Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +4 -0
- README.md +97 -0
- all_results.json +22 -0
- checkpoint-31250/config.json +59 -0
- checkpoint-31250/generation_config.json +12 -0
- checkpoint-31250/optimizer.pt +3 -0
- checkpoint-31250/pytorch_model.bin +3 -0
- checkpoint-31250/rng_state_0.pth +3 -0
- checkpoint-31250/rng_state_1.pth +3 -0
- checkpoint-31250/rng_state_2.pth +3 -0
- checkpoint-31250/rng_state_3.pth +3 -0
- checkpoint-31250/scheduler.pt +3 -0
- checkpoint-31250/sentencepiece.bpe.model +3 -0
- checkpoint-31250/special_tokens_map.json +69 -0
- checkpoint-31250/tokenizer.json +3 -0
- checkpoint-31250/tokenizer_config.json +528 -0
- checkpoint-31250/trainer_state.json +641 -0
- checkpoint-31250/training_args.bin +3 -0
- checkpoint-35000/config.json +59 -0
- checkpoint-35000/generation_config.json +12 -0
- checkpoint-35000/optimizer.pt +3 -0
- checkpoint-35000/pytorch_model.bin +3 -0
- checkpoint-35000/rng_state_0.pth +3 -0
- checkpoint-35000/rng_state_1.pth +3 -0
- checkpoint-35000/rng_state_2.pth +3 -0
- checkpoint-35000/rng_state_3.pth +3 -0
- checkpoint-35000/scheduler.pt +3 -0
- checkpoint-35000/sentencepiece.bpe.model +3 -0
- checkpoint-35000/special_tokens_map.json +69 -0
- checkpoint-35000/tokenizer.json +3 -0
- checkpoint-35000/tokenizer_config.json +528 -0
- checkpoint-35000/trainer_state.json +719 -0
- checkpoint-35000/training_args.bin +3 -0
- checkpoint-36250/config.json +59 -0
- checkpoint-36250/generation_config.json +12 -0
- checkpoint-36250/optimizer.pt +3 -0
- checkpoint-36250/pytorch_model.bin +3 -0
- checkpoint-36250/rng_state_0.pth +3 -0
- checkpoint-36250/rng_state_1.pth +3 -0
- checkpoint-36250/rng_state_2.pth +3 -0
- checkpoint-36250/rng_state_3.pth +3 -0
- checkpoint-36250/scheduler.pt +3 -0
- checkpoint-36250/sentencepiece.bpe.model +3 -0
- checkpoint-36250/special_tokens_map.json +69 -0
- checkpoint-36250/tokenizer.json +3 -0
- checkpoint-36250/tokenizer_config.json +528 -0
- checkpoint-36250/trainer_state.json +741 -0
- checkpoint-36250/training_args.bin +3 -0
- config.json +59 -0
- eval_results.json +10 -0
.gitattributes
CHANGED
@@ -33,3 +33,7 @@ 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-31250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
37 |
+
checkpoint-35000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
38 |
+
checkpoint-36250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
39 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: mbartLarge_koja_37p_exp2
|
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 |
+
# mbartLarge_koja_37p_exp2
|
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: 0.8988
|
23 |
+
- Bleu: 6.7577
|
24 |
+
- Gen Len: 17.8104
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 5e-05
|
44 |
+
- train_batch_size: 4
|
45 |
+
- eval_batch_size: 4
|
46 |
+
- seed: 42
|
47 |
+
- distributed_type: multi-GPU
|
48 |
+
- num_devices: 4
|
49 |
+
- gradient_accumulation_steps: 2
|
50 |
+
- total_train_batch_size: 32
|
51 |
+
- total_eval_batch_size: 16
|
52 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
53 |
+
- lr_scheduler_type: linear
|
54 |
+
- lr_scheduler_warmup_steps: 350
|
55 |
+
- num_epochs: 15
|
56 |
+
|
57 |
+
### Training results
|
58 |
+
|
59 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
60 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
|
61 |
+
| 2.0622 | 0.11 | 1250 | 1.6679 | 1.2834 | 17.8009 |
|
62 |
+
| 1.5139 | 0.22 | 2500 | 1.4378 | 2.0427 | 17.8496 |
|
63 |
+
| 1.4121 | 0.33 | 3750 | 1.3116 | 2.7599 | 17.7667 |
|
64 |
+
| 1.2879 | 0.44 | 5000 | 1.2381 | 3.1444 | 17.8887 |
|
65 |
+
| 1.2344 | 0.55 | 6250 | 1.1769 | 3.3835 | 17.8323 |
|
66 |
+
| 1.1778 | 0.66 | 7500 | 1.1382 | 3.9511 | 17.4892 |
|
67 |
+
| 1.1461 | 0.77 | 8750 | 1.0938 | 3.9402 | 18.0136 |
|
68 |
+
| 1.1151 | 0.88 | 10000 | 1.0749 | 4.2134 | 18.0537 |
|
69 |
+
| 1.093 | 0.99 | 11250 | 1.0418 | 3.9587 | 17.8715 |
|
70 |
+
| 1.0626 | 1.1 | 12500 | 1.0315 | 4.6251 | 17.9406 |
|
71 |
+
| 1.0192 | 1.21 | 13750 | 1.0132 | 4.9573 | 18.1266 |
|
72 |
+
| 0.9957 | 1.32 | 15000 | 0.9989 | 4.3068 | 18.0925 |
|
73 |
+
| 0.9778 | 1.43 | 16250 | 0.9850 | 5.0517 | 17.8783 |
|
74 |
+
| 0.9446 | 1.54 | 17500 | 0.9748 | 5.0194 | 17.9348 |
|
75 |
+
| 0.9236 | 1.65 | 18750 | 0.9619 | 4.6011 | 17.7926 |
|
76 |
+
| 0.9091 | 1.76 | 20000 | 0.9564 | 4.6035 | 17.9399 |
|
77 |
+
| 0.9072 | 1.87 | 21250 | 0.9533 | 4.8313 | 17.6221 |
|
78 |
+
| 0.8758 | 1.98 | 22500 | 0.9421 | 5.2707 | 17.5851 |
|
79 |
+
| 0.8539 | 2.09 | 23750 | 0.9304 | 5.2661 | 17.821 |
|
80 |
+
| 0.8575 | 2.2 | 25000 | 0.9329 | 4.9143 | 17.8879 |
|
81 |
+
| 0.8314 | 2.31 | 26250 | 0.9262 | 5.106 | 18.0037 |
|
82 |
+
| 0.8248 | 2.42 | 27500 | 0.9241 | 5.3073 | 17.6632 |
|
83 |
+
| 0.8151 | 2.53 | 28750 | 0.9302 | 5.5675 | 17.7676 |
|
84 |
+
| 0.8093 | 2.64 | 30000 | 0.9149 | 6.2644 | 17.8475 |
|
85 |
+
| 0.7691 | 2.75 | 31250 | 0.8988 | 6.6682 | 17.7685 |
|
86 |
+
| 0.771 | 2.86 | 32500 | 0.9189 | 5.7856 | 17.8678 |
|
87 |
+
| 0.7658 | 2.97 | 33750 | 0.9175 | 6.2468 | 17.7313 |
|
88 |
+
| 0.7914 | 3.08 | 35000 | 0.9020 | 5.5525 | 17.7627 |
|
89 |
+
| 0.7264 | 3.19 | 36250 | 0.9046 | 6.2055 | 17.7662 |
|
90 |
+
|
91 |
+
|
92 |
+
### Framework versions
|
93 |
+
|
94 |
+
- Transformers 4.34.1
|
95 |
+
- Pytorch 2.1.0+cu121
|
96 |
+
- Datasets 2.14.6
|
97 |
+
- Tokenizers 0.14.1
|
all_results.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.19,
|
3 |
+
"eval_bleu": 6.7577,
|
4 |
+
"eval_gen_len": 17.8104,
|
5 |
+
"eval_loss": 0.8987509608268738,
|
6 |
+
"eval_runtime": 1309.9044,
|
7 |
+
"eval_samples": 22707,
|
8 |
+
"eval_samples_per_second": 17.335,
|
9 |
+
"eval_steps_per_second": 1.084,
|
10 |
+
"predict_bleu": 6.8529,
|
11 |
+
"predict_gen_len": 17.7633,
|
12 |
+
"predict_loss": 0.8972814679145813,
|
13 |
+
"predict_runtime": 1291.805,
|
14 |
+
"predict_samples": 22707,
|
15 |
+
"predict_samples_per_second": 17.578,
|
16 |
+
"predict_steps_per_second": 1.099,
|
17 |
+
"train_loss": 1.0393056295460668,
|
18 |
+
"train_runtime": 72152.6791,
|
19 |
+
"train_samples": 181661,
|
20 |
+
"train_samples_per_second": 37.766,
|
21 |
+
"train_steps_per_second": 2.36
|
22 |
+
}
|
checkpoint-31250/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": "4.34.1",
|
57 |
+
"use_cache": true,
|
58 |
+
"vocab_size": 250054
|
59 |
+
}
|
checkpoint-31250/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": "4.34.1"
|
12 |
+
}
|
checkpoint-31250/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f110040ae2c21dc780d5284031fe11e818537ec7ebf38a436ee3a97830935aa8
|
3 |
+
size 4887473903
|
checkpoint-31250/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b08d414e2f0e4f15988eac340dd5d54d42eeba57ea07248b2c1a5fc590cb7389
|
3 |
+
size 2444694490
|
checkpoint-31250/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:def9db3a853813bd5bbb44db53e1766c4c62800fcac523ab841526469c8d6847
|
3 |
+
size 15024
|
checkpoint-31250/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:129a0cf7217f523a5fb07008f7c5d58f4e9018340eee87c01d943f632836eb52
|
3 |
+
size 15024
|
checkpoint-31250/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e7860511189184e184ba201b8bc18837ca3d45eba69e9ccfbbbc5ee8cb1ba9e
|
3 |
+
size 15024
|
checkpoint-31250/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:251ae6cf85950228a69fa1d4b9daed9b4cd6d235114c8a01a3226ed416182ed0
|
3 |
+
size 15024
|
checkpoint-31250/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51784abf22293633a20652acdd6e6dfea63a9cf66f2aaba7487a961a6ceab61a
|
3 |
+
size 1064
|
checkpoint-31250/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-31250/special_tokens_map.json
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"ar_AR",
|
4 |
+
"cs_CZ",
|
5 |
+
"de_DE",
|
6 |
+
"en_XX",
|
7 |
+
"es_XX",
|
8 |
+
"et_EE",
|
9 |
+
"fi_FI",
|
10 |
+
"fr_XX",
|
11 |
+
"gu_IN",
|
12 |
+
"hi_IN",
|
13 |
+
"it_IT",
|
14 |
+
"ja_XX",
|
15 |
+
"kk_KZ",
|
16 |
+
"ko_KR",
|
17 |
+
"lt_LT",
|
18 |
+
"lv_LV",
|
19 |
+
"my_MM",
|
20 |
+
"ne_NP",
|
21 |
+
"nl_XX",
|
22 |
+
"ro_RO",
|
23 |
+
"ru_RU",
|
24 |
+
"si_LK",
|
25 |
+
"tr_TR",
|
26 |
+
"vi_VN",
|
27 |
+
"zh_CN",
|
28 |
+
"af_ZA",
|
29 |
+
"az_AZ",
|
30 |
+
"bn_IN",
|
31 |
+
"fa_IR",
|
32 |
+
"he_IL",
|
33 |
+
"hr_HR",
|
34 |
+
"id_ID",
|
35 |
+
"ka_GE",
|
36 |
+
"km_KH",
|
37 |
+
"mk_MK",
|
38 |
+
"ml_IN",
|
39 |
+
"mn_MN",
|
40 |
+
"mr_IN",
|
41 |
+
"pl_PL",
|
42 |
+
"ps_AF",
|
43 |
+
"pt_XX",
|
44 |
+
"sv_SE",
|
45 |
+
"sw_KE",
|
46 |
+
"ta_IN",
|
47 |
+
"te_IN",
|
48 |
+
"th_TH",
|
49 |
+
"tl_XX",
|
50 |
+
"uk_UA",
|
51 |
+
"ur_PK",
|
52 |
+
"xh_ZA",
|
53 |
+
"gl_ES",
|
54 |
+
"sl_SI"
|
55 |
+
],
|
56 |
+
"bos_token": "<s>",
|
57 |
+
"cls_token": "<s>",
|
58 |
+
"eos_token": "</s>",
|
59 |
+
"mask_token": {
|
60 |
+
"content": "<mask>",
|
61 |
+
"lstrip": true,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false
|
65 |
+
},
|
66 |
+
"pad_token": "<pad>",
|
67 |
+
"sep_token": "</s>",
|
68 |
+
"unk_token": "<unk>"
|
69 |
+
}
|
checkpoint-31250/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fc2a9a463953c664738ef8571ed97361b8de258b2aca93c0214a89676a73379
|
3 |
+
size 17110043
|
checkpoint-31250/tokenizer_config.json
ADDED
@@ -0,0 +1,528 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "ar_AR",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"250002": {
|
44 |
+
"content": "cs_CZ",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"250003": {
|
52 |
+
"content": "de_DE",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"250004": {
|
60 |
+
"content": "en_XX",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"250005": {
|
68 |
+
"content": "es_XX",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"250006": {
|
76 |
+
"content": "et_EE",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"250007": {
|
84 |
+
"content": "fi_FI",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"250008": {
|
92 |
+
"content": "fr_XX",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"250009": {
|
100 |
+
"content": "gu_IN",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"250010": {
|
108 |
+
"content": "hi_IN",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"250011": {
|
116 |
+
"content": "it_IT",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"250012": {
|
124 |
+
"content": "ja_XX",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"250013": {
|
132 |
+
"content": "kk_KZ",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"250014": {
|
140 |
+
"content": "ko_KR",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"250015": {
|
148 |
+
"content": "lt_LT",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"250016": {
|
156 |
+
"content": "lv_LV",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"250017": {
|
164 |
+
"content": "my_MM",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"250018": {
|
172 |
+
"content": "ne_NP",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"250019": {
|
180 |
+
"content": "nl_XX",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"250020": {
|
188 |
+
"content": "ro_RO",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"250021": {
|
196 |
+
"content": "ru_RU",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"250022": {
|
204 |
+
"content": "si_LK",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"250023": {
|
212 |
+
"content": "tr_TR",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"250024": {
|
220 |
+
"content": "vi_VN",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"250025": {
|
228 |
+
"content": "zh_CN",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"250026": {
|
236 |
+
"content": "af_ZA",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"250027": {
|
244 |
+
"content": "az_AZ",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"250028": {
|
252 |
+
"content": "bn_IN",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"250029": {
|
260 |
+
"content": "fa_IR",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"250030": {
|
268 |
+
"content": "he_IL",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"250031": {
|
276 |
+
"content": "hr_HR",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"250032": {
|
284 |
+
"content": "id_ID",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": true
|
290 |
+
},
|
291 |
+
"250033": {
|
292 |
+
"content": "ka_GE",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": true
|
298 |
+
},
|
299 |
+
"250034": {
|
300 |
+
"content": "km_KH",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": true
