Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- README.md +73 -0
- added_tokens.json +32 -0
- all_results.json +22 -0
- checkpoint-6000/added_tokens.json +32 -0
- checkpoint-6000/config.json +60 -0
- checkpoint-6000/generation_config.json +10 -0
- checkpoint-6000/optimizer.pt +3 -0
- checkpoint-6000/pytorch_model.bin +3 -0
- checkpoint-6000/rng_state_0.pth +3 -0
- checkpoint-6000/rng_state_1.pth +3 -0
- checkpoint-6000/rng_state_2.pth +3 -0
- checkpoint-6000/rng_state_3.pth +3 -0
- checkpoint-6000/scheduler.pt +3 -0
- checkpoint-6000/sentencepiece.bpe.model +3 -0
- checkpoint-6000/special_tokens_map.json +36 -0
- checkpoint-6000/tokenizer.json +3 -0
- checkpoint-6000/tokenizer_config.json +283 -0
- checkpoint-6000/trainer_state.json +121 -0
- checkpoint-6000/training_args.bin +3 -0
- config.json +60 -0
- eval_results.json +10 -0
- generated_predictions.txt +0 -0
- generation_config.json +10 -0
- predict_results.json +9 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +36 -0
- tokenizer.json +3 -0
- tokenizer_config.json +283 -0
- train_results.json +8 -0
- trainer_state.json +232 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,5 @@ 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-6000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- ko
|
| 4 |
+
- zh
|
| 5 |
+
base_model: facebook/mbart-large-cc25
|
| 6 |
+
tags:
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
metrics:
|
| 9 |
+
- bleu
|
| 10 |
+
model-index:
|
| 11 |
+
- name: tst-translation-output4
|
| 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-output4
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [facebook/mbart-large-cc25](https://huggingface.co/facebook/mbart-large-cc25) on an unknown dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 1.3569
|
| 23 |
+
- Bleu: 11.508
|
| 24 |
+
- Gen Len: 14.3854
|
| 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: 1500
|
| 54 |
+
- num_epochs: 40
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
| 59 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
|
| 60 |
+
| 1.5428 | 0.86 | 2000 | 1.4469 | 8.6101 | 16.9959 |
|
| 61 |
+
| 1.1195 | 1.71 | 4000 | 1.3471 | 10.3699 | 14.5055 |
|
| 62 |
+
| 0.8028 | 2.57 | 6000 | 1.3569 | 11.508 | 14.3955 |
|
| 63 |
+
| 0.5856 | 3.43 | 8000 | 1.4776 | 10.7663 | 15.0208 |
|
| 64 |
+
| 0.378 | 4.29 | 10000 | 1.6134 | 10.5237 | 14.3284 |
|
| 65 |
+
| 0.3093 | 5.14 | 12000 | 1.7701 | 10.7522 | 14.0819 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.34.0
|
| 71 |
+
- Pytorch 2.0.1+cu117
|
| 72 |
+
- Datasets 2.14.5
|
| 73 |
+
- Tokenizers 0.14.0
|
added_tokens.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s>": 2,
|
| 3 |
+
"<mask>": 250026,
|
| 4 |
+
"<pad>": 1,
|
| 5 |
+
"<s>": 0,
|
| 6 |
+
"<unk>": 3,
|
| 7 |
+
"ar_AR": 250001,
|
| 8 |
+
"cs_CZ": 250002,
|
| 9 |
+
"de_DE": 250003,
|
| 10 |
+
"en_XX": 250004,
|
| 11 |
+
"es_XX": 250005,
|
| 12 |
+
"et_EE": 250006,
|
| 13 |
+
"fi_FI": 250007,
|
| 14 |
+
"fr_XX": 250008,
|
| 15 |
+
"gu_IN": 250009,
|
| 16 |
+
"hi_IN": 250010,
|
| 17 |
+
"it_IT": 250011,
|
| 18 |
+
"ja_XX": 250012,
|
| 19 |
+
"kk_KZ": 250013,
|
| 20 |
+
"ko_KR": 250014,
|
| 21 |
+
"lt_LT": 250015,
|
| 22 |
+
"lv_LV": 250016,
|
| 23 |
+
"my_MM": 250017,
|
| 24 |
+
"ne_NP": 250018,
|
| 25 |
+
"nl_XX": 250019,
|
| 26 |
+
"ro_RO": 250020,
|
| 27 |
+
"ru_RU": 250021,
|
| 28 |
+
"si_LK": 250022,
|
| 29 |
+
"tr_TR": 250023,
|
| 30 |
+
"vi_VN": 250024,
|
| 31 |
+
"zh_CN": 250025
|
| 32 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.14,
|
| 3 |
+
"eval_bleu": 11.508,
|
| 4 |
+
"eval_gen_len": 14.3854,
|
| 5 |
+
"eval_loss": 1.3568514585494995,
|
| 6 |
+
"eval_runtime": 272.9589,
|
| 7 |
+
"eval_samples": 4665,
|
| 8 |
+
