Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- 04.pretrain.sh +75 -0
- 04.pretrain_200k_base_5120.sh +54 -0
- README.md +56 -0
- all_results.json +16 -0
- checkpoint-191000/config.json +25 -0
- checkpoint-191000/generation_config.json +6 -0
- checkpoint-191000/model.safetensors +3 -0
- checkpoint-191000/optimizer.pt +3 -0
- checkpoint-191000/rng_state.pth +3 -0
- checkpoint-191000/scheduler.pt +3 -0
- checkpoint-191000/trainer_state.json +1165 -0
- checkpoint-191000/training_args.bin +3 -0
- checkpoint-192000/config.json +25 -0
- checkpoint-192000/generation_config.json +6 -0
- checkpoint-192000/model.safetensors +3 -0
- checkpoint-192000/optimizer.pt +3 -0
- checkpoint-192000/rng_state.pth +3 -0
- checkpoint-192000/scheduler.pt +3 -0
- checkpoint-192000/trainer_state.json +1171 -0
- checkpoint-192000/training_args.bin +3 -0
- checkpoint-193000/config.json +25 -0
- checkpoint-193000/generation_config.json +6 -0
- checkpoint-193000/model.safetensors +3 -0
- checkpoint-193000/optimizer.pt +3 -0
- checkpoint-193000/rng_state.pth +3 -0
- checkpoint-193000/scheduler.pt +3 -0
- checkpoint-193000/trainer_state.json +1177 -0
- checkpoint-193000/training_args.bin +3 -0
- checkpoint-194000/config.json +25 -0
- checkpoint-194000/generation_config.json +6 -0
- checkpoint-194000/model.safetensors +3 -0
- checkpoint-194000/optimizer.pt +3 -0
- checkpoint-194000/rng_state.pth +3 -0
- checkpoint-194000/scheduler.pt +3 -0
- checkpoint-194000/trainer_state.json +1183 -0
- checkpoint-194000/training_args.bin +3 -0
- checkpoint-195000/config.json +25 -0
- checkpoint-195000/generation_config.json +6 -0
- checkpoint-195000/model.safetensors +3 -0
- checkpoint-195000/optimizer.pt +3 -0
- checkpoint-195000/rng_state.pth +3 -0
- checkpoint-195000/scheduler.pt +3 -0
- checkpoint-195000/trainer_state.json +1189 -0
- checkpoint-195000/training_args.bin +3 -0
- checkpoint-196000/config.json +25 -0
- checkpoint-196000/generation_config.json +6 -0
- checkpoint-196000/model.safetensors +3 -0
- checkpoint-196000/optimizer.pt +3 -0
- checkpoint-196000/rng_state.pth +3 -0
- checkpoint-196000/scheduler.pt +3 -0
04.pretrain.sh
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env bash
|
| 2 |
+
set -e
|
| 3 |
+
|
| 4 |
+
# --- initialize conda ---
|
| 5 |
+
source /root/miniconda3/etc/profile.d/conda.sh
|
| 6 |
+
|
| 7 |
+
# --- activate env ---
|
| 8 |
+
conda activate bpe_v2
|
| 9 |
+
|
| 10 |
+
# select GPU
|
| 11 |
+
work_dir=/root/NaN/dna-tokenizer
|
| 12 |
+
data_dir=${work_dir}/dna-tokenizer-data
|
| 13 |
+
cache_dir=${data_dir}/cache
|
| 14 |
+
|
| 15 |
+
# runnum=len2_2048
|
| 16 |
+
runnum=base_5120
|
| 17 |
+
|
| 18 |
+
mkdir -p ${work_dir}/pretrain/models/model_${runnum}
|
| 19 |
+
output_dir=${work_dir}/pretrain/models/model_${runnum}
|
| 20 |
+
|
| 21 |
+
# export CUDA_VISIBLE_DEVICES=0
|
| 22 |
+
# export WORLD_SIZE=1
|
| 23 |
+
# export RANK=0
|
| 24 |
+
# export LOCAL_RANK=0
|
| 25 |
+
# export MASTER_ADDR=127.0.0.1
|
| 26 |
+
# export MASTER_PORT=29500
|
| 27 |
+
|
| 28 |
+
cp 04.pretrain.sh ${output_dir}
|
| 29 |
+
torchrun --nproc_per_node=8 run_mlm.py \
|
| 30 |
+
--output_dir ${output_dir} \
|
| 31 |
+
--model_type bert \
|
| 32 |
+
--tokenizer_name ${work_dir}/baseline_bpe/vocab_5120/5120_tokenizer.json \
|
| 33 |
+
--config_name ${work_dir}/BPE_merge/config_5120.json \
|
| 34 |
+
--project_name token_eval_base_5120 \
|
| 35 |
+
--do_train True \
|
| 36 |
+
--model_max_length 512 \
|
| 37 |
+
--max_seq_length 512 \
|
| 38 |
+
--line_by_line True \
|
| 39 |
+
--pad_to_max_length True \
|
| 40 |
+
--train_file ${data_dir}/baseline_bpe_5120_allchr_all_tokenized_train_chrOnly.tsv \
|
| 41 |
+
--validation_file ${data_dir}/baseline_bpe_5120_allchr_all_tokenized_val_chrOnly.tsv \
|
| 42 |
+
--cache_dir ${cache_dir} \
|
| 43 |
+
--use_fast_tokenizer True \
|
| 44 |
+
--do_eval True \
|
| 45 |
+
--gradient_accumulation_steps 1 \
|
| 46 |
+
--per_device_train_batch_size 96 \
|
| 47 |
+
--per_device_eval_batch_size 96 \
|
| 48 |
+
--save_steps 1000 \
|
| 49 |
+
--save_total_limit 10 \
|
| 50 |
+
--max_steps 100000 \
|
| 51 |
+
--logging_steps 1000 \
|
| 52 |
+
--learning_rate 4e-5 \
|
| 53 |
+
--adam_epsilon 1e-6 \
|
| 54 |
+
--weight_decay 0.01 \
|
| 55 |
+
--adam_beta1 0.9 \
|
| 56 |
+
--adam_beta2 0.98 \
|
| 57 |
+
--mlm_probability 0.15 \
|
| 58 |
+
--warmup_steps 10000 \
|
| 59 |
+
--seed 42 \
|
| 60 |
+
--preprocessing_num_workers 8 \
|
| 61 |
+
--overwrite_output_dir True
|
| 62 |
+
# --resume_from_checkpoint /root/NaN/dna-tokenizer/pretrain/models/model_base_2048/checkpoint-37000
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
|
04.pretrain_200k_base_5120.sh
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/bin/bash
|
| 2 |
+
# Activate conda
|
| 3 |
+
source ~/miniconda3/etc/profile.d/conda.sh
|
| 4 |
+
conda activate bpe
|
| 5 |
+
|
| 6 |
+
# select GPU
|
| 7 |
+
export CUDA_VISIBLE_DEVICES=4
|
| 8 |
+
|
| 9 |
+
work_dir=/home/n5huang/dna_token
|
| 10 |
+
data_dir=${work_dir}/output_tokens
|
| 11 |
+
cache_dir=${data_dir}/cache
|
| 12 |
+
|
| 13 |
+
runnum=base_5120
|
| 14 |
+
|
| 15 |
+
# -p to use existing directory
|
| 16 |
+
mkdir -p ${work_dir}/pretrain/models/${runnum}
|
| 17 |
+
output_dir=${work_dir}/pretrain/models/${runnum}
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
cp /home/n5huang/dna-tokenizer/BPE_merge/04.pretrain_200k_base_5120.sh ${output_dir}
|
| 21 |
+
python /home/n5huang/dna-tokenizer/BPE_merge/run_mlm_200k.py \
|
| 22 |
+
--output_dir ${output_dir} \
|
| 23 |
+
--model_type bert \
|
| 24 |
+
--tokenizer_name ${work_dir}/tokenizer_evaluation/baseline_bpe/vocab_5120/5120_tokenizer.json \
|
| 25 |
+
--config_name ${work_dir}/pretrain/models/base_5120/config.json \
|
| 26 |
+
--project_name token_eval_base_5120 \
|
| 27 |
+
--do_train True \
|
| 28 |
+
--model_max_length 512 \
|
| 29 |
+
--max_seq_length 512 \
|
| 30 |
+
--line_by_line True \
|
| 31 |
+
--pad_to_max_length True \
|
| 32 |
+
--train_file ${data_dir}/baseline_bpe_5120_allchr_all_tokenized_train_chrOnly.tsv \
|
| 33 |
+
--validation_file ${data_dir}/baseline_bpe_5120_allchr_all_tokenized_val_chrOnly.tsv \
|
| 34 |
+
--cache_dir ${cache_dir} \
|
| 35 |
+
--use_fast_tokenizer True \
|
| 36 |
+
--do_eval True \
|
| 37 |
+
--gradient_accumulation_steps 1 \
|
| 38 |
+
--per_device_train_batch_size 96 \
|
| 39 |
+
--per_device_eval_batch_size 96 \
|
| 40 |
+
--save_steps 1000 \
|
| 41 |
+
--save_total_limit 10 \
|
| 42 |
+
--max_steps 200000 \
|
| 43 |
+
--logging_steps 1000 \
|
| 44 |
+
--learning_rate 4e-5 \
|
| 45 |
+
--adam_epsilon 1e-6 \
|
| 46 |
+
--weight_decay 0.01 \
|
| 47 |
+
--adam_beta1 0.9 \
|
| 48 |
+
--adam_beta2 0.98 \
|
| 49 |
+
--mlm_probability 0.15 \
|
| 50 |
+
--warmup_steps 10000 \
|
| 51 |
+
--seed 42 \
|
| 52 |
+
--preprocessing_num_workers 8 \
|
| 53 |
+
--resume_from_checkpoint /home/n5huang/dna_token/pretrain/models/base_5120/checkpoint-100000
|
| 54 |
+
|
README.md
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
model-index:
|
| 7 |
+
- name: base_5120
|
| 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 |
+
# base_5120
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 5.0263
|
| 19 |
+
- Accuracy: 0.2365
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 4e-05
|
| 39 |
+
- train_batch_size: 96
|
| 40 |
+
- eval_batch_size: 96
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- lr_scheduler_warmup_steps: 10000
|
| 45 |
+
- training_steps: 200000
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
### Framework versions
|
| 52 |
+
|
| 53 |
+
- Transformers 4.35.2
|
| 54 |
+
- Pytorch 2.8.0+cu128
|
| 55 |
+
- Datasets 4.4.1
|
| 56 |
+
- Tokenizers 0.15.2
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.2,
|
| 3 |
+
"eval_accuracy": 0.23648028980869085,
|
| 4 |
+
"eval_loss": 5.026269435882568,
|
| 5 |
+
"eval_runtime": 1174.1399,
|
| 6 |
+
"eval_samples": 105689,
|
| 7 |
+
"eval_samples_per_second": 90.014,
|
| 8 |
+
"eval_step": 200000,
|
| 9 |
+
"eval_steps_per_second": 0.938,
|
| 10 |
+
"perplexity": 152.3635491566444,
|
| 11 |
+
"train_loss": 2.548693740234375,
|
| 12 |
+
"train_runtime": 257533.7655,
|
| 13 |
+
"train_samples": 950449,
|
| 14 |
+
"train_samples_per_second": 74.553,
|
| 15 |
+
"train_steps_per_second": 0.777
|
| 16 |
+
}
|
checkpoint-191000/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 12 |
+
"layer_norm_eps": 1e-12,
|
| 13 |
+
"max_length": 512,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.35.2",
|
| 22 |
+
"type_vocab_size": 2,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 5120
|
| 25 |
+
}
|
checkpoint-191000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"max_length": 512,
|
| 4 |
+
"pad_token_id": 0,
|
| 5 |
+
"transformers_version": "4.35.2"
|
| 6 |
+
}
|
checkpoint-191000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca29308ed4d7d18a3575675ff451eef120710fa541ee8ed54a4c6a0cbbaa2064
|
| 3 |
+
size 359944256
|
checkpoint-191000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d773953d8d27b3c38fe4a2025a6c88f2b4f5d25df60628f36d59fd855d94b5df
|
| 3 |
+
size 720010699
|
checkpoint-191000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acbc4c64cd953ee6b38ce701fa7ba01b6b8927333c73a8d03cb07ca265667bae
|
| 3 |
+
size 14645
|
checkpoint-191000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03801543841a49721ffa8d88e86d4edc246ccb0f1b28ddcb8c3e3197118fe676
|
| 3 |
+
size 1465
|
checkpoint-191000/trainer_state.json
ADDED
|
@@ -0,0 +1,1165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 19.29098070901929,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 191000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.81,
|
| 13 |
+
"learning_rate": 4.000000000000001e-06,
|
| 14 |
+
"loss": 7.87,
|
| 15 |
+
"step": 1000
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.62,
|
| 19 |
+
"learning_rate": 8.000000000000001e-06,
|
| 20 |
+
"loss": 6.8831,
|
| 21 |
+
"step": 2000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 2.42,
|
| 25 |
+
"learning_rate": 1.2e-05,
|