|
306 |
+
},
|
307 |
+
"250035": {
|
308 |
+
"content": "mk_MK",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": true
|
314 |
+
},
|
315 |
+
"250036": {
|
316 |
+
"content": "ml_IN",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": true
|
322 |
+
},
|
323 |
+
"250037": {
|
324 |
+
"content": "mn_MN",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": true
|
330 |
+
},
|
331 |
+
"250038": {
|
332 |
+
"content": "mr_IN",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": true
|
338 |
+
},
|
339 |
+
"250039": {
|
340 |
+
"content": "pl_PL",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": true
|
346 |
+
},
|
347 |
+
"250040": {
|
348 |
+
"content": "ps_AF",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": true
|
354 |
+
},
|
355 |
+
"250041": {
|
356 |
+
"content": "pt_XX",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": true
|
362 |
+
},
|
363 |
+
"250042": {
|
364 |
+
"content": "sv_SE",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": true
|
370 |
+
},
|
371 |
+
"250043": {
|
372 |
+
"content": "sw_KE",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": true
|
378 |
+
},
|
379 |
+
"250044": {
|
380 |
+
"content": "ta_IN",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": true
|
386 |
+
},
|
387 |
+
"250045": {
|
388 |
+
"content": "te_IN",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": true
|
394 |
+
},
|
395 |
+
"250046": {
|
396 |
+
"content": "th_TH",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": true
|
402 |
+
},
|
403 |
+
"250047": {
|
404 |
+
"content": "tl_XX",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": true
|
410 |
+
},
|
411 |
+
"250048": {
|
412 |
+
"content": "uk_UA",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": true
|
418 |
+
},
|
419 |
+
"250049": {
|
420 |
+
"content": "ur_PK",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": false,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": true
|
426 |
+
},
|
427 |
+
"250050": {
|
428 |
+
"content": "xh_ZA",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": false,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": true
|
434 |
+
},
|
435 |
+
"250051": {
|
436 |
+
"content": "gl_ES",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": false,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": true
|
442 |
+
},
|
443 |
+
"250052": {
|
444 |
+
"content": "sl_SI",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": false,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": true
|
450 |
+
},
|
451 |
+
"250053": {
|
452 |
+
"content": "<mask>",
|
453 |
+
"lstrip": true,
|
454 |
+
"normalized": true,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": true
|
458 |
+
}
|
459 |
+
},
|
460 |
+
"additional_special_tokens": [
|
461 |
+
"ar_AR",
|
462 |
+
"cs_CZ",
|
463 |
+
"de_DE",
|
464 |
+
"en_XX",
|
465 |
+
"es_XX",
|
466 |
+
"et_EE",
|
467 |
+
"fi_FI",
|
468 |
+
"fr_XX",
|
469 |
+
"gu_IN",
|
470 |
+
"hi_IN",
|
471 |
+
"it_IT",
|
472 |
+
"ja_XX",
|
473 |
+
"kk_KZ",
|
474 |
+
"ko_KR",
|
475 |
+
"lt_LT",
|
476 |
+
"lv_LV",
|
477 |
+
"my_MM",
|
478 |
+
"ne_NP",
|
479 |
+
"nl_XX",
|
480 |
+
"ro_RO",
|
481 |
+
"ru_RU",
|
482 |
+
"si_LK",
|
483 |
+
"tr_TR",
|
484 |
+
"vi_VN",
|
485 |
+
"zh_CN",
|
486 |
+
"af_ZA",
|
487 |
+
"az_AZ",
|
488 |
+
"bn_IN",
|
489 |
+
"fa_IR",
|
490 |
+
"he_IL",
|
491 |
+
"hr_HR",
|
492 |
+
"id_ID",
|
493 |
+
"ka_GE",
|
494 |
+
"km_KH",
|
495 |
+
"mk_MK",
|
496 |
+
"ml_IN",
|
497 |
+
"mn_MN",
|
498 |
+
"mr_IN",
|
499 |
+
"pl_PL",
|
500 |
+
"ps_AF",
|
501 |
+
"pt_XX",
|
502 |
+
"sv_SE",
|
503 |
+
"sw_KE",
|
504 |
+
"ta_IN",
|
505 |
+
"te_IN",
|
506 |
+
"th_TH",
|
507 |
+
"tl_XX",
|
508 |
+
"uk_UA",
|
509 |
+
"ur_PK",
|
510 |
+
"xh_ZA",
|
511 |
+
"gl_ES",
|
512 |
+
"sl_SI"
|
513 |
+
],
|
514 |
+
"bos_token": "<s>",
|
515 |
+
"clean_up_tokenization_spaces": true,
|
516 |
+
"cls_token": "<s>",
|
517 |
+
"eos_token": "</s>",
|
518 |
+
"language_codes": "ML50",
|
519 |
+
"mask_token": "<mask>",
|
520 |
+
"model_max_length": 1000000000000000019884624838656,
|
521 |
+
"pad_token": "<pad>",
|
522 |
+
"sep_token": "</s>",
|
523 |
+
"sp_model_kwargs": {},
|
524 |
+
"src_lang": "ko_KR",
|
525 |
+
"tgt_lang": "ja_XX",
|
526 |
+
"tokenizer_class": "MBart50Tokenizer",
|
527 |
+
"unk_token": "<unk>"
|
528 |
+
}
|
checkpoint-31250/trainer_state.json
ADDED
@@ -0,0 +1,641 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8987509608268738,
|
3 |
+
"best_model_checkpoint": "./mbartLarge_koja_37p_exp2/checkpoint-31250",
|
4 |
+
"epoch": 2.7523339792143737,
|
5 |
+
"eval_steps": 1250,
|
6 |
+
"global_step": 31250,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.04,
|
13 |
+
"learning_rate": 4.995587196987527e-05,
|
14 |
+
"loss": 3.3474,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.09,
|
19 |
+
"learning_rate": 4.9808778536126146e-05,
|
20 |
+
"loss": 2.0622,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.11,
|
25 |
+
"eval_bleu": 1.2834,
|
26 |
+
"eval_gen_len": 17.8009,
|
27 |
+
"eval_loss": 1.6679450273513794,
|
28 |
+
"eval_runtime": 1488.7514,
|
29 |
+
"eval_samples_per_second": 15.252,
|
30 |
+
"eval_steps_per_second": 0.954,
|
31 |
+
"step": 1250
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.13,
|
35 |
+
"learning_rate": 4.966168510237703e-05,
|
36 |
+
"loss": 1.7123,
|
37 |
+
"step": 1500
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.18,
|
41 |
+
"learning_rate": 4.951459166862791e-05,
|
42 |
+
"loss": 1.59,
|
43 |
+
"step": 2000
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 0.22,
|
47 |
+
"learning_rate": 4.936749823487879e-05,
|
48 |
+
"loss": 1.5139,
|
49 |
+
"step": 2500
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 0.22,
|
53 |
+
"eval_bleu": 2.0427,
|
54 |
+
"eval_gen_len": 17.8496,
|
55 |
+
"eval_loss": 1.4377689361572266,
|
56 |
+
"eval_runtime": 1494.0047,
|
57 |
+
"eval_samples_per_second": 15.199,
|
58 |
+
"eval_steps_per_second": 0.95,
|
59 |
+
"step": 2500
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.26,
|
63 |
+
"learning_rate": 4.922040480112968e-05,
|
64 |
+
"loss": 1.4565,
|
65 |
+
"step": 3000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.31,
|
69 |
+
"learning_rate": 4.9073311367380564e-05,
|
70 |
+
"loss": 1.4121,
|
71 |
+
"step": 3500
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 0.33,
|
75 |
+
"eval_bleu": 2.7599,
|
76 |
+
"eval_gen_len": 17.7667,
|
77 |
+
"eval_loss": 1.3115850687026978,
|
78 |
+
"eval_runtime": 1502.2991,
|
79 |
+
"eval_samples_per_second": 15.115,
|
80 |
+
"eval_steps_per_second": 0.945,
|
81 |
+
"step": 3750
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.35,
|
85 |
+
"learning_rate": 4.892621793363145e-05,
|
86 |
+
"loss": 1.3511,
|
87 |
+
"step": 4000
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.4,
|
91 |
+
"learning_rate": 4.877912449988233e-05,
|
92 |
+
"loss": 1.3052,
|
93 |
+
"step": 4500
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.44,
|
97 |
+
"learning_rate": 4.863203106613321e-05,
|
98 |
+
"loss": 1.2879,
|
99 |
+
"step": 5000
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.44,
|
103 |
+
"eval_bleu": 3.1444,
|
104 |
+
"eval_gen_len": 17.8887,
|
105 |
+
"eval_loss": 1.23811936378479,
|
106 |
+
"eval_runtime": 1519.5015,
|
107 |
+
"eval_samples_per_second": 14.944,
|
108 |
+
"eval_steps_per_second": 0.935,
|
109 |
+
"step": 5000
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 0.48,
|
113 |
+
"learning_rate": 4.8484937632384094e-05,
|
114 |
+
"loss": 1.2634,
|
115 |
+
"step": 5500
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.53,
|
119 |
+
"learning_rate": 4.8337844198634976e-05,
|
120 |
+
"loss": 1.2344,
|
121 |
+
"step": 6000
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.55,
|
125 |
+
"eval_bleu": 3.3835,
|
126 |
+
"eval_gen_len": 17.8323,
|
127 |
+
"eval_loss": 1.1769133806228638,
|
128 |
+
"eval_runtime": 1506.2285,
|
129 |
+
"eval_samples_per_second": 15.075,
|
130 |
+
"eval_steps_per_second": 0.943,
|
131 |
+
"step": 6250
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 0.57,
|
135 |
+
"learning_rate": 4.819075076488586e-05,
|
136 |
+
"loss": 1.2213,
|
137 |
+
"step": 6500
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.62,
|
141 |
+
"learning_rate": 4.804365733113674e-05,
|
142 |
+
"loss": 1.1918,
|
143 |
+
"step": 7000
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.66,
|
147 |
+
"learning_rate": 4.789656389738762e-05,
|
148 |
+
"loss": 1.1778,
|
149 |
+
"step": 7500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.66,
|
153 |
+
"eval_bleu": 3.9511,
|
154 |
+
"eval_gen_len": 17.4892,
|
155 |
+
"eval_loss": 1.1381820440292358,
|
156 |
+
"eval_runtime": 1485.4261,
|
157 |
+
"eval_samples_per_second": 15.287,
|
158 |
+
"eval_steps_per_second": 0.956,
|
159 |
+
"step": 7500
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.7,
|
163 |
+
"learning_rate": 4.7749470463638505e-05,
|
164 |
+
"loss": 1.1651,
|
165 |
+
"step": 8000
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.75,
|
169 |
+
"learning_rate": 4.760237702988939e-05,
|
170 |
+
"loss": 1.1461,
|
171 |
+
"step": 8500
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.77,
|
175 |
+
"eval_bleu": 3.9402,
|
176 |
+
"eval_gen_len": 18.0136,
|
177 |
+
"eval_loss": 1.09383225440979,
|
178 |
+
"eval_runtime": 1503.0162,
|
179 |
+
"eval_samples_per_second": 15.108,
|
180 |
+
"eval_steps_per_second": 0.945,
|
181 |
+
"step": 8750
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.79,
|
185 |
+
"learning_rate": 4.745528359614027e-05,
|
186 |
+
"loss": 1.1341,
|
187 |
+
"step": 9000
|
188 |
+
},
|
189 |
+
{
|
190 |
+
"epoch": 0.84,
|
191 |
+
"learning_rate": 4.730819016239115e-05,
|
192 |
+
"loss": 1.1294,
|
193 |
+
"step": 9500
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.88,
|
197 |
+
"learning_rate": 4.7161096728642035e-05,
|
198 |
+
"loss": 1.1151,
|
199 |
+
"step": 10000
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.88,
|
203 |
+
"eval_bleu": 4.2134,
|
204 |
+
"eval_gen_len": 18.0537,
|
205 |
+
"eval_loss": 1.074916124343872,
|
206 |
+
"eval_runtime": 1564.4468,
|
207 |
+
"eval_samples_per_second": 14.514,
|
208 |
+
"eval_steps_per_second": 0.908,
|
209 |
+
"step": 10000
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.92,
|
213 |
+
"learning_rate": 4.701400329489292e-05,
|
214 |
+
"loss": 1.1102,
|
215 |
+
"step": 10500
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 0.97,
|
219 |
+
"learning_rate": 4.68669098611438e-05,
|
220 |
+
"loss": 1.093,
|
221 |
+
"step": 11000
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.99,
|
225 |
+
"eval_bleu": 3.9587,
|
226 |
+
"eval_gen_len": 17.8715,
|
227 |
+
"eval_loss": 1.0418165922164917,
|
228 |
+
"eval_runtime": 1534.6245,
|
229 |
+
"eval_samples_per_second": 14.796,
|
230 |
+
"eval_steps_per_second": 0.925,
|
231 |
+
"step": 11250
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 1.01,
|
235 |
+
"learning_rate": 4.671981642739469e-05,
|
236 |
+
"loss": 1.084,
|
237 |
+
"step": 11500
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 1.06,
|
241 |
+
"learning_rate": 4.657272299364557e-05,
|
242 |
+
"loss": 1.0641,
|
243 |
+
"step": 12000
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 1.1,
|
247 |
+
"learning_rate": 4.6425629559896446e-05,
|
248 |
+
"loss": 1.0626,
|
249 |
+
"step": 12500
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 1.1,
|
253 |
+
"eval_bleu": 4.6251,
|
254 |
+
"eval_gen_len": 17.9406,
|
255 |
+
"eval_loss": 1.0315195322036743,
|
256 |
+
"eval_runtime": 1499.6187,
|
257 |
+
"eval_samples_per_second": 15.142,
|
258 |
+
"eval_steps_per_second": 0.947,
|
259 |
+
"step": 12500
|
260 |
+
},
|
261 |
+
{
|
262 |
+
"epoch": 1.14,
|
263 |
+
"learning_rate": 4.627853612614733e-05,
|
264 |
+
"loss": 1.0332,
|
265 |
+
"step": 13000
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 1.19,
|
269 |
+
"learning_rate": 4.613144269239821e-05,
|
270 |
+
"loss": 1.0192,
|
271 |
+
"step": 13500
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 1.21,
|
275 |
+
"eval_bleu": 4.9573,
|
276 |
+
"eval_gen_len": 18.1266,
|
277 |
+
"eval_loss": 1.0131869316101074,
|
278 |
+
"eval_runtime": 1514.9755,
|
279 |
+
"eval_samples_per_second": 14.988,
|
280 |
+
"eval_steps_per_second": 0.937,
|
281 |
+
"step": 13750
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 1.23,
|
285 |
+
"learning_rate": 4.598434925864909e-05,
|
286 |
+
"loss": 1.0234,
|
287 |
+
"step": 14000