"eval_samples_per_second": 17.09,
|
| 9 |
+
"eval_steps_per_second": 1.07,
|
| 10 |
+
"predict_bleu": 9.159,
|
| 11 |
+
"predict_gen_len": 15.5275,
|
| 12 |
+
"predict_loss": 1.928805947303772,
|
| 13 |
+
"predict_runtime": 292.501,
|
| 14 |
+
"predict_samples": 4665,
|
| 15 |
+
"predict_samples_per_second": 15.949,
|
| 16 |
+
"predict_steps_per_second": 0.998,
|
| 17 |
+
"train_loss": 1.0545102322896323,
|
| 18 |
+
"train_runtime": 10410.1428,
|
| 19 |
+
"train_samples": 37324,
|
| 20 |
+
"train_samples_per_second": 143.414,
|
| 21 |
+
"train_steps_per_second": 8.964
|
| 22 |
+
}
|
checkpoint-6000/added_tokens.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s>": 2,
|
| 3 |
+
"<mask>": 250026,
|
| 4 |
+
"<pad>": 1,
|
| 5 |
+
"<s>": 0,
|
| 6 |
+
"<unk>": 3,
|
| 7 |
+
"ar_AR": 250001,
|
| 8 |
+
"cs_CZ": 250002,
|
| 9 |
+
"de_DE": 250003,
|
| 10 |
+
"en_XX": 250004,
|
| 11 |
+
"es_XX": 250005,
|
| 12 |
+
"et_EE": 250006,
|
| 13 |
+
"fi_FI": 250007,
|
| 14 |
+
"fr_XX": 250008,
|
| 15 |
+
"gu_IN": 250009,
|
| 16 |
+
"hi_IN": 250010,
|
| 17 |
+
"it_IT": 250011,
|
| 18 |
+
"ja_XX": 250012,
|
| 19 |
+
"kk_KZ": 250013,
|
| 20 |
+
"ko_KR": 250014,
|
| 21 |
+
"lt_LT": 250015,
|
| 22 |
+
"lv_LV": 250016,
|
| 23 |
+
"my_MM": 250017,
|
| 24 |
+
"ne_NP": 250018,
|
| 25 |
+
"nl_XX": 250019,
|
| 26 |
+
"ro_RO": 250020,
|
| 27 |
+
"ru_RU": 250021,
|
| 28 |
+
"si_LK": 250022,
|
| 29 |
+
"tr_TR": 250023,
|
| 30 |
+
"vi_VN": 250024,
|
| 31 |
+
"zh_CN": 250025
|
| 32 |
+
}
|
checkpoint-6000/config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/mbart-large-cc25",
|
| 3 |
+
"_num_labels": 3,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "gelu",
|
| 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": 250025,
|
| 21 |
+
"dropout": 0.1,
|
| 22 |
+
"encoder_attention_heads": 16,
|
| 23 |
+
"encoder_ffn_dim": 4096,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 12,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"forced_eos_token_id": 2,
|
| 28 |
+
"id2label": {
|
| 29 |
+
"0": "LABEL_0",
|
| 30 |
+
"1": "LABEL_1",
|
| 31 |
+
"2": "LABEL_2"
|
| 32 |
+
},
|
| 33 |
+
"init_std": 0.02,
|
| 34 |
+
"is_encoder_decoder": true,
|
| 35 |
+
"label2id": {
|
| 36 |
+
"LABEL_0": 0,
|
| 37 |
+
"LABEL_1": 1,
|
| 38 |
+
"LABEL_2": 2
|
| 39 |
+
},
|
| 40 |
+
"max_length": 1024,
|
| 41 |
+
"max_position_embeddings": 1024,
|
| 42 |
+
"model_type": "mbart",
|
| 43 |
+
"normalize_before": true,
|
| 44 |
+
"normalize_embedding": true,
|
| 45 |
+
"num_beams": 5,
|
| 46 |
+
"num_hidden_layers": 12,
|
| 47 |
+
"output_past": true,
|
| 48 |
+
"pad_token_id": 1,
|
| 49 |
+
"scale_embedding": true,
|
| 50 |
+
"static_position_embeddings": false,
|
| 51 |
+
"task_specific_params": {
|
| 52 |
+
"translation_en_to_ro": {
|
| 53 |
+
"decoder_start_token_id": 250020
|
| 54 |
+
}
|
| 55 |
+
},
|
| 56 |
+
"torch_dtype": "float32",
|
| 57 |
+
"transformers_version": "4.34.0",
|
| 58 |
+
"use_cache": true,
|
| 59 |
+
"vocab_size": 250027
|
| 60 |
+
}
|
checkpoint-6000/generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 0,
|
| 3 |
+
"decoder_start_token_id": 250025,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"forced_eos_token_id": 2,
|
| 6 |
+
"max_length": 1024,
|
| 7 |
+
"num_beams": 5,
|
| 8 |
+
"pad_token_id": 1,
|
| 9 |
+
"transformers_version": "4.34.0"
|
| 10 |
+
}
|
checkpoint-6000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c401da82f50825cfb3238769b75e99739aa2ff8e5e7df8b083c430638ce7f07
|
| 3 |
+
size 4887252270
|
checkpoint-6000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a59b162890bd563d2ccf6be6666b50beed00fd335eb90e67004def105c73be7a
|
| 3 |
+
size 2444583325
|
checkpoint-6000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b78b1399ced998685d7a9a6937fc21bc358de9960efd0bab98a4a147a14c03c4