| 26 |
+
"loss": 6.7256,
|
| 27 |
+
"step": 3000
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 3.23,
|
| 31 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 32 |
+
"loss": 6.6605,
|
| 33 |
+
"step": 4000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 4.04,
|
| 37 |
+
"learning_rate": 2e-05,
|
| 38 |
+
"loss": 6.6243,
|
| 39 |
+
"step": 5000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 4.85,
|
| 43 |
+
"learning_rate": 2.4e-05,
|
| 44 |
+
"loss": 6.6033,
|
| 45 |
+
"step": 6000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 5.65,
|
| 49 |
+
"learning_rate": 2.8e-05,
|
| 50 |
+
"loss": 6.5906,
|
| 51 |
+
"step": 7000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 6.46,
|
| 55 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 56 |
+
"loss": 6.5772,
|
| 57 |
+
"step": 8000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 7.27,
|
| 61 |
+
"learning_rate": 3.6e-05,
|
| 62 |
+
"loss": 6.5718,
|
| 63 |
+
"step": 9000
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 8.08,
|
| 67 |
+
"learning_rate": 4e-05,
|
| 68 |
+
"loss": 6.5653,
|
| 69 |
+
"step": 10000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 8.89,
|
| 73 |
+
"learning_rate": 3.955555555555556e-05,
|
| 74 |
+
"loss": 6.5602,
|
| 75 |
+
"step": 11000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 9.69,
|
| 79 |
+
"learning_rate": 3.9111111111111115e-05,
|
| 80 |
+
"loss": 6.5572,
|
| 81 |
+
"step": 12000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 10.5,
|
| 85 |
+
"learning_rate": 3.866666666666667e-05,
|
| 86 |
+
"loss": 6.5534,
|
| 87 |
+
"step": 13000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 11.31,
|
| 91 |
+
"learning_rate": 3.8222222222222226e-05,
|
| 92 |
+
"loss": 6.5533,
|
| 93 |
+
"step": 14000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 12.12,
|
| 97 |
+
"learning_rate": 3.777777777777778e-05,
|
| 98 |
+
"loss": 6.547,
|
| 99 |
+
"step": 15000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 12.92,
|
| 103 |
+
"learning_rate": 3.733333333333334e-05,
|
| 104 |
+
"loss": 6.5463,
|
| 105 |
+
"step": 16000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 13.73,
|
| 109 |
+
"learning_rate": 3.6888888888888896e-05,
|
| 110 |
+
"loss": 6.5437,
|
| 111 |
+
"step": 17000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 14.54,
|
| 115 |
+
"learning_rate": 3.644444444444445e-05,
|
| 116 |
+
"loss": 6.5322,
|
| 117 |
+
"step": 18000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 15.35,
|
| 121 |
+
"learning_rate": 3.6e-05,
|
| 122 |
+
"loss": 6.4474,
|
| 123 |
+
"step": 19000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 16.16,
|
| 127 |
+
"learning_rate": 3.555555555555555e-05,
|
| 128 |
+
"loss": 6.3968,
|
| 129 |
+
"step": 20000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 16.96,
|
| 133 |
+
"learning_rate": 3.511111111111111e-05,
|
| 134 |
+
"loss": 6.3516,
|
| 135 |
+
"step": 21000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 17.77,
|
| 139 |
+
"learning_rate": 3.466666666666667e-05,
|
| 140 |
+
"loss": 6.311,
|
| 141 |
+
"step": 22000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 18.58,
|
| 145 |
+
"learning_rate": 3.4222222222222224e-05,
|
| 146 |
+
"loss": 6.2707,
|
| 147 |
+
"step": 23000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 19.39,
|
| 151 |
+
"learning_rate": 3.377777777777778e-05,
|
| 152 |
+
"loss": 6.2294,
|
| 153 |
+
"step": 24000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 20.19,
|
| 157 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 158 |
+
"loss": 6.1822,
|
| 159 |
+
"step": 25000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 21.0,
|
| 163 |
+
"learning_rate": 3.288888888888889e-05,
|
| 164 |
+
"loss": 6.1128,
|
| 165 |
+
"step": 26000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 21.81,
|
| 169 |
+
"learning_rate": 3.2444444444444446e-05,
|
| 170 |
+
"loss": 6.0262,
|
| 171 |
+
"step": 27000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 22.62,
|
| 175 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 176 |
+
"loss": 5.9326,
|
| 177 |
+
"step": 28000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 23.42,
|
| 181 |
+
"learning_rate": 3.155555555555556e-05,
|
| 182 |
+
"loss": 5.8051,
|
| 183 |
+
"step": 29000
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 24.23,
|
| 187 |
+
"learning_rate": 3.111111111111112e-05,
|
| 188 |
+
"loss": 5.703,
|
| 189 |
+
"step": 30000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 25.04,
|
| 193 |
+
"learning_rate": 3.066666666666667e-05,
|
| 194 |
+
"loss": 5.6361,
|
| 195 |
+
"step": 31000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 25.85,
|
| 199 |
+
"learning_rate": 3.0222222222222225e-05,
|
| 200 |
+
"loss": 5.5885,
|
| 201 |
+
"step": 32000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 26.66,
|
| 205 |
+
"learning_rate": 2.977777777777778e-05,
|
| 206 |
+
"loss": 5.5487,
|
| 207 |
+
"step": 33000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 27.46,
|
| 211 |
+
"learning_rate": 2.9333333333333333e-05,
|
| 212 |
+
"loss": 5.5163,
|
| 213 |
+
"step": 34000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 28.27,
|
| 217 |
+
"learning_rate": 2.888888888888889e-05,
|
| 218 |
+
"loss": 5.4922,
|
| 219 |
+
"step": 35000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 29.08,
|
| 223 |
+
"learning_rate": 2.8444444444444447e-05,
|
| 224 |
+
"loss": 5.4659,
|
| 225 |
+
"step": 36000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 29.89,
|
| 229 |
+
"learning_rate": 2.8e-05,
|
| 230 |
+
"loss": 5.4453,
|
| 231 |
+
"step": 37000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 30.69,
|
| 235 |
+
"learning_rate": 2.755555555555556e-05,
|
| 236 |
+
"loss": 5.4257,
|
| 237 |
+
"step": 38000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 31.5,
|
| 241 |
+
"learning_rate": 2.7111111111111114e-05,
|
| 242 |
+
"loss": 5.4111,
|
| 243 |
+
"step": 39000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 32.31,
|
| 247 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 248 |
+
"loss": 5.3939,
|
| 249 |
+
"step": 40000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 33.12,
|
| 253 |
+
"learning_rate": 2.6222222222222226e-05,
|
| 254 |
+
"loss": 5.3814,
|
| 255 |
+
"step": 41000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 33.93,
|
| 259 |
+
"learning_rate": 2.577777777777778e-05,
|
| 260 |
+
"loss": 5.3658,
|
| 261 |
+
"step": 42000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 34.73,
|
| 265 |
+
"learning_rate": 2.5333333333333334e-05,
|
| 266 |
+
"loss": 5.353,
|
| 267 |
+
"step": 43000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 35.54,
|
| 271 |
+
"learning_rate": 2.4888888888888893e-05,
|
| 272 |
+
"loss": 5.3419,
|
| 273 |
+
"step": 44000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 36.35,
|
| 277 |
+
"learning_rate": 2.444444444444445e-05,
|
| 278 |
+
"loss": 5.3312,
|
| 279 |
+
"step": 45000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 37.16,
|
| 283 |
+
"learning_rate": 2.4e-05,
|
| 284 |
+
"loss": 5.3217,
|
| 285 |
+
"step": 46000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 37.96,
|
| 289 |
+
"learning_rate": 2.355555555555556e-05,
|
| 290 |
+
"loss": 5.3111,
|
| 291 |
+
"step": 47000
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 38.77,
|
| 295 |
+
"learning_rate": 2.3111111111111112e-05,
|
| 296 |
+
"loss": 5.3013,
|
| 297 |
+
"step": 48000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 39.58,
|
| 301 |
+
"learning_rate": 2.2666666666666668e-05,
|
| 302 |
+
"loss": 5.291,
|
| 303 |
+
"step": 49000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 40.39,
|
| 307 |
+
"learning_rate": 2.2222222222222227e-05,
|
| 308 |
+
"loss": 5.2835,
|
| 309 |
+
"step": 50000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 41.2,
|
| 313 |
+
"learning_rate": 2.177777777777778e-05,
|
| 314 |
+
"loss": 5.2753,
|
| 315 |
+
"step": 51000
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 42.0,
|
| 319 |
+
"learning_rate": 2.1333333333333335e-05,
|
| 320 |
+
"loss": 5.2666,
|
| 321 |
+
"step": 52000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 42.81,
|
| 325 |
+
"learning_rate": 2.088888888888889e-05,
|
| 326 |
+
"loss": 5.2594,
|
| 327 |
+
"step": 53000
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 43.62,
|
| 331 |
+
"learning_rate": 2.0444444444444446e-05,
|
| 332 |
+
"loss": 5.2513,
|
| 333 |
+
"step": 54000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 44.43,
|
| 337 |
+
"learning_rate": 2e-05,
|
| 338 |
+
"loss": 5.2441,
|
| 339 |
+
"step": 55000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 45.23,
|
| 343 |
+
"learning_rate": 1.9555555555555557e-05,
|
| 344 |
+
"loss": 5.2426,
|
| 345 |
+
"step": 56000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 46.04,
|
| 349 |
+
"learning_rate": 1.9111111111111113e-05,
|
| 350 |
+
"loss": 5.2328,
|
| 351 |
+
"step": 57000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 46.85,
|
| 355 |
+
"learning_rate": 1.866666666666667e-05,
|
| 356 |
+
"loss": 5.2278,
|
| 357 |
+
"step": 58000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 47.66,
|
| 361 |
+
"learning_rate": 1.8222222222222224e-05,
|
| 362 |
+
"loss": 5.2213,
|
| 363 |
+
"step": 59000
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 48.47,
|
| 367 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 368 |
+
"loss": 5.2155,
|
| 369 |
+
"step": 60000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 49.27,
|
| 373 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 374 |
+
"loss": 5.2102,
|
| 375 |
+
"step": 61000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 50.08,
|
| 379 |
+
"learning_rate": 1.688888888888889e-05,
|
| 380 |
+
"loss": 5.2048,
|
| 381 |
+
"step": 62000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 50.89,
|
| 385 |
+
"learning_rate": 1.6444444444444444e-05,
|
| 386 |
+
"loss": 5.2008,
|
| 387 |
+
"step": 63000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 51.7,
|