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 1.28,
|
291 |
+
"learning_rate": 4.5837255824899976e-05,
|
292 |
+
"loss": 1.0062,
|
293 |
+
"step": 14500
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 1.32,
|
297 |
+
"learning_rate": 4.569016239115086e-05,
|
298 |
+
"loss": 0.9957,
|
299 |
+
"step": 15000
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 1.32,
|
303 |
+
"eval_bleu": 4.3068,
|
304 |
+
"eval_gen_len": 18.0925,
|
305 |
+
"eval_loss": 0.9988749623298645,
|
306 |
+
"eval_runtime": 1565.2457,
|
307 |
+
"eval_samples_per_second": 14.507,
|
308 |
+
"eval_steps_per_second": 0.907,
|
309 |
+
"step": 15000
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 1.37,
|
313 |
+
"learning_rate": 4.554306895740174e-05,
|
314 |
+
"loss": 0.9843,
|
315 |
+
"step": 15500
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 1.41,
|
319 |
+
"learning_rate": 4.539597552365263e-05,
|
320 |
+
"loss": 0.9778,
|
321 |
+
"step": 16000
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 1.43,
|
325 |
+
"eval_bleu": 5.0517,
|
326 |
+
"eval_gen_len": 17.8783,
|
327 |
+
"eval_loss": 0.984965980052948,
|
328 |
+
"eval_runtime": 1508.5724,
|
329 |
+
"eval_samples_per_second": 15.052,
|
330 |
+
"eval_steps_per_second": 0.941,
|
331 |
+
"step": 16250
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 1.45,
|
335 |
+
"learning_rate": 4.524888208990351e-05,
|
336 |
+
"loss": 0.961,
|
337 |
+
"step": 16500
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 1.5,
|
341 |
+
"learning_rate": 4.5101788656154394e-05,
|
342 |
+
"loss": 0.9735,
|
343 |
+
"step": 17000
|
344 |
+
},
|
345 |
+
{
|
346 |
+
"epoch": 1.54,
|
347 |
+
"learning_rate": 4.4954695222405276e-05,
|
348 |
+
"loss": 0.9446,
|
349 |
+
"step": 17500
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 1.54,
|
353 |
+
"eval_bleu": 5.0194,
|
354 |
+
"eval_gen_len": 17.9348,
|
355 |
+
"eval_loss": 0.9747512936592102,
|
356 |
+
"eval_runtime": 1574.1886,
|
357 |
+
"eval_samples_per_second": 14.425,
|
358 |
+
"eval_steps_per_second": 0.902,
|
359 |
+
"step": 17500
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 1.59,
|
363 |
+
"learning_rate": 4.480760178865616e-05,
|
364 |
+
"loss": 0.9352,
|
365 |
+
"step": 18000
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 1.63,
|
369 |
+
"learning_rate": 4.466050835490704e-05,
|
370 |
+
"loss": 0.9236,
|
371 |
+
"step": 18500
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 1.65,
|
375 |
+
"eval_bleu": 4.6011,
|
376 |
+
"eval_gen_len": 17.7926,
|
377 |
+
"eval_loss": 0.9619229435920715,
|
378 |
+
"eval_runtime": 1510.4722,
|
379 |
+
"eval_samples_per_second": 15.033,
|
380 |
+
"eval_steps_per_second": 0.94,
|
381 |
+
"step": 18750
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 1.67,
|
385 |
+
"learning_rate": 4.4513414921157917e-05,
|
386 |
+
"loss": 0.9289,
|
387 |
+
"step": 19000
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 1.72,
|
391 |
+
"learning_rate": 4.43663214874088e-05,
|
392 |
+
"loss": 0.9216,
|
393 |
+
"step": 19500
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 1.76,
|
397 |
+
"learning_rate": 4.421922805365969e-05,
|
398 |
+
"loss": 0.9091,
|
399 |
+
"step": 20000
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 1.76,
|
403 |
+
"eval_bleu": 4.6035,
|
404 |
+
"eval_gen_len": 17.9399,
|
405 |
+
"eval_loss": 0.9564162492752075,
|
406 |
+
"eval_runtime": 1530.1826,
|
407 |
+
"eval_samples_per_second": 14.839,
|
408 |
+
"eval_steps_per_second": 0.928,
|
409 |
+
"step": 20000
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 1.81,
|
413 |
+
"learning_rate": 4.407213461991057e-05,
|
414 |
+
"loss": 0.9333,
|
415 |
+
"step": 20500
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 1.85,
|
419 |
+
"learning_rate": 4.392504118616145e-05,
|
420 |
+
"loss": 0.9072,
|
421 |
+
"step": 21000
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"epoch": 1.87,
|
425 |
+
"eval_bleu": 4.8313,
|
426 |
+
"eval_gen_len": 17.6221,
|
427 |
+
"eval_loss": 0.9533364176750183,
|
428 |
+
"eval_runtime": 1475.3262,
|
429 |
+
"eval_samples_per_second": 15.391,
|
430 |
+
"eval_steps_per_second": 0.962,
|
431 |
+
"step": 21250
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 1.89,
|
435 |
+
"learning_rate": 4.3777947752412335e-05,
|
436 |
+
"loss": 0.8896,
|
437 |
+
"step": 21500
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 1.94,
|
441 |
+
"learning_rate": 4.363085431866322e-05,
|
442 |
+
"loss": 0.8945,
|
443 |
+
"step": 22000
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 1.98,
|
447 |
+
"learning_rate": 4.34837608849141e-05,
|
448 |
+
"loss": 0.8758,
|
449 |
+
"step": 22500
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 1.98,
|
453 |
+
"eval_bleu": 5.2707,
|
454 |
+
"eval_gen_len": 17.5851,
|
455 |
+
"eval_loss": 0.9421375393867493,
|
456 |
+
"eval_runtime": 1516.2122,
|
457 |
+
"eval_samples_per_second": 14.976,
|
458 |
+
"eval_steps_per_second": 0.937,
|
459 |
+
"step": 22500
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 2.03,
|
463 |
+
"learning_rate": 4.333666745116498e-05,
|
464 |
+
"loss": 0.8723,
|
465 |
+
"step": 23000
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 2.07,
|
469 |
+
"learning_rate": 4.3189574017415864e-05,
|
470 |
+
"loss": 0.8539,
|
471 |
+
"step": 23500
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 2.09,
|
475 |
+
"eval_bleu": 5.2661,
|
476 |
+
"eval_gen_len": 17.821,
|
477 |
+
"eval_loss": 0.9304332137107849,
|
478 |
+
"eval_runtime": 1492.9401,
|
479 |
+
"eval_samples_per_second": 15.21,
|
480 |
+
"eval_steps_per_second": 0.951,
|
481 |
+
"step": 23750
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 2.11,
|
485 |
+
"learning_rate": 4.3042480583666747e-05,
|
486 |
+
"loss": 0.8461,
|
487 |
+
"step": 24000
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 2.16,
|
491 |
+
"learning_rate": 4.289538714991763e-05,
|
492 |
+
"loss": 0.842,
|
493 |
+
"step": 24500
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 2.2,
|
497 |
+
"learning_rate": 4.274829371616851e-05,
|
498 |
+
"loss": 0.8575,
|
499 |
+
"step": 25000
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 2.2,
|
503 |
+
"eval_bleu": 4.9143,
|
504 |
+
"eval_gen_len": 17.8879,
|
505 |
+
"eval_loss": 0.9329252243041992,
|
506 |
+
"eval_runtime": 1560.9154,
|
507 |
+
"eval_samples_per_second": 14.547,
|
508 |
+
"eval_steps_per_second": 0.91,
|
509 |
+
"step": 25000
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 2.25,
|
513 |
+
"learning_rate": 4.2601200282419394e-05,
|
514 |
+
"loss": 0.8424,
|
515 |
+
"step": 25500
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 2.29,
|
519 |
+
"learning_rate": 4.2454106848670276e-05,
|
520 |
+
"loss": 0.8314,
|
521 |
+
"step": 26000
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 2.31,
|
525 |
+
"eval_bleu": 5.106,
|
526 |
+
"eval_gen_len": 18.0037,
|
527 |
+
"eval_loss": 0.9262479543685913,
|
528 |
+
"eval_runtime": 1520.8802,
|
529 |
+
"eval_samples_per_second": 14.93,
|
530 |
+
"eval_steps_per_second": 0.934,
|
531 |
+
"step": 26250
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 2.33,
|
535 |
+
"learning_rate": 4.230701341492116e-05,
|
536 |
+
"loss": 0.8172,
|
537 |
+
"step": 26500
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 2.38,
|
541 |
+
"learning_rate": 4.215991998117204e-05,
|
542 |
+
"loss": 0.8219,
|
543 |
+
"step": 27000
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 2.42,
|
547 |
+
"learning_rate": 4.201282654742292e-05,
|
548 |
+
"loss": 0.8248,
|
549 |
+
"step": 27500
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 2.42,
|
553 |
+
"eval_bleu": 5.3073,
|
554 |
+
"eval_gen_len": 17.6632,
|
555 |
+
"eval_loss": 0.9241103529930115,
|
556 |
+
"eval_runtime": 1501.7783,
|
557 |
+
"eval_samples_per_second": 15.12,
|
558 |
+
"eval_steps_per_second": 0.946,
|
559 |
+
"step": 27500
|
560 |
+
},
|
561 |
+
{
|
562 |
+
"epoch": 2.47,
|
563 |
+
"learning_rate": 4.1865733113673805e-05,
|
564 |
+
"loss": 0.8046,
|
565 |
+
"step": 28000
|
566 |
+
},
|
567 |
+
{
|
568 |
+
"epoch": 2.51,
|
569 |
+
"learning_rate": 4.1718639679924694e-05,
|
570 |
+
"loss": 0.8151,
|
571 |
+
"step": 28500
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 2.53,
|
575 |
+
"eval_bleu": 5.5675,
|
576 |
+
"eval_gen_len": 17.7676,
|
577 |
+
"eval_loss": 0.9301652312278748,
|
578 |
+
"eval_runtime": 1487.7016,
|
579 |
+
"eval_samples_per_second": 15.263,
|
580 |
+
"eval_steps_per_second": 0.954,
|
581 |
+
"step": 28750
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 2.55,
|
585 |
+
"learning_rate": 4.157154624617558e-05,
|
586 |
+
"loss": 0.8019,
|
587 |
+
"step": 29000
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 2.6,
|
591 |
+
"learning_rate": 4.142445281242646e-05,
|
592 |
+
"loss": 0.8423,
|
593 |
+
"step": 29500
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 2.64,
|
597 |
+
"learning_rate": 4.127735937867734e-05,
|
598 |
+
"loss": 0.8093,
|
599 |
+
"step": 30000
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 2.64,
|
603 |
+
"eval_bleu": 6.2644,
|
604 |
+
"eval_gen_len": 17.8475,
|
605 |
+
"eval_loss": 0.9149118065834045,
|
606 |
+
"eval_runtime": 1510.1876,
|
607 |
+
"eval_samples_per_second": 15.036,
|
608 |
+
"eval_steps_per_second": 0.94,
|
609 |
+
"step": 30000
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 2.69,
|
613 |
+
"learning_rate": 4.113026594492822e-05,
|
614 |
+
"loss": 0.7833,
|
615 |
+
"step": 30500
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 2.73,
|
619 |
+
"learning_rate": 4.09831725111791e-05,
|
620 |
+
"loss": 0.7691,
|
621 |
+
"step": 31000
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 2.75,
|
625 |
+
"eval_bleu": 6.6682,
|
626 |
+
"eval_gen_len": 17.7685,
|
627 |
+
"eval_loss": 0.8987509608268738,
|
628 |
+
"eval_runtime": 1501.6272,
|
629 |
+
"eval_samples_per_second": 15.122,
|
630 |
+
"eval_steps_per_second": 0.946,
|
631 |
+
"step": 31250
|
632 |
+
}
|
633 |
+
],
|
634 |
+
"logging_steps": 500,
|
635 |
+
"max_steps": 170310,
|
636 |
+
"num_train_epochs": 15,
|
637 |
+
"save_steps": 1250,
|
638 |
+
"total_flos": 1.0837035802731479e+18,
|
639 |
+
"trial_name": null,
|
640 |
+
"trial_params": null
|
641 |
+
}
|
checkpoint-31250/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c014122aea94a2b193fe492a2512d39e6992ce344469c697d16d7a534625de8e
|
3 |
+
size 4728
|
checkpoint-35000/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": "4.34.1",
|
57 |
+
"use_cache": true,
|
58 |
+
"vocab_size": 250054
|
59 |
+
}
|
checkpoint-35000/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": "4.34.1"
|
12 |
+
}
|
checkpoint-35000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fb32e23e596a02de896b87cfa19a590d491e3c8ff8179245ab4b039d85f889e
|
3 |
+
size 4887473903
|
checkpoint-35000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3dfa2b63801cc70f9b90fe3983284b958dc94826bb9d54a53f3f952894630775
|
3 |
+
size 2444694490
|
checkpoint-35000/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ff1e3830fe2ca69aae31b2c6b117c2a8ee8afb3ee5919e302a6a04a8eacb812
|
3 |
+
size 15024
|
checkpoint-35000/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:850b5d5c1f7b3827c517fc1145b6061ef506d38fb4fb7ff9b8fe4f39dfdcc5bc
|
3 |
+
size 15024
|
checkpoint-35000/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c6f2e17a52ebdd98620fd6b8dd8dd86f6a23775a6ba6b5c4b97975d9cbe0f98
|
3 |
+
size 15024
|
checkpoint-35000/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c240138dc26459eceae1bf2b808766952bf8ba7b6d51213c6c6be1a7c204bba
|
3 |
+
size 15024
|
checkpoint-35000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4548d1b305957988baab09968d545f40df0090a31cee8f1b6ace855c6a0247b0
|
3 |
+
size 1064
|
checkpoint-35000/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-35000/special_tokens_map.json
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"ar_AR",
|
4 |
+
"cs_CZ",
|
5 |
+
"de_DE",
|
6 |
+
"en_XX",
|
7 |
+
"es_XX",
|
8 |
+
"et_EE",
|
9 |
+
"fi_FI",
|
10 |
+
"fr_XX",
|
11 |
+
"gu_IN",
|
12 |
+
"hi_IN",
|
13 |
+
"it_IT",
|
14 |
+
"ja_XX",
|
15 |
+
"kk_KZ",
|
16 |
+
"ko_KR",
|
17 |
+
"lt_LT",
|
18 |
+
"lv_LV",
|
19 |
+
"my_MM",
|
20 |
+
"ne_NP",
|
21 |
+
"nl_XX",
|
22 |
+
"ro_RO",
|
23 |
+
"ru_RU",
|
24 |
+
"si_LK",
|
25 |
+
"tr_TR",
|
26 |
+
"vi_VN",
|
27 |
+
"zh_CN",
|
28 |
+
"af_ZA",
|
29 |
+
"az_AZ",
|
30 |
+
"bn_IN",
|
31 |
+
"fa_IR",
|
32 |
+
"he_IL",
|
33 |
+
"hr_HR",
|
34 |
+
"id_ID",
|
35 |
+
"ka_GE",
|
36 |
+
"km_KH",
|
37 |
+
"mk_MK",
|
38 |
+
"ml_IN",
|
39 |
