End of training
Browse files- README.md +96 -0
- config.json +32 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +5 -0
- spiece.model +3 -0
- tokenizer_config.json +113 -0
- trainer_state.json +2000 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: cointegrated/rut5-small
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: text-normalization-ru-new
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# text-normalization-ru-new
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [cointegrated/rut5-small](https://huggingface.co/cointegrated/rut5-small) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.0442
|
| 19 |
+
- Mean Distance: 0
|
| 20 |
+
- Max Distance: 25
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 0.001
|
| 40 |
+
- train_batch_size: 15
|
| 41 |
+
- eval_batch_size: 15
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 46 |
+
- num_epochs: 30
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Max Distance | Mean Distance |
|
| 51 |
+
|:-------------:|:-----:|:------:|:---------------:|:------------:|:-------------:|
|
| 52 |
+
| 0.199 | 1.0 | 11526 | 0.8173 | 167 | 17 |
|
| 53 |
+
| 0.1286 | 2.0 | 23052 | 0.5453 | 158 | 14 |
|
| 54 |
+
| 0.0891 | 3.0 | 34578 | 0.3629 | 122 | 10 |
|
| 55 |
+
| 0.0711 | 4.0 | 46104 | 0.4011 | 114 | 12 |
|
| 56 |
+
| 0.0566 | 5.0 | 57630 | 0.2997 | 100 | 7 |
|
| 57 |
+
| 0.0402 | 6.0 | 69156 | 0.1552 | 75 | 4 |
|
| 58 |
+
| 0.0348 | 7.0 | 80682 | 0.1513 | 79 | 3 |
|
| 59 |
+
| 0.0302 | 8.0 | 92208 | 0.1452 | 76 | 3 |
|
| 60 |
+
| 0.0223 | 9.0 | 103734 | 0.0866 | 76 | 1 |
|
| 61 |
+
| 0.0202 | 10.0 | 115260 | 0.1091 | 71 | 2 |
|
| 62 |
+
| 0.0175 | 11.0 | 126786 | 0.0655 | 66 | 1 |
|
| 63 |
+
| 0.014 | 12.0 | 138312 | 0.0474 | 44 | 0 |
|
| 64 |
+
| 0.0122 | 13.0 | 149838 | 0.0515 | 42 | 0 |
|
| 65 |
+
| 0.0117 | 14.0 | 161364 | 0.0479 | 30 | 0 |
|
| 66 |
+
| 0.0093 | 15.0 | 172890 | 0.0565 | 56 | 0 |
|
| 67 |
+
| 0.0085 | 16.0 | 184416 | 0.0472 | 34 | 0 |
|
| 68 |
+
| 0.0075 | 17.0 | 195942 | 0.0420 | 28 | 0 |
|
| 69 |
+
| 0.0059 | 18.0 | 207468 | 0.0415 | 32 | 0 |
|
| 70 |
+
| 0.0054 | 19.0 | 218994 | 0.0406 | 28 | 0 |
|
| 71 |
+
| 0.0046 | 20.0 | 230520 | 0.0393 | 24 | 0 |
|
| 72 |
+
| 0.004 | 21.0 | 242046 | 0.0417 | 24 | 0 |
|
| 73 |
+
| 0.0034 | 22.0 | 253572 | 0.0403 | 18 | 0 |
|
| 74 |
+
| 0.0029 | 23.0 | 265098 | 0.0422 | 21 | 0 |
|
| 75 |
+
| 0.0024 | 24.0 | 276624 | 0.0410 | 21 | 0 |
|
| 76 |
+
| 0.002 | 25.0 | 288150 | 0.0435 | 15 | 0 |
|
| 77 |
+
| 0.0016 | 26.0 | 299676 | 0.0452 | 15 | 0 |
|
| 78 |
+
| 0.0013 | 27.0 | 311202 | 0.0414 | 14 | 0 |
|
| 79 |
+
| 0.0012 | 28.0 | 322728 | 0.0439 | 14 | 0 |
|
| 80 |
+
| 0.001 | 29.0 | 334254 | 0.0444 | 15 | 0 |
|
| 81 |
+
| 0.0026 | 30.0 | 345780 | 0.0427 | 19 | 0 |
|
| 82 |
+
| 0.0077 | 24.0 | 368808 | 0.0495 | 27 | 0 |
|
| 83 |
+
| 0.0083 | 25.0 | 384175 | 0.0446 | 37 | 0 |
|
| 84 |
+
| 0.0078 | 26.0 | 399542 | 0.0481 | 47 | 0 |
|
| 85 |
+
| 0.006 | 27.0 | 414909 | 0.0424 | 37 | 0 |
|
| 86 |
+
| 0.0056 | 28.0 | 430276 | 0.0439 | 22 | 0 |
|
| 87 |
+
| 0.0054 | 29.0 | 445643 | 0.0481 | 23 | 0 |
|
| 88 |
+
| 0.004 | 30.0 | 461010 | 0.0442 | 0 | 25 |
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
### Framework versions
|
| 92 |
+
|
| 93 |
+
- Transformers 4.32.1
|
| 94 |
+
- Pytorch 2.0.1+cu117
|
| 95 |
+
- Datasets 2.14.4
|
| 96 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "cointegrated/rut5-small",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 1024,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 512,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"num_decoder_layers": 8,
|
| 21 |
+
"num_heads": 6,
|
| 22 |
+
"num_layers": 8,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"relative_attention_max_distance": 128,
|
| 25 |
+
"relative_attention_num_buckets": 32,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"tokenizer_class": "T5Tokenizer",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.32.1",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 20100
|
| 32 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.32.1"
|
| 7 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1af9c44d78cc87dce6c9af177a92980e3657aa89417f862a6decf4575d013140
|
| 3 |
+
size 258643461
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": "</s>",
|
| 3 |
+
"pad_token": "<pad>",
|
| 4 |
+
"unk_token": "<unk>"
|
| 5 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6afde64def093a9d493d1f4254768c2e842ed45bcc9c184233f245cb29d2a31
|
| 3 |
+
size 639963
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"clean_up_tokenization_spaces": true,
|
| 105 |
+
"eos_token": "</s>",
|
| 106 |
+
"extra_ids": 100,
|
| 107 |
+
"legacy": true,
|
| 108 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 109 |
+
"pad_token": "<pad>",
|
| 110 |
+
"sp_model_kwargs": {},
|
| 111 |
+
"tokenizer_class": "T5Tokenizer",
|
| 112 |
+
"unk_token": "<unk>"
|
| 113 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2000 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 30.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 461010,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 2.8920122621319915e-08,
|
| 14 |
+
"loss": 14.3504,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.15,
|
| 19 |
+
"learning_rate": 5.000289201226213e-05,
|
| 20 |
+
"loss": 2.1001,
|
| 21 |
+
"step": 1729
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.3,
|
| 25 |
+
"learning_rate": 0.00010000578402452426,
|
| 26 |
+
"loss": 0.3756,
|
| 27 |
+
"step": 3458
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.45,
|
| 31 |
+
"learning_rate": 0.0001500086760367864,
|
| 32 |
+
"loss": 0.2527,
|
| 33 |
+
"step": 5187
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.6,
|
| 37 |
+
"learning_rate": 0.00020001156804904852,
|
| 38 |
+
"loss": 0.2076,
|
| 39 |
+
"step": 6916
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.75,
|
| 43 |
+
"learning_rate": 0.00025001446006131067,
|
| 44 |
+
"loss": 0.1864,
|
| 45 |
+
"step": 8645
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.9,
|
| 49 |
+
"learning_rate": 0.0003000173520735728,
|
| 50 |
+
"loss": 0.199,
|
| 51 |
+
"step": 10374
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.0,
|
| 55 |
+
"eval_loss": 0.8173184990882874,
|
| 56 |
+
"eval_max_distance": 167,
|
| 57 |
+
"eval_mean_distance": 17,
|
| 58 |
+
"eval_runtime": 64.0638,
|
| 59 |
+
"eval_samples_per_second": 15.609,
|
| 60 |
+
"eval_steps_per_second": 0.78,
|
| 61 |
+
"step": 11526
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.05,
|
| 65 |
+
"learning_rate": 0.0003500202440858349,
|
| 66 |
+
"loss": 0.2481,
|
| 67 |
+
"step": 12103
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 1.2,
|
| 71 |
+
"learning_rate": 0.00040002313609809704,
|
| 72 |
+
"loss": 0.1244,
|
| 73 |
+
"step": 13832
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 1.35,
|
| 77 |
+
"learning_rate": 0.0004500260281103592,
|
| 78 |
+
"loss": 0.1055,
|
| 79 |
+
"step": 15561
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.5,
|
| 83 |
+
"learning_rate": 0.0005000289201226213,
|
| 84 |
+
"loss": 0.102,
|
| 85 |
+
"step": 17290
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 1.65,
|
| 89 |
+
"learning_rate": 0.0005500318121348835,
|
| 90 |
+
"loss": 0.102,
|
| 91 |
+
"step": 19019
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 1.8,
|
| 95 |
+
"learning_rate": 0.0006000347041471456,
|
| 96 |
+
"loss": 0.1083,
|
| 97 |
+
"step": 20748
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 1.95,
|
| 101 |
+
"learning_rate": 0.0006500375961594078,
|
| 102 |
+
"loss": 0.1286,
|
| 103 |
+
"step": 22477
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 2.0,
|
| 107 |
+
"eval_loss": 0.5452634692192078,
|
| 108 |
+
"eval_max_distance": 158,
|
| 109 |
+
"eval_mean_distance": 14,
|
| 110 |
+
"eval_runtime": 30.4268,
|
| 111 |
+
"eval_samples_per_second": 32.866,
|
| 112 |
+
"eval_steps_per_second": 1.643,
|
| 113 |
+