|
| 3 |
+
size 17655
|
checkpoint-6000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:573acb6bb617c5855b9ecabab3040b42b7cc8479299ad783f338ff2c624c0614
|
| 3 |
+
size 17655
|
checkpoint-6000/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95c880b8d480dd1dec8f7af142fbcfc58ea783eefe12917d7944bf9cfdb4d667
|
| 3 |
+
size 17655
|
checkpoint-6000/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cb0fe75f0e31e1f17cf775d07fc11efefce780a51a65dccd458f4b638298541
|
| 3 |
+
size 17655
|
checkpoint-6000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a30b43195fcb573419ab4bf37cd522a2779c468af8c46ef8bdc2a7da798f76c
|
| 3 |
+
size 627
|
checkpoint-6000/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-6000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
],
|
| 29 |
+
"bos_token": "<s>",
|
| 30 |
+
"cls_token": "<s>",
|
| 31 |
+
"eos_token": "</s>",
|
| 32 |
+
"mask_token": "<mask>",
|
| 33 |
+
"pad_token": "<pad>",
|
| 34 |
+
"sep_token": "</s>",
|
| 35 |
+
"unk_token": "<unk>"
|
| 36 |
+
}
|
checkpoint-6000/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29dc894e8f2cdad9b6a9006377f54739240fba228269d60e9ba7092e83fa8eeb
|
| 3 |
+
size 17088468
|
checkpoint-6000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,283 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"250001": {
|
| 36 |
+
"content": "ar_AR",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"250002": {
|
| 44 |
+
"content": "cs_CZ",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"250003": {
|
| 52 |
+
"content": "de_DE",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"250004": {
|
| 60 |
+
"content": "en_XX",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"250005": {
|
| 68 |
+
"content": "es_XX",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"250006": {
|
| 76 |
+
"content": "et_EE",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"250007": {
|
| 84 |
+
"content": "fi_FI",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"250008": {
|
| 92 |
+
"content": "fr_XX",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"250009": {
|
| 100 |
+
"content": "gu_IN",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"250010": {
|
| 108 |
+
"content": "hi_IN",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"250011": {
|
| 116 |
+
"content": "it_IT",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"250012": {
|
| 124 |
+
"content": "ja_XX",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"250013": {
|
| 132 |
+
"content": "kk_KZ",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"250014": {
|
| 140 |
+
"content": "ko_KR",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"250015": {
|
| 148 |
+
"content": "lt_LT",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"250016": {
|
| 156 |
+
"content": "lv_LV",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"250017": {
|
| 164 |
+
"content": "my_MM",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"250018": {
|
| 172 |
+
"content": "ne_NP",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"250019": {
|
| 180 |
+
"content": "nl_XX",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"250020": {
|
| 188 |
+
"content": "ro_RO",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"250021": {
|
| 196 |
+
"content": "ru_RU",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"250022": {
|
| 204 |
+
"content": "si_LK",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"250023": {
|
| 212 |
+
"content": "tr_TR",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"250024": {
|
| 220 |
+
"content": "vi_VN",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"250025": {
|
| 228 |
+