+
"mn_MN",
|
40 |
+
"mr_IN",
|
41 |
+
"pl_PL",
|
42 |
+
"ps_AF",
|
43 |
+
"pt_XX",
|
44 |
+
"sv_SE",
|
45 |
+
"sw_KE",
|
46 |
+
"ta_IN",
|
47 |
+
"te_IN",
|
48 |
+
"th_TH",
|
49 |
+
"tl_XX",
|
50 |
+
"uk_UA",
|
51 |
+
"ur_PK",
|
52 |
+
"xh_ZA",
|
53 |
+
"gl_ES",
|
54 |
+
"sl_SI"
|
55 |
+
],
|
56 |
+
"bos_token": "<s>",
|
57 |
+
"cls_token": "<s>",
|
58 |
+
"eos_token": "</s>",
|
59 |
+
"mask_token": {
|
60 |
+
"content": "<mask>",
|
61 |
+
"lstrip": true,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false
|
65 |
+
},
|
66 |
+
"pad_token": "<pad>",
|
67 |
+
"sep_token": "</s>",
|
68 |
+
"unk_token": "<unk>"
|
69 |
+
}
|
checkpoint-35000/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fc2a9a463953c664738ef8571ed97361b8de258b2aca93c0214a89676a73379
|
3 |
+
size 17110043
|
checkpoint-35000/tokenizer_config.json
ADDED
@@ -0,0 +1,528 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "ar_AR",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"250002": {
|
44 |
+
"content": "cs_CZ",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"250003": {
|
52 |
+
"content": "de_DE",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"250004": {
|
60 |
+
"content": "en_XX",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"250005": {
|
68 |
+
"content": "es_XX",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"250006": {
|
76 |
+
"content": "et_EE",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"250007": {
|
84 |
+
"content": "fi_FI",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"250008": {
|
92 |
+
"content": "fr_XX",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"250009": {
|
100 |
+
"content": "gu_IN",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"250010": {
|
108 |
+
"content": "hi_IN",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"250011": {
|
116 |
+
"content": "it_IT",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"250012": {
|
124 |
+
"content": "ja_XX",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"250013": {
|
132 |
+
"content": "kk_KZ",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"250014": {
|
140 |
+
"content": "ko_KR",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"250015": {
|
148 |
+
"content": "lt_LT",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"250016": {
|
156 |
+
"content": "lv_LV",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"250017": {
|
164 |
+
"content": "my_MM",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"250018": {
|
172 |
+
"content": "ne_NP",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"250019": {
|
180 |
+
"content": "nl_XX",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"250020": {
|
188 |
+
"content": "ro_RO",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"250021": {
|
196 |
+
"content": "ru_RU",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"250022": {
|
204 |
+
"content": "si_LK",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"250023": {
|
212 |
+
"content": "tr_TR",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"250024": {
|
220 |
+
"content": "vi_VN",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"250025": {
|
228 |
+
"content": "zh_CN",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"250026": {
|
236 |
+
"content": "af_ZA",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"250027": {
|
244 |
+
"content": "az_AZ",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"250028": {
|
252 |
+
"content": "bn_IN",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"250029": {
|
260 |
+
"content": "fa_IR",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"250030": {
|
268 |
+
"content": "he_IL",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"250031": {
|
276 |
+
"content": "hr_HR",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"250032": {
|
284 |
+
"content": "id_ID",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": true
|
290 |
+
},
|
291 |
+
"250033": {
|
292 |
+
"content": "ka_GE",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": true
|
298 |
+
},
|
299 |
+
"250034": {
|
300 |
+
"content": "km_KH",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": true
|
306 |
+
},
|
307 |
+
"250035": {
|
308 |
+
"content": "mk_MK",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": true
|
314 |
+
},
|
315 |
+
"250036": {
|
316 |
+
"content": "ml_IN",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": true
|
322 |
+
},
|
323 |
+
"250037": {
|
324 |
+
"content": "mn_MN",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": true
|
330 |
+
},
|
331 |
+
"250038": {
|
332 |
+
"content": "mr_IN",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": true
|
338 |
+
},
|
339 |
+
"250039": {
|
340 |
+
"content": "pl_PL",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": true
|
346 |
+
},
|
347 |
+
"250040": {
|
348 |
+
"content": "ps_AF",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": true
|
354 |
+
},
|
355 |
+
"250041": {
|
356 |
+
"content": "pt_XX",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": true
|
362 |
+
},
|
363 |
+
"250042": {
|
364 |
+
"content": "sv_SE",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": true
|
370 |
+
},
|
371 |
+
"250043": {
|
372 |
+
"content": "sw_KE",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": true
|
378 |
+
},
|
379 |
+
"250044": {
|
380 |
+
"content": "ta_IN",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": true
|
386 |
+
},
|
387 |
+
"250045": {
|
388 |
+
"content": "te_IN",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": true
|
394 |
+
},
|
395 |
+
"250046": {
|
396 |
+
"content": "th_TH",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": true
|
402 |
+
},
|
403 |
+
"250047": {
|
404 |
+
"content": "tl_XX",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": true
|
410 |
+
},
|
411 |
+
"250048": {
|
412 |
+
"content": "uk_UA",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": true
|
418 |
+
},
|
419 |
+
"250049": {
|
420 |
+
"content": "ur_PK",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": false,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": true
|
426 |
+
},
|
427 |
+
"250050": {
|
428 |
+
"content": "xh_ZA",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": false,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": true
|
434 |
+
},
|
435 |
+
"250051": {
|
436 |
+
"content": "gl_ES",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": false,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": true
|
442 |
+
},
|
443 |
+
"250052": {
|
444 |
+
"content": "sl_SI",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": false,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": true
|
450 |
+
},
|
451 |
+
"250053": {
|
452 |
+
"content": "<mask>",
|
453 |
+
"lstrip": true,
|
454 |
+
"normalized": true,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": true
|
458 |
+
}
|
459 |
+
},
|
460 |
+
"additional_special_tokens": [
|
461 |
+
"ar_AR",
|
462 |
+
"cs_CZ",
|
463 |
+
"de_DE",
|
464 |
+
"en_XX",
|
465 |
+
"es_XX",
|
466 |
+
"et_EE",
|
467 |
+
"fi_FI",
|
468 |
+
"fr_XX",
|
469 |
+
"gu_IN",
|
470 |
+
"hi_IN",
|
471 |
+
"it_IT",
|
472 |
+
"ja_XX",
|
473 |
+
"kk_KZ",
|
474 |
+
"ko_KR",
|
475 |
+
"lt_LT",
|
476 |
+
"lv_LV",
|
477 |
+
"my_MM",
|
478 |
+
"ne_NP",
|
479 |
+
"nl_XX",
|
480 |
+
"ro_RO",
|
481 |
+
"ru_RU",
|
482 |
+
"si_LK",
|
483 |
+
"tr_TR",
|
484 |
+
"vi_VN",
|
485 |
+
"zh_CN",
|
486 |
+
"af_ZA",
|
487 |
+
"az_AZ",
|
488 |
+
"bn_IN",
|
489 |
+
"fa_IR",
|
490 |
+
"he_IL",
|
491 |
+
"hr_HR",
|
492 |
+
"id_ID",
|
493 |
+
"ka_GE",
|
494 |
+
"km_KH",
|
495 |
+
"mk_MK",
|
496 |
+
"ml_IN",
|
497 |
+
"mn_MN",
|
498 |
+
"mr_IN",
|
499 |
+
"pl_PL",
|
500 |
+
"ps_AF",
|
501 |
+
"pt_XX",
|
502 |
+
"sv_SE",
|
503 |
+
"sw_KE",
|
504 |
+
"ta_IN",
|
505 |
+
"te_IN",
|
506 |
+
"th_TH",
|
507 |
+
"tl_XX",
|
508 |
+
"uk_UA",
|
509 |
+
"ur_PK",
|
510 |
+
"xh_ZA",
|
511 |
+
"gl_ES",
|
512 |
+
"sl_SI"
|
513 |
+
],
|
514 |
+
"bos_token": "<s>",
|
515 |
+
"clean_up_tokenization_spaces": true,
|
516 |
+
"cls_token": "<s>",
|
517 |
+
"eos_token": "</s>",
|
518 |
+
"language_codes": "ML50",
|
519 |
+
"mask_token": "<mask>",
|
520 |
+
"model_max_length": 1000000000000000019884624838656,
|
521 |
+
"pad_token": "<pad>",
|
522 |
+
"sep_token": "</s>",
|
523 |
+
"sp_model_kwargs": {},
|
524 |
+
"src_lang": "ko_KR",
|
525 |
+
"tgt_lang": "ja_XX",
|
526 |
+
"tokenizer_class": "MBart50Tokenizer",
|
527 |
+
"unk_token": "<unk>"
|
528 |
+
}
|
checkpoint-35000/trainer_state.json
ADDED
@@ -0,0 +1,719 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8987509608268738,
|
3 |
+
"best_model_checkpoint": "./mbartLarge_koja_37p_exp2/checkpoint-31250",
|
4 |
+
"epoch": 3.082614056720099,
|
5 |
+
"eval_steps": 1250,
|
6 |
+
"global_step": 35000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.04,
|
13 |
+
"learning_rate": 4.995587196987527e-05,
|
14 |
+
"loss": 3.3474,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.09,
|
19 |
+
"learning_rate": 4.9808778536126146e-05,
|
20 |
+
"loss": 2.0622,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.11,
|
25 |
+
"eval_bleu": 1.2834,
|
26 |
+
"eval_gen_len": 17.8009,
|
27 |
+
"eval_loss": 1.6679450273513794,
|
28 |
+
"eval_runtime": 1488.7514,
|
29 |
+
"eval_samples_per_second": 15.252,
|
30 |
+
"eval_steps_per_second": 0.954,
|
31 |
+
"step": 1250
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.13,
|
35 |
+
"learning_rate": 4.966168510237703e-05,
|
36 |
+
"loss": 1.7123,
|
37 |
+
"step": 1500
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.18,
|
41 |
+
"learning_rate": 4.951459166862791e-05,
|
42 |
+
"loss": 1.59,
|
43 |
+
"step": 2000
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 0.22,
|
47 |
+
"learning_rate": 4.936749823487879e-05,
|
48 |
+
"loss": 1.5139,
|
49 |
+
"step": 2500
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 0.22,
|
53 |
+
"eval_bleu": 2.0427,
|
54 |
+
"eval_gen_len": 17.8496,
|
55 |
+
"eval_loss": 1.4377689361572266,
|
56 |
+
"eval_runtime": 1494.0047,
|
57 |
+
"eval_samples_per_second": 15.199,
|
58 |
+
"eval_steps_per_second": 0.95,
|
59 |
+
"step": 2500
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.26,
|
63 |
+
"learning_rate": 4.922040480112968e-05,
|
64 |
+
"loss": 1.4565,
|
65 |
+
"step": 3000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.31,
|
69 |
+
"learning_rate": 4.9073311367380564e-05,
|
70 |
+
"loss": 1.4121,
|
71 |
+
"step": 3500
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 0.33,
|
75 |
+
"eval_bleu": 2.7599,
|
76 |
+
"eval_gen_len": 17.7667,
|
77 |
+
"eval_loss": 1.3115850687026978,
|
78 |
+
"eval_runtime": 1502.2991,
|
79 |
+
"eval_samples_per_second": 15.115,
|
80 |
+
"eval_steps_per_second": 0.945,
|
81 |
+
"step": 3750
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.35,
|
85 |
+
"learning_rate": 4.892621793363145e-05,
|
86 |
+
"loss": 1.3511,
|
87 |
+
"step": 4000
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.4,
|
91 |
+
"learning_rate": 4.877912449988233e-05,
|
92 |
+
"loss": 1.3052,
|
93 |
+
"step": 4500
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.44,
|
97 |
+
"learning_rate": 4.863203106613321e-05,
|
98 |
+
"loss": 1.2879,
|
99 |
+
"step": 5000
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.44,
|
103 |
+
"eval_bleu": 3.1444,
|
104 |
+
"eval_gen_len": 17.8887,
|
105 |
+
"eval_loss": 1.23811936378479,
|
106 |
+
"eval_runtime": 1519.5015,
|
107 |
+
"eval_samples_per_second": 14.944,
|
108 |
+
"eval_steps_per_second": 0.935,
|
109 |
+
"step": 5000
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 0.48,
|
113 |
+
"learning_rate": 4.8484937632384094e-05,
|
114 |
+
"loss": 1.2634,
|
115 |
+
"step": 5500
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.53,
|
119 |
+
"learning_rate": 4.8337844198634976e-05,
|
120 |
+
"loss": 1.2344,
|
121 |
+
"step": 6000
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.55,
|
125 |
+
"eval_bleu": 3.3835,
|
126 |
+
"eval_gen_len": 17.8323,
|
127 |
+
"eval_loss": 1.1769133806228638,
|
128 |
+
"eval_runtime": 1506.2285,
|
129 |
+
"eval_samples_per_second": 15.075,
|
130 |
+
"eval_steps_per_second": 0.943,
|
131 |
+
"step": 6250
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 0.57,
|
135 |
+
"learning_rate": 4.819075076488586e-05,
|
136 |
+
"loss": 1.2213,
|
137 |
+
"step": 6500
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.62,
|
141 |
+
"learning_rate": 4.804365733113674e-05,
|
142 |
+
"loss": 1.1918,
|
143 |
+
"step": 7000
