro_RO",
481
+ "ru_RU",
482
+ "si_LK",
483
+ "tr_TR",
484
+ "vi_VN",
485
+ "zh_CN",
486
+ "af_ZA",
487
+ "az_AZ",
488
+ "bn_IN",
489
+ "fa_IR",
490
+ "he_IL",
491
+ "hr_HR",
492
+ "id_ID",
493
+ "ka_GE",
494
+ "km_KH",
495
+ "mk_MK",
496
+ "ml_IN",
497
+ "mn_MN",
498
+ "mr_IN",
499
+ "pl_PL",
500
+ "ps_AF",
501
+ "pt_XX",
502
+ "sv_SE",
503
+ "sw_KE",
504
+ "ta_IN",
505
+ "te_IN",
506
+ "th_TH",
507
+ "tl_XX",
508
+ "uk_UA",
509
+ "ur_PK",
510
+ "xh_ZA",
511
+ "gl_ES",
512
+ "sl_SI"
513
+ ],
514
+ "bos_token": "<s>",
515
+ "clean_up_tokenization_spaces": true,
516
+ "cls_token": "<s>",
517
+ "eos_token": "</s>",
518
+ "language_codes": "ML50",
519
+ "mask_token": "<mask>",
520
+ "model_max_length": 1000000000000000019884624838656,
521
+ "pad_token": "<pad>",
522
+ "sep_token": "</s>",
523
+ "sp_model_kwargs": {},
524
+ "src_lang": "ko_KR",
525
+ "tgt_lang": "en_XX",
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
checkpoint-60000/trainer_state.json ADDED
@@ -0,0 +1,889 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 29.1144,
3
+ "best_model_checkpoint": "./ko-en_mbartLarge_exp20p_linear_alpha/checkpoint-60000",
4
+ "epoch": 6.9613644274277755,
5
+ "eval_steps": 4000,
6
+ "global_step": 60000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.06,
13
+ "learning_rate": 5.4920234365935726e-05,
14
+ "loss": 2.3766,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.12,
19
+ "learning_rate": 5.484046873187145e-05,
20
+ "loss": 1.7994,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.17,
25
+ "learning_rate": 5.476070309780717e-05,
26
+ "loss": 1.6333,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.23,
31
+ "learning_rate": 5.4680937463742896e-05,
32
+ "loss": 1.554,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.29,
37
+ "learning_rate": 5.460117182967862e-05,
38
+ "loss": 1.5092,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.35,
43
+ "learning_rate": 5.4521406195614344e-05,
44
+ "loss": 1.4709,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.41,
49
+ "learning_rate": 5.444164056155007e-05,
50
+ "loss": 1.4354,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.46,
55
+ "learning_rate": 5.4361874927485784e-05,
56
+ "loss": 1.404,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.46,
61
+ "eval_bleu": 22.5375,
62
+ "eval_gen_len": 18.6852,
63
+ "eval_loss": 1.373841404914856,
64
+ "eval_runtime": 1144.9051,
65
+ "eval_samples_per_second": 15.055,
66
+ "eval_steps_per_second": 0.942,
67
+ "step": 4000
68
+ },
69
+ {
70
+ "epoch": 0.52,
71
+ "learning_rate": 5.4282109293421515e-05,
72
+ "loss": 1.3753,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 0.58,
77
+ "learning_rate": 5.420234365935724e-05,
78
+ "loss": 1.3399,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 0.64,
83
+ "learning_rate": 5.412257802529296e-05,
84
+ "loss": 1.3272,
85
+ "step": 5500
86
+ },
87
+ {
88
+ "epoch": 0.7,
89
+ "learning_rate": 5.404281239122868e-05,
90
+ "loss": 1.3226,
91
+ "step": 6000
92
+ },
93
+ {
94
+ "epoch": 0.75,
95
+ "learning_rate": 5.39630467571644e-05,
96
+ "loss": 1.2978,
97
+ "step": 6500
98
+ },
99
+ {
100
+ "epoch": 0.81,
101
+ "learning_rate": 5.388328112310013e-05,
102
+ "loss": 1.269,
103
+ "step": 7000
104
+ },
105
+ {
106
+ "epoch": 0.87,
107
+ "learning_rate": 5.3803515489035856e-05,
108
+ "loss": 1.2787,
109
+ "step": 7500
110
+ },
111
+ {
112
+ "epoch": 0.93,
113
+ "learning_rate": 5.372374985497158e-05,
114
+ "loss": 1.2629,
115
+ "step": 8000
116
+ },
117
+ {
118
+ "epoch": 0.93,
119
+ "eval_bleu": 25.3741,
120
+ "eval_gen_len": 18.7797,
121
+ "eval_loss": 1.245756983757019,
122
+ "eval_runtime": 1156.1784,
123
+ "eval_samples_per_second": 14.909,
124
+ "eval_steps_per_second": 0.932,
125
+ "step": 8000
126
+ },
127
+ {
128
+ "epoch": 0.99,
129
+ "learning_rate": 5.36439842209073e-05,
130
+ "loss": 1.2572,
131
+ "step": 8500
132
+ },
133
+ {
134
+ "epoch": 1.04,
135
+ "learning_rate": 5.356421858684302e-05,
136
+ "loss": 1.2035,
137
+ "step": 9000
138
+ },
139
+ {
140
+ "epoch": 1.1,
141
+ "learning_rate": 5.348445295277875e-05,
142
+ "loss": 1.1945,
143
+ "step": 9500
144
+ },
145
+ {
146
+ "epoch": 1.16,
147
+ "learning_rate": 5.3404687318714474e-05,
148
+ "loss": 1.179,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 1.22,
153
+ "learning_rate": 5.332492168465019e-05,
154
+ "loss": 1.2032,
155
+ "step": 10500
156
+ },
157
+ {
158
+ "epoch": 1.28,
159
+ "learning_rate": 5.3245156050585915e-05,
160
+ "loss": 1.192,
161
+ "step": 11000
162
+ },
163
+ {
164
+ "epoch": 1.33,
165
+ "learning_rate": 5.316539041652164e-05,
166
+ "loss": 1.1795,
167
+ "step": 11500
168
+ },
169
+ {
170
+ "epoch": 1.39,
171
+ "learning_rate": 5.308562478245736e-05,
172
+ "loss": 1.1951,
173
+ "step": 12000
174
+ },
175
+ {
176
+ "epoch": 1.39,
177
+ "eval_bleu": 26.1281,
178
+ "eval_gen_len": 18.6597,
179
+ "eval_loss": 1.2066867351531982,
180
+ "eval_runtime": 1158.2083,
181
+ "eval_samples_per_second": 14.882,
182
+ "eval_steps_per_second": 0.931,
183
+ "step": 12000
184
+ },
185
+ {
186
+ "epoch": 1.45,
187
+ "learning_rate": 5.300585914839309e-05,
188
+ "loss": 1.1704,
189
+ "step": 12500
190
+ },
191
+ {
192
+ "epoch": 1.51,
193
+ "learning_rate": 5.292609351432881e-05,
194
+ "loss": 1.1547,
195
+ "step": 13000
196
+ },
197
+ {
198
+ "epoch": 1.57,
199
+ "learning_rate": 5.284632788026453e-05,
200
+ "loss": 1.1419,
201
+ "step": 13500
202
+ },
203
+ {
204
+ "epoch": 1.62,
205
+ "learning_rate": 5.276656224620026e-05,
206
+ "loss": 1.1396,
207
+ "step": 14000
208
+ },
209
+ {
210
+ "epoch": 1.68,
211
+ "learning_rate": 5.268679661213598e-05,
212
+ "loss": 1.1549,
213
+ "step": 14500
214
+ },
215
+ {
216
+ "epoch": 1.74,
217
+ "learning_rate": 5.2607030978071704e-05,
218
+ "loss": 1.1255,
219
+ "step": 15000
220
+ },
221
+ {
222
+ "epoch": 1.8,
223
+ "learning_rate": 5.252726534400743e-05,
224
+ "loss": 1.1395,
225
+ "step": 15500
226
+ },
227
+ {
228
+ "epoch": 1.86,
229
+ "learning_rate": 5.244749970994315e-05,
230
+ "loss": 1.1317,
231
+ "step": 16000
232
+ },
233
+ {
234
+ "epoch": 1.86,
235
+ "eval_bleu": 26.5384,
236
+ "eval_gen_len": 19.2055,
237
+ "eval_loss": 1.1767752170562744,
238
+ "eval_runtime": 1178.3467,
239
+ "eval_samples_per_second": 14.628,
240
+ "eval_steps_per_second": 0.915,
241
+ "step": 16000
242
+ },
243
+ {
244
+ "epoch": 1.91,
245
+ "learning_rate": 5.2367734075878875e-05,
246
+ "loss": 1.1557,
247
+ "step": 16500
248
+ },
249
+ {
250
+ "epoch": 1.97,
251
+ "learning_rate": 5.22879684418146e-05,
252
+ "loss": 1.1478,
253
+ "step": 17000
254
+ },
255
+ {
256
+ "epoch": 2.03,
257
+ "learning_rate": 5.2208202807750315e-05,
258
+ "loss": 1.0771,
259
+ "step": 17500
260
+ },
261
+ {
262
+ "epoch": 2.09,
263
+ "learning_rate": 5.2128437173686046e-05,
264
+ "loss": 1.0135,
265
+ "step": 18000
266
+ },
267
+ {
268
+ "epoch": 2.15,
269
+ "learning_rate": 5.204867153962177e-05,
270
+ "loss": 1.0028,
271
+ "step": 18500
272
+ },
273
+ {
274
+ "epoch": 2.2,
275
+ "learning_rate": 5.196890590555749e-05,
276
+ "loss": 0.9894,
277
+ "step": 19000
278
+ },
279
+ {
280
+ "epoch": 2.26,
281
+ "learning_rate": 5.1889140271493216e-05,
282
+ "loss": 1.0178,
283
+ "step": 19500
284
+ },
285
+ {
286
+ "epoch": 2.32,
287
+ "learning_rate": 5.180937463742893e-05,
288
+ "loss": 0.9906,
289
+ "step": 20000
290
+ },
291
+ {
292
+ "epoch": 2.32,
293
+ "eval_bleu": 28.2459,
294
+ "eval_gen_len": 18.7269,
295
+ "eval_loss": 1.1362603902816772,
296
+ "eval_runtime": 1157.7765,
297
+ "eval_samples_per_second": 14.888,
298
+ "eval_steps_per_second": 0.931,
299
+ "step": 20000
300
+ },
301
+ {
302
+ "epoch": 2.38,
303
+ "learning_rate": 5.1729609003364664e-05,
304
+ "loss": 1.0083,
305
+ "step": 20500
306
+ },
307
+ {
308
+ "epoch": 2.44,
309
+ "learning_rate": 5.164984336930039e-05,
310
+ "loss": 0.9965,
311
+ "step": 21000
312
+ },
313
+ {
314
+ "epoch": 2.49,
315
+ "learning_rate": 5.157007773523611e-05,
316
+ "loss": 0.9992,
317
+ "step": 21500
318
+ },
319
+ {
320
+ "epoch": 2.55,
321
+ "learning_rate": 5.149031210117183e-05,
322
+ "loss": 1.0042,
323
+ "step": 22000
324
+ },
325
+ {
326
+ "epoch": 2.61,
327
+ "learning_rate": 5.141054646710755e-05,
328
+ "loss": 0.9998,
329
+ "step": 22500
330
+ },
331
+ {
332
+ "epoch": 2.67,
333
+ "learning_rate": 5.1330780833043275e-05,
334
+ "loss": 1.0076,
335
+ "step": 23000
336
+ },
337
+ {
338
+ "epoch": 2.73,
339
+ "learning_rate": 5.1251015198979005e-05,
340
+ "loss": 1.0047,
341
+ "step": 23500
342
+ },
343
+ {
344
+ "epoch": 2.78,
345
+ "learning_rate": 5.117124956491473e-05,
346
+ "loss": 0.9894,
347
+ "step": 24000
348
+ },
349
+ {
350
+ "epoch": 2.78,
351
+ "eval_bleu": 28.5124,
352
+ "eval_gen_len": 18.6882,
353
+ "eval_loss": 1.1238752603530884,
354
+ "eval_runtime": 1152.8912,
355
+ "eval_samples_per_second": 14.951,
356
+ "eval_steps_per_second": 0.935,
357
+ "step": 24000
358
+ },
359
+ {
360
+ "epoch": 2.84,
361
+ "learning_rate": 5.1091483930850446e-05,
362
+ "loss": 1.0115,
363
+ "step": 24500
364
+ },
365
+ {
366
+ "epoch": 2.9,
367
+ "learning_rate": 5.101171829678617e-05,
368
+ "loss": 0.9958,
369
+ "step": 25000
370
+ },
371
+ {
372
+ "epoch": 2.96,
373
+ "learning_rate": 5.093195266272189e-05,
374
+ "loss": 1.0044,
375
+ "step": 25500
376
+ },
377
+ {
378
+ "epoch": 3.02,
379
+ "learning_rate": 5.0852187028657624e-05,
380
+ "loss": 0.9668,
381
+ "step": 26000
382
+ },
383
+ {
384
+ "epoch": 3.07,
385
+ "learning_rate": 5.077242139459334e-05,
386
+ "loss": 0.8751,
387
+ "step": 26500
388
+ },
389
+ {
390
+ "epoch": 3.13,
391
+ "learning_rate": 5.0692655760529064e-05,
392
+ "loss": 0.8916,
393
+ "step": 27000
394
+ },
395
+ {
396
+ "epoch": 3.19,
397
+ "learning_rate": 5.061289012646479e-05,
398
+ "loss": 0.8861,
399
+ "step": 27500
400
+ },
401
+ {
402
+ "epoch": 3.25,
403
+ "learning_rate": 5.053312449240051e-05,
404
+ "loss": 0.8965,
405
+ "step": 28000
406
+ },
407
+ {
408
+ "epoch": 3.25,
409
+ "eval_bleu": 28.5335,
410
+ "eval_gen_len": 18.4917,
411
+ "eval_loss": 1.1277672052383423,
412
+ "eval_runtime": 1142.9887,
413
+ "eval_samples_per_second": 15.081,
414
+ "eval_steps_per_second": 0.943,
415
+ "step": 28000
416
+ },
417
+ {
418
+ "epoch": 3.31,
419
+ "learning_rate": 5.045335885833624e-05,
420
+ "loss": 0.8898,
421
+ "step": 28500
422
+ },
423
+ {
424
+ "epoch": 3.36,
425
+ "learning_rate": 5.037359322427196e-05,
426
+ "loss": 0.8982,
427
+ "step": 29000
428
+ },
429
+ {
430
+ "epoch": 3.42,
431
+ "learning_rate": 5.029382759020768e-05,
432
+ "loss": 0.896,
433
+ "step": 29500
434
+ },
435
+ {
436
+ "epoch": 3.48,
437
+ "learning_rate": 5.0214061956143406e-05,
438
+ "loss": 0.8889,
439
+ "step": 30000
440
+ },
441
+ {
442
+ "epoch": 3.54,
443
+ "learning_rate": 5.013429632207913e-05,
444
+ "loss": 0.9056,
445
+ "step": 30500
446
+ },
447
+ {
448
+ "epoch": 3.6,
449
+ "learning_rate": 5.005453068801485e-05,
450
+ "loss": 0.8867,
451
+ "step": 31000
452
+ },
453
+ {
454
+ "epoch": 3.65,
455
+ "learning_rate": 4.997476505395058e-05,
456
+ "loss": 0.911,
457
+ "step": 31500
458
+ },
459
+ {
460
+ "epoch": 3.71,
461
+ "learning_rate": 4.98949994198863e-05,
462
+ "loss": 0.9138,
463
+ "step": 32000
464
+ },
465
+ {
466
+ "epoch": 3.71,
467
+ "eval_bleu": 28.8189,
468
+ "eval_gen_len": 18.7873,
469
+ "eval_loss": 1.1216284036636353,
470
+ "eval_runtime": 1156.9444,
471
+ "eval_samples_per_second": 14.899,
472
+ "eval_steps_per_second": 0.932,
473
+ "step": 32000
474
+ },
475
+ {
476
+ "epoch": 3.77,
477
+ "learning_rate": 4.9815233785822024e-05,
478
+ "loss": 0.9023,
479
+ "step": 32500
480
+ },
481
+ {
482
+ "epoch": 3.83,
483
+ "learning_rate": 4.973546815175775e-05,
484
+ "loss": 0.9127,
485
+ "step": 33000
486
+ },
487
+ {
488
+ "epoch": 3.89,
489
+ "learning_rate": 4.9655702517693464e-05,
490
+ "loss": 0.9168,
491
+ "step": 33500
492
+ },
493
+ {
494
+ "epoch": 3.94,
495
+ "learning_rate": 4.9575936883629195e-05,
496
+ "loss": 0.8978,
497
+ "step": 34000
498
+ },
499
+ {
500
+ "epoch": 4.0,
501
+ "learning_rate": 4.949617124956492e-05,
502
+ "loss": 0.9229,
503
+ "step": 34500
504
+ },
505
+ {
506
+ "epoch": 4.06,