"content": "zh_CN",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"250026": {
|
| 236 |
+
"content": "<mask>",
|
| 237 |
+
"lstrip": true,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
}
|
| 243 |
+
},
|
| 244 |
+
"additional_special_tokens": [
|
| 245 |
+
"ar_AR",
|
| 246 |
+
"cs_CZ",
|
| 247 |
+
"de_DE",
|
| 248 |
+
"en_XX",
|
| 249 |
+
"es_XX",
|
| 250 |
+
"et_EE",
|
| 251 |
+
"fi_FI",
|
| 252 |
+
"fr_XX",
|
| 253 |
+
"gu_IN",
|
| 254 |
+
"hi_IN",
|
| 255 |
+
"it_IT",
|
| 256 |
+
"ja_XX",
|
| 257 |
+
"kk_KZ",
|
| 258 |
+
"ko_KR",
|
| 259 |
+
"lt_LT",
|
| 260 |
+
"lv_LV",
|
| 261 |
+
"my_MM",
|
| 262 |
+
"ne_NP",
|
| 263 |
+
"nl_XX",
|
| 264 |
+
"ro_RO",
|
| 265 |
+
"ru_RU",
|
| 266 |
+
"si_LK",
|
| 267 |
+
"tr_TR",
|
| 268 |
+
"vi_VN",
|
| 269 |
+
"zh_CN"
|
| 270 |
+
],
|
| 271 |
+
"bos_token": "<s>",
|
| 272 |
+
"clean_up_tokenization_spaces": true,
|
| 273 |
+
"cls_token": "<s>",
|
| 274 |
+
"eos_token": "</s>",
|
| 275 |
+
"mask_token": "<mask>",
|
| 276 |
+
"model_max_length": 1024,
|
| 277 |
+
"pad_token": "<pad>",
|
| 278 |
+
"sep_token": "</s>",
|
| 279 |
+
"src_lang": "ko_KR",
|
| 280 |
+
"tgt_lang": "zh_CN",
|
| 281 |
+
"tokenizer_class": "MBartTokenizer",
|
| 282 |
+
"unk_token": "<unk>"
|
| 283 |
+
}
|
checkpoint-6000/trainer_state.json
ADDED
|
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 11.508,
|
| 3 |
+
"best_model_checkpoint": "./tst-translation-output4/checkpoint-6000",
|
| 4 |
+
"epoch": 2.571795970852979,
|
| 5 |
+
"eval_steps": 2000,
|
| 6 |
+
"global_step": 6000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.21,
|
| 13 |
+
"learning_rate": 1.6366666666666667e-05,
|
| 14 |
+
"loss": 3.946,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.43,
|
| 19 |
+
"learning_rate": 3.3033333333333334e-05,
|
| 20 |
+
"loss": 1.7959,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.64,
|
| 25 |
+
"learning_rate": 4.97e-05,
|
| 26 |
+
"loss": 1.6545,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.86,
|
| 31 |
+
"learning_rate": 4.973262905685036e-05,
|
| 32 |
+
"loss": 1.5428,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.86,
|
| 37 |
+
"eval_bleu": 8.6101,
|
| 38 |
+
"eval_gen_len": 16.9959,
|
| 39 |
+
"eval_loss": 1.4468804597854614,
|
| 40 |
+
"eval_runtime": 677.1599,
|
| 41 |
+
"eval_samples_per_second": 6.889,
|
| 42 |
+
"eval_steps_per_second": 0.431,
|
| 43 |
+
"step": 2000
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 1.07,
|
| 47 |
+
"learning_rate": 4.94603572206491e-05,
|
| 48 |
+
"loss": 1.3602,
|
| 49 |
+
"step": 2500
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.29,
|
| 53 |
+
"learning_rate": 4.9188085384447834e-05,
|
| 54 |
+
"loss": 1.1488,
|
| 55 |
+
"step": 3000
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 1.5,
|
| 59 |
+
"learning_rate": 4.891581354824657e-05,
|
| 60 |
+
"loss": 1.1566,
|
| 61 |
+
"step": 3500
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.71,
|
| 65 |
+
"learning_rate": 4.864354171204531e-05,
|
| 66 |
+
"loss": 1.1195,
|
| 67 |
+
"step": 4000
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 1.71,
|
| 71 |
+
"eval_bleu": 10.3699,
|
| 72 |
+
"eval_gen_len": 14.5055,
|
| 73 |
+
"eval_loss": 1.347112774848938,
|
| 74 |
+
"eval_runtime": 470.7402,
|
| 75 |
+
"eval_samples_per_second": 9.91,
|
| 76 |
+
"eval_steps_per_second": 0.62,
|
| 77 |
+
"step": 4000
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.93,
|
| 81 |
+
"learning_rate": 4.8371269875844045e-05,
|
| 82 |
+
"loss": 1.1057,
|
| 83 |
+
"step": 4500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 2.14,
|
| 87 |
+
"learning_rate": 4.8098998039642784e-05,
|
| 88 |
+
"loss": 0.8761,
|
| 89 |
+
"step": 5000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.36,
|
| 93 |
+