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.66,
|
147 |
+
"learning_rate": 4.789656389738762e-05,
|
148 |
+
"loss": 1.1778,
|
149 |
+
"step": 7500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.66,
|
153 |
+
"eval_bleu": 3.9511,
|
154 |
+
"eval_gen_len": 17.4892,
|
155 |
+
"eval_loss": 1.1381820440292358,
|
156 |
+
"eval_runtime": 1485.4261,
|
157 |
+
"eval_samples_per_second": 15.287,
|
158 |
+
"eval_steps_per_second": 0.956,
|
159 |
+
"step": 7500
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.7,
|
163 |
+
"learning_rate": 4.7749470463638505e-05,
|
164 |
+
"loss": 1.1651,
|
165 |
+
"step": 8000
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.75,
|
169 |
+
"learning_rate": 4.760237702988939e-05,
|
170 |
+
"loss": 1.1461,
|
171 |
+
"step": 8500
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.77,
|
175 |
+
"eval_bleu": 3.9402,
|
176 |
+
"eval_gen_len": 18.0136,
|
177 |
+
"eval_loss": 1.09383225440979,
|
178 |
+
"eval_runtime": 1503.0162,
|
179 |
+
"eval_samples_per_second": 15.108,
|
180 |
+
"eval_steps_per_second": 0.945,
|
181 |
+
"step": 8750
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.79,
|
185 |
+
"learning_rate": 4.745528359614027e-05,
|
186 |
+
"loss": 1.1341,
|
187 |
+
"step": 9000
|
188 |
+
},
|
189 |
+
{
|
190 |
+
"epoch": 0.84,
|
191 |
+
"learning_rate": 4.730819016239115e-05,
|
192 |
+
"loss": 1.1294,
|
193 |
+
"step": 9500
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.88,
|
197 |
+
"learning_rate": 4.7161096728642035e-05,
|
198 |
+
"loss": 1.1151,
|
199 |
+
"step": 10000
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.88,
|
203 |
+
"eval_bleu": 4.2134,
|
204 |
+
"eval_gen_len": 18.0537,
|
205 |
+
"eval_loss": 1.074916124343872,
|
206 |
+
"eval_runtime": 1564.4468,
|
207 |
+
"eval_samples_per_second": 14.514,
|
208 |
+
"eval_steps_per_second": 0.908,
|
209 |
+
"step": 10000
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.92,
|
213 |
+
"learning_rate": 4.701400329489292e-05,
|
214 |
+
"loss": 1.1102,
|
215 |
+
"step": 10500
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 0.97,
|
219 |
+
"learning_rate": 4.68669098611438e-05,
|
220 |
+
"loss": 1.093,
|
221 |
+
"step": 11000
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.99,
|
225 |
+
"eval_bleu": 3.9587,
|
226 |
+
"eval_gen_len": 17.8715,
|
227 |
+
"eval_loss": 1.0418165922164917,
|
228 |
+
"eval_runtime": 1534.6245,
|
229 |
+
"eval_samples_per_second": 14.796,
|
230 |
+
"eval_steps_per_second": 0.925,
|
231 |
+
"step": 11250
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 1.01,
|
235 |
+
"learning_rate": 4.671981642739469e-05,
|
236 |
+
"loss": 1.084,
|
237 |
+
"step": 11500
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 1.06,
|
241 |
+
"learning_rate": 4.657272299364557e-05,
|
242 |
+
"loss": 1.0641,
|
243 |
+
"step": 12000
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 1.1,
|
247 |
+
"learning_rate": 4.6425629559896446e-05,
|
248 |
+
"loss": 1.0626,
|
249 |
+
"step": 12500
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 1.1,
|
253 |
+
"eval_bleu": 4.6251,
|
254 |
+
"eval_gen_len": 17.9406,
|
255 |
+
"eval_loss": 1.0315195322036743,
|
256 |
+
"eval_runtime": 1499.6187,
|
257 |
+
"eval_samples_per_second": 15.142,
|
258 |
+
"eval_steps_per_second": 0.947,
|
259 |
+
"step": 12500
|
260 |
+
},
|
261 |
+
{
|
262 |
+
"epoch": 1.14,
|
263 |
+
"learning_rate": 4.627853612614733e-05,
|
264 |
+
"loss": 1.0332,
|
265 |
+
"step": 13000
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 1.19,
|
269 |
+
"learning_rate": 4.613144269239821e-05,
|
270 |
+
"loss": 1.0192,
|
271 |
+
"step": 13500
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 1.21,
|
275 |
+
"eval_bleu": 4.9573,
|
276 |
+
"eval_gen_len": 18.1266,
|
277 |
+
"eval_loss": 1.0131869316101074,
|
278 |
+
"eval_runtime": 1514.9755,
|
279 |
+
"eval_samples_per_second": 14.988,
|
280 |
+
"eval_steps_per_second": 0.937,
|
281 |
+
"step": 13750
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 1.23,
|
285 |
+
"learning_rate": 4.598434925864909e-05,
|
286 |
+
"loss": 1.0234,
|
287 |
+
"step": 14000
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 1.28,
|
291 |
+
"learning_rate": 4.5837255824899976e-05,
|
292 |
+
"loss": 1.0062,
|
293 |
+
"step": 14500
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 1.32,
|
297 |
+
"learning_rate": 4.569016239115086e-05,
|
298 |
+
"loss": 0.9957,
|
299 |
+
"step": 15000
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 1.32,
|
303 |
+
"eval_bleu": 4.3068,
|
304 |
+
"eval_gen_len": 18.0925,
|
305 |
+
"eval_loss": 0.9988749623298645,
|
306 |
+
"eval_runtime": 1565.2457,
|
307 |
+
"eval_samples_per_second": 14.507,
|
308 |
+
"eval_steps_per_second": 0.907,
|
309 |
+
"step": 15000
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 1.37,
|
313 |
+
"learning_rate": 4.554306895740174e-05,
|
314 |
+
"loss": 0.9843,
|
315 |
+
"step": 15500
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 1.41,
|
319 |
+
"learning_rate": 4.539597552365263e-05,
|
320 |
+
"loss": 0.9778,
|
321 |
+
"step": 16000
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 1.43,
|
325 |
+
"eval_bleu": 5.0517,
|
326 |
+
"eval_gen_len": 17.8783,
|
327 |
+
"eval_loss": 0.984965980052948,
|
328 |
+
"eval_runtime": 1508.5724,
|
329 |
+
"eval_samples_per_second": 15.052,
|
330 |
+
"eval_steps_per_second": 0.941,
|
331 |
+
"step": 16250
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 1.45,
|
335 |
+
"learning_rate": 4.524888208990351e-05,
|
336 |
+
"loss": 0.961,
|
337 |
+
"step": 16500
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 1.5,
|
341 |
+
"learning_rate": 4.5101788656154394e-05,
|
342 |
+
"loss": 0.9735,
|
343 |
+
"step": 17000
|
344 |
+
},
|
345 |
+
{
|
346 |
+
"epoch": 1.54,
|
347 |
+
"learning_rate": 4.4954695222405276e-05,
|
348 |
+
"loss": 0.9446,
|
349 |
+
"step": 17500
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 1.54,
|
353 |
+
"eval_bleu": 5.0194,
|
354 |
+
"eval_gen_len": 17.9348,
|
355 |
+
"eval_loss": 0.9747512936592102,
|
356 |
+
"eval_runtime": 1574.1886,
|
357 |
+
"eval_samples_per_second": 14.425,
|
358 |
+
"eval_steps_per_second": 0.902,
|
359 |
+
"step": 17500
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 1.59,
|
363 |
+
"learning_rate": 4.480760178865616e-05,
|
364 |
+
"loss": 0.9352,
|
365 |
+
"step": 18000
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 1.63,
|
369 |
+
"learning_rate": 4.466050835490704e-05,
|
370 |
+
"loss": 0.9236,
|
371 |
+
"step": 18500
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 1.65,
|
375 |
+
"eval_bleu": 4.6011,
|
376 |
+
"eval_gen_len": 17.7926,
|
377 |
+
"eval_loss": 0.9619229435920715,
|
378 |
+
"eval_runtime": 1510.4722,
|
379 |
+
"eval_samples_per_second": 15.033,
|
380 |
+
"eval_steps_per_second": 0.94,
|
381 |
+
"step": 18750
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 1.67,
|
385 |
+
"learning_rate": 4.4513414921157917e-05,
|
386 |
+
"loss": 0.9289,
|
387 |
+
"step": 19000
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 1.72,
|
391 |
+
"learning_rate": 4.43663214874088e-05,
|
392 |
+
"loss": 0.9216,
|
393 |
+
"step": 19500
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 1.76,
|
397 |
+
"learning_rate": 4.421922805365969e-05,
|
398 |
+
"loss": 0.9091,
|
399 |
+
"step": 20000
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 1.76,
|
403 |
+
"eval_bleu": 4.6035,
|
404 |
+
"eval_gen_len": 17.9399,
|
405 |
+
"eval_loss": 0.9564162492752075,
|
406 |
+
"eval_runtime": 1530.1826,
|
407 |
+
"eval_samples_per_second": 14.839,
|
408 |
+
"eval_steps_per_second": 0.928,
|
409 |
+
"step": 20000
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 1.81,
|
413 |
+
"learning_rate": 4.407213461991057e-05,
|
414 |
+
"loss": 0.9333,
|
415 |
+
"step": 20500
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 1.85,
|
419 |
+
"learning_rate": 4.392504118616145e-05,
|
420 |
+
"loss": 0.9072,
|
421 |
+
"step": 21000
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"epoch": 1.87,
|
425 |
+
"eval_bleu": 4.8313,
|
426 |
+
"eval_gen_len": 17.6221,
|
427 |
+
"eval_loss": 0.9533364176750183,
|
428 |
+
"eval_runtime": 1475.3262,
|
429 |
+
"eval_samples_per_second": 15.391,
|
430 |
+
"eval_steps_per_second": 0.962,
|
431 |
+
"step": 21250
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 1.89,
|
435 |
+
"learning_rate": 4.3777947752412335e-05,
|
436 |
+
"loss": 0.8896,
|
437 |
+
"step": 21500
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 1.94,
|
441 |
+
"learning_rate": 4.363085431866322e-05,
|
442 |
+
"loss": 0.8945,
|
443 |
+
"step": 22000
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 1.98,
|
447 |
+
"learning_rate": 4.34837608849141e-05,
|
448 |
+
"loss": 0.8758,
|
449 |
+
"step": 22500
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 1.98,
|
453 |
+
"eval_bleu": 5.2707,
|
454 |
+
"eval_gen_len": 17.5851,
|
455 |
+
"eval_loss": 0.9421375393867493,
|
456 |
+
"eval_runtime": 1516.2122,
|
457 |
+
"eval_samples_per_second": 14.976,
|
458 |
+
"eval_steps_per_second": 0.937,
|
459 |
+
"step": 22500
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 2.03,
|
463 |
+
"learning_rate": 4.333666745116498e-05,
|
464 |
+
"loss": 0.8723,
|
465 |
+
"step": 23000
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 2.07,
|
469 |
+
"learning_rate": 4.3189574017415864e-05,
|
470 |
+
"loss": 0.8539,
|
471 |
+
"step": 23500
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 2.09,
|
475 |
+
"eval_bleu": 5.2661,
|
476 |
+
"eval_gen_len": 17.821,
|
477 |
+
"eval_loss": 0.9304332137107849,
|
478 |
+
"eval_runtime": 1492.9401,
|
479 |
+
"eval_samples_per_second": 15.21,
|
480 |
+
"eval_steps_per_second": 0.951,
|
481 |
+
"step": 23750
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 2.11,
|
485 |
+
"learning_rate": 4.3042480583666747e-05,
|
486 |
+
"loss": 0.8461,
|
487 |
+
"step": 24000
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 2.16,
|
491 |
+
"learning_rate": 4.289538714991763e-05,
|
492 |
+
"loss": 0.842,
|
493 |
+
"step": 24500
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 2.2,
|
497 |
+
"learning_rate": 4.274829371616851e-05,
|
498 |
+
"loss": 0.8575,
|
499 |
+
"step": 25000
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 2.2,
|
503 |
+
"eval_bleu": 4.9143,
|
504 |
+
"eval_gen_len": 17.8879,
|
505 |
+
"eval_loss": 0.9329252243041992,
|
506 |
+
"eval_runtime": 1560.9154,
|
507 |
+
"eval_samples_per_second": 14.547,
|
508 |
+
"eval_steps_per_second": 0.91,
|
509 |
+
"step": 25000
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 2.25,
|
513 |
+
"learning_rate": 4.2601200282419394e-05,
|
514 |
+
"loss": 0.8424,
|
515 |
+
"step": 25500
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 2.29,
|
519 |
+
"learning_rate": 4.2454106848670276e-05,
|
520 |
+
"loss": 0.8314,
|
521 |
+
"step": 26000
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 2.31,
|
525 |
+
"eval_bleu": 5.106,
|
526 |
+
"eval_gen_len": 18.0037,
|
527 |
+
"eval_loss": 0.9262479543685913,
|
528 |
+
"eval_runtime": 1520.8802,
|
529 |
+
"eval_samples_per_second": 14.93,
|
530 |
+
"eval_steps_per_second": 0.934,
|
531 |
+
"step": 26250
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 2.33,
|
535 |
+
"learning_rate": 4.230701341492116e-05,
|
536 |
+
"loss": 0.8172,
|
537 |
+
"step": 26500
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 2.38,
|
541 |
+
"learning_rate": 4.215991998117204e-05,
|
542 |
+
"loss": 0.8219,
|
543 |
+
"step": 27000
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 2.42,
|
547 |
+
"learning_rate": 4.201282654742292e-05,
|
548 |
+
"loss": 0.8248,
|
549 |
+
"step": 27500
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 2.42,
|
553 |
+
"eval_bleu": 5.3073,
|
554 |
+
"eval_gen_len": 17.6632,
|
555 |
+
"eval_loss": 0.9241103529930115,
|
556 |
+
"eval_runtime": 1501.7783,
|
557 |
+
"eval_samples_per_second": 15.12,
|
558 |
+
"eval_steps_per_second": 0.946,
|
559 |
+
"step": 27500
|
560 |
+
},
|
561 |
+
{
|
562 |
+
"epoch": 2.47,
|
563 |
+
"learning_rate": 4.1865733113673805e-05,
|
564 |
+
"loss": 0.8046,
|
565 |
+
"step": 28000
|
566 |
+
},
|
567 |
+
{
|
568 |
+
"epoch": 2.51,
|
569 |
+
"learning_rate": 4.1718639679924694e-05,
|
570 |
+
"loss": 0.8151,
|
571 |
+
"step": 28500
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 2.53,
|
575 |
+
"eval_bleu": 5.5675,
|
576 |
+
"eval_gen_len": 17.7676,
|
577 |
+
"eval_loss": 0.9301652312278748,
|
578 |
+
"eval_runtime": 1487.7016,
|
579 |
+