"step": 23052
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 2.1,
|
| 117 |
+
"learning_rate": 0.0007000404881716698,
|
| 118 |
+
"loss": 0.1449,
|
| 119 |
+
"step": 24206
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 2.25,
|
| 123 |
+
"learning_rate": 0.000750043380183932,
|
| 124 |
+
"loss": 0.0747,
|
| 125 |
+
"step": 25935
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 2.4,
|
| 129 |
+
"learning_rate": 0.0008000462721961941,
|
| 130 |
+
"loss": 0.0744,
|
| 131 |
+
"step": 27664
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 2.55,
|
| 135 |
+
"learning_rate": 0.0008500491642084563,
|
| 136 |
+
"loss": 0.0742,
|
| 137 |
+
"step": 29393
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 2.7,
|
| 141 |
+
"learning_rate": 0.0009000520562207184,
|
| 142 |
+
"loss": 0.0792,
|
| 143 |
+
"step": 31122
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 2.85,
|
| 147 |
+
"learning_rate": 0.0009500549482329805,
|
| 148 |
+
"loss": 0.0891,
|
| 149 |
+
"step": 32851
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 3.0,
|
| 153 |
+
"eval_loss": 0.3629104495048523,
|
| 154 |
+
"eval_max_distance": 122,
|
| 155 |
+
"eval_mean_distance": 10,
|
| 156 |
+
"eval_runtime": 35.1149,
|
| 157 |
+
"eval_samples_per_second": 28.478,
|
| 158 |
+
"eval_steps_per_second": 1.424,
|
| 159 |
+
"step": 34578
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.0,
|
| 163 |
+
"learning_rate": 0.0009999935733060843,
|
| 164 |
+
"loss": 0.1079,
|
| 165 |
+
"step": 34580
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 3.15,
|
| 169 |
+
"learning_rate": 0.000994437696415833,
|
| 170 |
+
"loss": 0.0962,
|
| 171 |
+
"step": 36309
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 3.3,
|
| 175 |
+
"learning_rate": 0.0009888818195255813,
|
| 176 |
+
"loss": 0.059,
|
| 177 |
+
"step": 38038
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 3.45,
|
| 181 |
+
"learning_rate": 0.0009833259426353302,
|
| 182 |
+
"loss": 0.0576,
|
| 183 |
+
"step": 39767
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 3.6,
|
| 187 |
+
"learning_rate": 0.0009777700657450789,
|
| 188 |
+
"loss": 0.058,
|
| 189 |
+
"step": 41496
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 3.75,
|
| 193 |
+
"learning_rate": 0.0009722141888548275,
|
| 194 |
+
"loss": 0.0611,
|
| 195 |
+
"step": 43225
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 3.9,
|
| 199 |
+
"learning_rate": 0.0009666583119645761,
|
| 200 |
+
"loss": 0.0711,
|
| 201 |
+
"step": 44954
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 4.0,
|
| 205 |
+
"eval_loss": 0.4011004865169525,
|
| 206 |
+
"eval_max_distance": 114,
|
| 207 |
+
"eval_mean_distance": 12,
|
| 208 |
+
"eval_runtime": 24.9859,
|
| 209 |
+
"eval_samples_per_second": 40.022,
|
| 210 |
+
"eval_steps_per_second": 2.001,
|
| 211 |
+
"step": 46104
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 4.05,
|
| 215 |
+
"learning_rate": 0.0009611024350743247,
|
| 216 |
+
"loss": 0.0991,
|
| 217 |
+
"step": 46683
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 4.2,
|
| 221 |
+
"learning_rate": 0.0009555465581840734,
|
| 222 |
+
"loss": 0.0481,
|
| 223 |
+
"step": 48412
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 4.35,
|
| 227 |
+
"learning_rate": 0.0009499906812938221,
|
| 228 |
+
"loss": 0.044,
|
| 229 |
+
"step": 50141
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 4.5,
|
| 233 |
+
"learning_rate": 0.0009444348044035706,
|
| 234 |
+
"loss": 0.0435,
|
| 235 |
+
"step": 51870
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 4.65,
|
| 239 |
+
"learning_rate": 0.0009388789275133194,
|
| 240 |
+
"loss": 0.0454,
|
| 241 |
+
"step": 53599
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 4.8,
|
| 245 |
+
"learning_rate": 0.000933323050623068,
|
| 246 |
+
"loss": 0.0483,
|
| 247 |
+
"step": 55328
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 4.95,
|
| 251 |
+
"learning_rate": 0.0009277671737328166,
|
| 252 |
+
"loss": 0.0566,
|
| 253 |
+
"step": 57057
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 5.0,
|
| 257 |
+
"eval_loss": 0.29974234104156494,
|
| 258 |
+
"eval_max_distance": 100,
|
| 259 |
+
"eval_mean_distance": 7,
|
| 260 |
+
"eval_runtime": 25.609,
|
| 261 |
+
"eval_samples_per_second": 39.049,
|
| 262 |
+
"eval_steps_per_second": 1.952,
|
| 263 |
+
"step": 57630
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 5.1,
|
| 267 |
+
"learning_rate": 0.0009222112968425653,
|
| 268 |
+
"loss": 0.0724,
|
| 269 |
+
"step": 58786
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 5.25,
|
| 273 |
+
"learning_rate": 0.000916655419952314,
|
| 274 |
+
"loss": 0.0364,
|
| 275 |
+
"step": 60515
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 5.4,
|
| 279 |
+
"learning_rate": 0.0009110995430620625,
|
| 280 |
+
"loss": 0.035,
|
| 281 |
+
"step": 62244
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 5.55,
|
| 285 |
+
"learning_rate": 0.0009055436661718113,
|
| 286 |
+
"loss": 0.0353,
|
| 287 |
+
"step": 63973
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 5.7,
|
| 291 |
+
"learning_rate": 0.0008999877892815599,
|
| 292 |
+
"loss": 0.0364,
|
| 293 |
+
"step": 65702
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 5.85,
|
| 297 |
+
"learning_rate": 0.0008944319123913086,
|
| 298 |
+
"loss": 0.0402,
|
| 299 |
+
"step": 67431
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 6.0,
|
| 303 |
+
"eval_loss": 0.15522713959217072,
|
| 304 |
+
"eval_max_distance": 75,
|
| 305 |
+
"eval_mean_distance": 4,
|
| 306 |
+
"eval_runtime": 24.8618,
|
| 307 |
+
"eval_samples_per_second": 40.222,
|
| 308 |
+
"eval_steps_per_second": 2.011,
|
| 309 |
+
"step": 69156
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 6.0,
|
| 313 |
+
"learning_rate": 0.0008888760355010572,
|
| 314 |
+
"loss": 0.0506,
|
| 315 |
+
"step": 69160
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 6.15,
|
| 319 |
+
"learning_rate": 0.0008833201586108059,
|
| 320 |
+
"loss": 0.0514,
|
| 321 |
+
"step": 70889
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 6.3,
|
| 325 |
+
"learning_rate": 0.0008777642817205546,
|
| 326 |
+
"loss": 0.0298,
|
| 327 |
+
"step": 72618
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 6.45,
|
| 331 |
+
"learning_rate": 0.0008722084048303031,
|
| 332 |
+
"loss": 0.0287,
|
| 333 |
+
"step": 74347
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 6.6,
|
| 337 |
+
"learning_rate": 0.0008666525279400518,
|
| 338 |
+
"loss": 0.0289,
|
| 339 |
+
"step": 76076
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 6.75,
|
| 343 |
+
"learning_rate": 0.0008610966510498005,
|
| 344 |
+
"loss": 0.0303,
|
| 345 |
+
"step": 77805
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 6.9,
|
| 349 |
+
"learning_rate": 0.0008555407741595491,
|
| 350 |
+
"loss": 0.0348,
|
| 351 |
+
"step": 79534
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 7.0,
|
| 355 |
+
"eval_loss": 0.15130603313446045,
|
| 356 |
+
"eval_max_distance": 79,
|
| 357 |
+
"eval_mean_distance": 3,
|
| 358 |
+
"eval_runtime": 25.5455,
|
| 359 |
+
"eval_samples_per_second": 39.146,
|
| 360 |
+
"eval_steps_per_second": 1.957,
|
| 361 |
+
"step": 80682
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 7.05,
|
| 365 |
+
"learning_rate": 0.0008499848972692977,
|
| 366 |
+
"loss": 0.0527,
|
| 367 |
+
"step": 81263
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 7.2,
|
| 371 |
+
"learning_rate": 0.0008444290203790465,
|
| 372 |
+
"loss": 0.0293,
|
| 373 |
+
"step": 82992
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 7.35,
|
| 377 |
+
"learning_rate": 0.000838873143488795,
|
| 378 |
+
"loss": 0.0247,
|
| 379 |
+
"step": 84721
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 7.5,
|
| 383 |
+
"learning_rate": 0.0008333172665985437,
|
| 384 |
+
"loss": 0.024,
|
| 385 |
+
"step": 86450
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 7.65,
|
| 389 |
+
"learning_rate": 0.0008277613897082924,