"learning_rate": 4.782672620344152e-05,
|
| 94 |
+
"loss": 0.7709,
|
| 95 |
+
"step": 5500
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 2.57,
|
| 99 |
+
"learning_rate": 4.7554454367240256e-05,
|
| 100 |
+
"loss": 0.8028,
|
| 101 |
+
"step": 6000
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 2.57,
|
| 105 |
+
"eval_bleu": 11.508,
|
| 106 |
+
"eval_gen_len": 14.3955,
|
| 107 |
+
"eval_loss": 1.3568514585494995,
|
| 108 |
+
"eval_runtime": 276.6335,
|
| 109 |
+
"eval_samples_per_second": 16.863,
|
| 110 |
+
"eval_steps_per_second": 1.056,
|
| 111 |
+
"step": 6000
|
| 112 |
+
}
|
| 113 |
+
],
|
| 114 |
+
"logging_steps": 500,
|
| 115 |
+
"max_steps": 93320,
|
| 116 |
+
"num_train_epochs": 40,
|
| 117 |
+
"save_steps": 2000,
|
| 118 |
+
"total_flos": 2.08044457721856e+17,
|
| 119 |
+
"trial_name": null,
|
| 120 |
+
"trial_params": null
|
| 121 |
+
}
|
checkpoint-6000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8b64864d9ab4060e033ff986454621f242b6568d857f20686e24d1f4872f1b6
|
| 3 |
+
size 4219
|
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/mbart-large-cc25",
|
| 3 |
+
"_num_labels": 3,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "gelu",
|
| 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": 250025,
|
| 21 |
+
"dropout": 0.1,
|
| 22 |
+
"encoder_attention_heads": 16,
|
| 23 |
+
"encoder_ffn_dim": 4096,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 12,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"forced_eos_token_id": 2,
|
| 28 |
+
"id2label": {
|
| 29 |
+
"0": "LABEL_0",
|
| 30 |
+
"1": "LABEL_1",
|
| 31 |
+
"2": "LABEL_2"
|
| 32 |
+
},
|
| 33 |
+
"init_std": 0.02,
|
| 34 |
+
"is_encoder_decoder": true,
|
| 35 |
+
"label2id": {
|
| 36 |
+
"LABEL_0": 0,
|
| 37 |
+
"LABEL_1": 1,
|
| 38 |
+
"LABEL_2": 2
|
| 39 |
+
},
|
| 40 |
+
"max_length": 1024,
|
| 41 |
+
"max_position_embeddings": 1024,
|
| 42 |
+
"model_type": "mbart",
|
| 43 |
+
"normalize_before": true,
|
| 44 |
+
"normalize_embedding": true,
|
| 45 |
+
"num_beams": 5,
|
| 46 |
+
"num_hidden_layers": 12,
|
| 47 |
+
"output_past": true,
|
| 48 |
+
"pad_token_id": 1,
|
| 49 |
+
"scale_embedding": true,
|
| 50 |
+
"static_position_embeddings": false,
|
| 51 |
+
"task_specific_params": {
|
| 52 |
+
"translation_en_to_ro": {
|
| 53 |
+
"decoder_start_token_id": 250020
|
| 54 |
+
}
|
| 55 |
+
},
|
| 56 |
+
"torch_dtype": "float32",
|
| 57 |
+
"transformers_version": "4.34.0",
|
| 58 |
+
"use_cache": true,
|
| 59 |
+
"vocab_size": 250027
|
| 60 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.14,
|
| 3 |
+
"eval_bleu": 11.508,
|
| 4 |
+
"eval_gen_len": 14.3854,
|
| 5 |
+
"eval_loss": 1.3568514585494995,
|
| 6 |
+
"eval_runtime": 272.9589,
|
| 7 |
+
"eval_samples": 4665,
|
| 8 |
+
"eval_samples_per_second": 17.09,
|
| 9 |
+
"eval_steps_per_second": 1.07
|
| 10 |
+
}
|
generated_predictions.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 0,
|
| 3 |
+
"decoder_start_token_id": 250025,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"forced_eos_token_id": 2,
|
| 6 |
+
"max_length": 1024,
|
| 7 |
+
"num_beams": 5,
|
| 8 |
+
"pad_token_id": 1,
|
| 9 |
+
"transformers_version": "4.34.0"
|
| 10 |
+
}
|
predict_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_bleu": 9.159,
|
| 3 |
+
"predict_gen_len": 15.5275,
|
| 4 |
+
"predict_loss": 1.928805947303772,
|
| 5 |
+
"predict_runtime": 292.501,
|
| 6 |
+
"predict_samples": 4665,
|
| 7 |
+
"predict_samples_per_second": 15.949,
|
| 8 |
+
"predict_steps_per_second": 0.998
|
| 9 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a59b162890bd563d2ccf6be6666b50beed00fd335eb90e67004def105c73be7a
|
| 3 |
+
size 2444583325
|
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 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