| 391 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 392 |
+
"loss": 5.1975,
|
| 393 |
+
"step": 64000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 52.5,
|
| 397 |
+
"learning_rate": 1.555555555555556e-05,
|
| 398 |
+
"loss": 5.1925,
|
| 399 |
+
"step": 65000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 53.31,
|
| 403 |
+
"learning_rate": 1.5111111111111112e-05,
|
| 404 |
+
"loss": 5.1883,
|
| 405 |
+
"step": 66000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 54.12,
|
| 409 |
+
"learning_rate": 1.4666666666666666e-05,
|
| 410 |
+
"loss": 5.1822,
|
| 411 |
+
"step": 67000
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 54.93,
|
| 415 |
+
"learning_rate": 1.4222222222222224e-05,
|
| 416 |
+
"loss": 5.1806,
|
| 417 |
+
"step": 68000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 55.74,
|
| 421 |
+
"learning_rate": 1.377777777777778e-05,
|
| 422 |
+
"loss": 5.1756,
|
| 423 |
+
"step": 69000
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 56.54,
|
| 427 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 428 |
+
"loss": 5.175,
|
| 429 |
+
"step": 70000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 57.35,
|
| 433 |
+
"learning_rate": 1.288888888888889e-05,
|
| 434 |
+
"loss": 5.1686,
|
| 435 |
+
"step": 71000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 58.16,
|
| 439 |
+
"learning_rate": 1.2444444444444446e-05,
|
| 440 |
+
"loss": 5.1672,
|
| 441 |
+
"step": 72000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 58.97,
|
| 445 |
+
"learning_rate": 1.2e-05,
|
| 446 |
+
"loss": 5.1644,
|
| 447 |
+
"step": 73000
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 59.77,
|
| 451 |
+
"learning_rate": 1.1555555555555556e-05,
|
| 452 |
+
"loss": 5.1609,
|
| 453 |
+
"step": 74000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 60.58,
|
| 457 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 458 |
+
"loss": 5.1582,
|
| 459 |
+
"step": 75000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 61.39,
|
| 463 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 464 |
+
"loss": 5.1539,
|
| 465 |
+
"step": 76000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 62.2,
|
| 469 |
+
"learning_rate": 1.0222222222222223e-05,
|
| 470 |
+
"loss": 5.1535,
|
| 471 |
+
"step": 77000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 63.0,
|
| 475 |
+
"learning_rate": 9.777777777777779e-06,
|
| 476 |
+
"loss": 5.1516,
|
| 477 |
+
"step": 78000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 63.81,
|
| 481 |
+
"learning_rate": 9.333333333333334e-06,
|
| 482 |
+
"loss": 5.1479,
|
| 483 |
+
"step": 79000
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 64.62,
|
| 487 |
+
"learning_rate": 8.888888888888888e-06,
|
| 488 |
+
"loss": 5.1451,
|
| 489 |
+
"step": 80000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 65.43,
|
| 493 |
+
"learning_rate": 8.444444444444446e-06,
|
| 494 |
+
"loss": 5.1439,
|
| 495 |
+
"step": 81000
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 66.24,
|
| 499 |
+
"learning_rate": 8.000000000000001e-06,
|
| 500 |
+
"loss": 5.1429,
|
| 501 |
+
"step": 82000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 67.04,
|
| 505 |
+
"learning_rate": 7.555555555555556e-06,
|
| 506 |
+
"loss": 5.1402,
|
| 507 |
+
"step": 83000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 67.85,
|
| 511 |
+
"learning_rate": 7.111111111111112e-06,
|
| 512 |
+
"loss": 5.1375,
|
| 513 |
+
"step": 84000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 68.66,
|
| 517 |
+
"learning_rate": 6.666666666666667e-06,
|
| 518 |
+
"loss": 5.1348,
|
| 519 |
+
"step": 85000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 69.47,
|
| 523 |
+
"learning_rate": 6.222222222222223e-06,
|
| 524 |
+
"loss": 5.1357,
|
| 525 |
+
"step": 86000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 70.27,
|
| 529 |
+
"learning_rate": 5.777777777777778e-06,
|
| 530 |
+
"loss": 5.1336,
|
| 531 |
+
"step": 87000
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 71.08,
|
| 535 |
+
"learning_rate": 5.333333333333334e-06,
|
| 536 |
+
"loss": 5.1308,
|
| 537 |
+
"step": 88000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 71.89,
|
| 541 |
+
"learning_rate": 4.888888888888889e-06,
|
| 542 |
+
"loss": 5.1304,
|
| 543 |
+
"step": 89000
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 72.7,
|
| 547 |
+
"learning_rate": 4.444444444444444e-06,
|
| 548 |
+
"loss": 5.1285,
|
| 549 |
+
"step": 90000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 73.51,
|
| 553 |
+
"learning_rate": 4.000000000000001e-06,
|
| 554 |
+
"loss": 5.1272,
|
| 555 |
+
"step": 91000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 74.31,
|
| 559 |
+
"learning_rate": 3.555555555555556e-06,
|
| 560 |
+
"loss": 5.1272,
|
| 561 |
+
"step": 92000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 75.12,
|
| 565 |
+
"learning_rate": 3.1111111111111116e-06,
|
| 566 |
+
"loss": 5.1281,
|
| 567 |
+
"step": 93000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 75.93,
|
| 571 |
+
"learning_rate": 2.666666666666667e-06,
|
| 572 |
+
"loss": 5.1257,
|
| 573 |
+
"step": 94000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 76.74,
|
| 577 |
+
"learning_rate": 2.222222222222222e-06,
|
| 578 |
+
"loss": 5.1245,
|
| 579 |
+
"step": 95000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 77.54,
|
| 583 |
+
"learning_rate": 1.777777777777778e-06,
|
| 584 |
+
"loss": 5.1244,
|
| 585 |
+
"step": 96000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 78.35,
|
| 589 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 590 |
+
"loss": 5.1229,
|
| 591 |
+
"step": 97000
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 79.16,
|
| 595 |
+
"learning_rate": 8.88888888888889e-07,
|
| 596 |
+
"loss": 5.1223,
|
| 597 |
+
"step": 98000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 79.97,
|
| 601 |
+
"learning_rate": 4.444444444444445e-07,
|
| 602 |
+
"loss": 5.1231,
|
| 603 |
+
"step": 99000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 80.78,
|
| 607 |
+
"learning_rate": 0.0,
|
| 608 |
+
"loss": 5.1203,
|
| 609 |
+
"step": 100000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 10.2,
|
| 613 |
+
"learning_rate": 2.0842105263157895e-05,
|
| 614 |
+
"loss": 5.1411,
|
| 615 |
+
"step": 101000
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 10.3,
|
| 619 |
+
"learning_rate": 2.0631578947368425e-05,
|
| 620 |
+
"loss": 5.1408,
|
| 621 |
+
"step": 102000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 10.4,
|
| 625 |
+
"learning_rate": 2.0421052631578952e-05,
|
| 626 |
+
"loss": 5.1433,
|
| 627 |
+
"step": 103000
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 10.5,
|
| 631 |
+
"learning_rate": 2.0210526315789475e-05,
|
| 632 |
+
"loss": 5.154,
|
| 633 |
+
"step": 104000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 10.6,
|
| 637 |
+
"learning_rate": 2e-05,
|
| 638 |
+
"loss": 5.1553,
|
| 639 |
+
"step": 105000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 10.71,
|
| 643 |
+
"learning_rate": 1.9789473684210528e-05,
|
| 644 |
+
"loss": 5.1442,
|
| 645 |
+
"step": 106000
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 10.81,
|
| 649 |
+
"learning_rate": 1.9578947368421055e-05,
|
| 650 |
+
"loss": 5.1442,
|
| 651 |
+
"step": 107000
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 10.91,
|
| 655 |
+
"learning_rate": 1.936842105263158e-05,
|
| 656 |
+
"loss": 5.147,
|
| 657 |
+
"step": 108000
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 11.01,
|
| 661 |
+
"learning_rate": 1.9157894736842108e-05,
|
| 662 |
+
"loss": 5.1433,
|
| 663 |
+
"step": 109000
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 11.11,
|
| 667 |
+
"learning_rate": 1.894736842105263e-05,
|
| 668 |
+
"loss": 5.1374,
|
| 669 |
+
"step": 110000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 11.21,
|
| 673 |
+
"learning_rate": 1.873684210526316e-05,
|
| 674 |
+
"loss": 5.1411,
|
| 675 |
+
"step": 111000
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 11.31,
|
| 679 |
+
"learning_rate": 1.8526315789473684e-05,
|
| 680 |
+
"loss": 5.1371,
|
| 681 |
+
"step": 112000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 11.41,
|
| 685 |
+
"learning_rate": 1.831578947368421e-05,
|
| 686 |
+
"loss": 5.1379,
|
| 687 |
+
"step": 113000
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 11.51,
|
| 691 |
+
"learning_rate": 1.810526315789474e-05,
|
| 692 |
+
"loss": 5.139,
|
| 693 |
+
"step": 114000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 11.61,
|
| 697 |
+
"learning_rate": 1.7894736842105264e-05,
|
| 698 |
+
"loss": 5.131,
|
| 699 |
+
"step": 115000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 11.72,
|
| 703 |
+
"learning_rate": 1.768421052631579e-05,
|
| 704 |
+
"loss": 5.1313,
|
| 705 |
+
"step": 116000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 11.82,
|
| 709 |
+
"learning_rate": 1.7473684210526317e-05,
|
| 710 |
+
"loss": 5.1287,
|
| 711 |
+
"step": 117000
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 11.92,
|
| 715 |
+
"learning_rate": 1.7263157894736843e-05,
|
| 716 |
+
"loss": 5.1304,
|
| 717 |
+
"step": 118000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 12.02,
|
| 721 |
+
"learning_rate": 1.705263157894737e-05,
|
| 722 |
+
"loss": 5.1309,
|
| 723 |
+
"step": 119000
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 12.12,
|
| 727 |
+
"learning_rate": 1.6842105263157896e-05,
|
| 728 |
+
"loss": 5.1256,
|
| 729 |
+
"step": 120000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 12.22,
|
| 733 |
+
"learning_rate": 1.6631578947368423e-05,
|
| 734 |
+
"loss": 5.1202,
|
| 735 |
+
"step": 121000
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 12.32,
|
| 739 |
+
"learning_rate": 1.642105263157895e-05,
|
| 740 |
+
"loss": 5.125,
|
| 741 |
+
"step": 122000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 12.42,
|
| 745 |
+
"learning_rate": 1.6210526315789473e-05,
|
| 746 |
+
"loss": 5.125,
|
| 747 |
+
"step": 123000
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 12.52,
|