507
+ "learning_rate": 4.941640561550064e-05,
508
+ "loss": 0.828,
509
+ "step": 35000
510
+ },
511
+ {
512
+ "epoch": 4.12,
513
+ "learning_rate": 4.9336639981436366e-05,
514
+ "loss": 0.8326,
515
+ "step": 35500
516
+ },
517
+ {
518
+ "epoch": 4.18,
519
+ "learning_rate": 4.925687434737208e-05,
520
+ "loss": 0.8272,
521
+ "step": 36000
522
+ },
523
+ {
524
+ "epoch": 4.18,
525
+ "eval_bleu": 28.332,
526
+ "eval_gen_len": 18.6516,
527
+ "eval_loss": 1.1468099355697632,
528
+ "eval_runtime": 1152.7736,
529
+ "eval_samples_per_second": 14.953,
530
+ "eval_steps_per_second": 0.935,
531
+ "step": 36000
532
+ },
533
+ {
534
+ "epoch": 4.23,
535
+ "learning_rate": 4.9177108713307806e-05,
536
+ "loss": 0.8259,
537
+ "step": 36500
538
+ },
539
+ {
540
+ "epoch": 4.29,
541
+ "learning_rate": 4.9097343079243536e-05,
542
+ "loss": 0.8243,
543
+ "step": 37000
544
+ },
545
+ {
546
+ "epoch": 4.35,
547
+ "learning_rate": 4.901757744517926e-05,
548
+ "loss": 0.8664,
549
+ "step": 37500
550
+ },
551
+ {
552
+ "epoch": 4.41,
553
+ "learning_rate": 4.893781181111498e-05,
554
+ "loss": 0.8893,
555
+ "step": 38000
556
+ },
557
+ {
558
+ "epoch": 4.47,
559
+ "learning_rate": 4.88580461770507e-05,
560
+ "loss": 0.8958,
561
+ "step": 38500
562
+ },
563
+ {
564
+ "epoch": 4.52,
565
+ "learning_rate": 4.8778280542986424e-05,
566
+ "loss": 0.8924,
567
+ "step": 39000
568
+ },
569
+ {
570
+ "epoch": 4.58,
571
+ "learning_rate": 4.8698514908922155e-05,
572
+ "loss": 0.885,
573
+ "step": 39500
574
+ },
575
+ {
576
+ "epoch": 4.64,
577
+ "learning_rate": 4.861874927485788e-05,
578
+ "loss": 0.8753,
579
+ "step": 40000
580
+ },
581
+ {
582
+ "epoch": 4.64,
583
+ "eval_bleu": 28.2695,
584
+ "eval_gen_len": 18.4919,
585
+ "eval_loss": 1.1344704627990723,
586
+ "eval_runtime": 1148.1227,
587
+ "eval_samples_per_second": 15.013,
588
+ "eval_steps_per_second": 0.939,
589
+ "step": 40000
590
+ },
591
+ {
592
+ "epoch": 4.7,
593
+ "learning_rate": 4.8538983640793595e-05,
594
+ "loss": 0.8749,
595
+ "step": 40500
596
+ },
597
+ {
598
+ "epoch": 4.76,
599
+ "learning_rate": 4.845921800672932e-05,
600
+ "loss": 0.8621,
601
+ "step": 41000
602
+ },
603
+ {
604
+ "epoch": 4.81,
605
+ "learning_rate": 4.837945237266504e-05,
606
+ "loss": 0.8616,
607
+ "step": 41500
608
+ },
609
+ {
610
+ "epoch": 4.87,
611
+ "learning_rate": 4.8299686738600766e-05,
612
+ "loss": 0.8551,
613
+ "step": 42000
614
+ },
615
+ {
616
+ "epoch": 4.93,
617
+ "learning_rate": 4.821992110453649e-05,
618
+ "loss": 0.8504,
619
+ "step": 42500
620
+ },
621
+ {
622
+ "epoch": 4.99,
623
+ "learning_rate": 4.814015547047221e-05,
624
+ "loss": 0.8459,
625
+ "step": 43000
626
+ },
627
+ {
628
+ "epoch": 5.05,
629
+ "learning_rate": 4.806038983640794e-05,
630
+ "loss": 0.7255,
631
+ "step": 43500
632
+ },
633
+ {
634
+ "epoch": 5.11,
635
+ "learning_rate": 4.798062420234366e-05,
636
+ "loss": 0.6855,
637
+ "step": 44000
638
+ },
639
+ {
640
+ "epoch": 5.11,
641
+ "eval_bleu": 28.7913,
642
+ "eval_gen_len": 18.7596,
643
+ "eval_loss": 1.154221773147583,
644
+ "eval_runtime": 1168.8964,
645
+ "eval_samples_per_second": 14.746,
646
+ "eval_steps_per_second": 0.922,
647
+ "step": 44000
648
+ },
649
+ {
650
+ "epoch": 5.16,
651
+ "learning_rate": 4.7900858568279384e-05,
652
+ "loss": 0.7002,
653
+ "step": 44500
654
+ },
655
+ {
656
+ "epoch": 5.22,
657
+ "learning_rate": 4.782109293421511e-05,
658
+ "loss": 0.6982,
659
+ "step": 45000
660
+ },
661
+ {
662
+ "epoch": 5.28,
663
+ "learning_rate": 4.774132730015083e-05,
664
+ "loss": 0.6976,
665
+ "step": 45500
666
+ },
667
+ {
668
+ "epoch": 5.34,
669
+ "learning_rate": 4.7661561666086555e-05,
670
+ "loss": 0.7028,
671
+ "step": 46000
672
+ },
673
+ {
674
+ "epoch": 5.4,
675
+ "learning_rate": 4.758179603202228e-05,
676
+ "loss": 0.7138,
677
+ "step": 46500
678
+ },
679
+ {
680
+ "epoch": 5.45,
681
+ "learning_rate": 4.7502030397958e-05,
682
+ "loss": 0.7121,
683
+ "step": 47000
684
+ },
685
+ {
686
+ "epoch": 5.51,
687
+ "learning_rate": 4.7422264763893726e-05,
688
+ "loss": 0.7043,
689
+ "step": 47500
690
+ },
691
+ {
692
+ "epoch": 5.57,
693
+ "learning_rate": 4.734249912982945e-05,
694
+ "loss": 0.7088,
695
+ "step": 48000
696
+ },
697
+ {
698
+ "epoch": 5.57,
699
+ "eval_bleu": 29.0865,
700
+ "eval_gen_len": 18.6626,
701
+ "eval_loss": 1.153067708015442,
702
+ "eval_runtime": 1149.2413,
703
+ "eval_samples_per_second": 14.999,
704
+ "eval_steps_per_second": 0.938,
705
+ "step": 48000
706
+ },
707
+ {
708
+ "epoch": 5.63,
709
+ "learning_rate": 4.726273349576517e-05,
710
+ "loss": 0.7116,
711
+ "step": 48500
712
+ },
713
+ {
714
+ "epoch": 5.69,
715
+ "learning_rate": 4.71829678617009e-05,
716
+ "loss": 0.7292,
717
+ "step": 49000
718
+ },
719
+ {
720
+ "epoch": 5.74,
721
+ "learning_rate": 4.710320222763662e-05,
722
+ "loss": 0.7289,
723
+ "step": 49500
724
+ },
725
+ {
726
+ "epoch": 5.8,
727
+ "learning_rate": 4.702343659357234e-05,
728
+ "loss": 0.7514,
729
+ "step": 50000
730
+ },
731
+ {
732
+ "epoch": 5.86,
733
+ "learning_rate": 4.694367095950807e-05,
734
+ "loss": 0.7545,
735
+ "step": 50500
736
+ },
737
+ {
738
+ "epoch": 5.92,
739
+ "learning_rate": 4.686390532544379e-05,
740
+ "loss": 0.7362,
741
+ "step": 51000
742
+ },
743
+ {
744
+ "epoch": 5.98,
745
+ "learning_rate": 4.6784139691379515e-05,
746
+ "loss": 0.7413,
747
+ "step": 51500
748
+ },
749
+ {
750
+ "epoch": 6.03,
751
+ "learning_rate": 4.670437405731523e-05,
752
+ "loss": 0.6738,
753
+ "step": 52000
754
+ },
755
+ {
756
+ "epoch": 6.03,
757
+ "eval_bleu": 28.0235,
758
+ "eval_gen_len": 18.4243,
759
+ "eval_loss": 1.190636396408081,
760
+ "eval_runtime": 1139.2873,
761
+ "eval_samples_per_second": 15.13,
762
+ "eval_steps_per_second": 0.946,
763
+ "step": 52000
764
+ },
765
+ {
766
+ "epoch": 6.09,
767
+ "learning_rate": 4.6624608423250955e-05,
768
+ "loss": 0.6467,
769
+ "step": 52500
770
+ },
771
+ {
772
+ "epoch": 6.15,
773
+ "learning_rate": 4.6544842789186686e-05,
774
+ "loss": 0.6508,
775
+ "step": 53000
776
+ },
777
+ {
778
+ "epoch": 6.21,
779
+ "learning_rate": 4.646507715512241e-05,
780
+ "loss": 0.6742,
781
+ "step": 53500
782
+ },
783
+ {
784
+ "epoch": 6.27,
785
+ "learning_rate": 4.638531152105813e-05,
786
+ "loss": 0.6609,
787
+ "step": 54000
788
+ },
789
+ {
790
+ "epoch": 6.32,
791
+ "learning_rate": 4.630554588699385e-05,
792
+ "loss": 0.6464,
793
+ "step": 54500
794
+ },
795
+ {
796
+ "epoch": 6.38,
797
+ "learning_rate": 4.622578025292957e-05,
798
+ "loss": 0.6362,
799
+ "step": 55000
800
+ },
801
+ {
802
+ "epoch": 6.44,
803
+ "learning_rate": 4.61460146188653e-05,
804
+ "loss": 0.6552,
805
+ "step": 55500
806
+ },
807
+ {
808
+ "epoch": 6.5,
809
+ "learning_rate": 4.606624898480103e-05,
810
+ "loss": 0.6763,
811
+ "step": 56000
812
+ },
813
+ {
814
+ "epoch": 6.5,
815
+ "eval_bleu": 28.1501,
816
+ "eval_gen_len": 18.6932,
817
+ "eval_loss": 1.1940782070159912,
818
+ "eval_runtime": 1154.4139,
819
+ "eval_samples_per_second": 14.931,
820
+ "eval_steps_per_second": 0.934,
821
+ "step": 56000
822
+ },
823
+ {
824
+ "epoch": 6.56,
825
+ "learning_rate": 4.5986483350736744e-05,
826
+ "loss": 0.6775,
827
+ "step": 56500
828
+ },
829
+ {
830
+ "epoch": 6.61,
831
+ "learning_rate": 4.590671771667247e-05,
832
+ "loss": 0.6765,
833
+ "step": 57000
834
+ },
835
+ {
836
+ "epoch": 6.67,
837
+ "learning_rate": 4.582695208260819e-05,
838
+ "loss": 0.681,
839
+ "step": 57500
840
+ },
841
+ {
842
+ "epoch": 6.73,
843
+ "learning_rate": 4.5747186448543915e-05,
844
+ "loss": 0.6747,
845
+ "step": 58000
846
+ },
847
+ {
848
+ "epoch": 6.79,
849
+ "learning_rate": 4.5667420814479645e-05,
850
+ "loss": 0.6612,
851
+ "step": 58500
852
+ },
853
+ {
854
+ "epoch": 6.85,
855
+ "learning_rate": 4.558765518041536e-05,
856
+ "loss": 0.6662,
857
+ "step": 59000
858
+ },
859
+ {
860
+ "epoch": 6.9,
861
+ "learning_rate": 4.5507889546351086e-05,
862
+ "loss": 0.6653,
863
+ "step": 59500
864
+ },
865
+ {
866
+ "epoch": 6.96,
867
+ "learning_rate": 4.542812391228681e-05,
868
+ "loss": 0.6594,
869
+ "step": 60000
870
+ },
871
+ {
872
+ "epoch": 6.96,
873
+ "eval_bleu": 29.1144,
874
+ "eval_gen_len": 18.5459,
875
+ "eval_loss": 1.1682050228118896,
876
+ "eval_runtime": 1139.7821,
877
+ "eval_samples_per_second": 15.123,
878
+ "eval_steps_per_second": 0.946,
879
+ "step": 60000
880
+ }
881
+ ],
882
+ "logging_steps": 500,
883
+ "max_steps": 344760,
884
+ "num_train_epochs": 40,
885
+ "save_steps": 4000,
886
+ "total_flos": 2.0805485991789855e+18,
887
+ "trial_name": null,
888
+ "trial_params": null
889
+ }
checkpoint-60000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bb1a208655fbdd6d2efe6842f38b33cb5a37243e0f443b39f19b8cba4439028
3
+ size 4728
checkpoint-76000/added_tokens.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<mask>": 250053,
4
+ "<pad>": 1,
5
+ "<s>": 0,
6
+ "<unk>": 3,
7
+ "af_ZA": 250026,
8
+ "ar_AR": 250001,
9
+ "az_AZ": 250027,
10
+ "bn_IN": 250028,
11
+ "cs_CZ": 250002,
12
+ "de_DE": 250003,
13
+ "en_XX": 250004,
14
+ "es_XX": 250005,
15
+ "et_EE": 250006,
16
+ "fa_IR": 250029,
17
+ "fi_FI": 250007,
18
+ "fr_XX": 250008,
19
+ "gl_ES": 250051,
20
+ "gu_IN": 250009,
21
+ "he_IL": 250030,
22
+ "hi_IN": 250010,
23
+ "hr_HR": 250031,
24
+ "id_ID": 250032,
25
+ "it_IT": 250011,
26
+ "ja_XX": 250012,
27
+ "ka_GE": 250033,
28
+ "kk_KZ": 250013,
29
+ "km_KH": 250034,
30
+ "ko_KR": 250014,
31
+ "lt_LT": 250015,
32
+ "lv_LV": 250016,
33
+ "mk_MK": 250035,
34
+ "ml_IN": 250036,
35
+ "mn_MN": 250037,
36
+ "mr_IN": 250038,
37
+ "my_MM": 250017,
38
+ "ne_NP": 250018,
39
+ "nl_XX": 250019,
40
+ "pl_PL": 250039,
41
+ "ps_AF": 250040,
42
+ "pt_XX": 250041,
43
+ "ro_RO": 250020,
44
+ "ru_RU": 250021,
45
+ "si_LK": 250022,
46
+ "sl_SI": 250052,
47
+ "sv_SE": 250042,
48
+ "sw_KE": 250043,
49
+ "ta_IN": 250044,
50
+ "te_IN": 250045,
51
+ "th_TH": 250046,
52
+ "tl_XX": 250047,
53
+ "tr_TR": 250023,
54
+ "uk_UA": 250048,
55
+ "ur_PK": 250049,
56
+ "vi_VN": 250024,
57
+ "xh_ZA": 250050,
58
+ "zh_CN": 250025
59
+ }
checkpoint-76000/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": true,
8
+ "architectures": [
9
+ "MBartForConditionalGeneration"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 1024,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 4096,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 12,
20
+ "decoder_start_token_id": 2,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 2,
28
+ "forced_bos_token_id": 250004,
29
+ "forced_eos_token_id": 2,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "max_length": 200,
44
+ "max_position_embeddings": 1024,
45
+ "model_type": "mbart",
46
+ "normalize_before": true,
47
+ "normalize_embedding": true,
48
+ "num_beams": 5,
49
+ "num_hidden_layers": 12,
50
+ "output_past": true,
51
+ "pad_token_id": 1,
52
+ "scale_embedding": true,
53
+ "static_position_embeddings": false,
54
+ "tokenizer_class": "MBart50Tokenizer",
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.34.0",
57
+ "use_cache": true,
58
+ "vocab_size": 250054
59
+ }
checkpoint-76000/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "forced_bos_token_id": 250004,
7
+ "forced_eos_token_id": 2,
8
+ "max_length": 200,
9
+ "num_beams": 5,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.34.0"
12
+ }
checkpoint-76000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16138a9522a6dce5a6af93502920a187c87dcfa857d238c08322f3ed669016e6
3
+ size 4887473903
checkpoint-76000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e836e292fec6e30c69861bf1fe9d4abece41d8e3029b5bd2b6279356f8b943a4
3
+ size 2444694490
checkpoint-76000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:790e56b251ca7e90cea9f76136f94882375644091c14fd98cf61333faa96d104
3
+ size 15024
checkpoint-76000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00630b71e2d33362602aedbc2c57c6771eca7568cdf8abfde557364760bf74de
3
+ size 15024
checkpoint-76000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7025a82efdf8f89ac3768c07416fedd3c0cb79e7952e6b05c79c64cf421e2a3
3
+ size 15024
checkpoint-76000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc7c805f0f36f7baf27745cc63ec6ce292a9419893056b7eef20df64405935d8