"eval_samples_per_second": 15.263,
|
580 |
+
"eval_steps_per_second": 0.954,
|
581 |
+
"step": 28750
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 2.55,
|
585 |
+
"learning_rate": 4.157154624617558e-05,
|
586 |
+
"loss": 0.8019,
|
587 |
+
"step": 29000
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 2.6,
|
591 |
+
"learning_rate": 4.142445281242646e-05,
|
592 |
+
"loss": 0.8423,
|
593 |
+
"step": 29500
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 2.64,
|
597 |
+
"learning_rate": 4.127735937867734e-05,
|
598 |
+
"loss": 0.8093,
|
599 |
+
"step": 30000
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 2.64,
|
603 |
+
"eval_bleu": 6.2644,
|
604 |
+
"eval_gen_len": 17.8475,
|
605 |
+
"eval_loss": 0.9149118065834045,
|
606 |
+
"eval_runtime": 1510.1876,
|
607 |
+
"eval_samples_per_second": 15.036,
|
608 |
+
"eval_steps_per_second": 0.94,
|
609 |
+
"step": 30000
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 2.69,
|
613 |
+
"learning_rate": 4.113026594492822e-05,
|
614 |
+
"loss": 0.7833,
|
615 |
+
"step": 30500
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 2.73,
|
619 |
+
"learning_rate": 4.09831725111791e-05,
|
620 |
+
"loss": 0.7691,
|
621 |
+
"step": 31000
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 2.75,
|
625 |
+
"eval_bleu": 6.6682,
|
626 |
+
"eval_gen_len": 17.7685,
|
627 |
+
"eval_loss": 0.8987509608268738,
|
628 |
+
"eval_runtime": 1501.6272,
|
629 |
+
"eval_samples_per_second": 15.122,
|
630 |
+
"eval_steps_per_second": 0.946,
|
631 |
+
"step": 31250
|
632 |
+
},
|
633 |
+
{
|
634 |
+
"epoch": 2.77,
|
635 |
+
"learning_rate": 4.083607907742998e-05,
|
636 |
+
"loss": 0.7673,
|
637 |
+
"step": 31500
|
638 |
+
},
|
639 |
+
{
|
640 |
+
"epoch": 2.82,
|
641 |
+
"learning_rate": 4.0688985643680864e-05,
|
642 |
+
"loss": 0.8064,
|
643 |
+
"step": 32000
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 2.86,
|
647 |
+
"learning_rate": 4.054189220993175e-05,
|
648 |
+
"loss": 0.771,
|
649 |
+
"step": 32500
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 2.86,
|
653 |
+
"eval_bleu": 5.7856,
|
654 |
+
"eval_gen_len": 17.8678,
|
655 |
+
"eval_loss": 0.9189176559448242,
|
656 |
+
"eval_runtime": 1503.2313,
|
657 |
+
"eval_samples_per_second": 15.105,
|
658 |
+
"eval_steps_per_second": 0.945,
|
659 |
+
"step": 32500
|
660 |
+
},
|
661 |
+
{
|
662 |
+
"epoch": 2.91,
|
663 |
+
"learning_rate": 4.0394798776182635e-05,
|
664 |
+
"loss": 0.7652,
|
665 |
+
"step": 33000
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"epoch": 2.95,
|
669 |
+
"learning_rate": 4.024770534243352e-05,
|
670 |
+
"loss": 0.7658,
|
671 |
+
"step": 33500
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 2.97,
|
675 |
+
"eval_bleu": 6.2468,
|
676 |
+
"eval_gen_len": 17.7313,
|
677 |
+
"eval_loss": 0.9175418019294739,
|
678 |
+
"eval_runtime": 1487.9561,
|
679 |
+
"eval_samples_per_second": 15.261,
|
680 |
+
"eval_steps_per_second": 0.954,
|
681 |
+
"step": 33750
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 2.99,
|
685 |
+
"learning_rate": 4.01006119086844e-05,
|
686 |
+
"loss": 0.7568,
|
687 |
+
"step": 34000
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 3.04,
|
691 |
+
"learning_rate": 3.995351847493528e-05,
|
692 |
+
"loss": 0.7913,
|
693 |
+
"step": 34500
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 3.08,
|
697 |
+
"learning_rate": 3.9806425041186165e-05,
|
698 |
+
"loss": 0.7914,
|
699 |
+
"step": 35000
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 3.08,
|
703 |
+
"eval_bleu": 5.5525,
|
704 |
+
"eval_gen_len": 17.7627,
|
705 |
+
"eval_loss": 0.9019802808761597,
|
706 |
+
"eval_runtime": 1501.9062,
|
707 |
+
"eval_samples_per_second": 15.119,
|
708 |
+
"eval_steps_per_second": 0.945,
|
709 |
+
"step": 35000
|
710 |
+
}
|
711 |
+
],
|
712 |
+
"logging_steps": 500,
|
713 |
+
"max_steps": 170310,
|
714 |
+
"num_train_epochs": 15,
|
715 |
+
"save_steps": 1250,
|
716 |
+
"total_flos": 1.213731366349308e+18,
|
717 |
+
"trial_name": null,
|
718 |
+
"trial_params": null
|
719 |
+
}
|
checkpoint-35000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c014122aea94a2b193fe492a2512d39e6992ce344469c697d16d7a534625de8e
|
3 |
+
size 4728
|
checkpoint-36250/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": "4.34.1",
|
57 |
+
"use_cache": true,
|
58 |
+
"vocab_size": 250054
|
59 |
+
}
|
checkpoint-36250/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": "4.34.1"
|
12 |
+
}
|
checkpoint-36250/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fad2f7796d00c34660287828921799494632e303c5b3bb572fcd9fe281364bee
|
3 |
+
size 4887473903
|
checkpoint-36250/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e96467aba85c836bc58fe0e8d3744c653774e99828cee4894eac1a4460c305b
|
3 |
+
size 2444694490
|
checkpoint-36250/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4d3d12194b8d4a065f89bb78784a7e728920b81005a5336b4f8c20cdcdc93b7
|
3 |
+
size 15024
|
checkpoint-36250/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1bded8d0a128149c1f477831e349cfae660fdb30a7f8e5a4c2a0f3c85b60339a
|
3 |
+
size 15024
|
checkpoint-36250/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cfe52b73a346eac2b6fc40f4c08ea8b2bf62429816a0d6ddb8a9ab25e8c6361
|
3 |
+
size 15024
|
checkpoint-36250/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0796b64f54fe54bf1b0186ab00d5cd1d9583b043472719e7f4d35f9b51f1245
|
3 |
+
size 15024
|
checkpoint-36250/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0336961f718674e14070980b8e81590495774dda5c403d0677323bc652ad5548
|
3 |
+
size 1064
|
checkpoint-36250/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-36250/special_tokens_map.json
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"ar_AR",
|
4 |
+
"cs_CZ",
|
5 |
+
"de_DE",
|
6 |
+
"en_XX",
|
7 |
+
"es_XX",
|
8 |
+
"et_EE",
|
9 |
+
"fi_FI",
|
10 |
+
"fr_XX",
|
11 |
+
"gu_IN",
|
12 |
+
"hi_IN",
|
13 |
+
"it_IT",
|
14 |
+
"ja_XX",
|
15 |
+
"kk_KZ",
|
16 |
+
"ko_KR",
|
17 |
+
"lt_LT",
|
18 |
+
"lv_LV",
|
19 |
+
"my_MM",
|
20 |
+
"ne_NP",
|
21 |
+
"nl_XX",
|
22 |
+
"ro_RO",
|
23 |
+
"ru_RU",
|
24 |
+
"si_LK",
|
25 |
+
"tr_TR",
|
26 |
+
"vi_VN",
|
27 |
+
"zh_CN",
|
28 |
+
"af_ZA",
|
29 |
+
"az_AZ",
|
30 |
+
"bn_IN",
|
31 |
+
"fa_IR",
|
32 |
+
"he_IL",
|
33 |
+
"hr_HR",
|
34 |
+
"id_ID",
|
35 |
+
"ka_GE",
|
36 |
+
"km_KH",
|
37 |
+
"mk_MK",
|
38 |
+
"ml_IN",
|
39 |
+
"mn_MN",
|
40 |
+
"mr_IN",
|
41 |
+
"pl_PL",
|
42 |
+
"ps_AF",
|
43 |
+
"pt_XX",
|
44 |
+
"sv_SE",
|
45 |
+
"sw_KE",
|
46 |
+
"ta_IN",
|
47 |
+
"te_IN",
|
48 |
+
"th_TH",
|
49 |
+
"tl_XX",
|
50 |
+
"uk_UA",
|
51 |
+
"ur_PK",
|
52 |
+
"xh_ZA",
|
53 |
+
"gl_ES",
|
54 |
+
"sl_SI"
|
55 |
+
],
|
56 |
+
"bos_token": "<s>",
|
57 |
+
"cls_token": "<s>",
|
58 |
+
"eos_token": "</s>",
|
59 |
+
"mask_token": {
|
60 |
+
"content": "<mask>",
|
61 |
+
"lstrip": true,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false
|
65 |
+
},
|
66 |
+
"pad_token": "<pad>",
|
67 |
+
"sep_token": "</s>",
|
68 |
+
"unk_token": "<unk>"
|
69 |
+
}
|
checkpoint-36250/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fc2a9a463953c664738ef8571ed97361b8de258b2aca93c0214a89676a73379
|
3 |
+
size 17110043
|
checkpoint-36250/tokenizer_config.json
ADDED
@@ -0,0 +1,528 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "ar_AR",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"250002": {
|
44 |
+
"content": "cs_CZ",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"250003": {
|
52 |
+
"content": "de_DE",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"250004": {
|
60 |
+
"content": "en_XX",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"250005": {
|
68 |
+
"content": "es_XX",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"250006": {
|
76 |
+
"content": "et_EE",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"250007": {
|
84 |
+
"content": "fi_FI",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"250008": {
|
92 |
+
"content": "fr_XX",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"250009": {
|
100 |
+
"content": "gu_IN",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"250010": {
|
108 |
+
"content": "hi_IN",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"250011": {
|
116 |
+
"content": "it_IT",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"250012": {
|
124 |
+
"content": "ja_XX",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"250013": {
|
132 |
+
"content": "kk_KZ",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"250014": {
|
140 |
+
"content": "ko_KR",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"250015": {
|
148 |
+
"content": "lt_LT",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"250016": {
|
156 |
+
"content": "lv_LV",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"250017": {
|
164 |
+
"content": "my_MM",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"250018": {
|
172 |
+
"content": "ne_NP",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"250019": {
|
180 |
+
"content": "nl_XX",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"250020": {
|
188 |
+
"content": "ro_RO",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"250021": {
|
196 |
+
"content": "ru_RU",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"250022": {
|
204 |
+
"content": "si_LK",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"250023": {
|
212 |
+
"content": "tr_TR",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"250024": {
|
220 |
+
"content": "vi_VN",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"250025": {
|
228 |
+
"content": "zh_CN",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"250026": {
|
236 |
+
"content": "af_ZA",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"250027": {
|
244 |
+
"content": "az_AZ",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"250028": {
|
252 |
+
"content": "bn_IN",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"250029": {
|
260 |
+
"content": "fa_IR",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"250030": {
|
268 |
+
"content": "he_IL",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"250031": {
|
276 |
+
"content": "hr_HR",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"250032": {
|
284 |
+
"content": "id_ID",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": true
|
290 |
+
},
|
291 |
+
"250033": {
|
292 |
+
"content": "ka_GE",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": true
|
298 |
+
},
|
299 |
+
"250034": {
|
300 |
+
"content": "km_KH",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": true
|
306 |
+
},
|
307 |
+
"250035": {
|
308 |
+
"content": "mk_MK",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": true
|
314 |
+
},
|
315 |
+
"250036": {
|
316 |
+
"content": "ml_IN",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": true
|
322 |
+
},
|
323 |
+
"250037": {
|
324 |
+
"content": "mn_MN",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": true
|
330 |
+
},
|
331 |
+
"250038": {
|
332 |
+
"content": "mr_IN",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": true
|
338 |
+
},
|
339 |
+
"250039": {
|
340 |
+
"content": "pl_PL",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": true
|
346 |
+
},
|
347 |
+
"250040": {
|
348 |
+
"content": "ps_AF",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": true
|
354 |
+
},
|
355 |
+
"250041": {
|
356 |
+
"content": "pt_XX",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": true
|
362 |
+
},
|
363 |
+
"250042": {
|
364 |
+
"content": "sv_SE",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": true
|
370 |
+
},
|
371 |
+
"250043": {
|
372 |
+
"content": "sw_KE",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": true
|
378 |
+
},
|
379 |
+
"250044": {
|
380 |
+
"content": "ta_IN",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": true
|
386 |
+
},
|
387 |
+
"250045": {
|
388 |
+
"content": "te_IN",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": true
|
394 |
+
},
|
395 |
+
"250046": {
|
396 |
+
"content": "th_TH",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": true
|
402 |
+
},
|
403 |
+
"250047": {
|
404 |
+
"content": "tl_XX",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": true
|
410 |
+
},
|
411 |
+
"250048": {
|
412 |
+
"content": "uk_UA",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": true
|
418 |
+
},
|
419 |
+
"250049": {
|
420 |
+
"content": "ur_PK",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": false,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": true
|
426 |
+
},