| 751 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 752 |
+
"loss": 5.1259,
|
| 753 |
+
"step": 124000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 12.62,
|
| 757 |
+
"learning_rate": 1.578947368421053e-05,
|
| 758 |
+
"loss": 5.1186,
|
| 759 |
+
"step": 125000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 12.73,
|
| 763 |
+
"learning_rate": 1.5578947368421052e-05,
|
| 764 |
+
"loss": 5.1097,
|
| 765 |
+
"step": 126000
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 12.83,
|
| 769 |
+
"learning_rate": 1.536842105263158e-05,
|
| 770 |
+
"loss": 5.12,
|
| 771 |
+
"step": 127000
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 12.93,
|
| 775 |
+
"learning_rate": 1.5157894736842107e-05,
|
| 776 |
+
"loss": 5.123,
|
| 777 |
+
"step": 128000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 13.03,
|
| 781 |
+
"learning_rate": 1.4947368421052632e-05,
|
| 782 |
+
"loss": 5.1113,
|
| 783 |
+
"step": 129000
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 13.13,
|
| 787 |
+
"learning_rate": 1.4736842105263159e-05,
|
| 788 |
+
"loss": 5.1071,
|
| 789 |
+
"step": 130000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 13.23,
|
| 793 |
+
"learning_rate": 1.4526315789473687e-05,
|
| 794 |
+
"loss": 5.1167,
|
| 795 |
+
"step": 131000
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 13.33,
|
| 799 |
+
"learning_rate": 1.4315789473684212e-05,
|
| 800 |
+
"loss": 5.1153,
|
| 801 |
+
"step": 132000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 13.43,
|
| 805 |
+
"learning_rate": 1.4105263157894738e-05,
|
| 806 |
+
"loss": 5.1171,
|
| 807 |
+
"step": 133000
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 13.53,
|
| 811 |
+
"learning_rate": 1.3894736842105265e-05,
|
| 812 |
+
"loss": 5.1101,
|
| 813 |
+
"step": 134000
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 13.63,
|
| 817 |
+
"learning_rate": 1.3684210526315791e-05,
|
| 818 |
+
"loss": 5.1096,
|
| 819 |
+
"step": 135000
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 13.74,
|
| 823 |
+
"learning_rate": 1.3473684210526316e-05,
|
| 824 |
+
"loss": 5.107,
|
| 825 |
+
"step": 136000
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 13.84,
|
| 829 |
+
"learning_rate": 1.3263157894736843e-05,
|
| 830 |
+
"loss": 5.1048,
|
| 831 |
+
"step": 137000
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 13.94,
|
| 835 |
+
"learning_rate": 1.305263157894737e-05,
|
| 836 |
+
"loss": 5.1077,
|
| 837 |
+
"step": 138000
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 14.04,
|
| 841 |
+
"learning_rate": 1.2842105263157896e-05,
|
| 842 |
+
"loss": 5.0998,
|
| 843 |
+
"step": 139000
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 14.14,
|
| 847 |
+
"learning_rate": 1.263157894736842e-05,
|
| 848 |
+
"loss": 5.1014,
|
| 849 |
+
"step": 140000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 14.24,
|
| 853 |
+
"learning_rate": 1.2421052631578949e-05,
|
| 854 |
+
"loss": 5.1028,
|
| 855 |
+
"step": 141000
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 14.34,
|
| 859 |
+
"learning_rate": 1.2210526315789475e-05,
|
| 860 |
+
"loss": 5.1065,
|
| 861 |
+
"step": 142000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 14.44,
|
| 865 |
+
"learning_rate": 1.2e-05,
|
| 866 |
+
"loss": 5.1024,
|
| 867 |
+
"step": 143000
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 14.54,
|
| 871 |
+
"learning_rate": 1.1789473684210527e-05,
|
| 872 |
+
"loss": 5.1055,
|
| 873 |
+
"step": 144000
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 14.64,
|
| 877 |
+
"learning_rate": 1.1578947368421053e-05,
|
| 878 |
+
"loss": 5.0966,
|
| 879 |
+
"step": 145000
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 14.75,
|
| 883 |
+
"learning_rate": 1.136842105263158e-05,
|
| 884 |
+
"loss": 5.0939,
|
| 885 |
+
"step": 146000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 14.85,
|
| 889 |
+
"learning_rate": 1.1157894736842105e-05,
|
| 890 |
+
"loss": 5.0932,
|
| 891 |
+
"step": 147000
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 14.95,
|
| 895 |
+
"learning_rate": 1.0947368421052633e-05,
|
| 896 |
+
"loss": 5.0971,
|
| 897 |
+
"step": 148000
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 15.05,
|
| 901 |
+
"learning_rate": 1.073684210526316e-05,
|
| 902 |
+
"loss": 5.0802,
|
| 903 |
+
"step": 149000
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 15.15,
|
| 907 |
+
"learning_rate": 1.0526315789473684e-05,
|
| 908 |
+
"loss": 5.0969,
|
| 909 |
+
"step": 150000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 15.25,
|
| 913 |
+
"learning_rate": 1.0315789473684213e-05,
|
| 914 |
+
"loss": 5.0889,
|
| 915 |
+
"step": 151000
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 15.35,
|
| 919 |
+
"learning_rate": 1.0105263157894738e-05,
|
| 920 |
+
"loss": 5.0934,
|
| 921 |
+
"step": 152000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 15.45,
|
| 925 |
+
"learning_rate": 9.894736842105264e-06,
|
| 926 |
+
"loss": 5.0961,
|
| 927 |
+
"step": 153000
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 15.55,
|
| 931 |
+
"learning_rate": 9.68421052631579e-06,
|
| 932 |
+
"loss": 5.0874,
|
| 933 |
+
"step": 154000
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 15.65,
|
| 937 |
+
"learning_rate": 9.473684210526315e-06,
|
| 938 |
+
"loss": 5.0896,
|
| 939 |
+
"step": 155000
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 15.76,
|
| 943 |
+
"learning_rate": 9.263157894736842e-06,
|
| 944 |
+
"loss": 5.0879,
|
| 945 |
+
"step": 156000
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 15.86,
|
| 949 |
+
"learning_rate": 9.05263157894737e-06,
|
| 950 |
+
"loss": 5.0848,
|
| 951 |
+
"step": 157000
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 15.96,
|
| 955 |
+
"learning_rate": 8.842105263157895e-06,
|
| 956 |
+
"loss": 5.0879,
|
| 957 |
+
"step": 158000
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 16.06,
|
| 961 |
+
"learning_rate": 8.631578947368422e-06,
|
| 962 |
+
"loss": 5.0799,
|
| 963 |
+
"step": 159000
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 16.16,
|
| 967 |
+
"learning_rate": 8.421052631578948e-06,
|
| 968 |
+
"loss": 5.0847,
|
| 969 |
+
"step": 160000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 16.26,
|
| 973 |
+
"learning_rate": 8.210526315789475e-06,
|
| 974 |
+
"loss": 5.0897,
|
| 975 |
+
"step": 161000
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 16.36,
|
| 979 |
+
"learning_rate": 8.000000000000001e-06,
|
| 980 |
+
"loss": 5.0799,
|
| 981 |
+
"step": 162000
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 16.46,
|
| 985 |
+
"learning_rate": 7.789473684210526e-06,
|
| 986 |
+
"loss": 5.0847,
|
| 987 |
+
"step": 163000
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 16.56,
|
| 991 |
+
"learning_rate": 7.578947368421054e-06,
|
| 992 |
+
"loss": 5.0764,
|
| 993 |
+
"step": 164000
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 16.66,
|
| 997 |
+
"learning_rate": 7.368421052631579e-06,
|
| 998 |
+
"loss": 5.0756,
|
| 999 |
+
"step": 165000
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 16.77,
|
| 1003 |
+
"learning_rate": 7.157894736842106e-06,
|
| 1004 |
+
"loss": 5.0755,
|
| 1005 |
+
"step": 166000
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 16.87,
|
| 1009 |
+
"learning_rate": 6.947368421052632e-06,
|
| 1010 |
+
"loss": 5.0788,
|
| 1011 |
+
"step": 167000
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 16.97,
|
| 1015 |
+
"learning_rate": 6.736842105263158e-06,
|
| 1016 |
+
"loss": 5.0793,
|
| 1017 |
+
"step": 168000
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 17.07,
|
| 1021 |
+
"learning_rate": 6.526315789473685e-06,
|
| 1022 |
+
"loss": 5.0768,
|
| 1023 |
+
"step": 169000
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 17.17,
|
| 1027 |
+
"learning_rate": 6.31578947368421e-06,
|
| 1028 |
+
"loss": 5.0746,
|
| 1029 |
+
"step": 170000
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 17.27,
|
| 1033 |
+
"learning_rate": 6.105263157894738e-06,
|
| 1034 |
+
"loss": 5.075,
|
| 1035 |
+
"step": 171000
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 17.37,
|
| 1039 |
+
"learning_rate": 5.8947368421052634e-06,
|
| 1040 |
+
"loss": 5.0799,
|
| 1041 |
+
"step": 172000
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 17.47,
|
| 1045 |
+
"learning_rate": 5.68421052631579e-06,
|
| 1046 |
+
"loss": 5.0684,
|
| 1047 |
+
"step": 173000
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 17.57,
|
| 1051 |
+
"learning_rate": 5.4736842105263165e-06,
|
| 1052 |
+
"loss": 5.0741,
|
| 1053 |
+
"step": 174000
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 17.67,
|
| 1057 |
+
"learning_rate": 5.263157894736842e-06,
|
| 1058 |
+
"loss": 5.0756,
|
| 1059 |
+
"step": 175000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 17.78,
|
| 1063 |
+
"learning_rate": 5.052631578947369e-06,
|
| 1064 |
+
"loss": 5.0711,
|
| 1065 |
+
"step": 176000
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 17.88,
|
| 1069 |
+
"learning_rate": 4.842105263157895e-06,
|
| 1070 |
+
"loss": 5.0701,
|
| 1071 |
+
"step": 177000
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 17.98,
|
| 1075 |
+
"learning_rate": 4.631578947368421e-06,
|
| 1076 |
+
"loss": 5.0724,
|
| 1077 |
+
"step": 178000
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 18.08,
|
| 1081 |
+
"learning_rate": 4.4210526315789476e-06,
|
| 1082 |
+
"loss": 5.0729,
|
| 1083 |
+
"step": 179000
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 18.18,
|
| 1087 |
+
"learning_rate": 4.210526315789474e-06,
|
| 1088 |
+
"loss": 5.0667,
|
| 1089 |
+
"step": 180000
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 18.28,
|
| 1093 |
+
"learning_rate": 4.000000000000001e-06,
|
| 1094 |
+
"loss": 5.0692,
|
| 1095 |
+
"step": 181000
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 18.38,
|
| 1099 |
+
"learning_rate": 3.789473684210527e-06,
|
| 1100 |
+
"loss": 5.0714,
|
| 1101 |
+
"step": 182000
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 18.48,
|
| 1105 |
+