3
+ size 15024
checkpoint-76000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:915461a8952830fce1d4a2e2747c36dca42d874d3ed87d68e60a764e08e234c7
3
+ size 1064
checkpoint-76000/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-76000/special_tokens_map.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN",
28
+ "af_ZA",
29
+ "az_AZ",
30
+ "bn_IN",
31
+ "fa_IR",
32
+ "he_IL",
33
+ "hr_HR",
34
+ "id_ID",
35
+ "ka_GE",
36
+ "km_KH",
37
+ "mk_MK",
38
+ "ml_IN",
39
+ "mn_MN",
40
+ "mr_IN",
41
+ "pl_PL",
42
+ "ps_AF",
43
+ "pt_XX",
44
+ "sv_SE",
45
+ "sw_KE",
46
+ "ta_IN",
47
+ "te_IN",
48
+ "th_TH",
49
+ "tl_XX",
50
+ "uk_UA",
51
+ "ur_PK",
52
+ "xh_ZA",
53
+ "gl_ES",
54
+ "sl_SI"
55
+ ],
56
+ "bos_token": "<s>",
57
+ "cls_token": "<s>",
58
+ "eos_token": "</s>",
59
+ "mask_token": "<mask>",
60
+ "pad_token": "<pad>",
61
+ "sep_token": "</s>",
62
+ "unk_token": "<unk>"
63
+ }
checkpoint-76000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3a71a6430f26d8667787032844b9efe0d820460f1eb2e56a96b5f171813bc1a
3
+ size 17109939
checkpoint-76000/tokenizer_config.json ADDED
@@ -0,0 +1,528 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "ar_AR",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "250002": {
44
+ "content": "cs_CZ",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "250003": {
52
+ "content": "de_DE",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "250004": {
60
+ "content": "en_XX",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "250005": {
68
+ "content": "es_XX",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "250006": {
76
+ "content": "et_EE",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "250007": {
84
+ "content": "fi_FI",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "250008": {
92
+ "content": "fr_XX",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "250009": {
100
+ "content": "gu_IN",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "250010": {
108
+ "content": "hi_IN",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "250011": {
116
+ "content": "it_IT",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "250012": {
124
+ "content": "ja_XX",
125
+ "lstrip": true,
126
+ "normalized": false,
127
+ "rstrip": true,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "250013": {
132
+ "content": "kk_KZ",
133
+ "lstrip": true,
134
+ "normalized": false,
135
+ "rstrip": true,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "250014": {
140
+ "content": "ko_KR",
141
+ "lstrip": true,
142
+ "normalized": false,
143
+ "rstrip": true,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "250015": {
148
+ "content": "lt_LT",
149
+ "lstrip": true,
150
+ "normalized": false,
151
+ "rstrip": true,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "250016": {
156
+ "content": "lv_LV",
157
+ "lstrip": true,
158
+ "normalized": false,
159
+ "rstrip": true,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "250017": {
164
+ "content": "my_MM",
165
+ "lstrip": true,
166
+ "normalized": false,
167
+ "rstrip": true,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "250018": {
172
+ "content": "ne_NP",
173
+ "lstrip": true,
174
+ "normalized": false,
175
+ "rstrip": true,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "250019": {
180
+ "content": "nl_XX",
181
+ "lstrip": true,
182
+ "normalized": false,
183
+ "rstrip": true,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "250020": {
188
+ "content": "ro_RO",
189
+ "lstrip": true,
190
+ "normalized": false,
191
+ "rstrip": true,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "250021": {
196
+ "content": "ru_RU",
197
+ "lstrip": true,
198
+ "normalized": false,
199
+ "rstrip": true,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "250022": {
204
+ "content": "si_LK",
205
+ "lstrip": true,
206
+ "normalized": false,
207
+ "rstrip": true,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "250023": {
212
+ "content": "tr_TR",
213
+ "lstrip": true,
214
+ "normalized": false,
215
+ "rstrip": true,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "250024": {
220
+ "content": "vi_VN",
221
+ "lstrip": true,
222
+ "normalized": false,
223
+ "rstrip": true,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "250025": {
228
+ "content": "zh_CN",
229
+ "lstrip": true,
230
+ "normalized": false,
231
+ "rstrip": true,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "250026": {
236
+ "content": "af_ZA",
237
+ "lstrip": true,
238
+ "normalized": false,
239
+ "rstrip": true,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "250027": {
244
+ "content": "az_AZ",
245
+ "lstrip": true,
246
+ "normalized": false,
247
+ "rstrip": true,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "250028": {
252
+ "content": "bn_IN",
253
+ "lstrip": true,
254
+ "normalized": false,
255
+ "rstrip": true,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "250029": {
260
+ "content": "fa_IR",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": true,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "250030": {
268
+ "content": "he_IL",
269
+ "lstrip": true,
270
+ "normalized": false,
271
+ "rstrip": true,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "250031": {
276
+ "content": "hr_HR",
277
+ "lstrip": true,
278
+ "normalized": false,
279
+ "rstrip": true,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "250032": {
284
+ "content": "id_ID",
285
+ "lstrip": true,
286
+ "normalized": false,
287
+ "rstrip": true,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "250033": {
292
+ "content": "ka_GE",
293
+ "lstrip": true,
294
+ "normalized": false,
295
+ "rstrip": true,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "250034": {
300
+ "content": "km_KH",
301
+ "lstrip": true,
302
+ "normalized": false,
303
+ "rstrip": true,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "250035": {
308
+ "content": "mk_MK",
309
+ "lstrip": true,
310
+ "normalized": false,
311
+ "rstrip": true,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "250036": {
316
+ "content": "ml_IN",
317
+ "lstrip": true,
318
+ "normalized": false,
319
+ "rstrip": true,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "250037": {
324
+ "content": "mn_MN",
325
+ "lstrip": true,
326
+ "normalized": false,
327
+ "rstrip": true,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "250038": {
332
+ "content": "mr_IN",
333
+ "lstrip": true,
334
+ "normalized": false,
335
+ "rstrip": true,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "250039": {
340
+ "content": "pl_PL",
341
+ "lstrip": true,
342
+ "normalized": false,
343
+ "rstrip": true,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "250040": {
348
+ "content": "ps_AF",
349
+ "lstrip": true,
350
+ "normalized": false,
351
+ "rstrip": true,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "250041": {
356
+ "content": "pt_XX",
357
+ "lstrip": true,
358
+ "normalized": false,
359
+ "rstrip": true,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "250042": {
364
+ "content": "sv_SE",
365
+ "lstrip": true,
366
+ "normalized": false,
367
+ "rstrip": true,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "250043": {
372
+ "content": "sw_KE",
373
+ "lstrip": true,
374
+ "normalized": false,
375
+ "rstrip": true,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "250044": {
380
+ "content": "ta_IN",
381
+ "lstrip": true,
382
+ "normalized": false,
383
+ "rstrip": true,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "250045": {
388
+ "content": "te_IN",
389
+ "lstrip": true,
390
+ "normalized": false,
391
+ "rstrip": true,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "250046": {
396
+ "content": "th_TH",
397
+ "lstrip": true,
398
+ "normalized": false,
399
+ "rstrip": true,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "250047": {
404
+ "content": "tl_XX",
405
+ "lstrip": true,
406
+ "normalized": false,
407
+ "rstrip": true,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "250048": {
412
+ "content": "uk_UA",
413
+ "lstrip": true,
414
+ "normalized": false,
415
+ "rstrip": true,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "250049": {
420
+ "content": "ur_PK",
421
+ "lstrip": true,
422
+ "normalized": false,
423
+ "rstrip": true,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "250050": {
428
+ "content": "xh_ZA",
429
+ "lstrip": true,
430
+ "normalized": false,
431
+ "rstrip": true,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "250051": {
436
+ "content": "gl_ES",
437
+ "lstrip": true,
438
+ "normalized": false,
439
+ "rstrip": true,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "250052": {
444
+ "content": "sl_SI",
445
+ "lstrip": true,
446
+ "normalized": false,
447
+ "rstrip": true,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "250053": {
452
+ "content": "<mask>",
453
+ "lstrip": true,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ }
459
+ },
460
+ "additional_special_tokens": [
461
+ "ar_AR",
462
+ "cs_CZ",
463
+ "de_DE",
464
+ "en_XX",
465
+ "es_XX",
466
+ "et_EE",
467
+ "fi_FI",
468
+ "fr_XX",
469
+ "gu_IN",
470
+ "hi_IN",
471
+ "it_IT",
472
+ "ja_XX",
473
+ "kk_KZ",
474
+ "ko_KR",
475
+ "lt_LT",
476
+ "lv_LV",
477
+ "my_MM",
478
+ "ne_NP",
479
+ "nl_XX",
480
+ "ro_RO",
481
+ "ru_RU",
482
+ "si_LK",
483
+ "tr_TR",
484
+ "vi_VN",
485
+ "zh_CN",
486
+ "af_ZA",
487
+ "az_AZ",
488
+ "bn_IN",
489
+ "fa_IR",
490
+ "he_IL",
491
+ "hr_HR",
492
+ "id_ID",
493
+ "ka_GE",
494
+ "km_KH",
495
+ "mk_MK",
496
+ "ml_IN",
497
+ "mn_MN",
498
+ "mr_IN",
499
+ "pl_PL",
500
+ "ps_AF",
501
+ "pt_XX",
502
+ "sv_SE",
503
+ "sw_KE",
504
+ "ta_IN",
505
+ "te_IN",
506
+ "th_TH",
507
+ "tl_XX",
508
+ "uk_UA",
509
+ "ur_PK",
510
+ "xh_ZA",
511
+ "gl_ES",
512
+ "sl_SI"
513
+ ],
514
+ "bos_token": "<s>",
515
+ "clean_up_tokenization_spaces": true,
516
+ "cls_token": "<s>",
517
+ "eos_token": "</s>",
518
+ "language_codes": "ML50",
519
+ "mask_token": "<mask>",
520
+ "model_max_length": 1000000000000000019884624838656,
521
+ "pad_token": "<pad>",
522
+ "sep_token": "</s>",
523
+ "sp_model_kwargs": {},
524
+ "src_lang": "ko_KR",
525
+ "tgt_lang": "en_XX",
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
checkpoint-76000/trainer_state.json ADDED
@@ -0,0 +1,1121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 29.1144,
3
+ "best_model_checkpoint": "./ko-en_mbartLarge_exp20p_linear_alpha/checkpoint-60000",
4
+ "epoch": 8.81772827474185,
5
+ "eval_steps": 4000,
6
+ "global_step": 76000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.06,
13
+ "learning_rate": 5.4920234365935726e-05,
14
+ "loss": 2.3766,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.12,
19
+ "learning_rate": 5.484046873187145e-05,
20
+ "loss": 1.7994,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.17,
25
+ "learning_rate": 5.476070309780717e-05,
26
+ "loss": 1.6333,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.23,
31
+ "learning_rate": 5.4680937463742896e-05,
32
+ "loss": 1.554,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.29,
37
+ "learning_rate": 5.460117182967862e-05,
38
+ "loss": 1.5092,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.35,
43
+ "learning_rate": 5.4521406195614344e-05,
44
+ "loss": 1.4709,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.41,
49
+ "learning_rate": 5.444164056155007e-05,
50
+ "loss": 1.4354,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.46,
55
+ "learning_rate": 5.4361874927485784e-05,
56
+ "loss": 1.404,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.46,
61
+ "eval_bleu": 22.5375,
62
+ "eval_gen_len": 18.6852,
63
+ "eval_loss": 1.373841404914856,
64
+ "eval_runtime": 1144.9051,
65
+ "eval_samples_per_second": 15.055,
66
+ "eval_steps_per_second": 0.942,
67
+ "step": 4000
68
+ },
69
+ {
70
+ "epoch": 0.52,
71
+ "learning_rate": 5.4282109293421515e-05,
72
+ "loss": 1.3753,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 0.58,
77
+ "learning_rate": 5.420234365935724e-05,
78
+ "loss": 1.3399,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 0.64,
83
+ "learning_rate": 5.412257802529296e-05,
84
+ "loss": 1.3272,
85
+ "step": 5500
86
+ },