],
|
| 29 |
+
"bos_token": "<s>",
|
| 30 |
+
"cls_token": "<s>",
|
| 31 |
+
"eos_token": "</s>",
|
| 32 |
+
"mask_token": "<mask>",
|
| 33 |
+
"pad_token": "<pad>",
|
| 34 |
+
"sep_token": "</s>",
|
| 35 |
+
"unk_token": "<unk>"
|
| 36 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29dc894e8f2cdad9b6a9006377f54739240fba228269d60e9ba7092e83fa8eeb
|
| 3 |
+
size 17088468
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,283 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"250001": {
|
| 36 |
+
"content": "ar_AR",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"250002": {
|
| 44 |
+
"content": "cs_CZ",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"250003": {
|
| 52 |
+
"content": "de_DE",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"250004": {
|
| 60 |
+
"content": "en_XX",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"250005": {
|
| 68 |
+
"content": "es_XX",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"250006": {
|
| 76 |
+
"content": "et_EE",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"250007": {
|
| 84 |
+
"content": "fi_FI",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"250008": {
|
| 92 |
+
"content": "fr_XX",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"250009": {
|
| 100 |
+
"content": "gu_IN",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"250010": {
|
| 108 |
+
"content": "hi_IN",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"250011": {
|
| 116 |
+
"content": "it_IT",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"250012": {
|
| 124 |
+
"content": "ja_XX",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"250013": {
|
| 132 |
+
"content": "kk_KZ",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"250014": {
|
| 140 |
+
"content": "ko_KR",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"250015": {
|
| 148 |
+
"content": "lt_LT",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"250016": {
|
| 156 |
+
"content": "lv_LV",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"250017": {
|
| 164 |
+
"content": "my_MM",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"250018": {
|
| 172 |
+
"content": "ne_NP",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"250019": {
|
| 180 |
+
"content": "nl_XX",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"250020": {
|
| 188 |
+
"content": "ro_RO",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"250021": {
|
| 196 |
+
"content": "ru_RU",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"250022": {
|
| 204 |
+
"content": "si_LK",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"250023": {
|
| 212 |
+
"content": "tr_TR",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"250024": {
|
| 220 |
+
"content": "vi_VN",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"250025": {
|
| 228 |
+
"content": "zh_CN",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"250026": {
|
| 236 |
+
"content": "<mask>",
|
| 237 |
+
"lstrip": true,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
}
|
| 243 |
+
},
|
| 244 |
+
"additional_special_tokens": [
|
| 245 |
+
"ar_AR",
|
| 246 |
+
"cs_CZ",
|
| 247 |
+
"de_DE",
|
| 248 |
+
"en_XX",
|
| 249 |
+
"es_XX",
|
| 250 |
+
"et_EE",
|
| 251 |
+
"fi_FI",
|
| 252 |
+
"fr_XX",
|
| 253 |
+
"gu_IN",
|
| 254 |
+
"hi_IN",
|
| 255 |
+
"it_IT",
|
| 256 |
+
"ja_XX",
|
| 257 |
+
"kk_KZ",
|
| 258 |
+
"ko_KR",
|
| 259 |
+
"lt_LT",
|
| 260 |
+
"lv_LV",
|
| 261 |
+
"my_MM",
|
| 262 |
+
"ne_NP",
|
| 263 |
+
"nl_XX",
|
| 264 |
+
"ro_RO",
|
| 265 |
+
"ru_RU",
|
| 266 |
+
"si_LK",
|
| 267 |
+
"tr_TR",
|
| 268 |
+
"vi_VN",
|
| 269 |
+
"zh_CN"
|
| 270 |
+
],
|
| 271 |
+
"bos_token": "<s>",
|
| 272 |
+