"learning_rate": 3.578947368421053e-06,
|
| 1106 |
+
"loss": 5.0662,
|
| 1107 |
+
"step": 183000
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 18.58,
|
| 1111 |
+
"learning_rate": 3.368421052631579e-06,
|
| 1112 |
+
"loss": 5.0726,
|
| 1113 |
+
"step": 184000
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 18.68,
|
| 1117 |
+
"learning_rate": 3.157894736842105e-06,
|
| 1118 |
+
"loss": 5.0743,
|
| 1119 |
+
"step": 185000
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 18.79,
|
| 1123 |
+
"learning_rate": 2.9473684210526317e-06,
|
| 1124 |
+
"loss": 5.059,
|
| 1125 |
+
"step": 186000
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 18.89,
|
| 1129 |
+
"learning_rate": 2.7368421052631583e-06,
|
| 1130 |
+
"loss": 5.064,
|
| 1131 |
+
"step": 187000
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 18.99,
|
| 1135 |
+
"learning_rate": 2.5263157894736844e-06,
|
| 1136 |
+
"loss": 5.0659,
|
| 1137 |
+
"step": 188000
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 19.09,
|
| 1141 |
+
"learning_rate": 2.3157894736842105e-06,
|
| 1142 |
+
"loss": 5.0645,
|
| 1143 |
+
"step": 189000
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 19.19,
|
| 1147 |
+
"learning_rate": 2.105263157894737e-06,
|
| 1148 |
+
"loss": 5.0657,
|
| 1149 |
+
"step": 190000
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 19.29,
|
| 1153 |
+
"learning_rate": 1.8947368421052634e-06,
|
| 1154 |
+
"loss": 5.0674,
|
| 1155 |
+
"step": 191000
|
| 1156 |
+
}
|
| 1157 |
+
],
|
| 1158 |
+
"logging_steps": 1000,
|
| 1159 |
+
"max_steps": 200000,
|
| 1160 |
+
"num_train_epochs": 21,
|
| 1161 |
+
"save_steps": 1000,
|
| 1162 |
+
"total_flos": 2.250670146599597e+19,
|
| 1163 |
+
"trial_name": null,
|
| 1164 |
+
"trial_params": null
|
| 1165 |
+
}
|
checkpoint-191000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f7b759ef851ee3a68e8c9ad880cbb1bc393f7d811df1a445efe7298474f0c09
|
| 3 |
+
size 5137
|
checkpoint-192000/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 12 |
+
"layer_norm_eps": 1e-12,
|
| 13 |
+
"max_length": 512,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.35.2",
|
| 22 |
+
"type_vocab_size": 2,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 5120
|
| 25 |
+
}
|
checkpoint-192000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"max_length": 512,
|
| 4 |
+
"pad_token_id": 0,
|
| 5 |
+
"transformers_version": "4.35.2"
|
| 6 |
+
}
|
checkpoint-192000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56c4aa8ba360a6b1e3cd7340f6d008b5df8cd87e79bd795f5ef9ba9e4fce010e
|
| 3 |
+
size 359944256
|
checkpoint-192000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67a17bde8a67185aaf9f6b462a1e56f97af9d6c9e65b6b7a8f2cc9d51135e176
|
| 3 |
+
size 720010699
|
checkpoint-192000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23866a6a53c857145e79786c035c111dd416d96163de087f4fab581b3059bcc5
|
| 3 |
+
size 14645
|
checkpoint-192000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8987c093fe567c44cd8f1b73e4b15e5d4b9c5495e847cc1b11a0915470ccf64f
|
| 3 |
+
size 1465
|
checkpoint-192000/trainer_state.json
ADDED
|
@@ -0,0 +1,1171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 19.39198060801939,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 192000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.81,
|
| 13 |
+
"learning_rate": 4.000000000000001e-06,
|
| 14 |
+
"loss": 7.87,
|
| 15 |
+
"step": 1000
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.62,
|
| 19 |
+
"learning_rate": 8.000000000000001e-06,
|
| 20 |
+
"loss": 6.8831,
|
| 21 |
+
"step": 2000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 2.42,
|
| 25 |
+
"learning_rate": 1.2e-05,
|
| 26 |
+
"loss": 6.7256,
|
| 27 |
+
"step": 3000
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 3.23,
|
| 31 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 32 |
+
"loss": 6.6605,
|
| 33 |
+
"step": 4000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 4.04,
|
| 37 |
+
"learning_rate": 2e-05,
|
| 38 |
+
"loss": 6.6243,
|
| 39 |
+
"step": 5000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 4.85,
|
| 43 |
+
"learning_rate": 2.4e-05,
|
| 44 |
+
"loss": 6.6033,
|
| 45 |
+
"step": 6000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 5.65,
|
| 49 |
+
"learning_rate": 2.8e-05,
|
| 50 |
+
"loss": 6.5906,
|
| 51 |
+
"step": 7000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 6.46,
|
| 55 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 56 |
+
"loss": 6.5772,
|
| 57 |
+
"step": 8000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 7.27,
|
| 61 |
+
"learning_rate": 3.6e-05,
|
| 62 |
+
"loss": 6.5718,
|
| 63 |
+
"step": 9000
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 8.08,
|
| 67 |
+
"learning_rate": 4e-05,
|
| 68 |
+
"loss": 6.5653,
|
| 69 |
+
"step": 10000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 8.89,
|
| 73 |
+
"learning_rate": 3.955555555555556e-05,
|
| 74 |
+
"loss": 6.5602,
|
| 75 |
+
"step": 11000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 9.69,
|
| 79 |
+
"learning_rate": 3.9111111111111115e-05,
|
| 80 |
+
"loss": 6.5572,
|
| 81 |
+
"step": 12000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 10.5,
|
| 85 |
+
"learning_rate": 3.866666666666667e-05,
|
| 86 |
+
"loss": 6.5534,
|
| 87 |
+
"step": 13000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 11.31,
|
| 91 |
+
"learning_rate": 3.8222222222222226e-05,
|
| 92 |
+
"loss": 6.5533,
|
| 93 |
+
"step": 14000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 12.12,
|
| 97 |
+
"learning_rate": 3.777777777777778e-05,
|
| 98 |
+
"loss": 6.547,
|
| 99 |
+
"step": 15000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 12.92,
|
| 103 |
+
"learning_rate": 3.733333333333334e-05,
|
| 104 |
+
"loss": 6.5463,
|
| 105 |
+
"step": 16000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 13.73,
|
| 109 |
+
"learning_rate": 3.6888888888888896e-05,
|
| 110 |
+
"loss": 6.5437,
|
| 111 |
+
"step": 17000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 14.54,
|
| 115 |
+
"learning_rate": 3.644444444444445e-05,
|
| 116 |
+
"loss": 6.5322,
|
| 117 |
+
"step": 18000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 15.35,
|
| 121 |
+
"learning_rate": 3.6e-05,
|
| 122 |
+
"loss": 6.4474,
|
| 123 |
+
"step": 19000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 16.16,
|
| 127 |
+
"learning_rate": 3.555555555555555e-05,
|
| 128 |
+
"loss": 6.3968,
|
| 129 |
+
"step": 20000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 16.96,
|
| 133 |
+
"learning_rate": 3.511111111111111e-05,
|
| 134 |
+
"loss": 6.3516,
|
| 135 |
+
"step": 21000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 17.77,
|
| 139 |
+
"learning_rate": 3.466666666666667e-05,
|
| 140 |
+
"loss": 6.311,
|
| 141 |
+
"step": 22000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 18.58,
|
| 145 |
+
"learning_rate": 3.4222222222222224e-05,
|
| 146 |
+
"loss": 6.2707,
|
| 147 |
+
"step": 23000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 19.39,
|
| 151 |
+
"learning_rate": 3.377777777777778e-05,
|
| 152 |
+
"loss": 6.2294,
|
| 153 |
+
"step": 24000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 20.19,
|
| 157 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 158 |
+
"loss": 6.1822,
|
| 159 |
+
"step": 25000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 21.0,
|
| 163 |
+
"learning_rate": 3.288888888888889e-05,
|
| 164 |
+
"loss": 6.1128,
|
| 165 |
+
"step": 26000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 21.81,
|
| 169 |
+
"learning_rate": 3.2444444444444446e-05,
|
| 170 |
+
"loss": 6.0262,
|
| 171 |
+
"step": 27000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 22.62,
|
| 175 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 176 |
+
"loss": 5.9326,
|
| 177 |
+
"step": 28000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 23.42,
|
| 181 |
+
"learning_rate": 3.155555555555556e-05,
|
| 182 |
+
"loss": 5.8051,
|
| 183 |
+
"step": 29000
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 24.23,
|
| 187 |
+
"learning_rate": 3.111111111111112e-05,
|
| 188 |
+
"loss": 5.703,
|
| 189 |
+
"step": 30000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 25.04,
|
| 193 |
+
"learning_rate": 3.066666666666667e-05,
|
| 194 |
+
"loss": 5.6361,
|
| 195 |
+
"step": 31000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 25.85,
|
| 199 |
+
"learning_rate": 3.0222222222222225e-05,
|
| 200 |
+
"loss": 5.5885,
|
| 201 |
+
"step": 32000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 26.66,
|
| 205 |
+
"learning_rate": 2.977777777777778e-05,
|
| 206 |
+
"loss": 5.5487,
|
| 207 |
+
"step": 33000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 27.46,
|
| 211 |
+
"learning_rate": 2.9333333333333333e-05,
|
| 212 |
+
"loss": 5.5163,
|
| 213 |
+
"step": 34000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 28.27,
|
| 217 |
+
"learning_rate": 2.888888888888889e-05,
|
| 218 |
+
"loss": 5.4922,
|
| 219 |
+
"step": 35000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 29.08,
|
| 223 |
+
"learning_rate": 2.8444444444444447e-05,
|
| 224 |
+
"loss": 5.4659,
|
| 225 |
+
"step": 36000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 29.89,
|
| 229 |
+
"learning_rate": 2.8e-05,
|
| 230 |
+
"loss": 5.4453,
|
| 231 |
+
"step": 37000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 30.69,
|
| 235 |
+
"learning_rate": 2.755555555555556e-05,
|
| 236 |
+
"loss": 5.4257,
|
| 237 |
+
"step": 38000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 31.5,
|
| 241 |
+
"learning_rate": 2.7111111111111114e-05,
|
| 242 |
+
"loss": 5.4111,
|
| 243 |
+
"step": 39000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 32.31,
|
| 247 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 248 |
+
"loss": 5.3939,
|
| 249 |
+
"step": 40000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 33.12,
|
| 253 |
+
"learning_rate": 2.6222222222222226e-05,
|
| 254 |
+
"loss": 5.3814,
|
| 255 |
+
"step": 41000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 33.93,
|
| 259 |
+