|
| 390 |
+
"loss": 0.0243,
|
| 391 |
+
"step": 88179
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 7.8,
|
| 395 |
+
"learning_rate": 0.000822205512818041,
|
| 396 |
+
"loss": 0.0263,
|
| 397 |
+
"step": 89908
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 7.95,
|
| 401 |
+
"learning_rate": 0.0008166496359277897,
|
| 402 |
+
"loss": 0.0302,
|
| 403 |
+
"step": 91637
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 8.0,
|
| 407 |
+
"eval_loss": 0.14522188901901245,
|
| 408 |
+
"eval_max_distance": 76,
|
| 409 |
+
"eval_mean_distance": 3,
|
| 410 |
+
"eval_runtime": 25.6271,
|
| 411 |
+
"eval_samples_per_second": 39.021,
|
| 412 |
+
"eval_steps_per_second": 1.951,
|
| 413 |
+
"step": 92208
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 8.1,
|
| 417 |
+
"learning_rate": 0.0008110937590375384,
|
| 418 |
+
"loss": 0.0445,
|
| 419 |
+
"step": 93366
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 8.25,
|
| 423 |
+
"learning_rate": 0.0008055378821472869,
|
| 424 |
+
"loss": 0.0229,
|
| 425 |
+
"step": 95095
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 8.4,
|
| 429 |
+
"learning_rate": 0.0007999820052570357,
|
| 430 |
+
"loss": 0.0207,
|
| 431 |
+
"step": 96824
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 8.55,
|
| 435 |
+
"learning_rate": 0.0007944261283667843,
|
| 436 |
+
"loss": 0.0203,
|
| 437 |
+
"step": 98553
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 8.7,
|
| 441 |
+
"learning_rate": 0.000788870251476533,
|
| 442 |
+
"loss": 0.021,
|
| 443 |
+
"step": 100282
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 8.85,
|
| 447 |
+
"learning_rate": 0.0007833143745862816,
|
| 448 |
+
"loss": 0.0223,
|
| 449 |
+
"step": 102011
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 9.0,
|
| 453 |
+
"eval_loss": 0.08658243715763092,
|
| 454 |
+
"eval_max_distance": 76,
|
| 455 |
+
"eval_mean_distance": 1,
|
| 456 |
+
"eval_runtime": 23.498,
|
| 457 |
+
"eval_samples_per_second": 42.557,
|
| 458 |
+
"eval_steps_per_second": 2.128,
|
| 459 |
+
"step": 103734
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 9.0,
|
| 463 |
+
"learning_rate": 0.0007777584976960303,
|
| 464 |
+
"loss": 0.0284,
|
| 465 |
+
"step": 103740
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 9.15,
|
| 469 |
+
"learning_rate": 0.0007722026208057789,
|
| 470 |
+
"loss": 0.034,
|
| 471 |
+
"step": 105469
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 9.3,
|
| 475 |
+
"learning_rate": 0.0007666467439155275,
|
| 476 |
+
"loss": 0.0193,
|
| 477 |
+
"step": 107198
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 9.45,
|
| 481 |
+
"learning_rate": 0.0007610908670252762,
|
| 482 |
+
"loss": 0.0175,
|
| 483 |
+
"step": 108927
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 9.6,
|
| 487 |
+
"learning_rate": 0.0007555349901350248,
|
| 488 |
+
"loss": 0.0172,
|
| 489 |
+
"step": 110656
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 9.75,
|
| 493 |
+
"learning_rate": 0.0007499791132447735,
|
| 494 |
+
"loss": 0.018,
|
| 495 |
+
"step": 112385
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 9.9,
|
| 499 |
+
"learning_rate": 0.0007444232363545221,
|
| 500 |
+
"loss": 0.0202,
|
| 501 |
+
"step": 114114
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 10.0,
|
| 505 |
+
"eval_loss": 0.10908353328704834,
|
| 506 |
+
"eval_max_distance": 71,
|
| 507 |
+
"eval_mean_distance": 2,
|
| 508 |
+
"eval_runtime": 25.0909,
|
| 509 |
+
"eval_samples_per_second": 39.855,
|
| 510 |
+
"eval_steps_per_second": 1.993,
|
| 511 |
+
"step": 115260
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 10.05,
|
| 515 |
+
"learning_rate": 0.0007388673594642709,
|
| 516 |
+
"loss": 0.0342,
|
| 517 |
+
"step": 115843
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 10.2,
|
| 521 |
+
"learning_rate": 0.0007333114825740194,
|
| 522 |
+
"loss": 0.0202,
|
| 523 |
+
"step": 117572
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 10.35,
|
| 527 |
+
"learning_rate": 0.0007277556056837681,
|
| 528 |
+
"loss": 0.0159,
|
| 529 |
+
"step": 119301
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 10.5,
|
| 533 |
+
"learning_rate": 0.0007221997287935168,
|
| 534 |
+
"loss": 0.0149,
|
| 535 |
+
"step": 121030
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 10.65,
|
| 539 |
+
"learning_rate": 0.0007166438519032654,
|
| 540 |
+
"loss": 0.015,
|
| 541 |
+
"step": 122759
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 10.8,
|
| 545 |
+
"learning_rate": 0.000711087975013014,
|
| 546 |
+
"loss": 0.0155,
|
| 547 |
+
"step": 124488
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 10.95,
|
| 551 |
+
"learning_rate": 0.0007055320981227628,
|
| 552 |
+
"loss": 0.0175,
|
| 553 |
+
"step": 126217
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 11.0,
|
| 557 |
+
"eval_loss": 0.06553788483142853,
|
| 558 |
+
"eval_max_distance": 66,
|
| 559 |
+
"eval_mean_distance": 1,
|
| 560 |
+
"eval_runtime": 22.988,
|
| 561 |
+
"eval_samples_per_second": 43.501,
|
| 562 |
+
"eval_steps_per_second": 2.175,
|
| 563 |
+
"step": 126786
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 11.1,
|
| 567 |
+
"learning_rate": 0.0006999762212325114,
|
| 568 |
+
"loss": 0.0305,
|
| 569 |
+
"step": 127946
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 11.25,
|
| 573 |
+
"learning_rate": 0.00069442034434226,
|
| 574 |
+
"loss": 0.0157,
|
| 575 |
+
"step": 129675
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 11.4,
|
| 579 |
+
"learning_rate": 0.0006888644674520087,
|
| 580 |
+
"loss": 0.0134,
|
| 581 |
+
"step": 131404
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 11.55,
|
| 585 |
+
"learning_rate": 0.0006833085905617574,
|
| 586 |
+
"loss": 0.0124,
|
| 587 |
+
"step": 133133
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 11.7,
|
| 591 |
+
"learning_rate": 0.0006777527136715059,
|
| 592 |
+
"loss": 0.0131,
|
| 593 |
+
"step": 134862
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 11.85,
|
| 597 |
+
"learning_rate": 0.0006721968367812547,
|
| 598 |
+
"loss": 0.014,
|
| 599 |
+
"step": 136591
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 12.0,
|
| 603 |
+
"eval_loss": 0.04735955968499184,
|
| 604 |
+
"eval_max_distance": 44,
|
| 605 |
+
"eval_mean_distance": 0,
|
| 606 |
+
"eval_runtime": 22.5236,
|
| 607 |
+
"eval_samples_per_second": 44.398,
|
| 608 |
+
"eval_steps_per_second": 2.22,
|
| 609 |
+
"step": 138312
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 12.0,
|
| 613 |
+
"learning_rate": 0.0006666409598910033,
|
| 614 |
+
"loss": 0.0182,
|
| 615 |
+
"step": 138320
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 12.15,
|
| 619 |
+
"learning_rate": 0.000661085083000752,
|
| 620 |
+
"loss": 0.025,
|
| 621 |
+
"step": 140049
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 12.3,
|
| 625 |
+
"learning_rate": 0.0006555292061105006,
|
| 626 |
+
"loss": 0.0128,
|
| 627 |
+
"step": 141778
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 12.45,
|
| 631 |
+
"learning_rate": 0.0006499733292202492,
|
| 632 |
+
"loss": 0.0114,
|
| 633 |
+
"step": 143507
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 12.6,
|
| 637 |
+
"learning_rate": 0.0006444174523299979,
|
| 638 |
+
"loss": 0.011,
|
| 639 |
+
"step": 145236
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 12.75,
|
| 643 |
+
"learning_rate": 0.0006388615754397465,
|
| 644 |
+
"loss": 0.0117,
|
| 645 |
+
"step": 146965
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 12.9,
|
| 649 |
+
"learning_rate": 0.0006333056985494952,
|
| 650 |
+
"loss": 0.0122,
|
| 651 |
+
"step": 148694
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 13.0,
|
| 655 |
+
"eval_loss": 0.05152251571416855,
|
| 656 |
+
"eval_max_distance": 42,
|
| 657 |
+
"eval_mean_distance": 0,
|
| 658 |
+
"eval_runtime": 23.898,
|
| 659 |
+
"eval_samples_per_second": 41.845,
|
| 660 |
+
"eval_steps_per_second": 2.092,
|
| 661 |
+
"step": 149838