"clean_up_tokenization_spaces": true,
|
| 273 |
+
"cls_token": "<s>",
|
| 274 |
+
"eos_token": "</s>",
|
| 275 |
+
"mask_token": "<mask>",
|
| 276 |
+
"model_max_length": 1024,
|
| 277 |
+
"pad_token": "<pad>",
|
| 278 |
+
"sep_token": "</s>",
|
| 279 |
+
"src_lang": "ko_KR",
|
| 280 |
+
"tgt_lang": "zh_CN",
|
| 281 |
+
"tokenizer_class": "MBartTokenizer",
|
| 282 |
+
"unk_token": "<unk>"
|
| 283 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.14,
|
| 3 |
+
"train_loss": 1.0545102322896323,
|
| 4 |
+
"train_runtime": 10410.1428,
|
| 5 |
+
"train_samples": 37324,
|
| 6 |
+
"train_samples_per_second": 143.414,
|
| 7 |
+
"train_steps_per_second": 8.964
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,232 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 11.508,
|
| 3 |
+
"best_model_checkpoint": "./tst-translation-output4/checkpoint-6000",
|
| 4 |
+
"epoch": 5.143591941705958,
|
| 5 |
+
"eval_steps": 2000,
|
| 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": 0.21,
|
| 13 |
+
"learning_rate": 1.6366666666666667e-05,
|
| 14 |
+
"loss": 3.946,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.43,
|
| 19 |
+
"learning_rate": 3.3033333333333334e-05,
|
| 20 |
+
"loss": 1.7959,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.64,
|
| 25 |
+
"learning_rate": 4.97e-05,
|
| 26 |
+
"loss": 1.6545,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.86,
|
| 31 |
+
"learning_rate": 4.973262905685036e-05,
|
| 32 |
+
"loss": 1.5428,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.86,
|
| 37 |
+
"eval_bleu": 8.6101,
|
| 38 |
+
"eval_gen_len": 16.9959,
|
| 39 |
+
"eval_loss": 1.4468804597854614,
|
| 40 |
+
"eval_runtime": 677.1599,
|
| 41 |
+
"eval_samples_per_second": 6.889,
|
| 42 |
+
"eval_steps_per_second": 0.431,
|
| 43 |
+
"step": 2000
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 1.07,
|
| 47 |
+
"learning_rate": 4.94603572206491e-05,
|
| 48 |
+
"loss": 1.3602,
|
| 49 |
+
"step": 2500
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.29,
|
| 53 |
+
"learning_rate": 4.9188085384447834e-05,
|
| 54 |
+
"loss": 1.1488,
|
| 55 |
+
"step": 3000
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 1.5,
|
| 59 |
+
"learning_rate": 4.891581354824657e-05,
|
| 60 |
+
"loss": 1.1566,
|
| 61 |
+
"step": 3500
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.71,
|
| 65 |
+
"learning_rate": 4.864354171204531e-05,
|
| 66 |
+
"loss": 1.1195,
|
| 67 |
+
"step": 4000
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 1.71,
|
| 71 |
+
"eval_bleu": 10.3699,
|
| 72 |
+
"eval_gen_len": 14.5055,
|
| 73 |
+
"eval_loss": 1.347112774848938,
|
| 74 |
+
"eval_runtime": 470.7402,
|
| 75 |
+
"eval_samples_per_second": 9.91,
|
| 76 |
+
"eval_steps_per_second": 0.62,
|
| 77 |
+
"step": 4000
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.93,
|
| 81 |
+
"learning_rate": 4.8371269875844045e-05,
|
| 82 |
+
"loss": 1.1057,
|
| 83 |
+
"step": 4500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 2.14,
|
| 87 |
+
"learning_rate": 4.8098998039642784e-05,
|
| 88 |
+
"loss": 0.8761,
|
| 89 |
+
"step": 5000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.36,
|
| 93 |
+
"learning_rate": 4.782672620344152e-05,
|
| 94 |
+
"loss": 0.7709,
|
| 95 |
+
"step": 5500
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 2.57,
|
| 99 |
+
"learning_rate": 4.7554454367240256e-05,
|
| 100 |
+
"loss": 0.8028,
|
| 101 |
+
"step": 6000
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 2.57,
|
| 105 |
+
"eval_bleu": 11.508,
|
| 106 |
+
"eval_gen_len": 14.3955,
|
| 107 |
+
"eval_loss": 1.3568514585494995,
|
| 108 |
+
"eval_runtime": 276.6335,
|
| 109 |
+
"eval_samples_per_second": 16.863,
|
| 110 |
+
"eval_steps_per_second": 1.056,
|
| 111 |
+
