Upload folder using huggingface_hub
Browse files- .gitattributes +3 -0
- README.md +79 -0
- added_tokens.json +59 -0
- all_results.json +22 -0
- checkpoint-12000/added_tokens.json +59 -0
- checkpoint-12000/config.json +59 -0
- checkpoint-12000/generation_config.json +12 -0
- checkpoint-12000/optimizer.pt +3 -0
- checkpoint-12000/pytorch_model.bin +3 -0
- checkpoint-12000/rng_state_0.pth +3 -0
- checkpoint-12000/rng_state_1.pth +3 -0
- checkpoint-12000/rng_state_2.pth +3 -0
- checkpoint-12000/rng_state_3.pth +3 -0
- checkpoint-12000/scheduler.pt +3 -0
- checkpoint-12000/sentencepiece.bpe.model +3 -0
- checkpoint-12000/special_tokens_map.json +63 -0
- checkpoint-12000/tokenizer.json +3 -0
- checkpoint-12000/tokenizer_config.json +528 -0
- checkpoint-12000/trainer_state.json +243 -0
- checkpoint-12000/training_args.bin +3 -0
- checkpoint-18000/added_tokens.json +59 -0
- checkpoint-18000/config.json +59 -0
- checkpoint-18000/generation_config.json +12 -0
- checkpoint-18000/optimizer.pt +3 -0
- checkpoint-18000/pytorch_model.bin +3 -0
- checkpoint-18000/rng_state_0.pth +3 -0
- checkpoint-18000/rng_state_1.pth +3 -0
- checkpoint-18000/rng_state_2.pth +3 -0
- checkpoint-18000/rng_state_3.pth +3 -0
- checkpoint-18000/scheduler.pt +3 -0
- checkpoint-18000/sentencepiece.bpe.model +3 -0
- checkpoint-18000/special_tokens_map.json +63 -0
- checkpoint-18000/tokenizer.json +3 -0
- checkpoint-18000/tokenizer_config.json +528 -0
- checkpoint-18000/trainer_state.json +355 -0
- checkpoint-18000/training_args.bin +3 -0
- config.json +59 -0
- eval_results.json +10 -0
- generated_predictions.txt +0 -0
- generation_config.json +12 -0
- predict_results.json +9 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +63 -0
- tokenizer.json +3 -0
- tokenizer_config.json +528 -0
- train_results.json +8 -0
- trainer_state.json +364 -0
- 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-12000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
checkpoint-18000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- ko
|
| 4 |
+
- ja
|
| 5 |
+
base_model: facebook/mbart-large-50-many-to-many-mmt
|
| 6 |
+
tags:
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
metrics:
|
| 9 |
+
- bleu
|
| 10 |
+
model-index:
|
| 11 |
+
- name: tst-translation-output2
|
| 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 |
+
# tst-translation-output2
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on an unknown dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.9049
|
| 23 |
+
- Bleu: 10.3643
|
| 24 |
+
- Gen Len: 17.4046
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 5e-05
|
| 44 |
+
- train_batch_size: 4
|
| 45 |
+
- eval_batch_size: 4
|
| 46 |
+
- seed: 42
|
| 47 |
+
- distributed_type: multi-GPU
|
| 48 |
+
- num_devices: 4
|
| 49 |
+
- total_train_batch_size: 16
|
| 50 |
+
- total_eval_batch_size: 16
|
| 51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
+
- lr_scheduler_type: linear
|
| 53 |
+
- lr_scheduler_warmup_steps: 500
|
| 54 |
+
- num_epochs: 35
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
| 59 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
|
| 60 |
+
| 1.2499 | 0.23 | 1500 | 1.1806 | 6.1112 | 18.0495 |
|
| 61 |
+
| 1.1007 | 0.46 | 3000 | 1.0686 | 7.4845 | 17.6068 |
|
| 62 |
+
| 1.0334 | 0.68 | 4500 | 1.0013 | 9.0076 | 17.6214 |
|
| 63 |
+
| 0.992 | 0.91 | 6000 | 0.9599 | 8.6786 | 17.868 |
|
| 64 |
+
| 0.7881 | 1.14 | 7500 | 0.9644 | 9.2343 | 17.2061 |
|
| 65 |
+
| 0.7675 | 1.37 | 9000 | 0.9427 | 10.0578 | 17.6006 |
|
| 66 |
+
| 0.7665 | 1.59 | 10500 | 0.9238 | 10.436 | 17.2095 |
|
| 67 |
+
| 0.7707 | 1.82 | 12000 | 0.9049 | 10.5971 | 17.2971 |
|
| 68 |
+
| 0.6119 | 2.05 | 13500 | 0.9392 | 10.8369 | 17.3201 |
|
| 69 |
+
| 0.5579 | 2.28 | 15000 | 0.9429 | 10.3486 | 17.3221 |
|
| 70 |
+
| 0.5633 | 2.5 | 16500 | 0.9310 | 10.6114 | 17.3679 |
|
| 71 |
+
| 0.5764 | 2.73 | 18000 | 0.9265 | 9.9612 | 17.1339 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- Transformers 4.34.0
|
| 77 |
+
- Pytorch 2.1.0+cu121
|
| 78 |
+
- Datasets 2.14.5
|
| 79 |
+
- 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": 2.73,
|
| 3 |
+
"eval_bleu": 10.3643,
|
| 4 |
+
"eval_gen_len": 17.4046,
|
| 5 |
+
"eval_loss": 0.9049463272094727,
|
| 6 |
+
"eval_runtime": 762.7452,
|
| 7 |
+
"eval_samples": 13172,
|
| 8 |
+
"eval_samples_per_second": 17.269,
|
| 9 |
+
"eval_steps_per_second": 1.08,
|
| 10 |
+
"predict_bleu": 13.1113,
|
| 11 |
+
"predict_gen_len": 17.5101,
|
| 12 |
+
"predict_loss": 0.9021268486976624,
|
| 13 |
+
"predict_runtime": 763.1074,
|
| 14 |
+
"predict_samples": 13173,
|
| 15 |
+
"predict_samples_per_second": 17.262,
|
| 16 |
+
"predict_steps_per_second": 1.08,
|
| 17 |
+
"train_loss": 0.8521621839735243,
|
| 18 |
+
"train_runtime": 30046.6476,
|
| 19 |
+
"train_samples": 105385,
|
| 20 |
+
"train_samples_per_second": 122.758,
|
| 21 |
+
"train_steps_per_second": 7.673
|
| 22 |
+
}
|
checkpoint-12000/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-12000/config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",
|
| 3 |
+
"_num_labels": 3,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "relu",
|
| 6 |
+
"add_bias_logits": false,
|
| 7 |
+
"add_final_layer_norm": true,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"MBartForConditionalGeneration"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"bos_token_id": 0,
|
| 13 |
+
"classif_dropout": 0.0,
|
| 14 |
+
"classifier_dropout": 0.0,
|
| 15 |
+
"d_model": 1024,
|
| 16 |
+
"decoder_attention_heads": 16,
|
| 17 |
+
"decoder_ffn_dim": 4096,
|
| 18 |
+
"decoder_layerdrop": 0.0,
|
| 19 |
+
"decoder_layers": 12,
|