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 13.05,
|
| 665 |
+
"learning_rate": 0.0006277498216592438,
|
| 666 |
+
"loss": 0.0241,
|
| 667 |
+
"step": 150423
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 13.2,
|
| 671 |
+
"learning_rate": 0.0006221939447689925,
|
| 672 |
+
"loss": 0.0148,
|
| 673 |
+
"step": 152152
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 13.35,
|
| 677 |
+
"learning_rate": 0.0006166380678787411,
|
| 678 |
+
"loss": 0.0106,
|
| 679 |
+
"step": 153881
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 13.5,
|
| 683 |
+
"learning_rate": 0.0006110821909884899,
|
| 684 |
+
"loss": 0.0096,
|
| 685 |
+
"step": 155610
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 13.65,
|
| 689 |
+
"learning_rate": 0.0006055263140982384,
|
| 690 |
+
"loss": 0.0098,
|
| 691 |
+
"step": 157339
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 13.8,
|
| 695 |
+
"learning_rate": 0.0005999704372079872,
|
| 696 |
+
"loss": 0.0104,
|
| 697 |
+
"step": 159068
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 13.95,
|
| 701 |
+
"learning_rate": 0.0005944145603177358,
|
| 702 |
+
"loss": 0.0117,
|
| 703 |
+
"step": 160797
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 14.0,
|
| 707 |
+
"eval_loss": 0.047906968742609024,
|
| 708 |
+
"eval_max_distance": 30,
|
| 709 |
+
"eval_mean_distance": 0,
|
| 710 |
+
"eval_runtime": 23.3531,
|
| 711 |
+
"eval_samples_per_second": 42.821,
|
| 712 |
+
"eval_steps_per_second": 2.141,
|
| 713 |
+
"step": 161364
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 14.1,
|
| 717 |
+
"learning_rate": 0.0005888586834274844,
|
| 718 |
+
"loss": 0.0224,
|
| 719 |
+
"step": 162526
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 14.25,
|
| 723 |
+
"learning_rate": 0.0005833028065372331,
|
| 724 |
+
"loss": 0.0111,
|
| 725 |
+
"step": 164255
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 14.4,
|
| 729 |
+
"learning_rate": 0.0005777469296469818,
|
| 730 |
+
"loss": 0.009,
|
| 731 |
+
"step": 165984
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 14.55,
|
| 735 |
+
"learning_rate": 0.0005721910527567303,
|
| 736 |
+
"loss": 0.0086,
|
| 737 |
+
"step": 167713
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 14.7,
|
| 741 |
+
"learning_rate": 0.000566635175866479,
|
| 742 |
+
"loss": 0.0088,
|
| 743 |
+
"step": 169442
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 14.85,
|
| 747 |
+
"learning_rate": 0.0005610792989762277,
|
| 748 |
+
"loss": 0.0093,
|
| 749 |
+
"step": 171171
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 15.0,
|
| 753 |
+
"eval_loss": 0.05651288107037544,
|
| 754 |
+
"eval_max_distance": 56,
|
| 755 |
+
"eval_mean_distance": 0,
|
| 756 |
+
"eval_runtime": 23.6545,
|
| 757 |
+
"eval_samples_per_second": 42.275,
|
| 758 |
+
"eval_steps_per_second": 2.114,
|
| 759 |
+
"step": 172890
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 15.0,
|
| 763 |
+
"learning_rate": 0.0005555234220859762,
|
| 764 |
+
"loss": 0.0124,
|
| 765 |
+
"step": 172900
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 15.15,
|
| 769 |
+
"learning_rate": 0.000549967545195725,
|
| 770 |
+
"loss": 0.0181,
|
| 771 |
+
"step": 174629
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 15.3,
|
| 775 |
+
"learning_rate": 0.0005444116683054736,
|
| 776 |
+
"loss": 0.0091,
|
| 777 |
+
"step": 176358
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 15.45,
|
| 781 |
+
"learning_rate": 0.0005388557914152222,
|
| 782 |
+
"loss": 0.0075,
|
| 783 |
+
"step": 178087
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 15.6,
|
| 787 |
+
"learning_rate": 0.0005332999145249709,
|
| 788 |
+
"loss": 0.0075,
|
| 789 |
+
"step": 179816
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 15.75,
|
| 793 |
+
"learning_rate": 0.0005277440376347196,
|
| 794 |
+
"loss": 0.0075,
|
| 795 |
+
"step": 181545
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 15.9,
|
| 799 |
+
"learning_rate": 0.0005221881607444683,
|
| 800 |
+
"loss": 0.0085,
|
| 801 |
+
"step": 183274
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 16.0,
|
| 805 |
+
"eval_loss": 0.047154366970062256,
|
| 806 |
+
"eval_max_distance": 34,
|
| 807 |
+
"eval_mean_distance": 0,
|
| 808 |
+
"eval_runtime": 23.554,
|
| 809 |
+
"eval_samples_per_second": 42.456,
|
| 810 |
+
"eval_steps_per_second": 2.123,
|
| 811 |
+
"step": 184416
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 16.05,
|
| 815 |
+
"learning_rate": 0.0005166322838542169,
|
| 816 |
+
"loss": 0.0169,
|
| 817 |
+
"step": 185003
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 16.2,
|
| 821 |
+
"learning_rate": 0.0005110764069639655,
|
| 822 |
+
"loss": 0.0104,
|
| 823 |
+
"step": 186732
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 16.35,
|
| 827 |
+
"learning_rate": 0.0005055205300737143,
|
| 828 |
+
"loss": 0.0072,
|
| 829 |
+
"step": 188461
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 16.5,
|
| 833 |
+
"learning_rate": 0.0004999646531834628,
|
| 834 |
+
"loss": 0.0068,
|
| 835 |
+
"step": 190190
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 16.65,
|
| 839 |
+
"learning_rate": 0.0004944087762932115,
|
| 840 |
+
"loss": 0.0064,
|
| 841 |
+
"step": 191919
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 16.8,
|
| 845 |
+
"learning_rate": 0.0004888528994029601,
|
| 846 |
+
"loss": 0.0068,
|
| 847 |
+
"step": 193648
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 16.95,
|
| 851 |
+
"learning_rate": 0.0004832970225127088,
|
| 852 |
+
"loss": 0.0075,
|
| 853 |
+
"step": 195377
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 17.0,
|
| 857 |
+
"eval_loss": 0.04200902581214905,
|
| 858 |
+
"eval_max_distance": 28,
|
| 859 |
+
"eval_mean_distance": 0,
|
| 860 |
+
"eval_runtime": 22.1607,
|
| 861 |
+
"eval_samples_per_second": 45.125,
|
| 862 |
+
"eval_steps_per_second": 2.256,
|
| 863 |
+
"step": 195942
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 17.1,
|
| 867 |
+
"learning_rate": 0.00047774114562245746,
|
| 868 |
+
"loss": 0.0162,
|
| 869 |
+
"step": 197106
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 17.25,
|
| 873 |
+
"learning_rate": 0.00047218526873220605,
|
| 874 |
+
"loss": 0.0077,
|
| 875 |
+
"step": 198835
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 17.4,
|
| 879 |
+
"learning_rate": 0.00046662939184195475,
|
| 880 |
+
"loss": 0.0063,
|
| 881 |
+
"step": 200564
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 17.55,
|
| 885 |
+
"learning_rate": 0.0004610735149517034,
|
| 886 |
+
"loss": 0.0058,
|
| 887 |
+
"step": 202293
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 17.7,
|
| 891 |
+
"learning_rate": 0.0004555176380614521,
|
| 892 |
+
"loss": 0.0057,
|
| 893 |
+
"step": 204022
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 17.85,
|
| 897 |
+
"learning_rate": 0.0004499617611712007,
|
| 898 |
+
"loss": 0.0059,
|
| 899 |
+
"step": 205751
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 18.0,
|
| 903 |
+
"eval_loss": 0.04149915650486946,
|
| 904 |
+
"eval_max_distance": 32,
|
| 905 |
+
"eval_mean_distance": 0,
|
| 906 |
+
"eval_runtime": 22.9895,
|
| 907 |
+
"eval_samples_per_second": 43.498,
|
| 908 |
+
"eval_steps_per_second": 2.175,
|
| 909 |
+
"step": 207468
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 18.0,
|
| 913 |
+
"learning_rate": 0.00044440588428094934,
|
| 914 |
+
"loss": 0.0082,
|
| 915 |
+
"step": 207480
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 18.15,
|
| 919 |
+
"learning_rate": 0.00043885000739069804,
|
| 920 |
+
"loss": 0.0133,
|
| 921 |
+
"step": 209209
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 18.3,
|
| 925 |
+
"learning_rate": 0.00043329413050044663,
|
| 926 |
+
"loss": 0.0063,
|
| 927 |
+
"step": 210938
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 18.45,
|
| 931 |
+
"learning_rate": 0.0004277382536101953,
|
| 932 |
+
"loss": 0.0051,
|
| 933 |
+
"step": 212667
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 18.6,