"learning_rate": 2.577777777777778e-05,
|
| 260 |
+
"loss": 5.3658,
|
| 261 |
+
"step": 42000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 34.73,
|
| 265 |
+
"learning_rate": 2.5333333333333334e-05,
|
| 266 |
+
"loss": 5.353,
|
| 267 |
+
"step": 43000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 35.54,
|
| 271 |
+
"learning_rate": 2.4888888888888893e-05,
|
| 272 |
+
"loss": 5.3419,
|
| 273 |
+
"step": 44000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 36.35,
|
| 277 |
+
"learning_rate": 2.444444444444445e-05,
|
| 278 |
+
"loss": 5.3312,
|
| 279 |
+
"step": 45000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 37.16,
|
| 283 |
+
"learning_rate": 2.4e-05,
|
| 284 |
+
"loss": 5.3217,
|
| 285 |
+
"step": 46000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 37.96,
|
| 289 |
+
"learning_rate": 2.355555555555556e-05,
|
| 290 |
+
"loss": 5.3111,
|
| 291 |
+
"step": 47000
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 38.77,
|
| 295 |
+
"learning_rate": 2.3111111111111112e-05,
|
| 296 |
+
"loss": 5.3013,
|
| 297 |
+
"step": 48000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 39.58,
|
| 301 |
+
"learning_rate": 2.2666666666666668e-05,
|
| 302 |
+
"loss": 5.291,
|
| 303 |
+
"step": 49000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 40.39,
|
| 307 |
+
"learning_rate": 2.2222222222222227e-05,
|
| 308 |
+
"loss": 5.2835,
|
| 309 |
+
"step": 50000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 41.2,
|
| 313 |
+
"learning_rate": 2.177777777777778e-05,
|
| 314 |
+
"loss": 5.2753,
|
| 315 |
+
"step": 51000
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 42.0,
|
| 319 |
+
"learning_rate": 2.1333333333333335e-05,
|
| 320 |
+
"loss": 5.2666,
|
| 321 |
+
"step": 52000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 42.81,
|
| 325 |
+
"learning_rate": 2.088888888888889e-05,
|
| 326 |
+
"loss": 5.2594,
|
| 327 |
+
"step": 53000
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 43.62,
|
| 331 |
+
"learning_rate": 2.0444444444444446e-05,
|
| 332 |
+
"loss": 5.2513,
|
| 333 |
+
"step": 54000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 44.43,
|
| 337 |
+
"learning_rate": 2e-05,
|
| 338 |
+
"loss": 5.2441,
|
| 339 |
+
"step": 55000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 45.23,
|
| 343 |
+
"learning_rate": 1.9555555555555557e-05,
|
| 344 |
+
"loss": 5.2426,
|
| 345 |
+
"step": 56000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 46.04,
|
| 349 |
+
"learning_rate": 1.9111111111111113e-05,
|
| 350 |
+
"loss": 5.2328,
|
| 351 |
+
"step": 57000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 46.85,
|
| 355 |
+
"learning_rate": 1.866666666666667e-05,
|
| 356 |
+
"loss": 5.2278,
|
| 357 |
+
"step": 58000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 47.66,
|
| 361 |
+
"learning_rate": 1.8222222222222224e-05,
|
| 362 |
+
"loss": 5.2213,
|
| 363 |
+
"step": 59000
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 48.47,
|
| 367 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 368 |
+
"loss": 5.2155,
|
| 369 |
+
"step": 60000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 49.27,
|
| 373 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 374 |
+
"loss": 5.2102,
|
| 375 |
+
"step": 61000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 50.08,
|
| 379 |
+
"learning_rate": 1.688888888888889e-05,
|
| 380 |
+
"loss": 5.2048,
|
| 381 |
+
"step": 62000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 50.89,
|
| 385 |
+
"learning_rate": 1.6444444444444444e-05,
|
| 386 |
+
"loss": 5.2008,
|
| 387 |
+
"step": 63000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 51.7,
|
| 391 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 392 |
+
"loss": 5.1975,
|
| 393 |
+
"step": 64000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 52.5,
|
| 397 |
+
"learning_rate": 1.555555555555556e-05,
|
| 398 |
+
"loss": 5.1925,
|
| 399 |
+
"step": 65000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 53.31,
|
| 403 |
+
"learning_rate": 1.5111111111111112e-05,
|
| 404 |
+
"loss": 5.1883,
|
| 405 |
+
"step": 66000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 54.12,
|
| 409 |
+
"learning_rate": 1.4666666666666666e-05,
|
| 410 |
+
"loss": 5.1822,
|
| 411 |
+
"step": 67000
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 54.93,
|
| 415 |
+
"learning_rate": 1.4222222222222224e-05,
|
| 416 |
+
"loss": 5.1806,
|
| 417 |
+
"step": 68000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 55.74,
|
| 421 |
+
"learning_rate": 1.377777777777778e-05,
|
| 422 |
+
"loss": 5.1756,
|
| 423 |
+
"step": 69000
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 56.54,
|
| 427 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 428 |
+
"loss": 5.175,
|
| 429 |
+
"step": 70000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 57.35,
|
| 433 |
+
"learning_rate": 1.288888888888889e-05,
|
| 434 |
+
"loss": 5.1686,
|
| 435 |
+
"step": 71000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 58.16,
|
| 439 |
+
"learning_rate": 1.2444444444444446e-05,
|
| 440 |
+
"loss": 5.1672,
|
| 441 |
+
"step": 72000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 58.97,
|
| 445 |
+
"learning_rate": 1.2e-05,
|
| 446 |
+
"loss": 5.1644,
|
| 447 |
+
"step": 73000
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 59.77,
|
| 451 |
+
"learning_rate": 1.1555555555555556e-05,
|
| 452 |
+
"loss": 5.1609,
|
| 453 |
+
"step": 74000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 60.58,
|
| 457 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 458 |
+
"loss": 5.1582,
|
| 459 |
+
"step": 75000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 61.39,
|
| 463 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 464 |
+
"loss": 5.1539,
|
| 465 |
+
"step": 76000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 62.2,
|
| 469 |
+
"learning_rate": 1.0222222222222223e-05,
|
| 470 |
+
"loss": 5.1535,
|
| 471 |
+
"step": 77000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 63.0,
|
| 475 |
+
"learning_rate": 9.777777777777779e-06,
|
| 476 |
+
"loss": 5.1516,
|
| 477 |
+
"step": 78000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 63.81,
|
| 481 |
+
"learning_rate": 9.333333333333334e-06,
|
| 482 |
+
"loss": 5.1479,
|
| 483 |
+
"step": 79000
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 64.62,
|
| 487 |
+
"learning_rate": 8.888888888888888e-06,
|
| 488 |
+
"loss": 5.1451,
|
| 489 |
+
"step": 80000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 65.43,
|
| 493 |
+
"learning_rate": 8.444444444444446e-06,
|
| 494 |
+
"loss": 5.1439,
|
| 495 |
+
"step": 81000
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 66.24,
|
| 499 |
+
"learning_rate": 8.000000000000001e-06,
|
| 500 |
+
"loss": 5.1429,
|
| 501 |
+
"step": 82000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 67.04,
|
| 505 |
+
"learning_rate": 7.555555555555556e-06,
|
| 506 |
+
"loss": 5.1402,
|
| 507 |
+
"step": 83000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 67.85,
|
| 511 |
+
"learning_rate": 7.111111111111112e-06,
|
| 512 |
+
"loss": 5.1375,
|
| 513 |
+
"step": 84000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 68.66,
|
| 517 |
+
"learning_rate": 6.666666666666667e-06,
|
| 518 |
+
"loss": 5.1348,
|
| 519 |
+
"step": 85000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 69.47,
|
| 523 |
+
"learning_rate": 6.222222222222223e-06,
|
| 524 |
+
"loss": 5.1357,
|
| 525 |
+
"step": 86000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 70.27,
|
| 529 |
+
"learning_rate": 5.777777777777778e-06,
|
| 530 |
+
"loss": 5.1336,
|
| 531 |
+
"step": 87000
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 71.08,
|
| 535 |
+
"learning_rate": 5.333333333333334e-06,
|
| 536 |
+
"loss": 5.1308,
|
| 537 |
+
"step": 88000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 71.89,
|
| 541 |
+
"learning_rate": 4.888888888888889e-06,
|
| 542 |
+
"loss": 5.1304,
|
| 543 |
+
"step": 89000
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 72.7,
|
| 547 |
+
"learning_rate": 4.444444444444444e-06,
|
| 548 |
+
"loss": 5.1285,
|
| 549 |
+
"step": 90000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 73.51,
|
| 553 |
+
"learning_rate": 4.000000000000001e-06,
|
| 554 |
+
"loss": 5.1272,
|
| 555 |
+
"step": 91000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 74.31,
|
| 559 |
+
"learning_rate": 3.555555555555556e-06,
|
| 560 |
+
"loss": 5.1272,
|
| 561 |
+
"step": 92000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 75.12,
|
| 565 |
+
"learning_rate": 3.1111111111111116e-06,
|
| 566 |
+
"loss": 5.1281,
|
| 567 |
+
"step": 93000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 75.93,
|
| 571 |
+
"learning_rate": 2.666666666666667e-06,
|
| 572 |
+
"loss": 5.1257,
|
| 573 |
+
"step": 94000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 76.74,
|
| 577 |
+
"learning_rate": 2.222222222222222e-06,
|
| 578 |
+
"loss": 5.1245,
|
| 579 |
+
"step": 95000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 77.54,
|
| 583 |
+
"learning_rate": 1.777777777777778e-06,
|
| 584 |
+
"loss": 5.1244,
|
| 585 |
+
"step": 96000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 78.35,
|
| 589 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 590 |
+
"loss": 5.1229,
|
| 591 |
+
"step": 97000
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 79.16,
|
| 595 |
+
"learning_rate": 8.88888888888889e-07,
|
| 596 |
+
"loss": 5.1223,
|
| 597 |
+
"step": 98000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 79.97,
|
| 601 |
+
"learning_rate": 4.444444444444445e-07,
|
| 602 |
+
"loss": 5.1231,
|
| 603 |
+
"step": 99000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 80.78,
|
| 607 |
+
"learning_rate": 0.0,
|
| 608 |
+
"loss": 5.1203,
|
| 609 |
+
"step": 100000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 10.2,
|
| 613 |
+
"learning_rate": 2.0842105263157895e-05,
|
| 614 |
+
"loss": 5.1411,
|
| 615 |
+
"step": 101000
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 10.3,
|
| 619 |
+
"learning_rate": 2.0631578947368425e-05,