87
+ {
88
+ "epoch": 0.7,
89
+ "learning_rate": 5.404281239122868e-05,
90
+ "loss": 1.3226,
91
+ "step": 6000
92
+ },
93
+ {
94
+ "epoch": 0.75,
95
+ "learning_rate": 5.39630467571644e-05,
96
+ "loss": 1.2978,
97
+ "step": 6500
98
+ },
99
+ {
100
+ "epoch": 0.81,
101
+ "learning_rate": 5.388328112310013e-05,
102
+ "loss": 1.269,
103
+ "step": 7000
104
+ },
105
+ {
106
+ "epoch": 0.87,
107
+ "learning_rate": 5.3803515489035856e-05,
108
+ "loss": 1.2787,
109
+ "step": 7500
110
+ },
111
+ {
112
+ "epoch": 0.93,
113
+ "learning_rate": 5.372374985497158e-05,
114
+ "loss": 1.2629,
115
+ "step": 8000
116
+ },
117
+ {
118
+ "epoch": 0.93,
119
+ "eval_bleu": 25.3741,
120
+ "eval_gen_len": 18.7797,
121
+ "eval_loss": 1.245756983757019,
122
+ "eval_runtime": 1156.1784,
123
+ "eval_samples_per_second": 14.909,
124
+ "eval_steps_per_second": 0.932,
125
+ "step": 8000
126
+ },
127
+ {
128
+ "epoch": 0.99,
129
+ "learning_rate": 5.36439842209073e-05,
130
+ "loss": 1.2572,
131
+ "step": 8500
132
+ },
133
+ {
134
+ "epoch": 1.04,
135
+ "learning_rate": 5.356421858684302e-05,
136
+ "loss": 1.2035,
137
+ "step": 9000
138
+ },
139
+ {
140
+ "epoch": 1.1,
141
+ "learning_rate": 5.348445295277875e-05,
142
+ "loss": 1.1945,
143
+ "step": 9500
144
+ },
145
+ {
146
+ "epoch": 1.16,
147
+ "learning_rate": 5.3404687318714474e-05,
148
+ "loss": 1.179,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 1.22,
153
+ "learning_rate": 5.332492168465019e-05,
154
+ "loss": 1.2032,
155
+ "step": 10500
156
+ },
157
+ {
158
+ "epoch": 1.28,
159
+ "learning_rate": 5.3245156050585915e-05,
160
+ "loss": 1.192,
161
+ "step": 11000
162
+ },
163
+ {
164
+ "epoch": 1.33,
165
+ "learning_rate": 5.316539041652164e-05,
166
+ "loss": 1.1795,
167
+ "step": 11500
168
+ },
169
+ {
170
+ "epoch": 1.39,
171
+ "learning_rate": 5.308562478245736e-05,
172
+ "loss": 1.1951,
173
+ "step": 12000
174
+ },
175
+ {
176
+ "epoch": 1.39,
177
+ "eval_bleu": 26.1281,
178
+ "eval_gen_len": 18.6597,
179
+ "eval_loss": 1.2066867351531982,
180
+ "eval_runtime": 1158.2083,
181
+ "eval_samples_per_second": 14.882,
182
+ "eval_steps_per_second": 0.931,
183
+ "step": 12000
184
+ },
185
+ {
186
+ "epoch": 1.45,
187
+ "learning_rate": 5.300585914839309e-05,
188
+ "loss": 1.1704,
189
+ "step": 12500
190
+ },
191
+ {
192
+ "epoch": 1.51,
193
+ "learning_rate": 5.292609351432881e-05,
194
+ "loss": 1.1547,
195
+ "step": 13000
196
+ },
197
+ {
198
+ "epoch": 1.57,
199
+ "learning_rate": 5.284632788026453e-05,
200
+ "loss": 1.1419,
201
+ "step": 13500
202
+ },
203
+ {
204
+ "epoch": 1.62,
205
+ "learning_rate": 5.276656224620026e-05,
206
+ "loss": 1.1396,
207
+ "step": 14000
208
+ },
209
+ {
210
+ "epoch": 1.68,
211
+ "learning_rate": 5.268679661213598e-05,
212
+ "loss": 1.1549,
213
+ "step": 14500
214
+ },
215
+ {
216
+ "epoch": 1.74,
217
+ "learning_rate": 5.2607030978071704e-05,
218
+ "loss": 1.1255,
219
+ "step": 15000
220
+ },
221
+ {
222
+ "epoch": 1.8,
223
+ "learning_rate": 5.252726534400743e-05,
224
+ "loss": 1.1395,
225
+ "step": 15500
226
+ },
227
+ {
228
+ "epoch": 1.86,
229
+ "learning_rate": 5.244749970994315e-05,
230
+ "loss": 1.1317,
231
+ "step": 16000
232
+ },
233
+ {
234
+ "epoch": 1.86,
235
+ "eval_bleu": 26.5384,
236
+ "eval_gen_len": 19.2055,
237
+ "eval_loss": 1.1767752170562744,
238
+ "eval_runtime": 1178.3467,
239
+ "eval_samples_per_second": 14.628,
240
+ "eval_steps_per_second": 0.915,
241
+ "step": 16000
242
+ },
243
+ {
244
+ "epoch": 1.91,
245
+ "learning_rate": 5.2367734075878875e-05,
246
+ "loss": 1.1557,
247
+ "step": 16500
248
+ },
249
+ {
250
+ "epoch": 1.97,
251
+ "learning_rate": 5.22879684418146e-05,
252
+ "loss": 1.1478,
253
+ "step": 17000
254
+ },
255
+ {
256
+ "epoch": 2.03,
257
+ "learning_rate": 5.2208202807750315e-05,
258
+ "loss": 1.0771,
259
+ "step": 17500
260
+ },
261
+ {
262
+ "epoch": 2.09,
263
+ "learning_rate": 5.2128437173686046e-05,
264
+ "loss": 1.0135,
265
+ "step": 18000
266
+ },
267
+ {
268
+ "epoch": 2.15,
269
+ "learning_rate": 5.204867153962177e-05,
270
+ "loss": 1.0028,
271
+ "step": 18500
272
+ },
273
+ {
274
+ "epoch": 2.2,
275
+ "learning_rate": 5.196890590555749e-05,
276
+ "loss": 0.9894,
277
+ "step": 19000
278
+ },
279
+ {
280
+ "epoch": 2.26,
281
+ "learning_rate": 5.1889140271493216e-05,
282
+ "loss": 1.0178,
283
+ "step": 19500
284
+ },
285
+ {
286
+ "epoch": 2.32,
287
+ "learning_rate": 5.180937463742893e-05,
288
+ "loss": 0.9906,
289
+ "step": 20000
290
+ },
291
+ {
292
+ "epoch": 2.32,
293
+ "eval_bleu": 28.2459,
294
+ "eval_gen_len": 18.7269,
295
+ "eval_loss": 1.1362603902816772,
296
+ "eval_runtime": 1157.7765,
297
+ "eval_samples_per_second": 14.888,
298
+ "eval_steps_per_second": 0.931,
299
+ "step": 20000
300
+ },
301
+ {
302
+ "epoch": 2.38,
303
+ "learning_rate": 5.1729609003364664e-05,
304
+ "loss": 1.0083,
305
+ "step": 20500
306
+ },
307
+ {
308
+ "epoch": 2.44,
309
+ "learning_rate": 5.164984336930039e-05,
310
+ "loss": 0.9965,
311
+ "step": 21000
312
+ },
313
+ {
314
+ "epoch": 2.49,
315
+ "learning_rate": 5.157007773523611e-05,
316
+ "loss": 0.9992,
317
+ "step": 21500
318
+ },
319
+ {
320
+ "epoch": 2.55,
321
+ "learning_rate": 5.149031210117183e-05,
322
+ "loss": 1.0042,
323
+ "step": 22000
324
+ },
325
+ {
326
+ "epoch": 2.61,
327
+ "learning_rate": 5.141054646710755e-05,
328
+ "loss": 0.9998,
329
+ "step": 22500
330
+ },
331
+ {
332
+ "epoch": 2.67,
333
+ "learning_rate": 5.1330780833043275e-05,
334
+ "loss": 1.0076,
335
+ "step": 23000
336
+ },
337
+ {
338
+ "epoch": 2.73,
339
+ "learning_rate": 5.1251015198979005e-05,
340
+ "loss": 1.0047,
341
+ "step": 23500
342
+ },
343
+ {
344
+ "epoch": 2.78,
345
+ "learning_rate": 5.117124956491473e-05,
346
+ "loss": 0.9894,
347
+ "step": 24000
348
+ },
349
+ {
350
+ "epoch": 2.78,
351
+ "eval_bleu": 28.5124,
352
+ "eval_gen_len": 18.6882,
353
+ "eval_loss": 1.1238752603530884,
354
+ "eval_runtime": 1152.8912,
355
+ "eval_samples_per_second": 14.951,
356
+ "eval_steps_per_second": 0.935,
357
+ "step": 24000
358
+ },
359
+ {
360
+ "epoch": 2.84,
361
+ "learning_rate": 5.1091483930850446e-05,
362
+ "loss": 1.0115,
363
+ "step": 24500
364
+ },
365
+ {
366
+ "epoch": 2.9,
367
+ "learning_rate": 5.101171829678617e-05,
368
+ "loss": 0.9958,
369
+ "step": 25000
370
+ },
371
+ {
372
+ "epoch": 2.96,
373
+ "learning_rate": 5.093195266272189e-05,
374
+ "loss": 1.0044,
375
+ "step": 25500
376
+ },
377
+ {
378
+ "epoch": 3.02,
379
+ "learning_rate": 5.0852187028657624e-05,
380
+ "loss": 0.9668,
381
+ "step": 26000
382
+ },
383
+ {
384
+ "epoch": 3.07,
385
+ "learning_rate": 5.077242139459334e-05,
386
+ "loss": 0.8751,
387
+ "step": 26500
388
+ },
389
+ {
390
+ "epoch": 3.13,
391
+ "learning_rate": 5.0692655760529064e-05,
392
+ "loss": 0.8916,
393
+ "step": 27000
394
+ },
395
+ {
396
+ "epoch": 3.19,
397
+ "learning_rate": 5.061289012646479e-05,
398
+ "loss": 0.8861,
399
+ "step": 27500
400
+ },
401
+ {
402
+ "epoch": 3.25,
403
+ "learning_rate": 5.053312449240051e-05,
404
+ "loss": 0.8965,
405
+ "step": 28000
406
+ },
407
+ {
408
+ "epoch": 3.25,
409
+ "eval_bleu": 28.5335,
410
+ "eval_gen_len": 18.4917,
411
+ "eval_loss": 1.1277672052383423,
412
+ "eval_runtime": 1142.9887,
413
+ "eval_samples_per_second": 15.081,
414
+ "eval_steps_per_second": 0.943,
415
+ "step": 28000
416
+ },
417
+ {
418
+ "epoch": 3.31,
419
+ "learning_rate": 5.045335885833624e-05,
420
+ "loss": 0.8898,
421
+ "step": 28500
422
+ },
423
+ {
424
+ "epoch": 3.36,
425
+ "learning_rate": 5.037359322427196e-05,
426
+ "loss": 0.8982,
427
+ "step": 29000
428
+ },
429
+ {
430
+ "epoch": 3.42,
431
+ "learning_rate": 5.029382759020768e-05,
432
+ "loss": 0.896,
433
+ "step": 29500
434
+ },
435
+ {
436
+ "epoch": 3.48,
437
+ "learning_rate": 5.0214061956143406e-05,
438
+ "loss": 0.8889,
439
+ "step": 30000
440
+ },
441
+ {
442
+ "epoch": 3.54,
443
+ "learning_rate": 5.013429632207913e-05,
444
+ "loss": 0.9056,
445
+ "step": 30500
446
+ },
447
+ {
448
+ "epoch": 3.6,
449
+ "learning_rate": 5.005453068801485e-05,
450
+ "loss": 0.8867,
451
+ "step": 31000
452
+ },
453
+ {
454
+ "epoch": 3.65,
455
+ "learning_rate": 4.997476505395058e-05,
456
+ "loss": 0.911,
457
+ "step": 31500
458
+ },
459
+ {
460
+ "epoch": 3.71,
461
+ "learning_rate": 4.98949994198863e-05,
462
+ "loss": 0.9138,
463
+ "step": 32000
464
+ },
465
+ {
466
+ "epoch": 3.71,
467
+ "eval_bleu": 28.8189,
468
+ "eval_gen_len": 18.7873,
469
+ "eval_loss": 1.1216284036636353,
470
+ "eval_runtime": 1156.9444,
471
+ "eval_samples_per_second": 14.899,
472
+ "eval_steps_per_second": 0.932,
473
+ "step": 32000
474
+ },
475
+ {
476
+ "epoch": 3.77,
477
+ "learning_rate": 4.9815233785822024e-05,
478
+ "loss": 0.9023,
479
+ "step": 32500
480
+ },
481
+ {
482
+ "epoch": 3.83,
483
+ "learning_rate": 4.973546815175775e-05,
484
+ "loss": 0.9127,
485
+ "step": 33000
486
+ },
487
+ {
488
+ "epoch": 3.89,
489
+ "learning_rate": 4.9655702517693464e-05,
490
+ "loss": 0.9168,
491
+ "step": 33500
492
+ },
493
+ {
494
+ "epoch": 3.94,
495
+ "learning_rate": 4.9575936883629195e-05,
496
+ "loss": 0.8978,
497
+ "step": 34000
498
+ },
499
+ {
500
+ "epoch": 4.0,
501
+ "learning_rate": 4.949617124956492e-05,
502
+ "loss": 0.9229,
503
+ "step": 34500
504
+ },
505
+ {
506
+ "epoch": 4.06,
507
+ "learning_rate": 4.941640561550064e-05,
508
+ "loss": 0.828,
509
+ "step": 35000
510
+ },
511
+ {
512
+ "epoch": 4.12,
513
+ "learning_rate": 4.9336639981436366e-05,
514
+ "loss": 0.8326,
515
+ "step": 35500
516
+ },
517
+ {
518
+ "epoch": 4.18,
519
+ "learning_rate": 4.925687434737208e-05,
520
+ "loss": 0.8272,
521
+ "step": 36000
522
+ },
523
+ {
524
+ "epoch": 4.18,
525
+ "eval_bleu": 28.332,
526
+ "eval_gen_len": 18.6516,
527
+ "eval_loss": 1.1468099355697632,
528
+ "eval_runtime": 1152.7736,
529
+ "eval_samples_per_second": 14.953,
530
+ "eval_steps_per_second": 0.935,
531
+ "step": 36000
532
+ },
533
+ {
534
+ "epoch": 4.23,
535
+ "learning_rate": 4.9177108713307806e-05,
536
+ "loss": 0.8259,
537
+ "step": 36500
538
+ },
539
+ {
540
+ "epoch": 4.29,
541
+ "learning_rate": 4.9097343079243536e-05,
542
+ "loss": 0.8243,
543
+ "step": 37000
544
+ },
545
+ {
546
+ "epoch": 4.35,
547
+ "learning_rate": 4.901757744517926e-05,
548
+ "loss": 0.8664,
549
+ "step": 37500
550
+ },
551
+ {
552
+ "epoch": 4.41,
553
+ "learning_rate": 4.893781181111498e-05,
554
+ "loss": 0.8893,
555
+ "step": 38000
556
+ },
557
+ {
558
+ "epoch": 4.47,
559
+ "learning_rate": 4.88580461770507e-05,
560
+ "loss": 0.8958,
561
+ "step": 38500
562
+ },
563
+ {
564
+ "epoch": 4.52,
565
+ "learning_rate": 4.8778280542986424e-05,
566
+ "loss": 0.8924,
567
+ "step": 39000
568
+ },
569
+ {
570
+ "epoch": 4.58,
571
+ "learning_rate": 4.8698514908922155e-05,
572
+ "loss": 0.885,
573
+ "step": 39500
574
+ },
575
+ {
576
+ "epoch": 4.64,
577
+ "learning_rate": 4.861874927485788e-05,
578
+ "loss": 0.8753,
579
+ "step": 40000
580
+ },
581
+ {
582
+ "epoch": 4.64,
583
+ "eval_bleu": 28.2695,
584
+ "eval_gen_len": 18.4919,
585
+ "eval_loss": 1.1344704627990723,
586
+ "eval_runtime": 1148.1227,
587
+ "eval_samples_per_second": 15.013,
588
+ "eval_steps_per_second": 0.939,
589
+ "step": 40000
590
+ },
591
+ {
592
+ "epoch": 4.7,
593
+ "learning_rate": 4.8538983640793595e-05,
594
+ "loss": 0.8749,
595
+ "step": 40500
596
+ },
597
+ {
598
+ "epoch": 4.76,
599
+ "learning_rate": 4.845921800672932e-05,
600
+ "loss": 0.8621,
601
+ "step": 41000
602
+ },
603
+ {
604
+ "epoch": 4.81,
605
+ "learning_rate": 4.837945237266504e-05,
606
+ "loss": 0.8616,
607
+ "step": 41500
608
+ },
609
+ {
610
+ "epoch": 4.87,
611
+ "learning_rate": 4.8299686738600766e-05,
612
+ "loss": 0.8551,
613
+ "step": 42000
614
+ },
615
+ {
616
+ "epoch": 4.93,
617
+ "learning_rate": 4.821992110453649e-05,
618
+ "loss": 0.8504,
619
+ "step": 42500
620
+ },
621
+ {
622
+ "epoch": 4.99,
623
+ "learning_rate": 4.814015547047221e-05,
624
+ "loss": 0.8459,
625
+ "step": 43000
626
+ },
627
+ {
628
+ "epoch": 5.05,
629
+ "learning_rate": 4.806038983640794e-05,
630
+ "loss": 0.7255,
631
+ "step": 43500
632
+ },
633
+ {
634
+ "epoch": 5.11,
635
+ "learning_rate": 4.798062420234366e-05,
636