|
| 937 |
+
"learning_rate": 0.000422182376719944,
|
| 938 |
+
"loss": 0.0051,
|
| 939 |
+
"step": 214396
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 18.75,
|
| 943 |
+
"learning_rate": 0.00041662649982969263,
|
| 944 |
+
"loss": 0.0051,
|
| 945 |
+
"step": 216125
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 18.9,
|
| 949 |
+
"learning_rate": 0.0004110706229394413,
|
| 950 |
+
"loss": 0.0054,
|
| 951 |
+
"step": 217854
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 19.0,
|
| 955 |
+
"eval_loss": 0.0405677855014801,
|
| 956 |
+
"eval_max_distance": 28,
|
| 957 |
+
"eval_mean_distance": 0,
|
| 958 |
+
"eval_runtime": 21.777,
|
| 959 |
+
"eval_samples_per_second": 45.92,
|
| 960 |
+
"eval_steps_per_second": 2.296,
|
| 961 |
+
"step": 218994
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 19.05,
|
| 965 |
+
"learning_rate": 0.0004055147460491899,
|
| 966 |
+
"loss": 0.0117,
|
| 967 |
+
"step": 219583
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 19.2,
|
| 971 |
+
"learning_rate": 0.00039995886915893857,
|
| 972 |
+
"loss": 0.0075,
|
| 973 |
+
"step": 221312
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 19.35,
|
| 977 |
+
"learning_rate": 0.00039440299226868727,
|
| 978 |
+
"loss": 0.0051,
|
| 979 |
+
"step": 223041
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 19.5,
|
| 983 |
+
"learning_rate": 0.00038884711537843586,
|
| 984 |
+
"loss": 0.0046,
|
| 985 |
+
"step": 224770
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 19.65,
|
| 989 |
+
"learning_rate": 0.0003832912384881845,
|
| 990 |
+
"loss": 0.0043,
|
| 991 |
+
"step": 226499
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 19.8,
|
| 995 |
+
"learning_rate": 0.0003777353615979332,
|
| 996 |
+
"loss": 0.0044,
|
| 997 |
+
"step": 228228
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 19.95,
|
| 1001 |
+
"learning_rate": 0.0003721794847076818,
|
| 1002 |
+
"loss": 0.0046,
|
| 1003 |
+
"step": 229957
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 20.0,
|
| 1007 |
+
"eval_loss": 0.03926468640565872,
|
| 1008 |
+
"eval_max_distance": 24,
|
| 1009 |
+
"eval_mean_distance": 0,
|
| 1010 |
+
"eval_runtime": 23.1294,
|
| 1011 |
+
"eval_samples_per_second": 43.235,
|
| 1012 |
+
"eval_steps_per_second": 2.162,
|
| 1013 |
+
"step": 230520
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 20.1,
|
| 1017 |
+
"learning_rate": 0.0003666236078174305,
|
| 1018 |
+
"loss": 0.0118,
|
| 1019 |
+
"step": 231686
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 20.25,
|
| 1023 |
+
"learning_rate": 0.00036106773092717915,
|
| 1024 |
+
"loss": 0.0056,
|
| 1025 |
+
"step": 233415
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 20.4,
|
| 1029 |
+
"learning_rate": 0.0003555118540369278,
|
| 1030 |
+
"loss": 0.0043,
|
| 1031 |
+
"step": 235144
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 20.55,
|
| 1035 |
+
"learning_rate": 0.00034995597714667645,
|
| 1036 |
+
"loss": 0.0039,
|
| 1037 |
+
"step": 236873
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 20.7,
|
| 1041 |
+
"learning_rate": 0.0003444001002564251,
|
| 1042 |
+
"loss": 0.0037,
|
| 1043 |
+
"step": 238602
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 20.85,
|
| 1047 |
+
"learning_rate": 0.00033884422336617374,
|
| 1048 |
+
"loss": 0.004,
|
| 1049 |
+
"step": 240331
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 21.0,
|
| 1053 |
+
"eval_loss": 0.04168349876999855,
|
| 1054 |
+
"eval_max_distance": 24,
|
| 1055 |
+
"eval_mean_distance": 0,
|
| 1056 |
+
"eval_runtime": 22.786,
|
| 1057 |
+
"eval_samples_per_second": 43.887,
|
| 1058 |
+
"eval_steps_per_second": 2.194,
|
| 1059 |
+
"step": 242046
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 21.0,
|
| 1063 |
+
"learning_rate": 0.0003332883464759224,
|
| 1064 |
+
"loss": 0.0053,
|
| 1065 |
+
"step": 242060
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 21.15,
|
| 1069 |
+
"learning_rate": 0.00032773246958567103,
|
| 1070 |
+
"loss": 0.0097,
|
| 1071 |
+
"step": 243789
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 21.3,
|
| 1075 |
+
"learning_rate": 0.00032217659269541973,
|
| 1076 |
+
"loss": 0.0044,
|
| 1077 |
+
"step": 245518
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 21.45,
|
| 1081 |
+
"learning_rate": 0.0003166207158051684,
|
| 1082 |
+
"loss": 0.0036,
|
| 1083 |
+
"step": 247247
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 21.6,
|
| 1087 |
+
"learning_rate": 0.000311064838914917,
|
| 1088 |
+
"loss": 0.0031,
|
| 1089 |
+
"step": 248976
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 21.75,
|
| 1093 |
+
"learning_rate": 0.0003055089620246657,
|
| 1094 |
+
"loss": 0.0031,
|
| 1095 |
+
"step": 250705
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 21.9,
|
| 1099 |
+
"learning_rate": 0.0002999530851344143,
|
| 1100 |
+
"loss": 0.0034,
|
| 1101 |
+
"step": 252434
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 22.0,
|
| 1105 |
+
"eval_loss": 0.040287140756845474,
|
| 1106 |
+
"eval_max_distance": 18,
|
| 1107 |
+
"eval_mean_distance": 0,
|
| 1108 |
+
"eval_runtime": 21.6664,
|
| 1109 |
+
"eval_samples_per_second": 46.155,
|
| 1110 |
+
"eval_steps_per_second": 2.308,
|
| 1111 |
+
"step": 253572
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 22.05,
|
| 1115 |
+
"learning_rate": 0.0002943972082441629,
|
| 1116 |
+
"loss": 0.0082,
|
| 1117 |
+
"step": 254163
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 22.2,
|
| 1121 |
+
"learning_rate": 0.0002888413313539116,
|
| 1122 |
+
"loss": 0.0053,
|
| 1123 |
+
"step": 255892
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 22.35,
|
| 1127 |
+
"learning_rate": 0.00028328545446366026,
|
| 1128 |
+
"loss": 0.0034,
|
| 1129 |
+
"step": 257621
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 22.5,
|
| 1133 |
+
"learning_rate": 0.00027772957757340896,
|
| 1134 |
+
"loss": 0.0031,
|
| 1135 |
+
"step": 259350
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 22.65,
|
| 1139 |
+
"learning_rate": 0.00027217370068315756,
|
| 1140 |
+
"loss": 0.0029,
|
| 1141 |
+
"step": 261079
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 22.8,
|
| 1145 |
+
"learning_rate": 0.0002666178237929062,
|
| 1146 |
+
"loss": 0.0027,
|
| 1147 |
+
"step": 262808
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 22.95,
|
| 1151 |
+
"learning_rate": 0.0002610619469026549,
|
| 1152 |
+
"loss": 0.0029,
|
| 1153 |
+
"step": 264537
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 23.0,
|
| 1157 |
+
"eval_loss": 0.04222797229886055,
|
| 1158 |
+
"eval_max_distance": 21,
|
| 1159 |
+
"eval_mean_distance": 0,
|
| 1160 |
+
"eval_runtime": 22.874,
|
| 1161 |
+
"eval_samples_per_second": 43.718,
|
| 1162 |
+
"eval_steps_per_second": 2.186,
|
| 1163 |
+
"step": 265098
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 23.1,
|
| 1167 |
+
"learning_rate": 0.0002555060700124035,
|
| 1168 |
+
"loss": 0.0081,
|
| 1169 |
+
"step": 266266
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 23.25,
|
| 1173 |
+
"learning_rate": 0.00024995019312215214,
|
| 1174 |
+
"loss": 0.0038,
|
| 1175 |
+
"step": 267995
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 23.4,
|
| 1179 |
+
"learning_rate": 0.00024439431623190085,
|
| 1180 |
+
"loss": 0.0028,
|
| 1181 |
+
"step": 269724
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 23.55,
|
| 1185 |
+
"learning_rate": 0.00023883843934164947,
|
| 1186 |
+
"loss": 0.0025,
|
| 1187 |
+
"step": 271453
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 23.7,
|
| 1191 |
+
"learning_rate": 0.00023328256245139814,
|
| 1192 |
+
"loss": 0.0026,
|
| 1193 |
+
"step": 273182
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 23.85,
|
| 1197 |
+
"learning_rate": 0.0002277266855611468,
|
| 1198 |
+
"loss": 0.0024,
|
| 1199 |
+
"step": 274911
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 24.0,
|
| 1203 |
+
"eval_loss": 0.04101773351430893,
|
| 1204 |