|
| 620 |
+
"loss": 5.1408,
|
| 621 |
+
"step": 102000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 10.4,
|
| 625 |
+
"learning_rate": 2.0421052631578952e-05,
|
| 626 |
+
"loss": 5.1433,
|
| 627 |
+
"step": 103000
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 10.5,
|
| 631 |
+
"learning_rate": 2.0210526315789475e-05,
|
| 632 |
+
"loss": 5.154,
|
| 633 |
+
"step": 104000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 10.6,
|
| 637 |
+
"learning_rate": 2e-05,
|
| 638 |
+
"loss": 5.1553,
|
| 639 |
+
"step": 105000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 10.71,
|
| 643 |
+
"learning_rate": 1.9789473684210528e-05,
|
| 644 |
+
"loss": 5.1442,
|
| 645 |
+
"step": 106000
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 10.81,
|
| 649 |
+
"learning_rate": 1.9578947368421055e-05,
|
| 650 |
+
"loss": 5.1442,
|
| 651 |
+
"step": 107000
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 10.91,
|
| 655 |
+
"learning_rate": 1.936842105263158e-05,
|
| 656 |
+
"loss": 5.147,
|
| 657 |
+
"step": 108000
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 11.01,
|
| 661 |
+
"learning_rate": 1.9157894736842108e-05,
|
| 662 |
+
"loss": 5.1433,
|
| 663 |
+
"step": 109000
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 11.11,
|
| 667 |
+
"learning_rate": 1.894736842105263e-05,
|
| 668 |
+
"loss": 5.1374,
|
| 669 |
+
"step": 110000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 11.21,
|
| 673 |
+
"learning_rate": 1.873684210526316e-05,
|
| 674 |
+
"loss": 5.1411,
|
| 675 |
+
"step": 111000
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 11.31,
|
| 679 |
+
"learning_rate": 1.8526315789473684e-05,
|
| 680 |
+
"loss": 5.1371,
|
| 681 |
+
"step": 112000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 11.41,
|
| 685 |
+
"learning_rate": 1.831578947368421e-05,
|
| 686 |
+
"loss": 5.1379,
|
| 687 |
+
"step": 113000
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 11.51,
|
| 691 |
+
"learning_rate": 1.810526315789474e-05,
|
| 692 |
+
"loss": 5.139,
|
| 693 |
+
"step": 114000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 11.61,
|
| 697 |
+
"learning_rate": 1.7894736842105264e-05,
|
| 698 |
+
"loss": 5.131,
|
| 699 |
+
"step": 115000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 11.72,
|
| 703 |
+
"learning_rate": 1.768421052631579e-05,
|
| 704 |
+
"loss": 5.1313,
|
| 705 |
+
"step": 116000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 11.82,
|
| 709 |
+
"learning_rate": 1.7473684210526317e-05,
|
| 710 |
+
"loss": 5.1287,
|
| 711 |
+
"step": 117000
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 11.92,
|
| 715 |
+
"learning_rate": 1.7263157894736843e-05,
|
| 716 |
+
"loss": 5.1304,
|
| 717 |
+
"step": 118000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 12.02,
|
| 721 |
+
"learning_rate": 1.705263157894737e-05,
|
| 722 |
+
"loss": 5.1309,
|
| 723 |
+
"step": 119000
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 12.12,
|
| 727 |
+
"learning_rate": 1.6842105263157896e-05,
|
| 728 |
+
"loss": 5.1256,
|
| 729 |
+
"step": 120000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 12.22,
|
| 733 |
+
"learning_rate": 1.6631578947368423e-05,
|
| 734 |
+
"loss": 5.1202,
|
| 735 |
+
"step": 121000
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 12.32,
|
| 739 |
+
"learning_rate": 1.642105263157895e-05,
|
| 740 |
+
"loss": 5.125,
|
| 741 |
+
"step": 122000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 12.42,
|
| 745 |
+
"learning_rate": 1.6210526315789473e-05,
|
| 746 |
+
"loss": 5.125,
|
| 747 |
+
"step": 123000
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 12.52,
|
| 751 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 752 |
+
"loss": 5.1259,
|
| 753 |
+
"step": 124000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 12.62,
|
| 757 |
+
"learning_rate": 1.578947368421053e-05,
|
| 758 |
+
"loss": 5.1186,
|
| 759 |
+
"step": 125000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 12.73,
|
| 763 |
+
"learning_rate": 1.5578947368421052e-05,
|
| 764 |
+
"loss": 5.1097,
|
| 765 |
+
"step": 126000
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 12.83,
|
| 769 |
+
"learning_rate": 1.536842105263158e-05,
|
| 770 |
+
"loss": 5.12,
|
| 771 |
+
"step": 127000
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 12.93,
|
| 775 |
+
"learning_rate": 1.5157894736842107e-05,
|
| 776 |
+
"loss": 5.123,
|
| 777 |
+
"step": 128000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 13.03,
|
| 781 |
+
"learning_rate": 1.4947368421052632e-05,
|
| 782 |
+
"loss": 5.1113,
|
| 783 |
+
"step": 129000
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 13.13,
|
| 787 |
+
"learning_rate": 1.4736842105263159e-05,
|
| 788 |
+
"loss": 5.1071,
|
| 789 |
+
"step": 130000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 13.23,
|
| 793 |
+
"learning_rate": 1.4526315789473687e-05,
|
| 794 |
+
"loss": 5.1167,
|
| 795 |
+
"step": 131000
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 13.33,
|
| 799 |
+
"learning_rate": 1.4315789473684212e-05,
|
| 800 |
+
"loss": 5.1153,
|
| 801 |
+
"step": 132000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 13.43,
|
| 805 |
+
"learning_rate": 1.4105263157894738e-05,
|
| 806 |
+
"loss": 5.1171,
|
| 807 |
+
"step": 133000
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 13.53,
|
| 811 |
+
"learning_rate": 1.3894736842105265e-05,
|
| 812 |
+
"loss": 5.1101,
|
| 813 |
+
"step": 134000
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 13.63,
|
| 817 |
+
"learning_rate": 1.3684210526315791e-05,
|
| 818 |
+
"loss": 5.1096,
|
| 819 |
+
"step": 135000
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 13.74,
|
| 823 |
+
"learning_rate": 1.3473684210526316e-05,
|
| 824 |
+
"loss": 5.107,
|
| 825 |
+
"step": 136000
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 13.84,
|
| 829 |
+
"learning_rate": 1.3263157894736843e-05,
|
| 830 |
+
"loss": 5.1048,
|
| 831 |
+
"step": 137000
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 13.94,
|
| 835 |
+
"learning_rate": 1.305263157894737e-05,
|
| 836 |
+
"loss": 5.1077,
|
| 837 |
+
"step": 138000
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 14.04,
|
| 841 |
+
"learning_rate": 1.2842105263157896e-05,
|
| 842 |
+
"loss": 5.0998,
|
| 843 |
+
"step": 139000
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 14.14,
|
| 847 |
+
"learning_rate": 1.263157894736842e-05,
|
| 848 |
+
"loss": 5.1014,
|
| 849 |
+
"step": 140000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 14.24,
|
| 853 |
+
"learning_rate": 1.2421052631578949e-05,
|
| 854 |
+
"loss": 5.1028,
|
| 855 |
+
"step": 141000
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 14.34,
|
| 859 |
+
"learning_rate": 1.2210526315789475e-05,
|
| 860 |
+
"loss": 5.1065,
|
| 861 |
+
"step": 142000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 14.44,
|
| 865 |
+
"learning_rate": 1.2e-05,
|
| 866 |
+
"loss": 5.1024,
|
| 867 |
+
"step": 143000
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 14.54,
|
| 871 |
+
"learning_rate": 1.1789473684210527e-05,
|
| 872 |
+
"loss": 5.1055,
|
| 873 |
+
"step": 144000
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 14.64,
|
| 877 |
+
"learning_rate": 1.1578947368421053e-05,
|
| 878 |
+
"loss": 5.0966,
|
| 879 |
+
"step": 145000
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 14.75,
|
| 883 |
+
"learning_rate": 1.136842105263158e-05,
|
| 884 |
+
"loss": 5.0939,
|
| 885 |
+
"step": 146000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 14.85,
|
| 889 |
+
"learning_rate": 1.1157894736842105e-05,
|
| 890 |
+
"loss": 5.0932,
|
| 891 |
+
"step": 147000
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 14.95,
|
| 895 |
+
"learning_rate": 1.0947368421052633e-05,
|
| 896 |
+
"loss": 5.0971,
|
| 897 |
+
"step": 148000
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 15.05,
|
| 901 |
+
"learning_rate": 1.073684210526316e-05,
|
| 902 |
+
"loss": 5.0802,
|
| 903 |
+
"step": 149000
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 15.15,
|
| 907 |
+
"learning_rate": 1.0526315789473684e-05,
|
| 908 |
+
"loss": 5.0969,
|
| 909 |
+
"step": 150000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 15.25,
|
| 913 |
+
"learning_rate": 1.0315789473684213e-05,
|
| 914 |
+
"loss": 5.0889,
|
| 915 |
+
"step": 151000
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 15.35,
|
| 919 |
+
"learning_rate": 1.0105263157894738e-05,
|
| 920 |
+
"loss": 5.0934,
|
| 921 |
+
"step": 152000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 15.45,
|
| 925 |
+
"learning_rate": 9.894736842105264e-06,
|
| 926 |
+
"loss": 5.0961,
|
| 927 |
+
"step": 153000
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 15.55,
|
| 931 |
+
"learning_rate": 9.68421052631579e-06,
|
| 932 |
+
"loss": 5.0874,
|
| 933 |
+
"step": 154000
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 15.65,
|
| 937 |
+
"learning_rate": 9.473684210526315e-06,
|
| 938 |
+
"loss": 5.0896,
|
| 939 |
+
"step": 155000
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 15.76,
|
| 943 |
+
"learning_rate": 9.263157894736842e-06,
|
| 944 |
+
"loss": 5.0879,
|
| 945 |
+
"step": 156000
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 15.86,
|
| 949 |
+
"learning_rate": 9.05263157894737e-06,
|
| 950 |
+
"loss": 5.0848,
|
| 951 |
+
"step": 157000
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 15.96,
|
| 955 |
+
"learning_rate": 8.842105263157895e-06,
|
| 956 |
+
"loss": 5.0879,
|
| 957 |
+
"step": 158000
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 16.06,
|
| 961 |
+
"learning_rate": 8.631578947368422e-06,
|
| 962 |
+
"loss": 5.0799,
|
| 963 |
+
"step": 159000
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 16.16,
|
| 967 |
+
"learning_rate": 8.421052631578948e-06,
|
| 968 |
+
"loss": 5.0847,
|
| 969 |
+
"step": 160000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 16.26,
|
| 973 |
+
"learning_rate": 8.210526315789475e-06,
|
| 974 |
+
"loss": 5.0897,
|
| 975 |
+
"step": 161000