| 20 |
+
"decoder_start_token_id": 2,
|
| 21 |
+
"dropout": 0.1,
|
| 22 |
+
"early_stopping": true,
|
| 23 |
+
"encoder_attention_heads": 16,
|
| 24 |
+
"encoder_ffn_dim": 4096,
|
| 25 |
+
"encoder_layerdrop": 0.0,
|
| 26 |
+
"encoder_layers": 12,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"forced_bos_token_id": 250012,
|
| 29 |
+
"forced_eos_token_id": 2,
|
| 30 |
+
"gradient_checkpointing": false,
|
| 31 |
+
"id2label": {
|
| 32 |
+
"0": "LABEL_0",
|
| 33 |
+
"1": "LABEL_1",
|
| 34 |
+
"2": "LABEL_2"
|
| 35 |
+
},
|
| 36 |
+
"init_std": 0.02,
|
| 37 |
+
"is_encoder_decoder": true,
|
| 38 |
+
"label2id": {
|
| 39 |
+
"LABEL_0": 0,
|
| 40 |
+
"LABEL_1": 1,
|
| 41 |
+
"LABEL_2": 2
|
| 42 |
+
},
|
| 43 |
+
"max_length": 200,
|
| 44 |
+
"max_position_embeddings": 1024,
|
| 45 |
+
"model_type": "mbart",
|
| 46 |
+
"normalize_before": true,
|
| 47 |
+
"normalize_embedding": true,
|
| 48 |
+
"num_beams": 5,
|
| 49 |
+
"num_hidden_layers": 12,
|
| 50 |
+
"output_past": true,
|
| 51 |
+
"pad_token_id": 1,
|
| 52 |
+
"scale_embedding": true,
|
| 53 |
+
"static_position_embeddings": false,
|
| 54 |
+
"tokenizer_class": "MBart50Tokenizer",
|
| 55 |
+
"torch_dtype": "float32",
|
| 56 |
+
"transformers_version": "4.34.0",
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"vocab_size": 250054
|
| 59 |
+
}
|
checkpoint-12000/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 0,
|
| 3 |
+
"decoder_start_token_id": 2,
|
| 4 |
+
"early_stopping": true,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"forced_bos_token_id": 250012,
|
| 7 |
+
"forced_eos_token_id": 2,
|
| 8 |
+
"max_length": 200,
|
| 9 |
+
"num_beams": 5,
|
| 10 |
+
"pad_token_id": 1,
|
| 11 |
+
"transformers_version": "4.34.0"
|
| 12 |
+
}
|
checkpoint-12000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1513125b0378a69da956de61bc8abaad17a7257ae21a5447dda7dbfd8985907f
|
| 3 |
+
size 4887473903
|
checkpoint-12000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0166078d1b193e9471cc8de7bd47486199749715a5734a180a476005681ef31f
|
| 3 |
+
size 2444694490
|
checkpoint-12000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa6828bbb6d12dbdd8064d7a98ff347b2edd4ac60b402f19fb566107b5d91fbc
|
| 3 |
+
size 15024
|
checkpoint-12000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f604e8709e465e8fa47dbc3b6ef3fcaae029d6b1ae93826ee284d49c97243e0
|
| 3 |
+
size 15024
|
checkpoint-12000/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9c3f875280181e1d098e0a17dba92565ad8274bf25333a974807d532f1fc889
|
| 3 |
+
size 15024
|
checkpoint-12000/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04ad8f6ac05bb029754bbe067e0c43d04d88fd4979d93fd092170c38321c377e
|
| 3 |
+
size 15024
|
checkpoint-12000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1206bdcaeafcab4e5a83f235cf6fa547aa62d73bb77a52edd0421f3b706174a4
|
| 3 |
+
size 1064
|
checkpoint-12000/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-12000/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-12000/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42a72efab312df69f4dda3c5e1d7eca7b8645f96023493a3834070caf20a2180
|
| 3 |
+
size 17109939
|
checkpoint-12000/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": "ja_XX",
|
| 526 |
+
"tokenizer_class": "MBart50Tokenizer",
|
| 527 |
+
"unk_token": "<unk>"
|
| 528 |
+
}
|
checkpoint-12000/trainer_state.json
ADDED
|
@@ -0,0 +1,243 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9049463272094727,
|
| 3 |
+
"best_model_checkpoint": "./tst-translation-output2/checkpoint-12000",
|
| 4 |
+
"epoch": 1.8217701533323214,
|
| 5 |
+
"eval_steps": 1500,
|
| 6 |
+
"global_step": 12000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08,
|
| 13 |
+
"learning_rate": 5e-05,
|
| 14 |
+
"loss": 1.7623,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.15,
|
| 19 |
+
"learning_rate": 4.98913256102067e-05,
|
| 20 |
+
"loss": 1.3653,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.23,
|
| 25 |
+
"learning_rate": 4.97826512204134e-05,
|
| 26 |
+
"loss": 1.2499,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.23,
|
| 31 |
+
"eval_bleu": 6.1112,
|
| 32 |
+
"eval_gen_len": 18.0495,
|
| 33 |
+
"eval_loss": 1.1805654764175415,
|
| 34 |
+
"eval_runtime": 916.5943,
|
| 35 |
+
"eval_samples_per_second": 14.371,
|
| 36 |
+
"eval_steps_per_second": 0.899,
|
| 37 |
+
"step": 1500
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.3,
|
| 41 |
+
"learning_rate": 4.96739768306201e-05,
|
| 42 |
+
"loss": 1.2038,
|
| 43 |
+
"step": 2000
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.38,
|
| 47 |
+
"learning_rate": 4.95653024408268e-05,
|
| 48 |
+
"loss": 1.1357,
|
| 49 |
+
"step": 2500
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.46,
|
| 53 |
+
"learning_rate": 4.945662805103349e-05,
|
| 54 |
+
"loss": 1.1007,
|
| 55 |
+
"step": 3000
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.46,
|
| 59 |
+
"eval_bleu": 7.4845,
|
| 60 |
+
"eval_gen_len": 17.6068,
|
| 61 |
+
"eval_loss": 1.0686322450637817,
|
| 62 |
+
"eval_runtime": 870.5195,
|
| 63 |
+
"eval_samples_per_second": 15.131,
|
| 64 |
+
"eval_steps_per_second": 0.947,
|
| 65 |
+
"step": 3000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.53,
|
| 69 |
+
"learning_rate": 4.9347953661240194e-05,
|
| 70 |
+
"loss": 1.0769,
|
| 71 |
+
"step": 3500
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.61,
|
| 75 |
+
"learning_rate": 4.923927927144689e-05,
|
| 76 |
+
"loss": 1.0708,
|
| 77 |
+
"step": 4000
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.68,
|
| 81 |
+
"learning_rate": 4.9130604881653594e-05,
|
| 82 |
+
"loss": 1.0334,
|
| 83 |
+