+ "loss": 0.6855,
637
+ "step": 44000
638
+ },
639
+ {
640
+ "epoch": 5.11,
641
+ "eval_bleu": 28.7913,
642
+ "eval_gen_len": 18.7596,
643
+ "eval_loss": 1.154221773147583,
644
+ "eval_runtime": 1168.8964,
645
+ "eval_samples_per_second": 14.746,
646
+ "eval_steps_per_second": 0.922,
647
+ "step": 44000
648
+ },
649
+ {
650
+ "epoch": 5.16,
651
+ "learning_rate": 4.7900858568279384e-05,
652
+ "loss": 0.7002,
653
+ "step": 44500
654
+ },
655
+ {
656
+ "epoch": 5.22,
657
+ "learning_rate": 4.782109293421511e-05,
658
+ "loss": 0.6982,
659
+ "step": 45000
660
+ },
661
+ {
662
+ "epoch": 5.28,
663
+ "learning_rate": 4.774132730015083e-05,
664
+ "loss": 0.6976,
665
+ "step": 45500
666
+ },
667
+ {
668
+ "epoch": 5.34,
669
+ "learning_rate": 4.7661561666086555e-05,
670
+ "loss": 0.7028,
671
+ "step": 46000
672
+ },
673
+ {
674
+ "epoch": 5.4,
675
+ "learning_rate": 4.758179603202228e-05,
676
+ "loss": 0.7138,
677
+ "step": 46500
678
+ },
679
+ {
680
+ "epoch": 5.45,
681
+ "learning_rate": 4.7502030397958e-05,
682
+ "loss": 0.7121,
683
+ "step": 47000
684
+ },
685
+ {
686
+ "epoch": 5.51,
687
+ "learning_rate": 4.7422264763893726e-05,
688
+ "loss": 0.7043,
689
+ "step": 47500
690
+ },
691
+ {
692
+ "epoch": 5.57,
693
+ "learning_rate": 4.734249912982945e-05,
694
+ "loss": 0.7088,
695
+ "step": 48000
696
+ },
697
+ {
698
+ "epoch": 5.57,
699
+ "eval_bleu": 29.0865,
700
+ "eval_gen_len": 18.6626,
701
+ "eval_loss": 1.153067708015442,
702
+ "eval_runtime": 1149.2413,
703
+ "eval_samples_per_second": 14.999,
704
+ "eval_steps_per_second": 0.938,
705
+ "step": 48000
706
+ },
707
+ {
708
+ "epoch": 5.63,
709
+ "learning_rate": 4.726273349576517e-05,
710
+ "loss": 0.7116,
711
+ "step": 48500
712
+ },
713
+ {
714
+ "epoch": 5.69,
715
+ "learning_rate": 4.71829678617009e-05,
716
+ "loss": 0.7292,
717
+ "step": 49000
718
+ },
719
+ {
720
+ "epoch": 5.74,
721
+ "learning_rate": 4.710320222763662e-05,
722
+ "loss": 0.7289,
723
+ "step": 49500
724
+ },
725
+ {
726
+ "epoch": 5.8,
727
+ "learning_rate": 4.702343659357234e-05,
728
+ "loss": 0.7514,
729
+ "step": 50000
730
+ },
731
+ {
732
+ "epoch": 5.86,
733
+ "learning_rate": 4.694367095950807e-05,
734
+ "loss": 0.7545,
735
+ "step": 50500
736
+ },
737
+ {
738
+ "epoch": 5.92,
739
+ "learning_rate": 4.686390532544379e-05,
740
+ "loss": 0.7362,
741
+ "step": 51000
742
+ },
743
+ {
744
+ "epoch": 5.98,
745
+ "learning_rate": 4.6784139691379515e-05,
746
+ "loss": 0.7413,
747
+ "step": 51500
748
+ },
749
+ {
750
+ "epoch": 6.03,
751
+ "learning_rate": 4.670437405731523e-05,
752
+ "loss": 0.6738,
753
+ "step": 52000
754
+ },
755
+ {
756
+ "epoch": 6.03,
757
+ "eval_bleu": 28.0235,
758
+ "eval_gen_len": 18.4243,
759
+ "eval_loss": 1.190636396408081,
760
+ "eval_runtime": 1139.2873,
761
+ "eval_samples_per_second": 15.13,
762
+ "eval_steps_per_second": 0.946,
763
+ "step": 52000
764
+ },
765
+ {
766
+ "epoch": 6.09,
767
+ "learning_rate": 4.6624608423250955e-05,
768
+ "loss": 0.6467,
769
+ "step": 52500
770
+ },
771
+ {
772
+ "epoch": 6.15,
773
+ "learning_rate": 4.6544842789186686e-05,
774
+ "loss": 0.6508,
775
+ "step": 53000
776
+ },
777
+ {
778
+ "epoch": 6.21,
779
+ "learning_rate": 4.646507715512241e-05,
780
+ "loss": 0.6742,
781
+ "step": 53500
782
+ },
783
+ {
784
+ "epoch": 6.27,
785
+ "learning_rate": 4.638531152105813e-05,
786
+ "loss": 0.6609,
787
+ "step": 54000
788
+ },
789
+ {
790
+ "epoch": 6.32,
791
+ "learning_rate": 4.630554588699385e-05,
792
+ "loss": 0.6464,
793
+ "step": 54500
794
+ },
795
+ {
796
+ "epoch": 6.38,
797
+ "learning_rate": 4.622578025292957e-05,
798
+ "loss": 0.6362,
799
+ "step": 55000
800
+ },
801
+ {
802
+ "epoch": 6.44,
803
+ "learning_rate": 4.61460146188653e-05,
804
+ "loss": 0.6552,
805
+ "step": 55500
806
+ },
807
+ {
808
+ "epoch": 6.5,
809
+ "learning_rate": 4.606624898480103e-05,
810
+ "loss": 0.6763,
811
+ "step": 56000
812
+ },
813
+ {
814
+ "epoch": 6.5,
815
+ "eval_bleu": 28.1501,
816
+ "eval_gen_len": 18.6932,
817
+ "eval_loss": 1.1940782070159912,
818
+ "eval_runtime": 1154.4139,
819
+ "eval_samples_per_second": 14.931,
820
+ "eval_steps_per_second": 0.934,
821
+ "step": 56000
822
+ },
823
+ {
824
+ "epoch": 6.56,
825
+ "learning_rate": 4.5986483350736744e-05,
826
+ "loss": 0.6775,
827
+ "step": 56500
828
+ },
829
+ {
830
+ "epoch": 6.61,
831
+ "learning_rate": 4.590671771667247e-05,
832
+ "loss": 0.6765,
833
+ "step": 57000
834
+ },
835
+ {
836
+ "epoch": 6.67,
837
+ "learning_rate": 4.582695208260819e-05,
838
+ "loss": 0.681,
839
+ "step": 57500
840
+ },
841
+ {
842
+ "epoch": 6.73,
843
+ "learning_rate": 4.5747186448543915e-05,
844
+ "loss": 0.6747,
845
+ "step": 58000
846
+ },
847
+ {
848
+ "epoch": 6.79,
849
+ "learning_rate": 4.5667420814479645e-05,
850
+ "loss": 0.6612,
851
+ "step": 58500
852
+ },
853
+ {
854
+ "epoch": 6.85,
855
+ "learning_rate": 4.558765518041536e-05,
856
+ "loss": 0.6662,
857
+ "step": 59000
858
+ },
859
+ {
860
+ "epoch": 6.9,
861
+ "learning_rate": 4.5507889546351086e-05,
862
+ "loss": 0.6653,
863
+ "step": 59500
864
+ },
865
+ {
866
+ "epoch": 6.96,
867
+ "learning_rate": 4.542812391228681e-05,
868
+ "loss": 0.6594,
869
+ "step": 60000
870
+ },
871
+ {
872
+ "epoch": 6.96,
873
+ "eval_bleu": 29.1144,
874
+ "eval_gen_len": 18.5459,
875
+ "eval_loss": 1.1682050228118896,
876
+ "eval_runtime": 1139.7821,
877
+ "eval_samples_per_second": 15.123,
878
+ "eval_steps_per_second": 0.946,
879
+ "step": 60000
880
+ },
881
+ {
882
+ "epoch": 7.02,
883
+ "learning_rate": 4.534835827822253e-05,
884
+ "loss": 0.6333,
885
+ "step": 60500
886
+ },
887
+ {
888
+ "epoch": 7.08,
889
+ "learning_rate": 4.526859264415826e-05,
890
+ "loss": 0.5491,
891
+ "step": 61000
892
+ },
893
+ {
894
+ "epoch": 7.14,
895
+ "learning_rate": 4.518882701009398e-05,
896
+ "loss": 0.5476,
897
+ "step": 61500
898
+ },
899
+ {
900
+ "epoch": 7.19,
901
+ "learning_rate": 4.5109061376029704e-05,
902
+ "loss": 0.5469,
903
+ "step": 62000
904
+ },
905
+ {
906
+ "epoch": 7.25,
907
+ "learning_rate": 4.502929574196543e-05,
908
+ "loss": 0.5708,
909
+ "step": 62500
910
+ },
911
+ {
912
+ "epoch": 7.31,
913
+ "learning_rate": 4.494953010790115e-05,
914
+ "loss": 0.5785,
915
+ "step": 63000
916
+ },
917
+ {
918
+ "epoch": 7.37,
919
+ "learning_rate": 4.486976447383687e-05,
920
+ "loss": 0.5803,
921
+ "step": 63500
922
+ },
923
+ {
924
+ "epoch": 7.43,
925
+ "learning_rate": 4.47899988397726e-05,
926
+ "loss": 0.5971,
927
+ "step": 64000
928
+ },
929
+ {
930
+ "epoch": 7.43,
931
+ "eval_bleu": 27.9464,
932
+ "eval_gen_len": 18.4482,
933
+ "eval_loss": 1.2448896169662476,
934
+ "eval_runtime": 1136.4568,
935
+ "eval_samples_per_second": 15.167,
936
+ "eval_steps_per_second": 0.949,
937
+ "step": 64000
938
+ },
939
+ {
940
+ "epoch": 7.48,
941
+ "learning_rate": 4.471023320570832e-05,
942
+ "loss": 0.5985,
943
+ "step": 64500
944
+ },
945
+ {
946
+ "epoch": 7.54,
947
+ "learning_rate": 4.4630467571644046e-05,
948
+ "loss": 0.6032,
949
+ "step": 65000
950
+ },
951
+ {
952
+ "epoch": 7.6,
953
+ "learning_rate": 4.455070193757977e-05,
954
+ "loss": 0.6079,
955
+ "step": 65500
956
+ },
957
+ {
958
+ "epoch": 7.66,
959
+ "learning_rate": 4.4470936303515486e-05,
960
+ "loss": 0.6104,
961
+ "step": 66000
962
+ },
963
+ {
964
+ "epoch": 7.72,
965
+ "learning_rate": 4.439117066945122e-05,
966
+ "loss": 0.6063,
967
+ "step": 66500
968
+ },
969
+ {
970
+ "epoch": 7.77,
971
+ "learning_rate": 4.431140503538694e-05,
972
+ "loss": 0.607,
973
+ "step": 67000
974
+ },
975
+ {
976
+ "epoch": 7.83,
977
+ "learning_rate": 4.4231639401322664e-05,
978
+ "loss": 0.5891,
979
+ "step": 67500
980
+ },
981
+ {
982
+ "epoch": 7.89,
983
+ "learning_rate": 4.415187376725838e-05,
984
+ "loss": 0.5935,
985
+ "step": 68000
986
+ },
987
+ {
988
+ "epoch": 7.89,
989
+ "eval_bleu": 28.6034,
990
+ "eval_gen_len": 18.5967,
991
+ "eval_loss": 1.2156028747558594,
992
+ "eval_runtime": 1146.9398,
993
+ "eval_samples_per_second": 15.029,
994
+ "eval_steps_per_second": 0.94,
995
+ "step": 68000
996
+ },
997
+ {
998
+ "epoch": 7.95,
999
+ "learning_rate": 4.4072108133194104e-05,
1000
+ "loss": 0.5981,
1001
+ "step": 68500
1002
+ },
1003
+ {
1004
+ "epoch": 8.01,
1005
+ "learning_rate": 4.399234249912983e-05,
1006
+ "loss": 0.5881,
1007
+ "step": 69000
1008
+ },
1009
+ {
1010
+ "epoch": 8.06,
1011
+ "learning_rate": 4.391257686506556e-05,
1012
+ "loss": 0.5013,
1013
+ "step": 69500
1014
+ },
1015
+ {
1016
+ "epoch": 8.12,
1017
+ "learning_rate": 4.383281123100128e-05,
1018
+ "loss": 0.5109,
1019
+ "step": 70000
1020
+ },
1021
+ {
1022
+ "epoch": 8.18,
1023
+ "learning_rate": 4.3753045596937e-05,
1024
+ "loss": 0.5187,
1025
+ "step": 70500
1026
+ },
1027
+ {
1028
+ "epoch": 8.24,
1029
+ "learning_rate": 4.367327996287272e-05,
1030
+ "loss": 0.5198,
1031
+ "step": 71000
1032
+ },
1033
+ {
1034
+ "epoch": 8.3,
1035
+ "learning_rate": 4.3593514328808446e-05,
1036
+ "loss": 0.5175,
1037
+ "step": 71500
1038
+ },
1039
+ {
1040
+ "epoch": 8.35,
1041
+ "learning_rate": 4.3513748694744177e-05,
1042
+ "loss": 0.5383,
1043
+ "step": 72000
1044
+ },
1045
+ {
1046
+ "epoch": 8.35,
1047
+ "eval_bleu": 27.891,
1048
+ "eval_gen_len": 18.6539,
1049
+ "eval_loss": 1.2927179336547852,
1050
+ "eval_runtime": 1152.5208,
1051
+ "eval_samples_per_second": 14.956,
1052
+ "eval_steps_per_second": 0.935,
1053
+ "step": 72000
1054
+ },
1055
+ {
1056
+ "epoch": 8.41,
1057
+ "learning_rate": 4.343398306067989e-05,
1058
+ "loss": 0.5285,
1059
+ "step": 72500
1060
+ },
1061
+ {
1062
+ "epoch": 8.47,
1063
+ "learning_rate": 4.335421742661562e-05,
1064
+ "loss": 0.5346,
1065
+ "step": 73000
1066
+ },
1067
+ {
1068
+ "epoch": 8.53,
1069
+ "learning_rate": 4.327445179255134e-05,
1070
+ "loss": 0.5601,
1071
+ "step": 73500
1072
+ },
1073
+ {
1074
+ "epoch": 8.59,
1075
+ "learning_rate": 4.3194686158487064e-05,
1076
+ "loss": 0.5869,
1077
+ "step": 74000
1078
+ },
1079
+ {
1080
+ "epoch": 8.64,
1081
+ "learning_rate": 4.311492052442279e-05,
1082
+ "loss": 0.5873,
1083
+ "step": 74500
1084
+ },
1085
+ {
1086
+ "epoch": 8.7,
1087
+ "learning_rate": 4.303515489035851e-05,
1088
+ "loss": 0.5924,
1089
+ "step": 75000
1090
+ },
1091
+ {
1092
+ "epoch": 8.76,
1093
+ "learning_rate": 4.2955389256294235e-05,
1094
+ "loss": 0.601,
1095
+ "step": 75500
1096
+ },
1097
+ {
1098
+ "epoch": 8.82,
1099
+ "learning_rate": 4.287562362222996e-05,
1100
+ "loss": 0.6022,
1101
+ "step": 76000
1102
+ },
1103
+ {
1104
+ "epoch": 8.82,
1105
+ "eval_bleu": 27.7624,
1106
+ "eval_gen_len": 18.5558,
1107
+ "eval_loss": 1.283076286315918,
1108
+ "eval_runtime": 1144.2558,
1109
+ "eval_samples_per_second": 15.064,
1110
+ "eval_steps_per_second": 0.942,
1111
+ "step": 76000
1112
+ }
1113
+ ],
1114
+ "logging_steps": 500,
1115
+ "max_steps": 344760,
1116
+ "num_train_epochs": 40,
1117
+ "save_steps": 4000,
1118
+ "total_flos": 2.6353338197706015e+18,
1119
+ "trial_name": null,
1120
+ "trial_params": null
1121
+ }
checkpoint-76000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bb1a208655fbdd6d2efe6842f38b33cb5a37243e0f443b39f19b8cba4439028
3
+ size 4728
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": true,
8
+ "architectures": [
9
+ "MBartForConditionalGeneration"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 1024,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 4096,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 12,
20
+ "decoder_start_token_id": 2,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 2,
28
+ "forced_bos_token_id": 250004,
29
+ "forced_eos_token_id": 2,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "max_length": 200,
44
+ "max_position_embeddings": 1024,
45
+ "model_type": "mbart",
46
+ "normalize_before": true,
47
+ "normalize_embedding": true,
48
+ "num_beams": 5,
49
+ "num_hidden_layers": 12,
50
+ "output_past": true,
51
+ "pad_token_id": 1,
52
+ "scale_embedding": true,
53
+ "static_position_embeddings": false,
54
+ "tokenizer_class": "MBart50Tokenizer",
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.34.0",
57
+ "use_cache": true,
58
+ "vocab_size": 250054
59
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 8.82,