+
"eval_max_distance": 21,
|
| 1205 |
+
"eval_mean_distance": 0,
|
| 1206 |
+
"eval_runtime": 22.8008,
|
| 1207 |
+
"eval_samples_per_second": 43.858,
|
| 1208 |
+
"eval_steps_per_second": 2.193,
|
| 1209 |
+
"step": 276624
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 24.0,
|
| 1213 |
+
"learning_rate": 0.00022217080867089543,
|
| 1214 |
+
"loss": 0.0033,
|
| 1215 |
+
"step": 276640
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 24.15,
|
| 1219 |
+
"learning_rate": 0.00021661493178064408,
|
| 1220 |
+
"loss": 0.0069,
|
| 1221 |
+
"step": 278369
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 24.3,
|
| 1225 |
+
"learning_rate": 0.00021105905489039273,
|
| 1226 |
+
"loss": 0.0029,
|
| 1227 |
+
"step": 280098
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 24.45,
|
| 1231 |
+
"learning_rate": 0.0002055031780001414,
|
| 1232 |
+
"loss": 0.0024,
|
| 1233 |
+
"step": 281827
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 24.6,
|
| 1237 |
+
"learning_rate": 0.00019994730110989005,
|
| 1238 |
+
"loss": 0.0021,
|
| 1239 |
+
"step": 283556
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 24.75,
|
| 1243 |
+
"learning_rate": 0.0001943914242196387,
|
| 1244 |
+
"loss": 0.002,
|
| 1245 |
+
"step": 285285
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 24.9,
|
| 1249 |
+
"learning_rate": 0.00018883554732938734,
|
| 1250 |
+
"loss": 0.002,
|
| 1251 |
+
"step": 287014
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 25.0,
|
| 1255 |
+
"eval_loss": 0.043479613959789276,
|
| 1256 |
+
"eval_max_distance": 15,
|
| 1257 |
+
"eval_mean_distance": 0,
|
| 1258 |
+
"eval_runtime": 21.481,
|
| 1259 |
+
"eval_samples_per_second": 46.553,
|
| 1260 |
+
"eval_steps_per_second": 2.328,
|
| 1261 |
+
"step": 288150
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 25.05,
|
| 1265 |
+
"learning_rate": 0.000183279670439136,
|
| 1266 |
+
"loss": 0.0055,
|
| 1267 |
+
"step": 288743
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 25.2,
|
| 1271 |
+
"learning_rate": 0.00017772379354888466,
|
| 1272 |
+
"loss": 0.0038,
|
| 1273 |
+
"step": 290472
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 25.35,
|
| 1277 |
+
"learning_rate": 0.00017216791665863328,
|
| 1278 |
+
"loss": 0.0023,
|
| 1279 |
+
"step": 292201
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 25.5,
|
| 1283 |
+
"learning_rate": 0.00016661203976838196,
|
| 1284 |
+
"loss": 0.002,
|
| 1285 |
+
"step": 293930
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 25.65,
|
| 1289 |
+
"learning_rate": 0.0001610561628781306,
|
| 1290 |
+
"loss": 0.0017,
|
| 1291 |
+
"step": 295659
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 25.8,
|
| 1295 |
+
"learning_rate": 0.00015550028598787928,
|
| 1296 |
+
"loss": 0.0018,
|
| 1297 |
+
"step": 297388
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 25.95,
|
| 1301 |
+
"learning_rate": 0.0001499444090976279,
|
| 1302 |
+
"loss": 0.0016,
|
| 1303 |
+
"step": 299117
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 26.0,
|
| 1307 |
+
"eval_loss": 0.04517431557178497,
|
| 1308 |
+
"eval_max_distance": 15,
|
| 1309 |
+
"eval_mean_distance": 0,
|
| 1310 |
+
"eval_runtime": 22.7192,
|
| 1311 |
+
"eval_samples_per_second": 44.016,
|
| 1312 |
+
"eval_steps_per_second": 2.201,
|
| 1313 |
+
"step": 299676
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 26.1,
|
| 1317 |
+
"learning_rate": 0.00014438853220737654,
|
| 1318 |
+
"loss": 0.0054,
|
| 1319 |
+
"step": 300846
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 26.25,
|
| 1323 |
+
"learning_rate": 0.00013883265531712522,
|
| 1324 |
+
"loss": 0.0026,
|
| 1325 |
+
"step": 302575
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 26.4,
|
| 1329 |
+
"learning_rate": 0.00013327677842687387,
|
| 1330 |
+
"loss": 0.0018,
|
| 1331 |
+
"step": 304304
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 26.55,
|
| 1335 |
+
"learning_rate": 0.0001277209015366225,
|
| 1336 |
+
"loss": 0.0016,
|
| 1337 |
+
"step": 306033
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 26.7,
|
| 1341 |
+
"learning_rate": 0.00012216502464637116,
|
| 1342 |
+
"loss": 0.0015,
|
| 1343 |
+
"step": 307762
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 26.85,
|
| 1347 |
+
"learning_rate": 0.00011660914775611982,
|
| 1348 |
+
"loss": 0.0013,
|
| 1349 |
+
"step": 309491
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 27.0,
|
| 1353 |
+
"eval_loss": 0.04144546017050743,
|
| 1354 |
+
"eval_max_distance": 14,
|
| 1355 |
+
"eval_mean_distance": 0,
|
| 1356 |
+
"eval_runtime": 22.686,
|
| 1357 |
+
"eval_samples_per_second": 44.08,
|
| 1358 |
+
"eval_steps_per_second": 2.204,
|
| 1359 |
+
"step": 311202
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 27.0,
|
| 1363 |
+
"learning_rate": 0.00011105327086586847,
|
| 1364 |
+
"loss": 0.0021,
|
| 1365 |
+
"step": 311220
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 27.15,
|
| 1369 |
+
"learning_rate": 0.00010549739397561713,
|
| 1370 |
+
"loss": 0.0046,
|
| 1371 |
+
"step": 312949
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 27.3,
|
| 1375 |
+
"learning_rate": 9.994151708536577e-05,
|
| 1376 |
+
"loss": 0.002,
|
| 1377 |
+
"step": 314678
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 27.45,
|
| 1381 |
+
"learning_rate": 9.438564019511443e-05,
|
| 1382 |
+
"loss": 0.0016,
|
| 1383 |
+
"step": 316407
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 27.6,
|
| 1387 |
+
"learning_rate": 8.882976330486308e-05,
|
| 1388 |
+
"loss": 0.0013,
|
| 1389 |
+
"step": 318136
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 27.75,
|
| 1393 |
+
"learning_rate": 8.327388641461173e-05,
|
| 1394 |
+
"loss": 0.0013,
|
| 1395 |
+
"step": 319865
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 27.9,
|
| 1399 |
+
"learning_rate": 7.771800952436038e-05,
|
| 1400 |
+
"loss": 0.0012,
|
| 1401 |
+
"step": 321594
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 28.0,
|
| 1405 |
+
"eval_loss": 0.04387975484132767,
|
| 1406 |
+
"eval_max_distance": 14,
|
| 1407 |
+
"eval_mean_distance": 0,
|
| 1408 |
+
"eval_runtime": 21.586,
|
| 1409 |
+
"eval_samples_per_second": 46.326,
|
| 1410 |
+
"eval_steps_per_second": 2.316,
|
| 1411 |
+
"step": 322728
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 28.05,
|
| 1415 |
+
"learning_rate": 7.216213263410904e-05,
|
| 1416 |
+
"loss": 0.0037,
|
| 1417 |
+
"step": 323323
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 28.2,
|
| 1421 |
+
"learning_rate": 6.660625574385768e-05,
|
| 1422 |
+
"loss": 0.0027,
|
| 1423 |
+
"step": 325052
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 28.35,
|
| 1427 |
+
"learning_rate": 6.105037885360634e-05,
|
| 1428 |
+
"loss": 0.0016,
|
| 1429 |
+
"step": 326781
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 28.5,
|
| 1433 |
+
"learning_rate": 5.5494501963355e-05,
|
| 1434 |
+
"loss": 0.0013,
|
| 1435 |
+
"step": 328510
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 28.65,
|
| 1439 |
+
"learning_rate": 4.9938625073103644e-05,
|
| 1440 |
+
"loss": 0.0011,
|
| 1441 |
+
"step": 330239
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 28.8,
|
| 1445 |
+
"learning_rate": 4.43827481828523e-05,
|
| 1446 |
+
"loss": 0.001,
|
| 1447 |
+
"step": 331968
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 28.95,
|
| 1451 |
+
"learning_rate": 3.882687129260095e-05,
|
| 1452 |
+
"loss": 0.001,
|
| 1453 |
+
"step": 333697
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 29.0,
|
| 1457 |
+
"eval_loss": 0.044395141303539276,
|
| 1458 |
+
"eval_max_distance": 15,
|
| 1459 |
+
"eval_mean_distance": 0,
|
| 1460 |
+
"eval_runtime": 22.6289,
|
| 1461 |
+
"eval_samples_per_second": 44.191,
|
| 1462 |
+
"eval_steps_per_second": 2.21,
|
| 1463 |
+
"step": 334254
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 29.1,
|
| 1467 |
+
"learning_rate": 3.32709944023496e-05,
|
| 1468 |
+
"loss": 0.0039,
|
| 1469 |
+