"step": 4500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.68,
|
| 87 |
+
"eval_bleu": 9.0076,
|
| 88 |
+
"eval_gen_len": 17.6214,
|
| 89 |
+
"eval_loss": 1.0013340711593628,
|
| 90 |
+
"eval_runtime": 888.8463,
|
| 91 |
+
"eval_samples_per_second": 14.819,
|
| 92 |
+
"eval_steps_per_second": 0.927,
|
| 93 |
+
"step": 4500
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.76,
|
| 97 |
+
"learning_rate": 4.902193049186029e-05,
|
| 98 |
+
"loss": 1.0175,
|
| 99 |
+
"step": 5000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.83,
|
| 103 |
+
"learning_rate": 4.891325610206699e-05,
|
| 104 |
+
"loss": 1.0074,
|
| 105 |
+
"step": 5500
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.91,
|
| 109 |
+
"learning_rate": 4.880458171227369e-05,
|
| 110 |
+
"loss": 0.992,
|
| 111 |
+
"step": 6000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.91,
|
| 115 |
+
"eval_bleu": 8.6786,
|
| 116 |
+
"eval_gen_len": 17.868,
|
| 117 |
+
"eval_loss": 0.9599339365959167,
|
| 118 |
+
"eval_runtime": 933.1213,
|
| 119 |
+
"eval_samples_per_second": 14.116,
|
| 120 |
+
"eval_steps_per_second": 0.883,
|
| 121 |
+
"step": 6000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.99,
|
| 125 |
+
"learning_rate": 4.8695907322480386e-05,
|
| 126 |
+
"loss": 0.9887,
|
| 127 |
+
"step": 6500
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.06,
|
| 131 |
+
"learning_rate": 4.858723293268709e-05,
|
| 132 |
+
"loss": 0.7834,
|
| 133 |
+
"step": 7000
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.14,
|
| 137 |
+
"learning_rate": 4.847855854289378e-05,
|
| 138 |
+
"loss": 0.7881,
|
| 139 |
+
"step": 7500
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 1.14,
|
| 143 |
+
"eval_bleu": 9.2343,
|
| 144 |
+
"eval_gen_len": 17.2061,
|
| 145 |
+
"eval_loss": 0.964439868927002,
|
| 146 |
+
"eval_runtime": 844.707,
|
| 147 |
+
"eval_samples_per_second": 15.594,
|
| 148 |
+
"eval_steps_per_second": 0.975,
|
| 149 |
+
"step": 7500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.21,
|
| 153 |
+
"learning_rate": 4.836988415310048e-05,
|
| 154 |
+
"loss": 0.7667,
|
| 155 |
+
"step": 8000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.29,
|
| 159 |
+
"learning_rate": 4.826120976330718e-05,
|
| 160 |
+
"loss": 0.7632,
|
| 161 |
+
"step": 8500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.37,
|
| 165 |
+
"learning_rate": 4.815253537351388e-05,
|
| 166 |
+
"loss": 0.7675,
|
| 167 |
+
"step": 9000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.37,
|
| 171 |
+
"eval_bleu": 10.0578,
|
| 172 |
+
"eval_gen_len": 17.6006,
|
| 173 |
+
"eval_loss": 0.942681610584259,
|
| 174 |
+
"eval_runtime": 1046.0952,
|
| 175 |
+
"eval_samples_per_second": 12.592,
|
| 176 |
+
"eval_steps_per_second": 0.788,
|
| 177 |
+
"step": 9000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.44,
|
| 181 |
+
"learning_rate": 4.804386098372058e-05,
|
| 182 |
+
"loss": 0.774,
|
| 183 |
+
"step": 9500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.52,
|
| 187 |
+
"learning_rate": 4.793518659392728e-05,
|
| 188 |
+
"loss": 0.7731,
|
| 189 |
+
"step": 10000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.59,
|
| 193 |
+
"learning_rate": 4.782651220413398e-05,
|
| 194 |
+
"loss": 0.7665,
|
| 195 |
+
"step": 10500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.59,
|
| 199 |
+
"eval_bleu": 10.436,
|
| 200 |
+
"eval_gen_len": 17.2095,
|
| 201 |
+
"eval_loss": 0.9237579703330994,
|
| 202 |
+
"eval_runtime": 854.5281,
|
| 203 |
+
"eval_samples_per_second": 15.414,
|
| 204 |
+
"eval_steps_per_second": 0.964,
|
| 205 |
+
"step": 10500
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.67,
|
| 209 |
+
"learning_rate": 4.7717837814340674e-05,
|
| 210 |
+
"loss": 0.761,
|
| 211 |
+
"step": 11000
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.75,
|
| 215 |
+
"learning_rate": 4.760916342454738e-05,
|
| 216 |
+
"loss": 0.7653,
|
| 217 |
+
"step": 11500
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.82,
|
| 221 |
+
"learning_rate": 4.750048903475407e-05,
|
| 222 |
+
"loss": 0.7707,
|
| 223 |
+
"step": 12000
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.82,
|
| 227 |
+
"eval_bleu": 10.5971,
|
| 228 |
+
"eval_gen_len": 17.2971,
|
| 229 |
+
"eval_loss": 0.9049463272094727,
|
| 230 |
+
"eval_runtime": 851.7484,
|
| 231 |
+
"eval_samples_per_second": 15.465,
|
| 232 |
+
"eval_steps_per_second": 0.967,
|
| 233 |
+
"step": 12000
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"logging_steps": 500,
|
| 237 |
+
"max_steps": 230545,
|
| 238 |
+
"num_train_epochs": 35,
|
| 239 |
+
"save_steps": 1500,
|
| 240 |
+
"total_flos": 4.16088915443712e+17,
|
| 241 |
+
"trial_name": null,
|
| 242 |
+
"trial_params": null
|
| 243 |
+
}
|
checkpoint-12000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f13c026b00370015a97978f7ef9ecb7e58c8b4cb621921c5d00fcd65afc05bf9
|
| 3 |
+
size 4664
|
checkpoint-18000/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-18000/config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",
|
| 3 |
+
"_num_labels": 3,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "relu",
|
| 6 |
+
"add_bias_logits": false,
|
| 7 |
+
"add_final_layer_norm": true,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"MBartForConditionalGeneration"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"bos_token_id": 0,
|
| 13 |
+
"classif_dropout": 0.0,
|
| 14 |
+
"classifier_dropout": 0.0,
|
| 15 |
+
"d_model": 1024,
|
| 16 |
+
"decoder_attention_heads": 16,
|
| 17 |
+
"decoder_ffn_dim": 4096,
|
| 18 |
+
"decoder_layerdrop": 0.0,
|
| 19 |
+
"decoder_layers": 12,
|
| 20 |
+