|
427 |
+
"250050": {
|
428 |
+
"content": "xh_ZA",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": false,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": true
|
434 |
+
},
|
435 |
+
"250051": {
|
436 |
+
"content": "gl_ES",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": false,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": true
|
442 |
+
},
|
443 |
+
"250052": {
|
444 |
+
"content": "sl_SI",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": false,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": true
|
450 |
+
},
|
451 |
+
"250053": {
|
452 |
+
"content": "<mask>",
|
453 |
+
"lstrip": true,
|
454 |
+
"normalized": true,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": true
|
458 |
+
}
|
459 |
+
},
|
460 |
+
"additional_special_tokens": [
|
461 |
+
"ar_AR",
|
462 |
+
"cs_CZ",
|
463 |
+
"de_DE",
|
464 |
+
"en_XX",
|
465 |
+
"es_XX",
|
466 |
+
"et_EE",
|
467 |
+
"fi_FI",
|
468 |
+
"fr_XX",
|
469 |
+
"gu_IN",
|
470 |
+
"hi_IN",
|
471 |
+
"it_IT",
|
472 |
+
"ja_XX",
|
473 |
+
"kk_KZ",
|
474 |
+
"ko_KR",
|
475 |
+
"lt_LT",
|
476 |
+
"lv_LV",
|
477 |
+
"my_MM",
|
478 |
+
"ne_NP",
|
479 |
+
"nl_XX",
|
480 |
+
"ro_RO",
|
481 |
+
"ru_RU",
|
482 |
+
"si_LK",
|
483 |
+
"tr_TR",
|
484 |
+
"vi_VN",
|
485 |
+
"zh_CN",
|
486 |
+
"af_ZA",
|
487 |
+
"az_AZ",
|
488 |
+
"bn_IN",
|
489 |
+
"fa_IR",
|
490 |
+
"he_IL",
|
491 |
+
"hr_HR",
|
492 |
+
"id_ID",
|
493 |
+
"ka_GE",
|
494 |
+
"km_KH",
|
495 |
+
"mk_MK",
|
496 |
+
"ml_IN",
|
497 |
+
"mn_MN",
|
498 |
+
"mr_IN",
|
499 |
+
"pl_PL",
|
500 |
+
"ps_AF",
|
501 |
+
"pt_XX",
|
502 |
+
"sv_SE",
|
503 |
+
"sw_KE",
|
504 |
+
"ta_IN",
|
505 |
+
"te_IN",
|
506 |
+
"th_TH",
|
507 |
+
"tl_XX",
|
508 |
+
"uk_UA",
|
509 |
+
"ur_PK",
|
510 |
+
"xh_ZA",
|
511 |
+
"gl_ES",
|
512 |
+
"sl_SI"
|
513 |
+
],
|
514 |
+
"bos_token": "<s>",
|
515 |
+
"clean_up_tokenization_spaces": true,
|
516 |
+
"cls_token": "<s>",
|
517 |
+
"eos_token": "</s>",
|
518 |
+
"language_codes": "ML50",
|
519 |
+
"mask_token": "<mask>",
|
520 |
+
"model_max_length": 1000000000000000019884624838656,
|
521 |
+
"pad_token": "<pad>",
|
522 |
+
"sep_token": "</s>",
|
523 |
+
"sp_model_kwargs": {},
|
524 |
+
"src_lang": "ko_KR",
|
525 |
+
"tgt_lang": "ja_XX",
|
526 |
+
"tokenizer_class": "MBart50Tokenizer",
|
527 |
+
"unk_token": "<unk>"
|
528 |
+
}
|
checkpoint-36250/trainer_state.json
ADDED
@@ -0,0 +1,741 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8987509608268738,
|
3 |
+
"best_model_checkpoint": "./mbartLarge_koja_37p_exp2/checkpoint-31250",
|
4 |
+
"epoch": 3.1927074158886737,
|
5 |
+
"eval_steps": 1250,
|
6 |
+
"global_step": 36250,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.04,
|
13 |
+
"learning_rate": 4.995587196987527e-05,
|
14 |
+
"loss": 3.3474,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.09,
|
19 |
+
"learning_rate": 4.9808778536126146e-05,
|
20 |
+
"loss": 2.0622,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.11,
|
25 |
+
"eval_bleu": 1.2834,
|
26 |
+
"eval_gen_len": 17.8009,
|
27 |
+
"eval_loss": 1.6679450273513794,
|
28 |
+
"eval_runtime": 1488.7514,
|
29 |
+
"eval_samples_per_second": 15.252,
|
30 |
+
"eval_steps_per_second": 0.954,
|
31 |
+
"step": 1250
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.13,
|
35 |
+
"learning_rate": 4.966168510237703e-05,
|
36 |
+
"loss": 1.7123,
|
37 |
+
"step": 1500
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.18,
|
41 |
+
"learning_rate": 4.951459166862791e-05,
|
42 |
+
"loss": 1.59,
|
43 |
+
"step": 2000
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 0.22,
|
47 |
+
"learning_rate": 4.936749823487879e-05,
|
48 |
+
"loss": 1.5139,
|
49 |
+
"step": 2500
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 0.22,
|
53 |
+
"eval_bleu": 2.0427,
|
54 |
+
"eval_gen_len": 17.8496,
|
55 |
+
"eval_loss": 1.4377689361572266,
|
56 |
+
"eval_runtime": 1494.0047,
|
57 |
+
"eval_samples_per_second": 15.199,
|
58 |
+
"eval_steps_per_second": 0.95,
|
59 |
+
"step": 2500
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.26,
|
63 |
+
"learning_rate": 4.922040480112968e-05,
|
64 |
+
"loss": 1.4565,
|
65 |
+
"step": 3000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.31,
|
69 |
+
"learning_rate": 4.9073311367380564e-05,
|
70 |
+
"loss": 1.4121,
|
71 |
+
"step": 3500
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 0.33,
|
75 |
+
"eval_bleu": 2.7599,
|
76 |
+
"eval_gen_len": 17.7667,
|
77 |
+
"eval_loss": 1.3115850687026978,
|
78 |
+
"eval_runtime": 1502.2991,
|
79 |
+
"eval_samples_per_second": 15.115,
|
80 |
+
"eval_steps_per_second": 0.945,
|
81 |
+
"step": 3750
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.35,
|
85 |
+
"learning_rate": 4.892621793363145e-05,
|
86 |
+
"loss": 1.3511,
|
87 |
+
"step": 4000
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.4,
|
91 |
+
"learning_rate": 4.877912449988233e-05,
|
92 |
+
"loss": 1.3052,
|
93 |
+
"step": 4500
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.44,
|
97 |
+
"learning_rate": 4.863203106613321e-05,
|
98 |
+
"loss": 1.2879,
|
99 |
+
"step": 5000
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.44,
|
103 |
+
"eval_bleu": 3.1444,
|
104 |
+
"eval_gen_len": 17.8887,
|
105 |
+
"eval_loss": 1.23811936378479,
|
106 |
+
"eval_runtime": 1519.5015,
|
107 |
+
"eval_samples_per_second": 14.944,
|
108 |
+
"eval_steps_per_second": 0.935,
|
109 |
+
"step": 5000
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 0.48,
|
113 |
+
"learning_rate": 4.8484937632384094e-05,
|
114 |
+
"loss": 1.2634,
|
115 |
+
"step": 5500
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.53,
|
119 |
+
"learning_rate": 4.8337844198634976e-05,
|
120 |
+
"loss": 1.2344,
|
121 |
+
"step": 6000
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.55,
|
125 |
+
"eval_bleu": 3.3835,
|
126 |
+
"eval_gen_len": 17.8323,
|
127 |
+
"eval_loss": 1.1769133806228638,
|
128 |
+
"eval_runtime": 1506.2285,
|
129 |
+
"eval_samples_per_second": 15.075,
|
130 |
+
"eval_steps_per_second": 0.943,
|
131 |
+
"step": 6250
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 0.57,
|
135 |
+
"learning_rate": 4.819075076488586e-05,
|
136 |
+
"loss": 1.2213,
|
137 |
+
"step": 6500
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.62,
|
141 |
+
"learning_rate": 4.804365733113674e-05,
|
142 |
+
"loss": 1.1918,
|
143 |
+
"step": 7000
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.66,
|
147 |
+
"learning_rate": 4.789656389738762e-05,
|
148 |
+
"loss": 1.1778,
|
149 |
+
"step": 7500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.66,
|
153 |
+
"eval_bleu": 3.9511,
|
154 |
+
"eval_gen_len": 17.4892,
|
155 |
+
"eval_loss": 1.1381820440292358,
|
156 |
+
"eval_runtime": 1485.4261,
|
157 |
+
"eval_samples_per_second": 15.287,
|
158 |
+
"eval_steps_per_second": 0.956,
|
159 |
+
"step": 7500
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.7,
|
163 |
+
"learning_rate": 4.7749470463638505e-05,
|
164 |
+
"loss": 1.1651,
|
165 |
+
"step": 8000
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.75,
|
169 |
+
"learning_rate": 4.760237702988939e-05,
|
170 |
+
"loss": 1.1461,
|
171 |
+
"step": 8500
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.77,
|
175 |
+
"eval_bleu": 3.9402,
|
176 |
+
"eval_gen_len": 18.0136,
|
177 |
+
"eval_loss": 1.09383225440979,
|
178 |
+
"eval_runtime": 1503.0162,
|
179 |
+
"eval_samples_per_second": 15.108,
|
180 |
+
"eval_steps_per_second": 0.945,
|
181 |
+
"step": 8750
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.79,
|
185 |
+
"learning_rate": 4.745528359614027e-05,
|
186 |
+
"loss": 1.1341,
|
187 |
+
"step": 9000
|
188 |
+
},
|
189 |
+
{
|
190 |
+
"epoch": 0.84,
|
191 |
+
"learning_rate": 4.730819016239115e-05,
|
192 |
+
"loss": 1.1294,
|
193 |
+
"step": 9500
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.88,
|
197 |
+
"learning_rate": 4.7161096728642035e-05,
|
198 |
+
"loss": 1.1151,
|
199 |
+
"step": 10000
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.88,
|
203 |
+
"eval_bleu": 4.2134,
|
204 |
+
"eval_gen_len": 18.0537,
|
205 |
+
"eval_loss": 1.074916124343872,
|
206 |
+
"eval_runtime": 1564.4468,
|
207 |
+
"eval_samples_per_second": 14.514,
|
208 |
+
"eval_steps_per_second": 0.908,
|
209 |
+
"step": 10000
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.92,
|
213 |
+
"learning_rate": 4.701400329489292e-05,
|
214 |
+
"loss": 1.1102,
|
215 |
+
"step": 10500
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 0.97,
|
219 |
+
"learning_rate": 4.68669098611438e-05,
|
220 |
+
"loss": 1.093,
|
221 |
+
"step": 11000
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.99,
|
225 |
+
"eval_bleu": 3.9587,
|
226 |
+
"eval_gen_len": 17.8715,
|
227 |
+
"eval_loss": 1.0418165922164917,
|
228 |
+
"eval_runtime": 1534.6245,
|
229 |
+
"eval_samples_per_second": 14.796,
|
230 |
+
"eval_steps_per_second": 0.925,
|
231 |
+
"step": 11250
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 1.01,
|
235 |
+
"learning_rate": 4.671981642739469e-05,
|
236 |
+
"loss": 1.084,
|
237 |
+
"step": 11500
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 1.06,
|
241 |
+
"learning_rate": 4.657272299364557e-05,
|
242 |
+
"loss": 1.0641,
|
243 |
+
"step": 12000
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 1.1,
|
247 |
+
"learning_rate": 4.6425629559896446e-05,
|
248 |
+
"loss": 1.0626,
|
249 |
+
"step": 12500
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 1.1,
|
253 |
+
"eval_bleu": 4.6251,
|
254 |
+
"eval_gen_len": 17.9406,
|
255 |
+
"eval_loss": 1.0315195322036743,
|
256 |
+
"eval_runtime": 1499.6187,
|
257 |
+
"eval_samples_per_second": 15.142,
|
258 |
+
"eval_steps_per_second": 0.947,
|
259 |
+
"step": 12500
|
260 |
+
},
|
261 |
+
{
|
262 |
+
"epoch": 1.14,
|
263 |
+
"learning_rate": 4.627853612614733e-05,
|
264 |
+
"loss": 1.0332,
|
265 |
+
"step": 13000
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 1.19,
|
269 |
+
"learning_rate": 4.613144269239821e-05,
|
270 |
+
"loss": 1.0192,
|
271 |
+
"step": 13500
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 1.21,
|
275 |
+
"eval_bleu": 4.9573,
|
276 |
+
"eval_gen_len": 18.1266,
|
277 |
+
"eval_loss": 1.0131869316101074,
|
278 |
+
"eval_runtime": 1514.9755,
|
279 |
+
"eval_samples_per_second": 14.988,
|
280 |
+
"eval_steps_per_second": 0.937,
|
281 |
+
"step": 13750
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 1.23,
|
285 |
+
"learning_rate": 4.598434925864909e-05,
|
286 |
+
"loss": 1.0234,
|
287 |
+
"step": 14000
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 1.28,
|
291 |
+
"learning_rate": 4.5837255824899976e-05,
|
292 |
+
"loss": 1.0062,
|
293 |
+
"step": 14500
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 1.32,
|
297 |
+
"learning_rate": 4.569016239115086e-05,
|
298 |
+
"loss": 0.9957,
|
299 |
+
"step": 15000
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 1.32,
|
303 |
+
"eval_bleu": 4.3068,
|
304 |
+
"eval_gen_len": 18.0925,
|
305 |
+
"eval_loss": 0.9988749623298645,
|
306 |
+
"eval_runtime": 1565.2457,
|
307 |
+
"eval_samples_per_second": 14.507,
|
308 |
+
"eval_steps_per_second": 0.907,
|
309 |
+
"step": 15000
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 1.37,
|
313 |
+
"learning_rate": 4.554306895740174e-05,
|
314 |
+
"loss": 0.9843,
|
315 |
+
"step": 15500
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 1.41,
|
319 |
+
"learning_rate": 4.539597552365263e-05,
|
320 |
+
"loss": 0.9778,
|
321 |
+
"step": 16000
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 1.43,
|
325 |
+
"eval_bleu": 5.0517,
|
326 |
+
"eval_gen_len": 17.8783,
|
327 |
+
"eval_loss": 0.984965980052948,
|
328 |
+
"eval_runtime": 1508.5724,
|
329 |
+
"eval_samples_per_second": 15.052,
|
330 |
+
"eval_steps_per_second": 0.941,
|
331 |
+
"step": 16250
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 1.45,
|
335 |
+
"learning_rate": 4.524888208990351e-05,
|
336 |
+
"loss": 0.961,
|
337 |
+
"step": 16500
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 1.5,
|
341 |
+
"learning_rate": 4.5101788656154394e-05,
|
342 |
+
"loss": 0.9735,
|
343 |
+
"step": 17000
|
344 |
+
},
|
345 |
+
{
|
346 |
+
"epoch": 1.54,
|
347 |
+
"learning_rate": 4.4954695222405276e-05,
|
348 |
+
"loss": 0.9446,
|
349 |
+
"step": 17500
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 1.54,
|
353 |
+
"eval_bleu": 5.0194,
|
354 |
+
"eval_gen_len": 17.9348,
|
355 |
+
"eval_loss": 0.9747512936592102,
|
356 |
+
"eval_runtime": 1574.1886,
|
357 |
+
"eval_samples_per_second": 14.425,
|
358 |