3
+ "eval_bleu": 29.1144,
4
+ "eval_gen_len": 18.5459,
5
+ "eval_loss": 1.1682050228118896,
6
+ "eval_runtime": 1138.2217,
7
+ "eval_samples": 17237,
8
+ "eval_samples_per_second": 15.144,
9
+ "eval_steps_per_second": 0.947
10
+ }
generated_predictions.txt ADDED
The diff for this file is too large to render. See raw diff
 
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "forced_bos_token_id": 250004,
7
+ "forced_eos_token_id": 2,
8
+ "max_length": 200,
9
+ "num_beams": 5,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.34.0"
12
+ }
predict_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "predict_bleu": 29.2336,
3
+ "predict_gen_len": 18.5319,
4
+ "predict_loss": 1.1511610746383667,
5
+ "predict_runtime": 1143.8858,
6
+ "predict_samples": 17237,
7
+ "predict_samples_per_second": 15.069,
8
+ "predict_steps_per_second": 0.942
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a465d06942b45eaada7790ed77f43e70b8bab3ac5e5a6ed682cb0ce1351e6b79
3
+ size 2444694490
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN",
28
+ "af_ZA",
29
+ "az_AZ",
30
+ "bn_IN",
31
+ "fa_IR",
32
+ "he_IL",
33
+ "hr_HR",
34
+ "id_ID",
35
+ "ka_GE",
36
+ "km_KH",
37
+ "mk_MK",
38
+ "ml_IN",
39
+ "mn_MN",
40
+ "mr_IN",
41
+ "pl_PL",
42
+ "ps_AF",
43
+ "pt_XX",
44
+ "sv_SE",
45
+ "sw_KE",
46
+ "ta_IN",
47
+ "te_IN",
48
+ "th_TH",
49
+ "tl_XX",
50
+ "uk_UA",
51
+ "ur_PK",
52
+ "xh_ZA",
53
+ "gl_ES",
54
+ "sl_SI"
55
+ ],
56
+ "bos_token": "<s>",
57
+ "cls_token": "<s>",
58
+ "eos_token": "</s>",
59
+ "mask_token": "<mask>",
60
+ "pad_token": "<pad>",
61
+ "sep_token": "</s>",
62
+ "unk_token": "<unk>"
63
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3a71a6430f26d8667787032844b9efe0d820460f1eb2e56a96b5f171813bc1a
3
+ size 17109939
tokenizer_config.json ADDED
@@ -0,0 +1,528 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "ar_AR",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "250002": {
44
+ "content": "cs_CZ",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "250003": {
52
+ "content": "de_DE",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "250004": {
60
+ "content": "en_XX",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "250005": {
68
+ "content": "es_XX",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "250006": {
76
+ "content": "et_EE",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "250007": {
84
+ "content": "fi_FI",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "250008": {
92
+ "content": "fr_XX",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "250009": {
100
+ "content": "gu_IN",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "250010": {
108
+ "content": "hi_IN",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "250011": {
116
+ "content": "it_IT",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "250012": {
124
+ "content": "ja_XX",
125
+ "lstrip": true,
126
+ "normalized": false,
127
+ "rstrip": true,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "250013": {
132
+ "content": "kk_KZ",
133
+ "lstrip": true,
134
+ "normalized": false,
135
+ "rstrip": true,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "250014": {
140
+ "content": "ko_KR",
141
+ "lstrip": true,
142
+ "normalized": false,
143
+ "rstrip": true,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "250015": {
148
+ "content": "lt_LT",
149
+ "lstrip": true,
150
+ "normalized": false,
151
+ "rstrip": true,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "250016": {
156
+ "content": "lv_LV",
157
+ "lstrip": true,
158
+ "normalized": false,
159
+ "rstrip": true,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "250017": {
164
+ "content": "my_MM",
165
+ "lstrip": true,
166
+ "normalized": false,
167
+ "rstrip": true,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "250018": {
172
+ "content": "ne_NP",
173
+ "lstrip": true,
174
+ "normalized": false,
175
+ "rstrip": true,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "250019": {
180
+ "content": "nl_XX",
181
+ "lstrip": true,
182
+ "normalized": false,
183
+ "rstrip": true,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "250020": {
188
+ "content": "ro_RO",
189
+ "lstrip": true,
190
+ "normalized": false,
191
+ "rstrip": true,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "250021": {
196
+ "content": "ru_RU",
197
+ "lstrip": true,
198
+ "normalized": false,
199
+ "rstrip": true,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "250022": {
204
+ "content": "si_LK",
205
+ "lstrip": true,
206
+ "normalized": false,
207
+ "rstrip": true,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "250023": {
212
+ "content": "tr_TR",
213
+ "lstrip": true,
214
+ "normalized": false,
215
+ "rstrip": true,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "250024": {
220
+ "content": "vi_VN",
221
+ "lstrip": true,
222
+ "normalized": false,
223
+ "rstrip": true,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "250025": {
228
+ "content": "zh_CN",
229
+ "lstrip": true,
230
+ "normalized": false,
231
+ "rstrip": true,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "250026": {
236
+ "content": "af_ZA",
237
+ "lstrip": true,
238
+ "normalized": false,
239
+ "rstrip": true,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "250027": {
244
+ "content": "az_AZ",
245
+ "lstrip": true,
246
+ "normalized": false,
247
+ "rstrip": true,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "250028": {
252
+ "content": "bn_IN",
253
+ "lstrip": true,
254
+ "normalized": false,
255
+ "rstrip": true,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "250029": {
260
+ "content": "fa_IR",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": true,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "250030": {
268
+ "content": "he_IL",
269
+ "lstrip": true,
270
+ "normalized": false,
271
+ "rstrip": true,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "250031": {
276
+ "content": "hr_HR",
277
+ "lstrip": true,
278
+ "normalized": false,
279
+ "rstrip": true,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "250032": {
284
+ "content": "id_ID",
285
+ "lstrip": true,
286
+ "normalized": false,
287
+ "rstrip": true,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "250033": {
292
+ "content": "ka_GE",
293
+ "lstrip": true,
294
+ "normalized": false,
295
+ "rstrip": true,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "250034": {
300
+ "content": "km_KH",
301
+ "lstrip": true,
302
+ "normalized": false,
303
+ "rstrip": true,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "250035": {
308
+ "content": "mk_MK",
309
+ "lstrip": true,
310
+ "normalized": false,
311
+ "rstrip": true,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "250036": {
316
+ "content": "ml_IN",
317
+ "lstrip": true,
318
+ "normalized": false,
319
+ "rstrip": true,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "250037": {
324
+ "content": "mn_MN",
325
+ "lstrip": true,
326
+ "normalized": false,
327
+ "rstrip": true,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "250038": {
332
+ "content": "mr_IN",
333
+ "lstrip": true,
334
+ "normalized": false,
335
+ "rstrip": true,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "250039": {
340
+ "content": "pl_PL",
341
+ "lstrip": true,
342
+ "normalized": false,
343
+ "rstrip": true,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "250040": {
348
+ "content": "ps_AF",
349
+ "lstrip": true,
350
+ "normalized": false,
351
+ "rstrip": true,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "250041": {
356
+ "content": "pt_XX",
357
+ "lstrip": true,
358
+ "normalized": false,
359
+ "rstrip": true,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "250042": {
364
+ "content": "sv_SE",
365
+ "lstrip": true,
366
+ "normalized": false,
367
+ "rstrip": true,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "250043": {
372
+ "content": "sw_KE",
373
+ "lstrip": true,
374
+ "normalized": false,
375
+ "rstrip": true,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "250044": {
380
+ "content": "ta_IN",
381
+ "lstrip": true,
382
+ "normalized": false,
383
+ "rstrip": true,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "250045": {
388
+ "content": "te_IN",
389
+ "lstrip": true,
390
+ "normalized": false,
391
+ "rstrip": true,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "250046": {
396
+ "content": "th_TH",
397
+ "lstrip": true,
398
+ "normalized": false,
399
+ "rstrip": true,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "250047": {
404
+ "content": "tl_XX",
405
+ "lstrip": true,
406
+ "normalized": false,
407
+ "rstrip": true,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "250048": {
412
+ "content": "uk_UA",
413
+ "lstrip": true,
414
+ "normalized": false,
415
+ "rstrip": true,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "250049": {
420
+ "content": "ur_PK",
421
+ "lstrip": true,
422
+ "normalized": false,
423
+ "rstrip": true,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "250050": {
428
+ "content": "xh_ZA",
429
+ "lstrip": true,
430
+ "normalized": false,
431
+ "rstrip": true,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "250051": {
436
+ "content": "gl_ES",
437
+ "lstrip": true,
438
+ "normalized": false,
439
+ "rstrip": true,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "250052": {
444
+ "content": "sl_SI",
445
+ "lstrip": true,
446
+ "normalized": false,
447
+ "rstrip": true,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "250053": {
452
+ "content": "<mask>",
453
+ "lstrip": true,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ }
459
+ },
460
+ "additional_special_tokens": [
461
+ "ar_AR",
462
+ "cs_CZ",
463
+ "de_DE",
464
+ "en_XX",
465
+ "es_XX",
466
+ "et_EE",
467
+ "fi_FI",
468
+ "fr_XX",
469
+ "gu_IN",
470
+ "hi_IN",
471
+ "it_IT",
472
+ "ja_XX",
473
+ "kk_KZ",
474
+ "ko_KR",
475
+ "lt_LT",
476
+ "lv_LV",
477
+ "my_MM",
478
+ "ne_NP",
479
+ "nl_XX",
480
+ "ro_RO",
481
+ "ru_RU",
482
+ "si_LK",
483
+ "tr_TR",
484
+ "vi_VN",
485
+ "zh_CN",
486
+ "af_ZA",
487
+ "az_AZ",
488
+ "bn_IN",
489
+ "fa_IR",
490
+ "he_IL",
491
+ "hr_HR",
492
+ "id_ID",
493
+ "ka_GE",
494
+ "km_KH",
495
+ "mk_MK",
496
+ "ml_IN",
497
+ "mn_MN",
498
+ "mr_IN",
499
+ "pl_PL",
500
+ "ps_AF",
501
+ "pt_XX",
502
+ "sv_SE",
503
+ "sw_KE",
504
+ "ta_IN",
505
+ "te_IN",
506
+ "th_TH",
507
+ "tl_XX",
508
+ "uk_UA",
509
+ "ur_PK",
510
+ "xh_ZA",
511
+ "gl_ES",
512
+ "sl_SI"
513
+ ],
514
+ "bos_token": "<s>",
515
+ "clean_up_tokenization_spaces": true,
516
+ "cls_token": "<s>",
517
+ "eos_token": "</s>",
518
+ "language_codes": "ML50",
519
+ "mask_token": "<mask>",
520
+ "model_max_length": 1000000000000000019884624838656,
521
+ "pad_token": "<pad>",
522
+ "sep_token": "</s>",
523
+ "sp_model_kwargs": {},
524
+ "src_lang": "ko_KR",
525
+ "tgt_lang": "en_XX",
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 8.82,
3
+ "train_loss": 0.8847039678473222,
4
+ "train_runtime": 77092.0129,
5
+ "train_samples": 137900,
6
+ "train_samples_per_second": 71.551,
7
+ "train_steps_per_second": 4.472
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 29.1144,
3
+ "best_model_checkpoint": "./ko-en_mbartLarge_exp20p_linear_alpha/checkpoint-60000",
4
+ "epoch": 8.81772827474185,
5
+ "eval_steps": 4000,
6
+ "global_step": 76000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.06,
13
+ "learning_rate": 5.4920234365935726e-05,
14
+ "loss": 2.3766,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.12,
19
+ "learning_rate": 5.484046873187145e-05,
20
+ "loss": 1.7994,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.17,
25
+ "learning_rate": 5.476070309780717e-05,
26
+ "loss": 1.6333,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.23,
31
+ "learning_rate": 5.4680937463742896e-05,
32
+ "loss": 1.554,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.29,
37
+ "learning_rate": 5.460117182967862e-05,
38
+ "loss": 1.5092,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.35,
43
+ "learning_rate": 5.4521406195614344e-05,
44
+ "loss": 1.4709,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.41,
49
+ "learning_rate": 5.444164056155007e-05,
50