"step": 335426
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 29.25,
|
| 1473 |
+
"learning_rate": 2.771511751209825e-05,
|
| 1474 |
+
"loss": 0.0017,
|
| 1475 |
+
"step": 337155
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 29.4,
|
| 1479 |
+
"learning_rate": 2.2159240621846906e-05,
|
| 1480 |
+
"loss": 0.0012,
|
| 1481 |
+
"step": 338884
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 29.55,
|
| 1485 |
+
"learning_rate": 1.6603363731595556e-05,
|
| 1486 |
+
"loss": 0.0011,
|
| 1487 |
+
"step": 340613
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 29.7,
|
| 1491 |
+
"learning_rate": 1.1047486841344207e-05,
|
| 1492 |
+
"loss": 0.001,
|
| 1493 |
+
"step": 342342
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 29.85,
|
| 1497 |
+
"learning_rate": 0.0004477394104151002,
|
| 1498 |
+
"loss": 0.0026,
|
| 1499 |
+
"step": 344071
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 30.0,
|
| 1503 |
+
"eval_loss": 0.042660146951675415,
|
| 1504 |
+
"eval_max_distance": 19,
|
| 1505 |
+
"eval_mean_distance": 0,
|
| 1506 |
+
"eval_runtime": 48.9711,
|
| 1507 |
+
"eval_samples_per_second": 20.42,
|
| 1508 |
+
"eval_steps_per_second": 1.021,
|
| 1509 |
+
"step": 345780
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 30.0,
|
| 1513 |
+
"learning_rate": 0.00044440588428094934,
|
| 1514 |
+
"loss": 0.0045,
|
| 1515 |
+
"step": 345800
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 30.15,
|
| 1519 |
+
"learning_rate": 0.00044107235814679855,
|
| 1520 |
+
"loss": 0.0068,
|
| 1521 |
+
"step": 347529
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 30.3,
|
| 1525 |
+
"learning_rate": 0.00043773883201264776,
|
| 1526 |
+
"loss": 0.0036,
|
| 1527 |
+
"step": 349258
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 30.45,
|
| 1531 |
+
"learning_rate": 0.0004344053058784969,
|
| 1532 |
+
"loss": 0.0032,
|
| 1533 |
+
"step": 350987
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 30.6,
|
| 1537 |
+
"learning_rate": 0.0004310717797443461,
|
| 1538 |
+
"loss": 0.0033,
|
| 1539 |
+
"step": 352716
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 30.75,
|
| 1543 |
+
"learning_rate": 0.0004277382536101953,
|
| 1544 |
+
"loss": 0.0034,
|
| 1545 |
+
"step": 354445
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 30.9,
|
| 1549 |
+
"learning_rate": 0.00042440472747604454,
|
| 1550 |
+
"loss": 0.004,
|
| 1551 |
+
"step": 356174
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 23.29,
|
| 1555 |
+
"learning_rate": 0.000593547500777279,
|
| 1556 |
+
"loss": 0.0057,
|
| 1557 |
+
"step": 357903
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 23.4,
|
| 1561 |
+
"learning_rate": 0.0005910471934809801,
|
| 1562 |
+
"loss": 0.0053,
|
| 1563 |
+
"step": 359632
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 23.52,
|
| 1567 |
+
"learning_rate": 0.0005885468861846814,
|
| 1568 |
+
"loss": 0.0055,
|
| 1569 |
+
"step": 361361
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 23.63,
|
| 1573 |
+
"learning_rate": 0.0005860465788883828,
|
| 1574 |
+
"loss": 0.0056,
|
| 1575 |
+
"step": 363090
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 23.74,
|
| 1579 |
+
"learning_rate": 0.0005835462715920841,
|
| 1580 |
+
"loss": 0.006,
|
| 1581 |
+
"step": 364819
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 23.85,
|
| 1585 |
+
"learning_rate": 0.0005810459642957853,
|
| 1586 |
+
"loss": 0.0064,
|
| 1587 |
+
"step": 366548
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 23.97,
|
| 1591 |
+
"learning_rate": 0.0005785456569994867,
|
| 1592 |
+
"loss": 0.0077,
|
| 1593 |
+
"step": 368277
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 24.0,
|
| 1597 |
+
"eval_loss": 0.049542564898729324,
|
| 1598 |
+
"eval_max_distance": 27,
|
| 1599 |
+
"eval_mean_distance": 0,
|
| 1600 |
+
"eval_runtime": 72.4399,
|
| 1601 |
+
"eval_samples_per_second": 13.805,
|
| 1602 |
+
"eval_steps_per_second": 0.925,
|
| 1603 |
+
"step": 368808
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 24.08,
|
| 1607 |
+
"learning_rate": 0.0005760453497031879,
|
| 1608 |
+
"loss": 0.0158,
|
| 1609 |
+
"step": 370006
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 24.19,
|
| 1613 |
+
"learning_rate": 0.0005735450424068892,
|
| 1614 |
+
"loss": 0.0082,
|
| 1615 |
+
"step": 371735
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 24.3,
|
| 1619 |
+
"learning_rate": 0.0005710447351105905,
|
| 1620 |
+
"loss": 0.0057,
|
| 1621 |
+
"step": 373464
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 24.42,
|
| 1625 |
+
"learning_rate": 0.0005685444278142918,
|
| 1626 |
+
"loss": 0.0059,
|
| 1627 |
+
"step": 375193
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 24.53,
|
| 1631 |
+
"learning_rate": 0.0005660441205179932,
|
| 1632 |
+
"loss": 0.0055,
|
| 1633 |
+
"step": 376922
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 24.64,
|
| 1637 |
+
"learning_rate": 0.0005635438132216944,
|
| 1638 |
+
"loss": 0.0062,
|
| 1639 |
+
"step": 378651
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 24.75,
|
| 1643 |
+
"learning_rate": 0.0005610435059253957,
|
| 1644 |
+
"loss": 0.0059,
|
| 1645 |
+
"step": 380380
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 24.87,
|
| 1649 |
+
"learning_rate": 0.000558543198629097,
|
| 1650 |
+
"loss": 0.0062,
|
| 1651 |
+
"step": 382109
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 24.98,
|
| 1655 |
+
"learning_rate": 0.0005560428913327982,
|
| 1656 |
+
"loss": 0.0083,
|
| 1657 |
+
"step": 383838
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 25.0,
|
| 1661 |
+
"eval_loss": 0.044624801725149155,
|
| 1662 |
+
"eval_max_distance": 37,
|
| 1663 |
+
"eval_mean_distance": 0,
|
| 1664 |
+
"eval_runtime": 35.859,
|
| 1665 |
+
"eval_samples_per_second": 27.887,
|
| 1666 |
+
"eval_steps_per_second": 1.868,
|
| 1667 |
+
"step": 384175
|
| 1668 |
+
},
|
| 1669 |
+
{
|
| 1670 |
+
"epoch": 25.09,
|
| 1671 |
+
"learning_rate": 0.0005535425840364996,
|
| 1672 |
+
"loss": 0.0154,
|
| 1673 |
+
"step": 385567
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 25.2,
|
| 1677 |
+
"learning_rate": 0.0005510422767402009,
|
| 1678 |
+
"loss": 0.0075,
|
| 1679 |
+
"step": 387296
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 25.32,
|
| 1683 |
+
"learning_rate": 0.0005485419694439023,
|
| 1684 |
+
"loss": 0.006,
|
| 1685 |
+
"step": 389025
|
| 1686 |
+
},
|
| 1687 |
+
{
|
| 1688 |
+
"epoch": 25.43,
|
| 1689 |
+
"learning_rate": 0.0005460416621476034,
|
| 1690 |
+
"loss": 0.0057,
|
| 1691 |
+
"step": 390754
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 25.54,
|
| 1695 |
+
"learning_rate": 0.0005435413548513047,
|
| 1696 |
+
"loss": 0.0057,
|
| 1697 |
+
"step": 392483
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 25.65,
|
| 1701 |
+
"learning_rate": 0.0005410410475550061,
|
| 1702 |
+
"loss": 0.0056,
|
| 1703 |
+
"step": 394212
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 25.77,
|
| 1707 |
+
"learning_rate": 0.0005385407402587073,
|
| 1708 |
+
"loss": 0.0059,
|
| 1709 |
+
"step": 395941
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 25.88,
|
| 1713 |
+
"learning_rate": 0.0005360404329624087,
|
| 1714 |
+
"loss": 0.0067,
|
| 1715 |
+
"step": 397670
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 25.99,
|
| 1719 |
+
"learning_rate": 0.0005335401256661099,
|
| 1720 |
+
"loss": 0.0078,
|
| 1721 |
+
"step": 399399
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 26.0,
|
| 1725 |
+
"eval_loss": 0.048115409910678864,
|
| 1726 |
+
"eval_max_distance": 47,
|
| 1727 |
+
"eval_mean_distance": 0,
|
| 1728 |
+
"eval_runtime": 35.8872,
|
| 1729 |
+
"eval_samples_per_second": 27.865,
|
| 1730 |
+
"eval_steps_per_second": 1.867,
|
| 1731 |
+
"step": 399542
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 26.1,
|
| 1735 |
+
"learning_rate": 0.0005310398183698112,
|
| 1736 |
+
"loss": 0.0151,
|
| 1737 |
+
"step": 401128
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 26.22,