"decoder_start_token_id": 2,
|
| 21 |
+
"dropout": 0.1,
|
| 22 |
+
"early_stopping": true,
|
| 23 |
+
"encoder_attention_heads": 16,
|
| 24 |
+
"encoder_ffn_dim": 4096,
|
| 25 |
+
"encoder_layerdrop": 0.0,
|
| 26 |
+
"encoder_layers": 12,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"forced_bos_token_id": 250012,
|
| 29 |
+
"forced_eos_token_id": 2,
|
| 30 |
+
"gradient_checkpointing": false,
|
| 31 |
+
"id2label": {
|
| 32 |
+
"0": "LABEL_0",
|
| 33 |
+
"1": "LABEL_1",
|
| 34 |
+
"2": "LABEL_2"
|
| 35 |
+
},
|
| 36 |
+
"init_std": 0.02,
|
| 37 |
+
"is_encoder_decoder": true,
|
| 38 |
+
"label2id": {
|
| 39 |
+
"LABEL_0": 0,
|
| 40 |
+
"LABEL_1": 1,
|
| 41 |
+
"LABEL_2": 2
|
| 42 |
+
},
|
| 43 |
+
"max_length": 200,
|
| 44 |
+
"max_position_embeddings": 1024,
|
| 45 |
+
"model_type": "mbart",
|
| 46 |
+
"normalize_before": true,
|
| 47 |
+
"normalize_embedding": true,
|
| 48 |
+
"num_beams": 5,
|
| 49 |
+
"num_hidden_layers": 12,
|
| 50 |
+
"output_past": true,
|
| 51 |
+
"pad_token_id": 1,
|
| 52 |
+
"scale_embedding": true,
|
| 53 |
+
"static_position_embeddings": false,
|
| 54 |
+
"tokenizer_class": "MBart50Tokenizer",
|
| 55 |
+
"torch_dtype": "float32",
|
| 56 |
+
"transformers_version": "4.34.0",
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"vocab_size": 250054
|
| 59 |
+
}
|
checkpoint-18000/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 0,
|
| 3 |
+
"decoder_start_token_id": 2,
|
| 4 |
+
"early_stopping": true,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"forced_bos_token_id": 250012,
|
| 7 |
+
"forced_eos_token_id": 2,
|
| 8 |
+
"max_length": 200,
|
| 9 |
+
"num_beams": 5,
|
| 10 |
+
"pad_token_id": 1,
|
| 11 |
+
"transformers_version": "4.34.0"
|
| 12 |
+
}
|
checkpoint-18000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d28c07ec0fb21394381cea59c092918343eb4e0cf5654120102f167be268c0e7
|
| 3 |
+
size 4887473903
|
checkpoint-18000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2d94f0686ca15e60b09a3f9b50f575b4283a55e8174d40b4ab6d8d661212987
|
| 3 |
+
size 2444694490
|
checkpoint-18000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f32e140ccf048a14b9444564fd83e75ce48133e657b00fd1d7e646ffda76dd83
|
| 3 |
+
size 15024
|
checkpoint-18000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90a1217a6a17ac0316b7c6c204835a007f6f4bd18a13a8e1e7f74daf34e3687e
|
| 3 |
+
size 15024
|
checkpoint-18000/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f975ceb93137e8d52de8e42c8fd9b1c6f7da0eba1d173ab87e2a8d55e268aac1
|
| 3 |
+
size 15024
|
checkpoint-18000/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c86c5393f98b68b06b2783e4744033400e52327a7de1a06665cccd94207df077
|
| 3 |
+
size 15024
|
checkpoint-18000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2922357026cf94cda7c6526460608934653991575a871fa0923e3c286a197268
|
| 3 |
+
size 1064
|
checkpoint-18000/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-18000/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-18000/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42a72efab312df69f4dda3c5e1d7eca7b8645f96023493a3834070caf20a2180
|
| 3 |
+
size 17109939
|
checkpoint-18000/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": "ja_XX",
|
| 526 |
+
"tokenizer_class": "MBart50Tokenizer",
|
| 527 |
+
"unk_token": "<unk>"
|
| 528 |
+
}
|
checkpoint-18000/trainer_state.json
ADDED
|
@@ -0,0 +1,355 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9049463272094727,
|
| 3 |
+
"best_model_checkpoint": "./tst-translation-output2/checkpoint-12000",
|
| 4 |
+
"epoch": 2.732655229998482,
|
| 5 |
+
"eval_steps": 1500,
|
| 6 |
+
"global_step": 18000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08,
|
| 13 |
+
"learning_rate": 5e-05,
|
| 14 |
+
"loss": 1.7623,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.15,
|
| 19 |
+
"learning_rate": 4.98913256102067e-05,
|
| 20 |
+
"loss": 1.3653,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.23,
|
| 25 |
+
"learning_rate": 4.97826512204134e-05,
|
| 26 |
+
"loss": 1.2499,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.23,
|
| 31 |
+
"eval_bleu": 6.1112,
|
| 32 |
+
"eval_gen_len": 18.0495,
|
| 33 |
+
"eval_loss": 1.1805654764175415,
|
| 34 |
+
"eval_runtime": 916.5943,
|
| 35 |
+
"eval_samples_per_second": 14.371,
|
| 36 |
+
"eval_steps_per_second": 0.899,
|
| 37 |
+
"step": 1500
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.3,
|
| 41 |
+
"learning_rate": 4.96739768306201e-05,
|
| 42 |
+
"loss": 1.2038,
|
| 43 |
+
"step": 2000
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.38,
|
| 47 |
+
"learning_rate": 4.95653024408268e-05,
|
| 48 |
+
"loss": 1.1357,
|
| 49 |
+
"step": 2500
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.46,
|
| 53 |
+
"learning_rate": 4.945662805103349e-05,
|
| 54 |
+
"loss": 1.1007,
|
| 55 |
+
"step": 3000
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.46,
|
| 59 |
+
"eval_bleu": 7.4845,
|
| 60 |
+
"eval_gen_len": 17.6068,
|
| 61 |
+
"eval_loss": 1.0686322450637817,
|
| 62 |
+
"eval_runtime": 870.5195,
|
| 63 |
+
"eval_samples_per_second": 15.131,
|
| 64 |
+
"eval_steps_per_second": 0.947,
|
| 65 |
+
"step": 3000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.53,
|
| 69 |
+
"learning_rate": 4.9347953661240194e-05,
|
| 70 |
+
"loss": 1.0769,
|
| 71 |
+
"step": 3500
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.61,
|
| 75 |
+
"learning_rate": 4.923927927144689e-05,
|
| 76 |
+
"loss": 1.0708,
|
| 77 |
+
"step": 4000
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.68,
|
| 81 |
+
"learning_rate": 4.9130604881653594e-05,
|
| 82 |
+
"loss": 1.0334,
|
| 83 |
+