+
"eval_steps_per_second": 0.902,
|
359 |
+
"step": 17500
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 1.59,
|
363 |
+
"learning_rate": 4.480760178865616e-05,
|
364 |
+
"loss": 0.9352,
|
365 |
+
"step": 18000
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 1.63,
|
369 |
+
"learning_rate": 4.466050835490704e-05,
|
370 |
+
"loss": 0.9236,
|
371 |
+
"step": 18500
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 1.65,
|
375 |
+
"eval_bleu": 4.6011,
|
376 |
+
"eval_gen_len": 17.7926,
|
377 |
+
"eval_loss": 0.9619229435920715,
|
378 |
+
"eval_runtime": 1510.4722,
|
379 |
+
"eval_samples_per_second": 15.033,
|
380 |
+
"eval_steps_per_second": 0.94,
|
381 |
+
"step": 18750
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 1.67,
|
385 |
+
"learning_rate": 4.4513414921157917e-05,
|
386 |
+
"loss": 0.9289,
|
387 |
+
"step": 19000
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 1.72,
|
391 |
+
"learning_rate": 4.43663214874088e-05,
|
392 |
+
"loss": 0.9216,
|
393 |
+
"step": 19500
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 1.76,
|
397 |
+
"learning_rate": 4.421922805365969e-05,
|
398 |
+
"loss": 0.9091,
|
399 |
+
"step": 20000
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 1.76,
|
403 |
+
"eval_bleu": 4.6035,
|
404 |
+
"eval_gen_len": 17.9399,
|
405 |
+
"eval_loss": 0.9564162492752075,
|
406 |
+
"eval_runtime": 1530.1826,
|
407 |
+
"eval_samples_per_second": 14.839,
|
408 |
+
"eval_steps_per_second": 0.928,
|
409 |
+
"step": 20000
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 1.81,
|
413 |
+
"learning_rate": 4.407213461991057e-05,
|
414 |
+
"loss": 0.9333,
|
415 |
+
"step": 20500
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 1.85,
|
419 |
+
"learning_rate": 4.392504118616145e-05,
|
420 |
+
"loss": 0.9072,
|
421 |
+
"step": 21000
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"epoch": 1.87,
|
425 |
+
"eval_bleu": 4.8313,
|
426 |
+
"eval_gen_len": 17.6221,
|
427 |
+
"eval_loss": 0.9533364176750183,
|
428 |
+
"eval_runtime": 1475.3262,
|
429 |
+
"eval_samples_per_second": 15.391,
|
430 |
+
"eval_steps_per_second": 0.962,
|
431 |
+
"step": 21250
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 1.89,
|
435 |
+
"learning_rate": 4.3777947752412335e-05,
|
436 |
+
"loss": 0.8896,
|
437 |
+
"step": 21500
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 1.94,
|
441 |
+
"learning_rate": 4.363085431866322e-05,
|
442 |
+
"loss": 0.8945,
|
443 |
+
"step": 22000
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 1.98,
|
447 |
+
"learning_rate": 4.34837608849141e-05,
|
448 |
+
"loss": 0.8758,
|
449 |
+
"step": 22500
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 1.98,
|
453 |
+
"eval_bleu": 5.2707,
|
454 |
+
"eval_gen_len": 17.5851,
|
455 |
+
"eval_loss": 0.9421375393867493,
|
456 |
+
"eval_runtime": 1516.2122,
|
457 |
+
"eval_samples_per_second": 14.976,
|
458 |
+
"eval_steps_per_second": 0.937,
|
459 |
+
"step": 22500
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 2.03,
|
463 |
+
"learning_rate": 4.333666745116498e-05,
|
464 |
+
"loss": 0.8723,
|
465 |
+
"step": 23000
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 2.07,
|
469 |
+
"learning_rate": 4.3189574017415864e-05,
|
470 |
+
"loss": 0.8539,
|
471 |
+
"step": 23500
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 2.09,
|
475 |
+
"eval_bleu": 5.2661,
|
476 |
+
"eval_gen_len": 17.821,
|
477 |
+
"eval_loss": 0.9304332137107849,
|
478 |
+
"eval_runtime": 1492.9401,
|
479 |
+
"eval_samples_per_second": 15.21,
|
480 |
+
"eval_steps_per_second": 0.951,
|
481 |
+
"step": 23750
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 2.11,
|
485 |
+
"learning_rate": 4.3042480583666747e-05,
|
486 |
+
"loss": 0.8461,
|
487 |
+
"step": 24000
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 2.16,
|
491 |
+
"learning_rate": 4.289538714991763e-05,
|
492 |
+
"loss": 0.842,
|
493 |
+
"step": 24500
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 2.2,
|
497 |
+
"learning_rate": 4.274829371616851e-05,
|
498 |
+
"loss": 0.8575,
|
499 |
+
"step": 25000
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 2.2,
|
503 |
+
"eval_bleu": 4.9143,
|
504 |
+
"eval_gen_len": 17.8879,
|
505 |
+
"eval_loss": 0.9329252243041992,
|
506 |
+
"eval_runtime": 1560.9154,
|
507 |
+
"eval_samples_per_second": 14.547,
|
508 |
+
"eval_steps_per_second": 0.91,
|
509 |
+
"step": 25000
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 2.25,
|
513 |
+
"learning_rate": 4.2601200282419394e-05,
|
514 |
+
"loss": 0.8424,
|
515 |
+
"step": 25500
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 2.29,
|
519 |
+
"learning_rate": 4.2454106848670276e-05,
|
520 |
+
"loss": 0.8314,
|
521 |
+
"step": 26000
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 2.31,
|
525 |
+
"eval_bleu": 5.106,
|
526 |
+
"eval_gen_len": 18.0037,
|
527 |
+
"eval_loss": 0.9262479543685913,
|
528 |
+
"eval_runtime": 1520.8802,
|
529 |
+
"eval_samples_per_second": 14.93,
|
530 |
+
"eval_steps_per_second": 0.934,
|
531 |
+
"step": 26250
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 2.33,
|
535 |
+
"learning_rate": 4.230701341492116e-05,
|
536 |
+
"loss": 0.8172,
|
537 |
+
"step": 26500
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 2.38,
|
541 |
+
"learning_rate": 4.215991998117204e-05,
|
542 |
+
"loss": 0.8219,
|
543 |
+
"step": 27000
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 2.42,
|
547 |
+
"learning_rate": 4.201282654742292e-05,
|
548 |
+
"loss": 0.8248,
|
549 |
+
"step": 27500
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 2.42,
|
553 |
+
"eval_bleu": 5.3073,
|
554 |
+
"eval_gen_len": 17.6632,
|
555 |
+
"eval_loss": 0.9241103529930115,
|
556 |
+
"eval_runtime": 1501.7783,
|
557 |
+
"eval_samples_per_second": 15.12,
|
558 |
+
"eval_steps_per_second": 0.946,
|
559 |
+
"step": 27500
|
560 |
+
},
|
561 |
+
{
|
562 |
+
"epoch": 2.47,
|
563 |
+
"learning_rate": 4.1865733113673805e-05,
|
564 |
+
"loss": 0.8046,
|
565 |
+
"step": 28000
|
566 |
+
},
|
567 |
+
{
|
568 |
+
"epoch": 2.51,
|
569 |
+
"learning_rate": 4.1718639679924694e-05,
|
570 |
+
"loss": 0.8151,
|
571 |
+
"step": 28500
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 2.53,
|
575 |
+
"eval_bleu": 5.5675,
|
576 |
+
"eval_gen_len": 17.7676,
|
577 |
+
"eval_loss": 0.9301652312278748,
|
578 |
+
"eval_runtime": 1487.7016,
|
579 |
+
"eval_samples_per_second": 15.263,
|
580 |
+
"eval_steps_per_second": 0.954,
|
581 |
+
"step": 28750
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 2.55,
|
585 |
+
"learning_rate": 4.157154624617558e-05,
|
586 |
+
"loss": 0.8019,
|
587 |
+
"step": 29000
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 2.6,
|
591 |
+
"learning_rate": 4.142445281242646e-05,
|
592 |
+
"loss": 0.8423,
|
593 |
+
"step": 29500
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 2.64,
|
597 |
+
"learning_rate": 4.127735937867734e-05,
|
598 |
+
"loss": 0.8093,
|
599 |
+
"step": 30000
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 2.64,
|
603 |
+
"eval_bleu": 6.2644,
|
604 |
+
"eval_gen_len": 17.8475,
|
605 |
+
"eval_loss": 0.9149118065834045,
|
606 |
+
"eval_runtime": 1510.1876,
|
607 |
+
"eval_samples_per_second": 15.036,
|
608 |
+
"eval_steps_per_second": 0.94,
|
609 |
+
"step": 30000
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 2.69,
|
613 |
+
"learning_rate": 4.113026594492822e-05,
|
614 |
+
"loss": 0.7833,
|
615 |
+
"step": 30500
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 2.73,
|
619 |
+
"learning_rate": 4.09831725111791e-05,
|
620 |
+
"loss": 0.7691,
|
621 |
+
"step": 31000
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 2.75,
|
625 |
+
"eval_bleu": 6.6682,
|
626 |
+
"eval_gen_len": 17.7685,
|
627 |
+
"eval_loss": 0.8987509608268738,
|
628 |
+
"eval_runtime": 1501.6272,
|
629 |
+
"eval_samples_per_second": 15.122,
|
630 |
+
"eval_steps_per_second": 0.946,
|
631 |
+
"step": 31250
|
632 |
+
},
|
633 |
+
{
|
634 |
+
"epoch": 2.77,
|
635 |
+
"learning_rate": 4.083607907742998e-05,
|
636 |
+
"loss": 0.7673,
|
637 |
+
"step": 31500
|
638 |
+
},
|
639 |
+
{
|
640 |
+
"epoch": 2.82,
|
641 |
+
"learning_rate": 4.0688985643680864e-05,
|
642 |
+
"loss": 0.8064,
|
643 |
+
"step": 32000
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 2.86,
|
647 |
+
"learning_rate": 4.054189220993175e-05,
|
648 |
+
"loss": 0.771,
|
649 |
+
"step": 32500
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 2.86,
|
653 |
+
"eval_bleu": 5.7856,
|
654 |
+
"eval_gen_len": 17.8678,
|
655 |
+
"eval_loss": 0.9189176559448242,
|
656 |
+
"eval_runtime": 1503.2313,
|
657 |
+
"eval_samples_per_second": 15.105,
|
658 |
+
"eval_steps_per_second": 0.945,
|
659 |
+
"step": 32500
|
660 |
+
},
|
661 |
+
{
|
662 |
+
"epoch": 2.91,
|
663 |
+
"learning_rate": 4.0394798776182635e-05,
|
664 |
+
"loss": 0.7652,
|
665 |
+
"step": 33000
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"epoch": 2.95,
|
669 |
+
"learning_rate": 4.024770534243352e-05,
|
670 |
+
"loss": 0.7658,
|
671 |
+
"step": 33500
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 2.97,
|
675 |
+
"eval_bleu": 6.2468,
|
676 |
+
"eval_gen_len": 17.7313,
|
677 |
+
"eval_loss": 0.9175418019294739,
|
678 |
+
"eval_runtime": 1487.9561,
|
679 |
+
"eval_samples_per_second": 15.261,
|
680 |
+
"eval_steps_per_second": 0.954,
|
681 |
+
"step": 33750
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 2.99,
|
685 |
+
"learning_rate": 4.01006119086844e-05,
|
686 |
+
"loss": 0.7568,
|
687 |
+
"step": 34000
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 3.04,
|
691 |
+
"learning_rate": 3.995351847493528e-05,
|
692 |
+
"loss": 0.7913,
|
693 |
+
"step": 34500
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 3.08,
|
697 |
+
"learning_rate": 3.9806425041186165e-05,
|
698 |
+
"loss": 0.7914,
|
699 |
+
"step": 35000
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 3.08,
|
703 |
+
"eval_bleu": 5.5525,
|
704 |
+
"eval_gen_len": 17.7627,
|
705 |
+
"eval_loss": 0.9019802808761597,
|
706 |
+
"eval_runtime": 1501.9062,
|
707 |
+
"eval_samples_per_second": 15.119,
|
708 |
+
"eval_steps_per_second": 0.945,
|
709 |
+
"step": 35000
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 3.13,
|
713 |
+
"learning_rate": 3.965933160743705e-05,
|
714 |
+
"loss": 0.7333,
|
715 |
+
"step": 35500
|
716 |
+
},
|
717 |
+
{
|
718 |
+
"epoch": 3.17,
|
719 |
+
"learning_rate": 3.951223817368793e-05,
|
720 |
+
"loss": 0.7264,
|
721 |
+
"step": 36000
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 3.19,
|
725 |
+
"eval_bleu": 6.2055,
|
726 |
+
"eval_gen_len": 17.7662,
|
727 |
+
"eval_loss": 0.9046412110328674,
|
728 |
+
"eval_runtime": 1496.9385,
|
729 |
+
"eval_samples_per_second": 15.169,
|
730 |
+
"eval_steps_per_second": 0.949,
|
731 |
+
"step": 36250
|
732 |
+
}
|
733 |
+
],
|
734 |
+
"logging_steps": 500,
|
735 |
+
"max_steps": 170310,
|
736 |
+
"num_train_epochs": 15,
|
737 |
+
"save_steps": 1250,
|
738 |
+
"total_flos": 1.257073961708028e+18,
|
739 |
+
"trial_name": null,
|
740 |
+
"trial_params": null
|
741 |
+
}
|
checkpoint-36250/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c014122aea94a2b193fe492a2512d39e6992ce344469c697d16d7a534625de8e
|
3 |
+
size 4728
|
config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "relu",
|
6 |
+
"add_bias_logits": false,
|
7 |
+
"add_final_layer_norm": true,
|
8 |
+
"architectures": [
|
9 |
+
"MBartForConditionalGeneration"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.0,
|
12 |
+
"bos_token_id": 0,
|
13 |
+
"classif_dropout": 0.0,
|
14 |
+
"classifier_dropout": 0.0,
|
15 |
+
"d_model": 1024,
|
16 |
+
"decoder_attention_heads": 16,
|
17 |
+
"decoder_ffn_dim": 4096,
|
18 |
+
"decoder_layerdrop": 0.0,
|
19 |
+
"decoder_layers": 12,
|
20 |
+
"decoder_start_token_id": 2,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"early_stopping": true,
|
23 |
+
"encoder_attention_heads": 16,
|
24 |
+
"encoder_ffn_dim": 4096,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 12,
|
27 |
+
"eos_token_id": 2,
|
28 |
+
"forced_bos_token_id": 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": "4.34.1",
|
57 |
+
"use_cache": true,
|
58 |
+
"vocab_size": 250054
|
59 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.19,
|
3 |
+
"eval_bleu": 6.7577,
|
4 |
+
"eval_gen_len": 17.8104,
|
5 |
+
"eval_loss": 0.8987509608268738,
|
6 |
+
"eval_runtime": 1309.9044,
|
7 |
+
"eval_samples": 22707,
|
8 |
+
"eval_samples_per_second": 17.335,
|
9 |
+
"eval_steps_per_second": 1.084
|
10 |
+
}
|