|
| 1741 |
+
"learning_rate": 0.0005285395110735125,
|
| 1742 |
+
"loss": 0.0068,
|
| 1743 |
+
"step": 402857
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 26.33,
|
| 1747 |
+
"learning_rate": 0.0005260392037772138,
|
| 1748 |
+
"loss": 0.0055,
|
| 1749 |
+
"step": 404586
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 26.44,
|
| 1753 |
+
"learning_rate": 0.0005235388964809152,
|
| 1754 |
+
"loss": 0.0052,
|
| 1755 |
+
"step": 406315
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 26.55,
|
| 1759 |
+
"learning_rate": 0.0005210385891846165,
|
| 1760 |
+
"loss": 0.0054,
|
| 1761 |
+
"step": 408044
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 26.67,
|
| 1765 |
+
"learning_rate": 0.0005185382818883176,
|
| 1766 |
+
"loss": 0.0053,
|
| 1767 |
+
"step": 409773
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 26.78,
|
| 1771 |
+
"learning_rate": 0.000516037974592019,
|
| 1772 |
+
"loss": 0.0052,
|
| 1773 |
+
"step": 411502
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 26.89,
|
| 1777 |
+
"learning_rate": 0.0005135376672957203,
|
| 1778 |
+
"loss": 0.006,
|
| 1779 |
+
"step": 413231
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 27.0,
|
| 1783 |
+
"eval_loss": 0.042408570647239685,
|
| 1784 |
+
"eval_max_distance": 37,
|
| 1785 |
+
"eval_mean_distance": 0,
|
| 1786 |
+
"eval_runtime": 14.3824,
|
| 1787 |
+
"eval_samples_per_second": 69.529,
|
| 1788 |
+
"eval_steps_per_second": 4.658,
|
| 1789 |
+
"step": 414909
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 27.0,
|
| 1793 |
+
"learning_rate": 0.0005110373599994215,
|
| 1794 |
+
"loss": 0.0095,
|
| 1795 |
+
"step": 414960
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 27.12,
|
| 1799 |
+
"learning_rate": 0.0005085370527031229,
|
| 1800 |
+
"loss": 0.0115,
|
| 1801 |
+
"step": 416689
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 27.23,
|
| 1805 |
+
"learning_rate": 0.0005060367454068242,
|
| 1806 |
+
"loss": 0.006,
|
| 1807 |
+
"step": 418418
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 27.34,
|
| 1811 |
+
"learning_rate": 0.0005035364381105254,
|
| 1812 |
+
"loss": 0.0051,
|
| 1813 |
+
"step": 420147
|
| 1814 |
+
},
|
| 1815 |
+
{
|
| 1816 |
+
"epoch": 27.45,
|
| 1817 |
+
"learning_rate": 0.0005010361308142267,
|
| 1818 |
+
"loss": 0.0047,
|
| 1819 |
+
"step": 421876
|
| 1820 |
+
},
|
| 1821 |
+
{
|
| 1822 |
+
"epoch": 27.57,
|
| 1823 |
+
"learning_rate": 0.000498535823517928,
|
| 1824 |
+
"loss": 0.0047,
|
| 1825 |
+
"step": 423605
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 27.68,
|
| 1829 |
+
"learning_rate": 0.0004960355162216294,
|
| 1830 |
+
"loss": 0.0054,
|
| 1831 |
+
"step": 425334
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 27.79,
|
| 1835 |
+
"learning_rate": 0.0004935352089253306,
|
| 1836 |
+
"loss": 0.0052,
|
| 1837 |
+
"step": 427063
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 27.9,
|
| 1841 |
+
"learning_rate": 0.000491034901629032,
|
| 1842 |
+
"loss": 0.0056,
|
| 1843 |
+
"step": 428792
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 28.0,
|
| 1847 |
+
"eval_loss": 0.04393070191144943,
|
| 1848 |
+
"eval_max_distance": 22,
|
| 1849 |
+
"eval_mean_distance": 0,
|
| 1850 |
+
"eval_runtime": 26.5483,
|
| 1851 |
+
"eval_samples_per_second": 37.667,
|
| 1852 |
+
"eval_steps_per_second": 2.524,
|
| 1853 |
+
"step": 430276
|
| 1854 |
+
},
|
| 1855 |
+
{
|
| 1856 |
+
"epoch": 28.02,
|
| 1857 |
+
"learning_rate": 0.0004885345943327332,
|
| 1858 |
+
"loss": 0.0105,
|
| 1859 |
+
"step": 430521
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 28.13,
|
| 1863 |
+
"learning_rate": 0.0004860342870364345,
|
| 1864 |
+
"loss": 0.0093,
|
| 1865 |
+
"step": 432250
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 28.24,
|
| 1869 |
+
"learning_rate": 0.0004835339797401358,
|
| 1870 |
+
"loss": 0.0055,
|
| 1871 |
+
"step": 433979
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 28.35,
|
| 1875 |
+
"learning_rate": 0.0004810336724438371,
|
| 1876 |
+
"loss": 0.0049,
|
| 1877 |
+
"step": 435708
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 28.47,
|
| 1881 |
+
"learning_rate": 0.00047853336514753835,
|
| 1882 |
+
"loss": 0.0044,
|
| 1883 |
+
"step": 437437
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 28.58,
|
| 1887 |
+
"learning_rate": 0.0004760330578512397,
|
| 1888 |
+
"loss": 0.0044,
|
| 1889 |
+
"step": 439166
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 28.69,
|
| 1893 |
+
"learning_rate": 0.000473532750554941,
|
| 1894 |
+
"loss": 0.0047,
|
| 1895 |
+
"step": 440895
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 28.8,
|
| 1899 |
+
"learning_rate": 0.0004710324432586423,
|
| 1900 |
+
"loss": 0.0047,
|
| 1901 |
+
"step": 442624
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 28.92,
|
| 1905 |
+
"learning_rate": 0.00046853213596234356,
|
| 1906 |
+
"loss": 0.0054,
|
| 1907 |
+
"step": 444353
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 29.0,
|
| 1911 |
+
"eval_loss": 0.04814203828573227,
|
| 1912 |
+
"eval_max_distance": 23,
|
| 1913 |
+
"eval_mean_distance": 0,
|
| 1914 |
+
"eval_runtime": 35.122,
|
| 1915 |
+
"eval_samples_per_second": 28.472,
|
| 1916 |
+
"eval_steps_per_second": 1.908,
|
| 1917 |
+
"step": 445643
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 29.03,
|
| 1921 |
+
"learning_rate": 0.00046603182866604485,
|
| 1922 |
+
"loss": 0.0103,
|
| 1923 |
+
"step": 446082
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 29.14,
|
| 1927 |
+
"learning_rate": 0.00046353152136974614,
|
| 1928 |
+
"loss": 0.0076,
|
| 1929 |
+
"step": 447811
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 29.25,
|
| 1933 |
+
"learning_rate": 0.00046103121407344743,
|
| 1934 |
+
"loss": 0.005,
|
| 1935 |
+
"step": 449540
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 29.37,
|
| 1939 |
+
"learning_rate": 0.00045853090677714877,
|
| 1940 |
+
"loss": 0.0043,
|
| 1941 |
+
"step": 451269
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 29.48,
|
| 1945 |
+
"learning_rate": 0.00045603059948085,
|
| 1946 |
+
"loss": 0.0043,
|
| 1947 |
+
"step": 452998
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 29.59,
|
| 1951 |
+
"learning_rate": 0.00045353029218455135,
|
| 1952 |
+
"loss": 0.004,
|
| 1953 |
+
"step": 454727
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 29.7,
|
| 1957 |
+
"learning_rate": 0.0004510299848882526,
|
| 1958 |
+
"loss": 0.0042,
|
| 1959 |
+
"step": 456456
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 29.82,
|
| 1963 |
+
"learning_rate": 6.808721912515757e-06,
|
| 1964 |
+
"loss": 0.0039,
|
| 1965 |
+
"step": 458185
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 29.93,
|
| 1969 |
+
"learning_rate": 2.641543085351246e-06,
|
| 1970 |
+
"loss": 0.004,
|
| 1971 |
+
"step": 459914
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 30.0,
|
| 1975 |
+
"eval_loss": 0.04417673125863075,
|
| 1976 |
+
"eval_max_distance": 25,
|
| 1977 |
+
"eval_mean_distance": 0,
|
| 1978 |
+
"eval_runtime": 68.6071,
|
| 1979 |
+
"eval_samples_per_second": 14.576,
|
| 1980 |
+
"eval_steps_per_second": 0.977,
|
| 1981 |
+
"step": 461010
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 30.0,
|
| 1985 |
+
"step": 461010,
|
| 1986 |
+
"total_flos": 1.1619438964958822e+17,
|
| 1987 |
+
"train_loss": 3.931375028864634e-05,
|
| 1988 |
+
"train_runtime": 411.3459,
|
| 1989 |
+
"train_samples_per_second": 16810.814,
|
| 1990 |
+
"train_steps_per_second": 1120.736
|
| 1991 |
+
}
|
| 1992 |
+
],
|
| 1993 |
+
"logging_steps": 1729,
|
| 1994 |
+
"max_steps": 461010,
|
| 1995 |
+
"num_train_epochs": 30,
|
| 1996 |
+
"save_steps": 3458,
|
| 1997 |
+
"total_flos": 1.1619438964958822e+17,
|
| 1998 |
+
"trial_name": null,
|
| 1999 |
+
"trial_params": null
|
| 2000 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d22aeb992bd9320e28438aa9818e67e4f3f8675fde0b30b307f79b248f69c20
|
| 3 |
+
size 4091
|