"step": 4500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.68,
|
| 87 |
+
"eval_bleu": 9.0076,
|
| 88 |
+
"eval_gen_len": 17.6214,
|
| 89 |
+
"eval_loss": 1.0013340711593628,
|
| 90 |
+
"eval_runtime": 888.8463,
|
| 91 |
+
"eval_samples_per_second": 14.819,
|
| 92 |
+
"eval_steps_per_second": 0.927,
|
| 93 |
+
"step": 4500
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.76,
|
| 97 |
+
"learning_rate": 4.902193049186029e-05,
|
| 98 |
+
"loss": 1.0175,
|
| 99 |
+
"step": 5000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.83,
|
| 103 |
+
"learning_rate": 4.891325610206699e-05,
|
| 104 |
+
"loss": 1.0074,
|
| 105 |
+
"step": 5500
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.91,
|
| 109 |
+
"learning_rate": 4.880458171227369e-05,
|
| 110 |
+
"loss": 0.992,
|
| 111 |
+
"step": 6000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.91,
|
| 115 |
+
"eval_bleu": 8.6786,
|
| 116 |
+
"eval_gen_len": 17.868,
|
| 117 |
+
"eval_loss": 0.9599339365959167,
|
| 118 |
+
"eval_runtime": 933.1213,
|
| 119 |
+
"eval_samples_per_second": 14.116,
|
| 120 |
+
"eval_steps_per_second": 0.883,
|
| 121 |
+
"step": 6000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.99,
|
| 125 |
+
"learning_rate": 4.8695907322480386e-05,
|
| 126 |
+
"loss": 0.9887,
|
| 127 |
+
"step": 6500
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.06,
|
| 131 |
+
"learning_rate": 4.858723293268709e-05,
|
| 132 |
+
"loss": 0.7834,
|
| 133 |
+
"step": 7000
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.14,
|
| 137 |
+
"learning_rate": 4.847855854289378e-05,
|
| 138 |
+
"loss": 0.7881,
|
| 139 |
+
"step": 7500
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 1.14,
|
| 143 |
+
"eval_bleu": 9.2343,
|
| 144 |
+
"eval_gen_len": 17.2061,
|
| 145 |
+
"eval_loss": 0.964439868927002,
|
| 146 |
+
"eval_runtime": 844.707,
|
| 147 |
+
"eval_samples_per_second": 15.594,
|
| 148 |
+
"eval_steps_per_second": 0.975,
|
| 149 |
+
"step": 7500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.21,
|
| 153 |
+
"learning_rate": 4.836988415310048e-05,
|
| 154 |
+
"loss": 0.7667,
|
| 155 |
+
"step": 8000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.29,
|
| 159 |
+
"learning_rate": 4.826120976330718e-05,
|
| 160 |
+
"loss": 0.7632,
|
| 161 |
+
"step": 8500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.37,
|
| 165 |
+
"learning_rate": 4.815253537351388e-05,
|
| 166 |
+
"loss": 0.7675,
|
| 167 |
+
"step": 9000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.37,
|
| 171 |
+
"eval_bleu": 10.0578,
|
| 172 |
+
"eval_gen_len": 17.6006,
|
| 173 |
+
"eval_loss": 0.942681610584259,
|
| 174 |
+
"eval_runtime": 1046.0952,
|
| 175 |
+
"eval_samples_per_second": 12.592,
|
| 176 |
+
"eval_steps_per_second": 0.788,
|
| 177 |
+
"step": 9000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.44,
|
| 181 |
+
"learning_rate": 4.804386098372058e-05,
|
| 182 |
+
"loss": 0.774,
|
| 183 |
+
"step": 9500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.52,
|
| 187 |
+
"learning_rate": 4.793518659392728e-05,
|
| 188 |
+
"loss": 0.7731,
|
| 189 |
+
"step": 10000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.59,
|
| 193 |
+
"learning_rate": 4.782651220413398e-05,
|
| 194 |
+
"loss": 0.7665,
|
| 195 |
+
"step": 10500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.59,
|
| 199 |
+
"eval_bleu": 10.436,
|
| 200 |
+
"eval_gen_len": 17.2095,
|
| 201 |
+
"eval_loss": 0.9237579703330994,
|
| 202 |
+
"eval_runtime": 854.5281,
|
| 203 |
+
"eval_samples_per_second": 15.414,
|
| 204 |
+
"eval_steps_per_second": 0.964,
|
| 205 |
+
"step": 10500
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.67,
|
| 209 |
+
"learning_rate": 4.7717837814340674e-05,
|
| 210 |
+
"loss": 0.761,
|
| 211 |
+
"step": 11000
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.75,
|
| 215 |
+
"learning_rate": 4.760916342454738e-05,
|
| 216 |
+
"loss": 0.7653,
|
| 217 |
+
"step": 11500
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.82,
|
| 221 |
+
"learning_rate": 4.750048903475407e-05,
|
| 222 |
+
"loss": 0.7707,
|
| 223 |
+
"step": 12000
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.82,
|
| 227 |
+
"eval_bleu": 10.5971,
|
| 228 |
+
"eval_gen_len": 17.2971,
|
| 229 |
+
"eval_loss": 0.9049463272094727,
|
| 230 |
+
"eval_runtime": 851.7484,
|
| 231 |
+
"eval_samples_per_second": 15.465,
|
| 232 |
+
"eval_steps_per_second": 0.967,
|
| 233 |
+
"step": 12000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.9,
|
| 237 |
+
"learning_rate": 4.739181464496077e-05,
|
| 238 |
+
"loss": 0.7691,
|
| 239 |
+
"step": 12500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.97,
|
| 243 |
+
"learning_rate": 4.7283140255167467e-05,
|
| 244 |
+
"loss": 0.7601,
|
| 245 |
+
"step": 13000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 2.05,
|
| 249 |
+
"learning_rate": 4.717446586537417e-05,
|
| 250 |
+
"loss": 0.6119,
|
| 251 |
+
"step": 13500
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.05,
|
| 255 |
+
"eval_bleu": 10.8369,
|
| 256 |
+
"eval_gen_len": 17.3201,
|
| 257 |
+
"eval_loss": 0.9391853213310242,
|
| 258 |
+
"eval_runtime": 840.2436,
|
| 259 |
+
"eval_samples_per_second": 15.676,
|
| 260 |
+
"eval_steps_per_second": 0.981,
|
| 261 |
+
"step": 13500
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.13,
|
| 265 |
+
"learning_rate": 4.7065791475580866e-05,
|
| 266 |
+
"loss": 0.5388,
|
| 267 |
+
"step": 14000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.2,
|
| 271 |
+
"learning_rate": 4.695711708578757e-05,
|
| 272 |
+
"loss": 0.5458,
|
| 273 |
+
"step": 14500
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.28,