"step": 6000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.79,
|
| 115 |
+
"learning_rate": 4.72832716183838e-05,
|
| 116 |
+
"loss": 2.3738,
|
| 117 |
+
"step": 6500
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 3.0,
|
| 121 |
+
"learning_rate": 4.701099978218254e-05,
|
| 122 |
+
"loss": 0.8245,
|
| 123 |
+
"step": 7000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 3.21,
|
| 127 |
+
"learning_rate": 4.673872794598127e-05,
|
| 128 |
+
"loss": 0.631,
|
| 129 |
+
"step": 7500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.43,
|
| 133 |
+
"learning_rate": 4.646645610978e-05,
|
| 134 |
+
"loss": 0.5856,
|
| 135 |
+
"step": 8000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 3.43,
|
| 139 |
+
"eval_bleu": 10.7663,
|
| 140 |
+
"eval_gen_len": 15.0208,
|
| 141 |
+
"eval_loss": 1.477591872215271,
|
| 142 |
+
"eval_runtime": 402.7514,
|
| 143 |
+
"eval_samples_per_second": 11.583,
|
| 144 |
+
"eval_steps_per_second": 0.725,
|
| 145 |
+
"step": 8000
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 3.64,
|
| 149 |
+
"learning_rate": 4.619418427357874e-05,
|
| 150 |
+
"loss": 0.5727,
|
| 151 |
+
"step": 8500
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 3.86,
|
| 155 |
+
"learning_rate": 4.592191243737748e-05,
|
| 156 |
+
"loss": 0.5967,
|
| 157 |
+
"step": 9000
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 4.07,
|
| 161 |
+
"learning_rate": 4.564964060117622e-05,
|
| 162 |
+
"loss": 0.5271,
|
| 163 |
+
"step": 9500
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 4.29,
|
| 167 |
+
"learning_rate": 4.537736876497495e-05,
|
| 168 |
+
"loss": 0.378,
|
| 169 |
+
"step": 10000
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 4.29,
|
| 173 |
+
"eval_bleu": 10.5237,
|
| 174 |
+
"eval_gen_len": 14.3284,
|
| 175 |
+
"eval_loss": 1.6134384870529175,
|
| 176 |
+
"eval_runtime": 272.0659,
|
| 177 |
+
"eval_samples_per_second": 17.147,
|
| 178 |
+
"eval_steps_per_second": 1.073,
|
| 179 |
+
"step": 10000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 4.5,
|
| 183 |
+
"learning_rate": 4.5105096928773685e-05,
|
| 184 |
+
"loss": 0.3928,
|
| 185 |
+
"step": 10500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 4.71,
|
| 189 |
+
"learning_rate": 4.483282509257243e-05,
|
| 190 |
+
"loss": 0.4139,
|
| 191 |
+
"step": 11000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 4.93,
|
| 195 |
+
"learning_rate": 4.4560553256371164e-05,
|
| 196 |
+
"loss": 0.4229,
|
| 197 |
+
"step": 11500
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 5.14,
|
| 201 |
+
"learning_rate": 4.4288281420169896e-05,
|
| 202 |
+
"loss": 0.3093,
|
| 203 |
+
"step": 12000
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 5.14,
|
| 207 |
+
"eval_bleu": 10.7522,
|
| 208 |
+
"eval_gen_len": 14.0819,
|
| 209 |
+
"eval_loss": 1.770087718963623,
|
| 210 |
+
"eval_runtime": 266.9255,
|
| 211 |
+
"eval_samples_per_second": 17.477,
|
| 212 |
+
"eval_steps_per_second": 1.094,
|
| 213 |
+
"step": 12000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 5.14,
|
| 217 |
+
"step": 12000,
|
| 218 |
+
"total_flos": 4.16088915443712e+17,
|
| 219 |
+
"train_loss": 1.0545102322896323,
|
| 220 |
+
"train_runtime": 10410.1428,
|
| 221 |
+
"train_samples_per_second": 143.414,
|
| 222 |
+
"train_steps_per_second": 8.964
|
| 223 |
+
}
|
| 224 |
+
],
|
| 225 |
+
"logging_steps": 500,
|
| 226 |
+
"max_steps": 93320,
|
| 227 |
+
"num_train_epochs": 40,
|
| 228 |
+
"save_steps": 2000,
|
| 229 |
+
"total_flos": 4.16088915443712e+17,
|
| 230 |
+
"trial_name": null,
|
| 231 |
+
"trial_params": null
|
| 232 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8b64864d9ab4060e033ff986454621f242b6568d857f20686e24d1f4872f1b6
|
| 3 |
+
size 4219
|