+ "loss": 1.4354,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.46,
55
+ "learning_rate": 5.4361874927485784e-05,
56
+ "loss": 1.404,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.46,
61
+ "eval_bleu": 22.5375,
62
+ "eval_gen_len": 18.6852,
63
+ "eval_loss": 1.373841404914856,
64
+ "eval_runtime": 1144.9051,
65
+ "eval_samples_per_second": 15.055,
66
+ "eval_steps_per_second": 0.942,
67
+ "step": 4000
68
+ },
69
+ {
70
+ "epoch": 0.52,
71
+ "learning_rate": 5.4282109293421515e-05,
72
+ "loss": 1.3753,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 0.58,
77
+ "learning_rate": 5.420234365935724e-05,
78
+ "loss": 1.3399,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 0.64,
83
+ "learning_rate": 5.412257802529296e-05,
84
+ "loss": 1.3272,
85
+ "step": 5500
86
+ },
87
+ {
88
+ "epoch": 0.7,
89
+ "learning_rate": 5.404281239122868e-05,
90
+ "loss": 1.3226,
91
+ "step": 6000
92
+ },
93
+ {
94
+ "epoch": 0.75,
95
+ "learning_rate": 5.39630467571644e-05,
96
+ "loss": 1.2978,
97
+ "step": 6500
98
+ },
99
+ {
100
+ "epoch": 0.81,
101
+ "learning_rate": 5.388328112310013e-05,
102
+ "loss": 1.269,
103
+ "step": 7000
104
+ },
105
+ {
106
+ "epoch": 0.87,
107
+ "learning_rate": 5.3803515489035856e-05,
108
+ "loss": 1.2787,
109
+ "step": 7500
110
+ },
111
+ {
112
+ "epoch": 0.93,
113
+ "learning_rate": 5.372374985497158e-05,
114
+ "loss": 1.2629,
115
+ "step": 8000
116
+ },
117
+ {
118
+ "epoch": 0.93,
119
+ "eval_bleu": 25.3741,
120
+ "eval_gen_len": 18.7797,
121
+ "eval_loss": 1.245756983757019,
122
+ "eval_runtime": 1156.1784,
123
+ "eval_samples_per_second": 14.909,
124
+ "eval_steps_per_second": 0.932,
125
+ "step": 8000
126
+ },
127
+ {
128
+ "epoch": 0.99,
129
+ "learning_rate": 5.36439842209073e-05,
130
+ "loss": 1.2572,
131
+ "step": 8500
132
+ },
133
+ {
134
+ "epoch": 1.04,
135
+ "learning_rate": 5.356421858684302e-05,
136
+ "loss": 1.2035,
137
+ "step": 9000
138
+ },
139
+ {
140
+ "epoch": 1.1,
141
+ "learning_rate": 5.348445295277875e-05,
142
+ "loss": 1.1945,
143
+ "step": 9500
144
+ },
145
+ {
146
+ "epoch": 1.16,
147
+ "learning_rate": 5.3404687318714474e-05,
148
+ "loss": 1.179,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 1.22,
153
+ "learning_rate": 5.332492168465019e-05,
154
+ "loss": 1.2032,
155
+ "step": 10500
156
+ },
157
+ {
158
+ "epoch": 1.28,
159
+ "learning_rate": 5.3245156050585915e-05,
160
+ "loss": 1.192,
161
+ "step": 11000
162
+ },
163
+ {
164
+ "epoch": 1.33,
165
+ "learning_rate": 5.316539041652164e-05,
166
+ "loss": 1.1795,
167
+ "step": 11500
168
+ },
169
+ {
170
+ "epoch": 1.39,
171
+ "learning_rate": 5.308562478245736e-05,
172
+ "loss": 1.1951,
173
+ "step": 12000
174
+ },
175
+ {
176
+ "epoch": 1.39,
177
+ "eval_bleu": 26.1281,
178
+ "eval_gen_len": 18.6597,
179
+ "eval_loss": 1.2066867351531982,
180
+ "eval_runtime": 1158.2083,
181
+ "eval_samples_per_second": 14.882,
182
+ "eval_steps_per_second": 0.931,
183
+ "step": 12000
184
+ },
185
+ {
186
+ "epoch": 1.45,
187
+ "learning_rate": 5.300585914839309e-05,
188
+ "loss": 1.1704,
189
+ "step": 12500
190
+ },
191
+ {
192
+ "epoch": 1.51,
193
+ "learning_rate": 5.292609351432881e-05,
194
+ "loss": 1.1547,
195
+ "step": 13000
196
+ },
197
+ {
198
+ "epoch": 1.57,
199
+ "learning_rate": 5.284632788026453e-05,
200
+ "loss": 1.1419,
201
+ "step": 13500
202
+ },
203
+ {
204
+ "epoch": 1.62,
205
+ "learning_rate": 5.276656224620026e-05,
206
+ "loss": 1.1396,
207
+ "step": 14000
208
+ },
209
+ {
210
+ "epoch": 1.68,
211
+ "learning_rate": 5.268679661213598e-05,
212
+ "loss": 1.1549,
213
+ "step": 14500
214
+ },
215
+ {
216
+ "epoch": 1.74,
217
+ "learning_rate": 5.2607030978071704e-05,
218
+ "loss": 1.1255,
219
+ "step": 15000
220
+ },
221
+ {
222
+ "epoch": 1.8,
223
+ "learning_rate": 5.252726534400743e-05,
224
+ "loss": 1.1395,
225
+ "step": 15500
226
+ },
227
+ {
228
+ "epoch": 1.86,
229
+ "learning_rate": 5.244749970994315e-05,
230
+ "loss": 1.1317,
231
+ "step": 16000
232
+ },
233
+ {
234
+ "epoch": 1.86,
235
+ "eval_bleu": 26.5384,
236
+ "eval_gen_len": 19.2055,
237
+ "eval_loss": 1.1767752170562744,
238
+ "eval_runtime": 1178.3467,
239
+ "eval_samples_per_second": 14.628,
240
+ "eval_steps_per_second": 0.915,
241
+ "step": 16000
242
+ },
243
+ {
244
+ "epoch": 1.91,
245
+ "learning_rate": 5.2367734075878875e-05,
246
+ "loss": 1.1557,
247
+ "step": 16500
248
+ },
249
+ {
250
+ "epoch": 1.97,
251
+ "learning_rate": 5.22879684418146e-05,
252
+ "loss": 1.1478,
253
+ "step": 17000
254
+ },
255
+ {
256
+ "epoch": 2.03,
257
+ "learning_rate": 5.2208202807750315e-05,
258
+ "loss": 1.0771,
259
+ "step": 17500
260
+ },
261
+ {
262
+ "epoch": 2.09,
263
+ "learning_rate": 5.2128437173686046e-05,
264
+ "loss": 1.0135,
265
+ "step": 18000
266
+ },
267
+ {
268
+ "epoch": 2.15,
269
+ "learning_rate": 5.204867153962177e-05,
270
+ "loss": 1.0028,
271
+ "step": 18500
272
+ },
273
+ {
274
+ "epoch": 2.2,
275
+ "learning_rate": 5.196890590555749e-05,
276
+ "loss": 0.9894,
277
+ "step": 19000
278
+ },
279
+ {
280
+ "epoch": 2.26,
281
+ "learning_rate": 5.1889140271493216e-05,
282
+ "loss": 1.0178,
283
+ "step": 19500
284
+ },
285
+ {
286
+ "epoch": 2.32,
287
+ "learning_rate": 5.180937463742893e-05,
288
+ "loss": 0.9906,
289
+ "step": 20000
290
+ },
291
+ {
292
+ "epoch": 2.32,
293
+ "eval_bleu": 28.2459,
294
+ "eval_gen_len": 18.7269,
295
+ "eval_loss": 1.1362603902816772,
296
+ "eval_runtime": 1157.7765,
297
+ "eval_samples_per_second": 14.888,
298
+ "eval_steps_per_second": 0.931,
299
+ "step": 20000
300
+ },
301
+ {
302
+ "epoch": 2.38,
303
+ "learning_rate": 5.1729609003364664e-05,
304
+ "loss": 1.0083,
305
+ "step": 20500
306
+ },
307
+ {
308
+ "epoch": 2.44,
309
+ "learning_rate": 5.164984336930039e-05,
310
+ "loss": 0.9965,
311
+ "step": 21000
312
+ },
313
+ {
314
+ "epoch": 2.49,
315
+ "learning_rate": 5.157007773523611e-05,
316
+ "loss": 0.9992,
317
+ "step": 21500
318
+ },
319
+ {
320
+ "epoch": 2.55,
321
+ "learning_rate": 5.149031210117183e-05,
322
+ "loss": 1.0042,
323
+ "step": 22000
324
+ },
325
+ {
326
+ "epoch": 2.61,
327
+ "learning_rate": 5.141054646710755e-05,
328
+ "loss": 0.9998,
329
+ "step": 22500
330
+ },
331
+ {
332
+ "epoch": 2.67,
333
+ "learning_rate": 5.1330780833043275e-05,
334
+ "loss": 1.0076,
335
+ "step": 23000
336
+ },
337
+ {
338
+ "epoch": 2.73,
339
+ "learning_rate": 5.1251015198979005e-05,
340
+ "loss": 1.0047,
341
+ "step": 23500
342
+ },
343
+ {
344
+ "epoch": 2.78,
345
+ "learning_rate": 5.117124956491473e-05,
346
+ "loss": 0.9894,
347
+ "step": 24000
348
+ },
349
+ {
350
+ "epoch": 2.78,
351
+ "eval_bleu": 28.5124,
352
+ "eval_gen_len": 18.6882,
353
+ "eval_loss": 1.1238752603530884,
354
+ "eval_runtime": 1152.8912,
355
+ "eval_samples_per_second": 14.951,
356
+ "eval_steps_per_second": 0.935,
357
+ "step": 24000
358
+ },
359
+ {
360
+ "epoch": 2.84,
361
+ "learning_rate": 5.1091483930850446e-05,
362
+ "loss": 1.0115,
363
+ "step": 24500
364
+ },
365
+ {
366
+ "epoch": 2.9,
367
+ "learning_rate": 5.101171829678617e-05,
368
+ "loss": 0.9958,
369
+ "step": 25000
370
+ },
371
+ {
372
+ "epoch": 2.96,
373
+ "learning_rate": 5.093195266272189e-05,
374
+ "loss": 1.0044,
375
+ "step": 25500
376
+ },
377
+ {
378
+ "epoch": 3.02,
379
+ "learning_rate": 5.0852187028657624e-05,
380
+ "loss": 0.9668,
381
+ "step": 26000
382
+ },
383
+ {
384
+ "epoch": 3.07,
385
+ "learning_rate": 5.077242139459334e-05,
386
+ "loss": 0.8751,
387
+ "step": 26500
388
+ },
389
+ {
390
+ "epoch": 3.13,
391
+ "learning_rate": 5.0692655760529064e-05,
392
+ "loss": 0.8916,
393
+ "step": 27000
394
+ },
395
+ {
396
+ "epoch": 3.19,
397
+ "learning_rate": 5.061289012646479e-05,
398
+ "loss": 0.8861,
399
+ "step": 27500
400
+ },
401
+ {
402
+ "epoch": 3.25,
403
+ "learning_rate": 5.053312449240051e-05,
404
+ "loss": 0.8965,
405
+ "step": 28000
406
+ },
407
+ {
408
+ "epoch": 3.25,
409
+ "eval_bleu": 28.5335,
410
+ "eval_gen_len": 18.4917,
411
+ "eval_loss": 1.1277672052383423,
412
+ "eval_runtime": 1142.9887,
413
+ "eval_samples_per_second": 15.081,
414
+ "eval_steps_per_second": 0.943,
415
+ "step": 28000
416
+ },
417
+ {
418
+ "epoch": 3.31,
419
+ "learning_rate": 5.045335885833624e-05,
420
+ "loss": 0.8898,
421
+ "step": 28500
422
+ },
423
+ {
424
+ "epoch": 3.36,
425
+ "learning_rate": 5.037359322427196e-05,
426
+ "loss": 0.8982,
427
+ "step": 29000
428
+ },
429
+ {
430
+ "epoch": 3.42,
431
+ "learning_rate": 5.029382759020768e-05,
432
+ "loss": 0.896,
433
+ "step": 29500
434
+ },
435
+ {
436
+ "epoch": 3.48,
437
+ "learning_rate": 5.0214061956143406e-05,
438
+ "loss": 0.8889,
439
+ "step": 30000
440
+ },
441
+ {
442
+ "epoch": 3.54,
443
+ "learning_rate": 5.013429632207913e-05,
444
+ "loss": 0.9056,
445
+ "step": 30500
446
+ },
447
+ {
448
+ "epoch": 3.6,
449
+ "learning_rate": 5.005453068801485e-05,
450
+ "loss": 0.8867,
451
+ "step": 31000
452
+ },
453
+ {
454
+ "epoch": 3.65,
455
+ "learning_rate": 4.997476505395058e-05,
456
+ "loss": 0.911,
457
+ "step": 31500
458
+ },
459
+ {
460
+ "epoch": 3.71,
461
+ "learning_rate": 4.98949994198863e-05,
462
+ "loss": 0.9138,
463
+ "step": 32000
464
+ },
465
+ {
466
+ "epoch": 3.71,
467
+ "eval_bleu": 28.8189,
468
+ "eval_gen_len": 18.7873,
469
+ "eval_loss": 1.1216284036636353,
470
+ "eval_runtime": 1156.9444,
471
+ "eval_samples_per_second": 14.899,
472
+ "eval_steps_per_second": 0.932,
473
+ "step": 32000
474
+ },
475
+ {
476
+ "epoch": 3.77,
477
+ "learning_rate": 4.9815233785822024e-05,
478
+ "loss": 0.9023,
479
+ "step": 32500
480
+ },
481
+ {
482
+ "epoch": 3.83,
483
+ "learning_rate": 4.973546815175775e-05,
484
+ "loss": 0.9127,
485
+ "step": 33000
486
+ },
487
+ {
488
+ "epoch": 3.89,
489
+ "learning_rate": 4.9655702517693464e-05,
490
+ "loss": 0.9168,
491
+ "step": 33500
492
+ },
493
+ {
494
+ "epoch": 3.94,
495
+ "learning_rate": 4.9575936883629195e-05,
496
+ "loss": 0.8978,
497
+ "step": 34000
498
+ },
499
+ {
500
+ "epoch": 4.0,
501
+ "learning_rate": 4.949617124956492e-05,
502
+ "loss": 0.9229,
503
+ "step": 34500
504
+ },
505
+ {
506
+ "epoch": 4.06,
507
+ "learning_rate": 4.941640561550064e-05,
508
+ "loss": 0.828,
509
+ "step": 35000
510
+ },
511
+ {
512
+ "epoch": 4.12,
513
+ "learning_rate": 4.9336639981436366e-05,
514
+ "loss": 0.8326,
515
+ "step": 35500
516
+ },
517
+ {
518
+ "epoch": 4.18,
519
+ "learning_rate": 4.925687434737208e-05,
520
+ "loss": 0.8272,
521
+ "step": 36000
522
+ },
523
+ {
524
+ "epoch": 4.18,
525
+ "eval_bleu": 28.332,
526
+ "eval_gen_len": 18.6516,
527
+ "eval_loss": 1.1468099355697632,
528
+ "eval_runtime": 1152.7736,
529
+ "eval_samples_per_second": 14.953,
530
+ "eval_steps_per_second": 0.935,
531
+ "step": 36000
532
+ },
533
+ {
534
+ "epoch": 4.23,
535
+ "learning_rate": 4.9177108713307806e-05,
536
+ "loss": 0.8259,
537
+ "step": 36500
538
+ },
539
+ {
540
+ "epoch": 4.29,
541
+ "learning_rate": 4.9097343079243536e-05,
542
+ "loss": 0.8243,
543
+ "step": 37000
544
+ },
545
+ {
546
+ "epoch": 4.35,
547
+ "learning_rate": 4.901757744517926e-05,
548
+ "loss": 0.8664,
549
+ "step": 37500
550
+ },
551
+ {
552
+ "epoch": 4.41,
553
+ "learning_rate": 4.893781181111498e-05,
554
+ "loss": 0.8893,
555
+ "step": 38000
556
+ },
557
+ {
558
+ "epoch": 4.47,
559
+ "learning_rate": 4.88580461770507e-05,
560
+ "loss": 0.8958,
561
+ "step": 38500
562
+ },
563
+ {
564
+ "epoch": 4.52,
565
+ "learning_rate": 4.8778280542986424e-05,
566
+ "loss": 0.8924,
567
+ "step": 39000
568
+ },
569
+ {
570
+ "epoch": 4.58,
571
+ "learning_rate": 4.8698514908922155e-05,
572
+ "loss": 0.885,
573
+ "step": 39500
574
+ },
575
+ {
576
+ "epoch": 4.64,
577
+ "learning_rate": 4.861874927485788e-05,
578
+ "loss": 0.8753,
579
+ "step": 40000
580
+ },
581
+ {
582
+ "epoch": 4.64,
583
+ "eval_bleu": 28.2695,
584
+ "eval_gen_len": 18.4919,
585
+ "eval_loss": 1.1344704627990723,
586
+ "eval_runtime": 1148.1227,
587
+ "eval_samples_per_second": 15.013,
588
+ "eval_steps_per_second": 0.939,
589
+ "step": 40000
590
+ },
591
+ {
592
+ "epoch": 4.7,
593
+ "learning_rate": 4.8538983640793595e-05,
594
+ "loss": 0.8749,
595
+ "step": 40500
596
+ },
597
+ {
598
+ "epoch": 4.76,
599