|
| 277 |
+
"learning_rate": 4.6848442695994266e-05,
|
| 278 |
+
"loss": 0.5579,
|
| 279 |
+
"step": 15000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.28,
|
| 283 |
+
"eval_bleu": 10.3486,
|
| 284 |
+
"eval_gen_len": 17.3221,
|
| 285 |
+
"eval_loss": 0.9428810477256775,
|
| 286 |
+
"eval_runtime": 843.3509,
|
| 287 |
+
"eval_samples_per_second": 15.619,
|
| 288 |
+
"eval_steps_per_second": 0.977,
|
| 289 |
+
"step": 15000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.35,
|
| 293 |
+
"learning_rate": 4.673976830620096e-05,
|
| 294 |
+
"loss": 0.5532,
|
| 295 |
+
"step": 15500
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.43,
|
| 299 |
+
"learning_rate": 4.6631093916407665e-05,
|
| 300 |
+
"loss": 0.5683,
|
| 301 |
+
"step": 16000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 2.5,
|
| 305 |
+
"learning_rate": 4.6522419526614355e-05,
|
| 306 |
+
"loss": 0.5633,
|
| 307 |
+
"step": 16500
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.5,
|
| 311 |
+
"eval_bleu": 10.6114,
|
| 312 |
+
"eval_gen_len": 17.3679,
|
| 313 |
+
"eval_loss": 0.9309932589530945,
|
| 314 |
+
"eval_runtime": 843.6293,
|
| 315 |
+
"eval_samples_per_second": 15.613,
|
| 316 |
+
"eval_steps_per_second": 0.977,
|
| 317 |
+
"step": 16500
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 2.58,
|
| 321 |
+
"learning_rate": 4.641374513682106e-05,
|
| 322 |
+
"loss": 0.5718,
|
| 323 |
+
"step": 17000
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 2.66,
|
| 327 |
+
"learning_rate": 4.6305070747027754e-05,
|
| 328 |
+
"loss": 0.5774,
|
| 329 |
+
"step": 17500
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.73,
|
| 333 |
+
"learning_rate": 4.619639635723446e-05,
|
| 334 |
+
"loss": 0.5764,
|
| 335 |
+
"step": 18000
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.73,
|
| 339 |
+
"eval_bleu": 9.9612,
|
| 340 |
+
"eval_gen_len": 17.1339,
|
| 341 |
+
"eval_loss": 0.9264906048774719,
|
| 342 |
+
"eval_runtime": 843.7333,
|
| 343 |
+
"eval_samples_per_second": 15.612,
|
| 344 |
+
"eval_steps_per_second": 0.977,
|
| 345 |
+
"step": 18000
|
| 346 |
+
}
|
| 347 |
+
],
|
| 348 |
+
"logging_steps": 500,
|
| 349 |
+
"max_steps": 230545,
|
| 350 |
+
"num_train_epochs": 35,
|
| 351 |
+
"save_steps": 1500,
|
| 352 |
+
"total_flos": 6.24133373165568e+17,
|
| 353 |
+
"trial_name": null,
|
| 354 |
+
"trial_params": null
|
| 355 |
+
}
|
checkpoint-18000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f13c026b00370015a97978f7ef9ecb7e58c8b4cb621921c5d00fcd65afc05bf9
|
| 3 |
+
size 4664
|
config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",
|
| 3 |
+
"_num_labels": 3,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "relu",
|
| 6 |
+
"add_bias_logits": false,
|
| 7 |
+
"add_final_layer_norm": true,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"MBartForConditionalGeneration"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"bos_token_id": 0,
|
| 13 |
+
"classif_dropout": 0.0,
|
| 14 |
+
"classifier_dropout": 0.0,
|
| 15 |
+
"d_model": 1024,
|
| 16 |
+
"decoder_attention_heads": 16,
|
| 17 |
+
"decoder_ffn_dim": 4096,
|
| 18 |
+
"decoder_layerdrop": 0.0,
|
| 19 |
+
"decoder_layers": 12,
|
| 20 |
+
"decoder_start_token_id": 2,
|
| 21 |
+
"dropout": 0.1,
|
| 22 |
+
"early_stopping": true,
|
| 23 |
+
"encoder_attention_heads": 16,
|
| 24 |
+
"encoder_ffn_dim": 4096,
|
| 25 |
+
"encoder_layerdrop": 0.0,
|
| 26 |
+
"encoder_layers": 12,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"forced_bos_token_id": 250012,
|
| 29 |
+
"forced_eos_token_id": 2,
|
| 30 |
+
"gradient_checkpointing": false,
|
| 31 |
+
"id2label": {
|
| 32 |
+
"0": "LABEL_0",
|
| 33 |
+
"1": "LABEL_1",
|
| 34 |
+
"2": "LABEL_2"
|
| 35 |
+
},
|
| 36 |
+
"init_std": 0.02,
|
| 37 |
+
"is_encoder_decoder": true,
|
| 38 |
+
"label2id": {
|
| 39 |
+
"LABEL_0": 0,
|
| 40 |
+
"LABEL_1": 1,
|
| 41 |
+
"LABEL_2": 2
|
| 42 |
+
},
|
| 43 |
+
"max_length": 200,
|
| 44 |
+
"max_position_embeddings": 1024,
|
| 45 |
+
"model_type": "mbart",
|
| 46 |
+
"normalize_before": true,
|
| 47 |
+
"normalize_embedding": true,
|
| 48 |
+
"num_beams": 5,
|
| 49 |
+
"num_hidden_layers": 12,
|
| 50 |
+
"output_past": true,
|
| 51 |
+
"pad_token_id": 1,
|
| 52 |
+
"scale_embedding": true,
|
| 53 |
+
"static_position_embeddings": false,
|
| 54 |
+
"tokenizer_class": "MBart50Tokenizer",
|
| 55 |
+
"torch_dtype": "float32",
|
| 56 |
+
"transformers_version": "4.34.0",
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"vocab_size": 250054
|
| 59 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.73,
|
| 3 |
+
"eval_bleu": 10.3643,
|
| 4 |
+
"eval_gen_len": 17.4046,
|
| 5 |
+
"eval_loss": 0.9049463272094727,
|
| 6 |
+
"eval_runtime": 762.7452,
|
| 7 |
+
"eval_samples": 13172,
|
| 8 |
+
"eval_samples_per_second": 17.269,
|
| 9 |
+
"eval_steps_per_second": 1.08
|
| 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": 250012,
|
| 7 |
+
"forced_eos_token_id": 2,
|
| 8 |
+
"max_length": 200,
|
| 9 |
+
"num_beams": 5,
|
| 10 |
+
"pad_token_id": 1,
|
| 11 |
+
"transformers_version": "4.34.0"
|
| 12 |
+
}
|
predict_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_bleu": 13.1113,
|
| 3 |
+
"predict_gen_len": 17.5101,
|
| 4 |
+
"predict_loss": 0.9021268486976624,
|
| 5 |
+
"predict_runtime": 763.1074,
|
| 6 |
+
"predict_samples": 13173,
|
| 7 |
+
"predict_samples_per_second": 17.262,
|
| 8 |
+
"predict_steps_per_second": 1.08
|
| 9 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0166078d1b193e9471cc8de7bd47486199749715a5734a180a476005681ef31f
|
| 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 sha256:42a72efab312df69f4dda3c5e1d7eca7b8645f96023493a3834070caf20a2180