+ "learning_rate": 4.845921800672932e-05,
600
+ "loss": 0.8621,
601
+ "step": 41000
602
+ },
603
+ {
604
+ "epoch": 4.81,
605
+ "learning_rate": 4.837945237266504e-05,
606
+ "loss": 0.8616,
607
+ "step": 41500
608
+ },
609
+ {
610
+ "epoch": 4.87,
611
+ "learning_rate": 4.8299686738600766e-05,
612
+ "loss": 0.8551,
613
+ "step": 42000
614
+ },
615
+ {
616
+ "epoch": 4.93,
617
+ "learning_rate": 4.821992110453649e-05,
618
+ "loss": 0.8504,
619
+ "step": 42500
620
+ },
621
+ {
622
+ "epoch": 4.99,
623
+ "learning_rate": 4.814015547047221e-05,
624
+ "loss": 0.8459,
625
+ "step": 43000
626
+ },
627
+ {
628
+ "epoch": 5.05,
629
+ "learning_rate": 4.806038983640794e-05,
630
+ "loss": 0.7255,
631
+ "step": 43500
632
+ },
633
+ {
634
+ "epoch": 5.11,
635
+ "learning_rate": 4.798062420234366e-05,
636
+ "loss": 0.6855,
637
+ "step": 44000
638
+ },
639
+ {
640
+ "epoch": 5.11,
641
+ "eval_bleu": 28.7913,
642
+ "eval_gen_len": 18.7596,
643
+ "eval_loss": 1.154221773147583,
644
+ "eval_runtime": 1168.8964,
645
+ "eval_samples_per_second": 14.746,
646
+ "eval_steps_per_second": 0.922,
647
+ "step": 44000
648
+ },
649
+ {
650
+ "epoch": 5.16,
651
+ "learning_rate": 4.7900858568279384e-05,
652
+ "loss": 0.7002,
653
+ "step": 44500
654
+ },
655
+ {
656
+ "epoch": 5.22,
657
+ "learning_rate": 4.782109293421511e-05,
658
+ "loss": 0.6982,
659
+ "step": 45000
660
+ },
661
+ {
662
+ "epoch": 5.28,
663
+ "learning_rate": 4.774132730015083e-05,
664
+ "loss": 0.6976,
665
+ "step": 45500
666
+ },
667
+ {
668
+ "epoch": 5.34,
669
+ "learning_rate": 4.7661561666086555e-05,
670
+ "loss": 0.7028,
671
+ "step": 46000
672
+ },
673
+ {
674
+ "epoch": 5.4,
675
+ "learning_rate": 4.758179603202228e-05,
676
+ "loss": 0.7138,
677
+ "step": 46500
678
+ },
679
+ {
680
+ "epoch": 5.45,
681
+ "learning_rate": 4.7502030397958e-05,
682
+ "loss": 0.7121,
683
+ "step": 47000
684
+ },
685
+ {
686
+ "epoch": 5.51,
687
+ "learning_rate": 4.7422264763893726e-05,
688
+ "loss": 0.7043,
689
+ "step": 47500
690
+ },
691
+ {
692
+ "epoch": 5.57,
693
+ "learning_rate": 4.734249912982945e-05,
694
+ "loss": 0.7088,
695
+ "step": 48000
696
+ },
697
+ {
698
+ "epoch": 5.57,
699
+ "eval_bleu": 29.0865,
700
+ "eval_gen_len": 18.6626,
701
+ "eval_loss": 1.153067708015442,
702
+ "eval_runtime": 1149.2413,
703
+ "eval_samples_per_second": 14.999,
704
+ "eval_steps_per_second": 0.938,
705
+ "step": 48000
706
+ },
707
+ {
708
+ "epoch": 5.63,
709
+ "learning_rate": 4.726273349576517e-05,
710
+ "loss": 0.7116,
711
+ "step": 48500
712
+ },
713
+ {
714
+ "epoch": 5.69,
715
+ "learning_rate": 4.71829678617009e-05,
716
+ "loss": 0.7292,
717
+ "step": 49000
718
+ },
719
+ {
720
+ "epoch": 5.74,
721
+ "learning_rate": 4.710320222763662e-05,
722
+ "loss": 0.7289,
723
+ "step": 49500
724
+ },
725
+ {
726
+ "epoch": 5.8,
727
+ "learning_rate": 4.702343659357234e-05,
728
+ "loss": 0.7514,
729
+ "step": 50000
730
+ },
731
+ {
732
+ "epoch": 5.86,
733
+ "learning_rate": 4.694367095950807e-05,
734
+ "loss": 0.7545,
735
+ "step": 50500
736
+ },
737
+ {
738
+ "epoch": 5.92,
739
+ "learning_rate": 4.686390532544379e-05,
740
+ "loss": 0.7362,
741
+ "step": 51000
742
+ },
743
+ {
744
+ "epoch": 5.98,
745
+ "learning_rate": 4.6784139691379515e-05,
746
+ "loss": 0.7413,
747
+ "step": 51500
748
+ },
749
+ {
750
+ "epoch": 6.03,
751
+ "learning_rate": 4.670437405731523e-05,
752
+ "loss": 0.6738,
753
+ "step": 52000
754
+ },
755
+ {
756
+ "epoch": 6.03,
757
+ "eval_bleu": 28.0235,
758
+ "eval_gen_len": 18.4243,
759
+ "eval_loss": 1.190636396408081,
760
+ "eval_runtime": 1139.2873,
761
+ "eval_samples_per_second": 15.13,
762
+ "eval_steps_per_second": 0.946,
763
+ "step": 52000
764
+ },
765
+ {
766
+ "epoch": 6.09,
767
+ "learning_rate": 4.6624608423250955e-05,
768
+ "loss": 0.6467,
769
+ "step": 52500
770
+ },
771
+ {
772
+ "epoch": 6.15,
773
+ "learning_rate": 4.6544842789186686e-05,
774
+ "loss": 0.6508,
775
+ "step": 53000
776
+ },
777
+ {
778
+ "epoch": 6.21,
779
+ "learning_rate": 4.646507715512241e-05,
780
+ "loss": 0.6742,
781
+ "step": 53500
782
+ },
783
+ {
784
+ "epoch": 6.27,
785
+ "learning_rate": 4.638531152105813e-05,
786
+ "loss": 0.6609,
787
+ "step": 54000
788
+ },
789
+ {
790
+ "epoch": 6.32,
791
+ "learning_rate": 4.630554588699385e-05,
792
+ "loss": 0.6464,
793
+ "step": 54500
794
+ },
795
+ {
796
+ "epoch": 6.38,
797
+ "learning_rate": 4.622578025292957e-05,
798
+ "loss": 0.6362,
799
+ "step": 55000
800
+ },
801
+ {
802
+ "epoch": 6.44,
803
+ "learning_rate": 4.61460146188653e-05,
804
+ "loss": 0.6552,
805
+ "step": 55500
806
+ },
807
+ {
808
+ "epoch": 6.5,
809
+ "learning_rate": 4.606624898480103e-05,
810
+ "loss": 0.6763,
811
+ "step": 56000
812
+ },
813
+ {
814
+ "epoch": 6.5,
815
+ "eval_bleu": 28.1501,
816
+ "eval_gen_len": 18.6932,
817
+ "eval_loss": 1.1940782070159912,
818
+ "eval_runtime": 1154.4139,
819
+ "eval_samples_per_second": 14.931,
820
+ "eval_steps_per_second": 0.934,
821
+ "step": 56000
822
+ },
823
+ {
824
+ "epoch": 6.56,
825
+ "learning_rate": 4.5986483350736744e-05,
826
+ "loss": 0.6775,
827
+ "step": 56500
828
+ },
829
+ {
830
+ "epoch": 6.61,
831
+ "learning_rate": 4.590671771667247e-05,
832
+ "loss": 0.6765,
833
+ "step": 57000
834
+ },
835
+ {
836
+ "epoch": 6.67,
837
+ "learning_rate": 4.582695208260819e-05,
838
+ "loss": 0.681,
839
+ "step": 57500
840
+ },
841
+ {
842
+ "epoch": 6.73,
843
+ "learning_rate": 4.5747186448543915e-05,
844
+ "loss": 0.6747,
845
+ "step": 58000
846
+ },
847
+ {
848
+ "epoch": 6.79,
849
+ "learning_rate": 4.5667420814479645e-05,
850
+ "loss": 0.6612,
851
+ "step": 58500
852
+ },
853
+ {
854
+ "epoch": 6.85,
855
+ "learning_rate": 4.558765518041536e-05,
856
+ "loss": 0.6662,
857
+ "step": 59000
858
+ },
859
+ {
860
+ "epoch": 6.9,
861
+ "learning_rate": 4.5507889546351086e-05,
862
+ "loss": 0.6653,
863
+ "step": 59500
864
+ },
865
+ {
866
+ "epoch": 6.96,
867
+ "learning_rate": 4.542812391228681e-05,
868
+ "loss": 0.6594,
869
+ "step": 60000
870
+ },
871
+ {
872
+ "epoch": 6.96,
873
+ "eval_bleu": 29.1144,
874
+ "eval_gen_len": 18.5459,
875
+ "eval_loss": 1.1682050228118896,
876
+ "eval_runtime": 1139.7821,
877
+ "eval_samples_per_second": 15.123,
878
+ "eval_steps_per_second": 0.946,
879
+ "step": 60000
880
+ },
881
+ {
882
+ "epoch": 7.02,
883
+ "learning_rate": 4.534835827822253e-05,
884
+ "loss": 0.6333,
885
+ "step": 60500
886
+ },
887
+ {
888
+ "epoch": 7.08,
889
+ "learning_rate": 4.526859264415826e-05,
890
+ "loss": 0.5491,
891
+ "step": 61000
892
+ },
893
+ {
894
+ "epoch": 7.14,
895
+ "learning_rate": 4.518882701009398e-05,
896
+ "loss": 0.5476,
897
+ "step": 61500
898
+ },
899
+ {
900
+ "epoch": 7.19,
901
+ "learning_rate": 4.5109061376029704e-05,
902
+ "loss": 0.5469,
903
+ "step": 62000
904
+ },
905
+ {
906
+ "epoch": 7.25,
907
+ "learning_rate": 4.502929574196543e-05,
908
+ "loss": 0.5708,
909
+ "step": 62500
910
+ },
911
+ {
912
+ "epoch": 7.31,
913
+ "learning_rate": 4.494953010790115e-05,
914
+ "loss": 0.5785,
915
+ "step": 63000
916
+ },
917
+ {
918
+ "epoch": 7.37,
919
+ "learning_rate": 4.486976447383687e-05,
920
+ "loss": 0.5803,
921
+ "step": 63500
922
+ },
923
+ {
924
+ "epoch": 7.43,
925
+ "learning_rate": 4.47899988397726e-05,
926
+ "loss": 0.5971,
927
+ "step": 64000
928
+ },
929
+ {
930
+ "epoch": 7.43,
931
+ "eval_bleu": 27.9464,
932
+ "eval_gen_len": 18.4482,
933
+ "eval_loss": 1.2448896169662476,
934
+ "eval_runtime": 1136.4568,
935
+ "eval_samples_per_second": 15.167,
936
+ "eval_steps_per_second": 0.949,
937
+ "step": 64000
938
+ },
939
+ {
940
+ "epoch": 7.48,
941
+ "learning_rate": 4.471023320570832e-05,
942
+ "loss": 0.5985,
943
+ "step": 64500
944
+ },
945
+ {
946
+ "epoch": 7.54,
947
+ "learning_rate": 4.4630467571644046e-05,
948
+ "loss": 0.6032,
949
+ "step": 65000
950
+ },
951
+ {
952
+ "epoch": 7.6,
953
+ "learning_rate": 4.455070193757977e-05,
954
+ "loss": 0.6079,
955
+ "step": 65500
956
+ },
957
+ {
958
+ "epoch": 7.66,
959
+ "learning_rate": 4.4470936303515486e-05,
960
+ "loss": 0.6104,
961
+ "step": 66000
962
+ },
963
+ {
964
+ "epoch": 7.72,
965
+ "learning_rate": 4.439117066945122e-05,
966
+ "loss": 0.6063,
967
+ "step": 66500
968
+ },
969
+ {
970
+ "epoch": 7.77,
971
+ "learning_rate": 4.431140503538694e-05,
972
+ "loss": 0.607,
973
+ "step": 67000
974
+ },
975
+ {
976
+ "epoch": 7.83,
977
+ "learning_rate": 4.4231639401322664e-05,
978
+ "loss": 0.5891,
979
+ "step": 67500
980
+ },
981
+ {
982
+ "epoch": 7.89,
983
+ "learning_rate": 4.415187376725838e-05,
984
+ "loss": 0.5935,
985
+ "step": 68000
986
+ },
987
+ {
988
+ "epoch": 7.89,
989
+ "eval_bleu": 28.6034,
990
+ "eval_gen_len": 18.5967,
991
+ "eval_loss": 1.2156028747558594,
992
+ "eval_runtime": 1146.9398,
993
+ "eval_samples_per_second": 15.029,
994
+ "eval_steps_per_second": 0.94,
995
+ "step": 68000
996
+ },
997
+ {
998
+ "epoch": 7.95,
999
+ "learning_rate": 4.4072108133194104e-05,
1000
+ "loss": 0.5981,
1001
+ "step": 68500
1002
+ },
1003
+ {
1004
+ "epoch": 8.01,
1005
+ "learning_rate": 4.399234249912983e-05,
1006
+ "loss": 0.5881,
1007
+ "step": 69000
1008
+ },
1009
+ {
1010
+ "epoch": 8.06,
1011
+ "learning_rate": 4.391257686506556e-05,
1012
+ "loss": 0.5013,
1013
+ "step": 69500
1014
+ },
1015
+ {
1016
+ "epoch": 8.12,
1017
+ "learning_rate": 4.383281123100128e-05,
1018
+ "loss": 0.5109,
1019
+ "step": 70000
1020
+ },
1021
+ {
1022
+ "epoch": 8.18,
1023
+ "learning_rate": 4.3753045596937e-05,
1024
+ "loss": 0.5187,
1025
+ "step": 70500
1026
+ },
1027
+ {
1028
+ "epoch": 8.24,
1029
+ "learning_rate": 4.367327996287272e-05,
1030
+ "loss": 0.5198,
1031
+ "step": 71000
1032
+ },
1033
+ {
1034
+ "epoch": 8.3,
1035
+ "learning_rate": 4.3593514328808446e-05,
1036
+ "loss": 0.5175,
1037
+ "step": 71500
1038
+ },
1039
+ {
1040
+ "epoch": 8.35,
1041
+ "learning_rate": 4.3513748694744177e-05,
1042
+ "loss": 0.5383,
1043
+ "step": 72000
1044
+ },
1045
+ {
1046
+ "epoch": 8.35,
1047
+ "eval_bleu": 27.891,
1048
+ "eval_gen_len": 18.6539,
1049
+ "eval_loss": 1.2927179336547852,
1050
+ "eval_runtime": 1152.5208,
1051
+ "eval_samples_per_second": 14.956,
1052
+ "eval_steps_per_second": 0.935,
1053
+ "step": 72000
1054
+ },
1055
+ {
1056
+ "epoch": 8.41,
1057
+ "learning_rate": 4.343398306067989e-05,
1058
+ "loss": 0.5285,
1059
+ "step": 72500
1060
+ },
1061
+ {
1062
+ "epoch": 8.47,
1063
+ "learning_rate": 4.335421742661562e-05,
1064
+ "loss": 0.5346,
1065
+ "step": 73000
1066
+ },
1067
+ {
1068
+ "epoch": 8.53,
1069
+ "learning_rate": 4.327445179255134e-05,
1070
+ "loss": 0.5601,
1071
+ "step": 73500
1072
+ },
1073
+ {
1074
+ "epoch": 8.59,
1075
+ "learning_rate": 4.3194686158487064e-05,
1076
+ "loss": 0.5869,
1077
+ "step": 74000
1078
+ },
1079
+ {
1080
+ "epoch": 8.64,
1081
+ "learning_rate": 4.311492052442279e-05,
1082
+ "loss": 0.5873,
1083
+ "step": 74500
1084
+ },
1085
+ {
1086
+ "epoch": 8.7,
1087
+ "learning_rate": 4.303515489035851e-05,
1088
+ "loss": 0.5924,
1089
+ "step": 75000
1090
+ },
1091
+ {
1092
+ "epoch": 8.76,
1093
+ "learning_rate": 4.2955389256294235e-05,
1094
+ "loss": 0.601,
1095
+ "step": 75500
1096
+ },
1097
+ {
1098
+ "epoch": 8.82,
1099
+ "learning_rate": 4.287562362222996e-05,
1100
+ "loss": 0.6022,
1101
+ "step": 76000
1102
+ },
1103
+ {
1104
+ "epoch": 8.82,
1105
+ "eval_bleu": 27.7624,
1106
+ "eval_gen_len": 18.5558,
1107
+ "eval_loss": 1.283076286315918,
1108
+ "eval_runtime": 1144.2558,
1109
+ "eval_samples_per_second": 15.064,
1110
+ "eval_steps_per_second": 0.942,
1111
+ "step": 76000
1112
+ },
1113
+ {
1114
+ "epoch": 8.82,
1115
+ "step": 76000,
1116
+ "total_flos": 2.6353338197706015e+18,
1117
+ "train_loss": 0.8847039678473222,
1118
+ "train_runtime": 77092.0129,
1119
+ "train_samples_per_second": 71.551,
1120
+ "train_steps_per_second": 4.472
1121
+ }
1122
+ ],
1123
+ "logging_steps": 500,
1124
+ "max_steps": 344760,
1125
+ "num_train_epochs": 40,
1126
+ "save_steps": 4000,
1127
+ "total_flos": 2.6353338197706015e+18,
1128
+ "trial_name": null,
1129
+ "trial_params": null
1130
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bb1a208655fbdd6d2efe6842f38b33cb5a37243e0f443b39f19b8cba4439028
3
+ size 4728