|
| 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": "ja_XX",
|
| 526 |
+
"tokenizer_class": "MBart50Tokenizer",
|
| 527 |
+
"unk_token": "<unk>"
|
| 528 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.73,
|
| 3 |
+
"train_loss": 0.8521621839735243,
|
| 4 |
+
"train_runtime": 30046.6476,
|
| 5 |
+
"train_samples": 105385,
|
| 6 |
+
"train_samples_per_second": 122.758,
|
| 7 |
+
"train_steps_per_second": 7.673
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,364 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9049463272094727,
|
| 3 |
+
"best_model_checkpoint": "./tst-translation-output2/checkpoint-12000",
|
| 4 |
+
"epoch": 2.732655229998482,
|
| 5 |
+
"eval_steps": 1500,
|
| 6 |
+
"global_step": 18000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08,
|
| 13 |
+
"learning_rate": 5e-05,
|
| 14 |
+
"loss": 1.7623,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.15,
|
| 19 |
+
"learning_rate": 4.98913256102067e-05,
|
| 20 |
+
"loss": 1.3653,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.23,
|
| 25 |
+
"learning_rate": 4.97826512204134e-05,
|
| 26 |
+
"loss": 1.2499,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.23,
|
| 31 |
+
"eval_bleu": 6.1112,
|
| 32 |
+
"eval_gen_len": 18.0495,
|
| 33 |
+
"eval_loss": 1.1805654764175415,
|
| 34 |
+
"eval_runtime": 916.5943,
|
| 35 |
+
"eval_samples_per_second": 14.371,
|
| 36 |
+
"eval_steps_per_second": 0.899,
|
| 37 |
+
"step": 1500
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.3,
|
| 41 |
+
"learning_rate": 4.96739768306201e-05,
|
| 42 |
+
"loss": 1.2038,
|
| 43 |
+
"step": 2000
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.38,
|
| 47 |
+
"learning_rate": 4.95653024408268e-05,
|
| 48 |
+
"loss": 1.1357,
|
| 49 |
+
"step": 2500
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.46,
|
| 53 |
+
"learning_rate": 4.945662805103349e-05,
|
| 54 |
+
"loss": 1.1007,
|
| 55 |
+
"step": 3000
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.46,
|
| 59 |
+
"eval_bleu": 7.4845,
|
| 60 |
+
"eval_gen_len": 17.6068,
|
| 61 |
+
"eval_loss": 1.0686322450637817,
|
| 62 |
+
"eval_runtime": 870.5195,
|
| 63 |
+
"eval_samples_per_second": 15.131,
|
| 64 |
+
"eval_steps_per_second": 0.947,
|
| 65 |
+
"step": 3000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.53,
|
| 69 |
+
"learning_rate": 4.9347953661240194e-05,
|
| 70 |
+
"loss": 1.0769,
|
| 71 |
+
"step": 3500
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.61,
|
| 75 |
+
"learning_rate": 4.923927927144689e-05,
|
| 76 |
+
"loss": 1.0708,
|
| 77 |
+
"step": 4000
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.68,
|
| 81 |
+
"learning_rate": 4.9130604881653594e-05,
|
| 82 |
+
"loss": 1.0334,
|
| 83 |
+
"step": 4500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.68,
|
| 87 |
+
"eval_bleu": 9.0076,
|
| 88 |
+
"eval_gen_len": 17.6214,
|
| 89 |
+
"eval_loss": 1.0013340711593628,
|
| 90 |
+
"eval_runtime": 888.8463,
|
| 91 |
+
"eval_samples_per_second": 14.819,
|
| 92 |
+
"eval_steps_per_second": 0.927,
|
| 93 |
+
"step": 4500
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.76,
|
| 97 |
+
"learning_rate": 4.902193049186029e-05,
|
| 98 |
+
"loss": 1.0175,
|
| 99 |
+
"step": 5000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.83,
|
| 103 |
+
"learning_rate": 4.891325610206699e-05,
|
| 104 |
+
"loss": 1.0074,
|
| 105 |
+
"step": 5500
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.91,
|
| 109 |
+
"learning_rate": 4.880458171227369e-05,
|
| 110 |
+
"loss": 0.992,
|
| 111 |
+
"step": 6000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.91,
|
| 115 |
+
"eval_bleu": 8.6786,
|
| 116 |
+
"eval_gen_len": 17.868,
|
| 117 |
+
"eval_loss": 0.9599339365959167,
|
| 118 |
+
"eval_runtime": 933.1213,
|
| 119 |
+
"eval_samples_per_second": 14.116,
|
| 120 |
+
"eval_steps_per_second": 0.883,
|
| 121 |
+
"step": 6000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.99,
|
| 125 |
+
"learning_rate": 4.8695907322480386e-05,
|
| 126 |
+
"loss": 0.9887,
|
| 127 |
+
"step": 6500
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.06,
|
| 131 |
+
"learning_rate": 4.858723293268709e-05,
|
| 132 |
+
"loss": 0.7834,
|
| 133 |
+
"step": 7000
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.14,
|
| 137 |
+
"learning_rate": 4.847855854289378e-05,
|
| 138 |
+
"loss": 0.7881,
|
| 139 |
+
"step": 7500
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 1.14,
|
| 143 |
+
"eval_bleu": 9.2343,
|
| 144 |
+
"eval_gen_len": 17.2061,
|
| 145 |
+
"eval_loss": 0.964439868927002,
|
| 146 |
+
"eval_runtime": 844.707,
|
| 147 |
+
"eval_samples_per_second": 15.594,
|
| 148 |
+
"eval_steps_per_second": 0.975,
|
| 149 |
+
"step": 7500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.21,
|
| 153 |
+
"learning_rate": 4.836988415310048e-05,
|
| 154 |
+
"loss": 0.7667,
|
| 155 |
+
"step": 8000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.29,
|
| 159 |
+
"learning_rate": 4.826120976330718e-05,
|
| 160 |
+
"loss": 0.7632,
|
| 161 |
+
"step": 8500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.37,
|
| 165 |
+
"learning_rate": 4.815253537351388e-05,
|
| 166 |
+
"loss": 0.7675,
|
| 167 |
+
"step": 9000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.37,
|
| 171 |
+
"eval_bleu": 10.0578,
|
| 172 |
+
"eval_gen_len": 17.6006,
|
| 173 |
+
"eval_loss": 0.942681610584259,
|
| 174 |
+
"eval_runtime": 1046.0952,
|
| 175 |
+
"eval_samples_per_second": 12.592,
|
| 176 |
+
"eval_steps_per_second": 0.788,
|
| 177 |
+
"step": 9000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.44,
|
| 181 |
+
"learning_rate": 4.804386098372058e-05,
|
| 182 |
+
"loss": 0.774,
|
| 183 |
+
"step": 9500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.52,
|
| 187 |
+
"learning_rate": 4.793518659392728e-05,
|
| 188 |
+
"loss": 0.7731,
|
| 189 |
+
"step": 10000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.59,
|
| 193 |
+
"learning_rate": 4.782651220413398e-05,
|
| 194 |
+
"loss": 0.7665,
|
| 195 |
+
"step": 10500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.59,
|
| 199 |
+
"eval_bleu": 10.436,
|
| 200 |
+
"eval_gen_len": 17.2095,
|
| 201 |
+
"eval_loss": 0.9237579703330994,
|
| 202 |
+
"eval_runtime": 854.5281,
|
| 203 |
+
"eval_samples_per_second": 15.414,
|
| 204 |
+
"eval_steps_per_second": 0.964,
|
| 205 |
+
"step": 10500
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.67,
|
| 209 |
+
"learning_rate": 4.7717837814340674e-05,
|
| 210 |
+
"loss": 0.761,
|
| 211 |
+
"step": 11000
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.75,
|
| 215 |
+
"learning_rate": 4.760916342454738e-05,
|
| 216 |
+
"loss": 0.7653,
|
| 217 |
+
"step": 11500
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.82,
|
| 221 |
+
"learning_rate": 4.750048903475407e-05,
|
| 222 |
+
"loss": 0.7707,
|
| 223 |
+
"step": 12000
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.82,
|
| 227 |
+
"eval_bleu": 10.5971,
|
| 228 |
+
"eval_gen_len": 17.2971,
|
| 229 |
+
"eval_loss": 0.9049463272094727,
|
| 230 |
+
"eval_runtime": 851.7484,
|
| 231 |
+
"eval_samples_per_second": 15.465,
|
| 232 |
+
"eval_steps_per_second": 0.967,
|
| 233 |
+
"step": 12000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.9,
|
| 237 |
+
"learning_rate": 4.739181464496077e-05,
|
| 238 |
+
"loss": 0.7691,
|
| 239 |
+
"step": 12500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.97,
|
| 243 |
+
"learning_rate": 4.7283140255167467e-05,
|
| 244 |
+
"loss": 0.7601,
|
| 245 |
+
"step": 13000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 2.05,
|
| 249 |
+
"learning_rate": 4.717446586537417e-05,
|
| 250 |
+
"loss": 0.6119,
|
| 251 |
+
"step": 13500
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.05,
|
| 255 |
+
"eval_bleu": 10.8369,
|
| 256 |
+
"eval_gen_len": 17.3201,
|
| 257 |
+
"eval_loss": 0.9391853213310242,
|
| 258 |
+
"eval_runtime": 840.2436,
|
| 259 |
+
"eval_samples_per_second": 15.676,
|
| 260 |
+
"eval_steps_per_second": 0.981,
|
| 261 |
+
"step": 13500
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.13,
|
| 265 |
+
"learning_rate": 4.7065791475580866e-05,
|
| 266 |
+
"loss": 0.5388,
|
| 267 |
+
"step": 14000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.2,
|
| 271 |
+
"learning_rate": 4.695711708578757e-05,
|
| 272 |
+
"loss": 0.5458,
|
| 273 |
+
"step": 14500
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.28,
|
| 277 |
+
"learning_rate": 4.6848442695994266e-05,
|
| 278 |
+
"loss": 0.5579,
|
| 279 |
+
"step": 15000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.28,
|
| 283 |
+
"eval_bleu": 10.3486,
|
| 284 |
+
"eval_gen_len": 17.3221,
|
| 285 |
+
"eval_loss": 0.9428810477256775,
|
| 286 |
+
"eval_runtime": 843.3509,
|
| 287 |
+
"eval_samples_per_second": 15.619,
|
| 288 |
+
"eval_steps_per_second": 0.977,
|
| 289 |
+
"step": 15000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.35,
|
| 293 |
+
"learning_rate": 4.673976830620096e-05,
|
| 294 |
+
"loss": 0.5532,
|
| 295 |
+
"step": 15500
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.43,
|
| 299 |
+
"learning_rate": 4.6631093916407665e-05,
|
| 300 |
+
"loss": 0.5683,
|
| 301 |
+
"step": 16000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 2.5,
|
| 305 |
+
"learning_rate": 4.6522419526614355e-05,
|
| 306 |
+
"loss": 0.5633,
|
| 307 |
+
"step": 16500
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.5,
|
| 311 |
+
"eval_bleu": 10.6114,
|
| 312 |
+
"eval_gen_len": 17.3679,
|
| 313 |
+
"eval_loss": 0.9309932589530945,
|
| 314 |
+
"eval_runtime": 843.6293,
|
| 315 |
+
"eval_samples_per_second": 15.613,
|
| 316 |
+
"eval_steps_per_second": 0.977,
|
| 317 |
+
"step": 16500
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 2.58,
|
| 321 |
+
"learning_rate": 4.641374513682106e-05,
|
| 322 |
+
"loss": 0.5718,
|
| 323 |
+
"step": 17000
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 2.66,
|
| 327 |
+
"learning_rate": 4.6305070747027754e-05,
|
| 328 |
+
"loss": 0.5774,
|
| 329 |
+
"step": 17500
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.73,
|
| 333 |
+
"learning_rate": 4.619639635723446e-05,
|
| 334 |
+
"loss": 0.5764,
|
| 335 |
+
"step": 18000
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.73,
|
| 339 |
+
"eval_bleu": 9.9612,
|
| 340 |
+
"eval_gen_len": 17.1339,
|
| 341 |
+
"eval_loss": 0.9264906048774719,
|
| 342 |
+
"eval_runtime": 843.7333,
|
| 343 |
+
"eval_samples_per_second": 15.612,
|
| 344 |
+
"eval_steps_per_second": 0.977,
|
| 345 |
+
"step": 18000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.73,
|
| 349 |
+
"step": 18000,
|
| 350 |
+
"total_flos": 6.24133373165568e+17,
|
| 351 |
+
"train_loss": 0.8521621839735243,
|
| 352 |
+
"train_runtime": 30046.6476,
|
| 353 |
+
"train_samples_per_second": 122.758,
|
| 354 |
+
"train_steps_per_second": 7.673
|
| 355 |
+
}
|
| 356 |
+
],
|
| 357 |
+
"logging_steps": 500,
|
| 358 |
+
"max_steps": 230545,
|
| 359 |
+
"num_train_epochs": 35,
|
| 360 |
+
"save_steps": 1500,
|
| 361 |
+
"total_flos": 6.24133373165568e+17,
|
| 362 |
+
"trial_name": null,
|
| 363 |
+
"trial_params": null
|
| 364 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f13c026b00370015a97978f7ef9ecb7e58c8b4cb621921c5d00fcd65afc05bf9
|
| 3 |
+
size 4664
|