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 16.36,
|
| 979 |
+
"learning_rate": 8.000000000000001e-06,
|
| 980 |
+
"loss": 5.0799,
|
| 981 |
+
"step": 162000
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 16.46,
|
| 985 |
+
"learning_rate": 7.789473684210526e-06,
|
| 986 |
+
"loss": 5.0847,
|
| 987 |
+
"step": 163000
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 16.56,
|
| 991 |
+
"learning_rate": 7.578947368421054e-06,
|
| 992 |
+
"loss": 5.0764,
|
| 993 |
+
"step": 164000
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 16.66,
|
| 997 |
+
"learning_rate": 7.368421052631579e-06,
|
| 998 |
+
"loss": 5.0756,
|
| 999 |
+
"step": 165000
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 16.77,
|
| 1003 |
+
"learning_rate": 7.157894736842106e-06,
|
| 1004 |
+
"loss": 5.0755,
|
| 1005 |
+
"step": 166000
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 16.87,
|
| 1009 |
+
"learning_rate": 6.947368421052632e-06,
|
| 1010 |
+
"loss": 5.0788,
|
| 1011 |
+
"step": 167000
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 16.97,
|
| 1015 |
+
"learning_rate": 6.736842105263158e-06,
|
| 1016 |
+
"loss": 5.0793,
|
| 1017 |
+
"step": 168000
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 17.07,
|
| 1021 |
+
"learning_rate": 6.526315789473685e-06,
|
| 1022 |
+
"loss": 5.0768,
|
| 1023 |
+
"step": 169000
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 17.17,
|
| 1027 |
+
"learning_rate": 6.31578947368421e-06,
|
| 1028 |
+
"loss": 5.0746,
|
| 1029 |
+
"step": 170000
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 17.27,
|
| 1033 |
+
"learning_rate": 6.105263157894738e-06,
|
| 1034 |
+
"loss": 5.075,
|
| 1035 |
+
"step": 171000
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 17.37,
|
| 1039 |
+
"learning_rate": 5.8947368421052634e-06,
|
| 1040 |
+
"loss": 5.0799,
|
| 1041 |
+
"step": 172000
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 17.47,
|
| 1045 |
+
"learning_rate": 5.68421052631579e-06,
|
| 1046 |
+
"loss": 5.0684,
|
| 1047 |
+
"step": 173000
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 17.57,
|
| 1051 |
+
"learning_rate": 5.4736842105263165e-06,
|
| 1052 |
+
"loss": 5.0741,
|
| 1053 |
+
"step": 174000
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 17.67,
|
| 1057 |
+
"learning_rate": 5.263157894736842e-06,
|
| 1058 |
+
"loss": 5.0756,
|
| 1059 |
+
"step": 175000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 17.78,
|
| 1063 |
+
"learning_rate": 5.052631578947369e-06,
|
| 1064 |
+
"loss": 5.0711,
|
| 1065 |
+
"step": 176000
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 17.88,
|
| 1069 |
+
"learning_rate": 4.842105263157895e-06,
|
| 1070 |
+
"loss": 5.0701,
|
| 1071 |
+
"step": 177000
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 17.98,
|
| 1075 |
+
"learning_rate": 4.631578947368421e-06,
|
| 1076 |
+
"loss": 5.0724,
|
| 1077 |
+
"step": 178000
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 18.08,
|
| 1081 |
+
"learning_rate": 4.4210526315789476e-06,
|
| 1082 |
+
"loss": 5.0729,
|
| 1083 |
+
"step": 179000
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 18.18,
|
| 1087 |
+
"learning_rate": 4.210526315789474e-06,
|
| 1088 |
+
"loss": 5.0667,
|
| 1089 |
+
"step": 180000
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 18.28,
|
| 1093 |
+
"learning_rate": 4.000000000000001e-06,
|
| 1094 |
+
"loss": 5.0692,
|
| 1095 |
+
"step": 181000
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 18.38,
|
| 1099 |
+
"learning_rate": 3.789473684210527e-06,
|
| 1100 |
+
"loss": 5.0714,
|
| 1101 |
+
"step": 182000
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 18.48,
|
| 1105 |
+
"learning_rate": 3.578947368421053e-06,
|
| 1106 |
+
"loss": 5.0662,
|
| 1107 |
+
"step": 183000
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 18.58,
|
| 1111 |
+
"learning_rate": 3.368421052631579e-06,
|
| 1112 |
+
"loss": 5.0726,
|
| 1113 |
+
"step": 184000
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 18.68,
|
| 1117 |
+
"learning_rate": 3.157894736842105e-06,
|
| 1118 |
+
"loss": 5.0743,
|
| 1119 |
+
"step": 185000
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 18.79,
|
| 1123 |
+
"learning_rate": 2.9473684210526317e-06,
|
| 1124 |
+
"loss": 5.059,
|
| 1125 |
+
"step": 186000
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 18.89,
|
| 1129 |
+
"learning_rate": 2.7368421052631583e-06,
|
| 1130 |
+
"loss": 5.064,
|
| 1131 |
+
"step": 187000
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 18.99,
|
| 1135 |
+
"learning_rate": 2.5263157894736844e-06,
|
| 1136 |
+
"loss": 5.0659,
|
| 1137 |
+
"step": 188000
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 19.09,
|
| 1141 |
+
"learning_rate": 2.3157894736842105e-06,
|
| 1142 |
+
"loss": 5.0645,
|
| 1143 |
+
"step": 189000
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 19.19,
|
| 1147 |
+
"learning_rate": 2.105263157894737e-06,
|
| 1148 |
+
"loss": 5.0657,
|
| 1149 |
+
"step": 190000
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 19.29,
|
| 1153 |
+
"learning_rate": 1.8947368421052634e-06,
|
| 1154 |
+
"loss": 5.0674,
|
| 1155 |
+
"step": 191000
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 19.39,
|
| 1159 |
+
"learning_rate": 1.6842105263157895e-06,
|
| 1160 |
+
"loss": 5.0609,
|
| 1161 |
+
"step": 192000
|
| 1162 |
+
}
|
| 1163 |
+
],
|
| 1164 |
+
"logging_steps": 1000,
|
| 1165 |
+
"max_steps": 200000,
|
| 1166 |
+
"num_train_epochs": 21,
|
| 1167 |
+
"save_steps": 1000,
|
| 1168 |
+
"total_flos": 2.2531961636670145e+19,
|
| 1169 |
+
"trial_name": null,
|
| 1170 |
+
"trial_params": null
|
| 1171 |
+
}
|
checkpoint-192000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f7b759ef851ee3a68e8c9ad880cbb1bc393f7d811df1a445efe7298474f0c09
|
| 3 |
+
size 5137
|
checkpoint-193000/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 12 |
+
"layer_norm_eps": 1e-12,
|
| 13 |
+
"max_length": 512,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.35.2",
|
| 22 |
+
"type_vocab_size": 2,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 5120
|
| 25 |
+
}
|
checkpoint-193000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"max_length": 512,
|
| 4 |
+
"pad_token_id": 0,
|
| 5 |
+
"transformers_version": "4.35.2"
|
| 6 |
+
}
|
checkpoint-193000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fd505a96358feaebeb9de52b4727609b1ac944c592f63c4bcd91d4c06f53388
|
| 3 |
+
size 359944256
|
checkpoint-193000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2bc9e23c49f2230623185932db3f0ea917bf141c85306af2c5b396b79c346ec
|
| 3 |
+
size 720010699
|
checkpoint-193000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15e495c69a62577dfff28ed3ec4a99a9761550c8c7a6b57f0d978d75cde80124
|
| 3 |
+
size 14645
|
checkpoint-193000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:193ff94d9f24279c5f8926a3af20ad4747ac16bb078d5e13b935e0b3be972c5b
|
| 3 |
+
size 1465
|
checkpoint-193000/trainer_state.json
ADDED
|
@@ -0,0 +1,1177 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 19.492980507019492,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 193000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.81,
|
| 13 |
+
"learning_rate": 4.000000000000001e-06,
|
| 14 |
+
"loss": 7.87,
|
| 15 |
+
"step": 1000
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.62,
|
| 19 |
+
"learning_rate": 8.000000000000001e-06,
|
| 20 |
+
"loss": 6.8831,
|
| 21 |
+
"step": 2000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 2.42,
|
| 25 |
+
"learning_rate": 1.2e-05,
|
| 26 |
+
"loss": 6.7256,
|
| 27 |
+
"step": 3000
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 3.23,
|
| 31 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 32 |
+
"loss": 6.6605,
|
| 33 |
+
"step": 4000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 4.04,
|
| 37 |
+
"learning_rate": 2e-05,
|
| 38 |
+
"loss": 6.6243,
|
| 39 |
+
"step": 5000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 4.85,
|
| 43 |
+
"learning_rate": 2.4e-05,
|
| 44 |
+
"loss": 6.6033,
|
| 45 |
+
"step": 6000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 5.65,
|
| 49 |
+
"learning_rate": 2.8e-05,
|
| 50 |
+
"loss": 6.5906,
|
| 51 |
+
"step": 7000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 6.46,
|
| 55 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 56 |
+
"loss": 6.5772,
|
| 57 |
+
"step": 8000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 7.27,
|
| 61 |
+
"learning_rate": 3.6e-05,
|
| 62 |
+
"loss": 6.5718,
|
| 63 |
+
"step": 9000
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 8.08,
|
| 67 |
+
"learning_rate": 4e-05,
|
| 68 |
+
"loss": 6.5653,
|
| 69 |
+
"step": 10000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 8.89,
|
| 73 |
+
"learning_rate": 3.955555555555556e-05,
|
| 74 |
+
"loss": 6.5602,
|
| 75 |
+
"step": 11000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 9.69,
|
| 79 |
+
"learning_rate": 3.9111111111111115e-05,
|
| 80 |
+
"loss": 6.5572,
|
| 81 |
+
"step": 12000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 10.5,
|
| 85 |
+
"learning_rate": 3.866666666666667e-05,
|
| 86 |
+
"loss": 6.5534,
|
| 87 |
+
"step": 13000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 11.31,
|
| 91 |
+
"learning_rate": 3.8222222222222226e-05,
|
| 92 |
+
"loss": 6.5533,
|
| 93 |
+
"step": 14000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 12.12,
|
| 97 |
+
"learning_rate": 3.777777777777778e-05,
|
| 98 |
+
"loss": 6.547,
|
| 99 |
+
"step": 15000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 12.92,
|
| 103 |
+
"learning_rate": 3.733333333333334e-05,
|
| 104 |
+
"loss": 6.5463,
|
| 105 |
+
"step": 16000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 13.73,
|
| 109 |
+
"learning_rate": 3.6888888888888896e-05,
|
| 110 |
+
"loss": 6.5437,
|
| 111 |
+
"step": 17000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 14.54,
|
| 115 |
+
"learning_rate": 3.644444444444445e-05,
|
| 116 |
+
"loss": 6.5322,
|
| 117 |
+
"step": 18000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 15.35,
|
| 121 |
+
"learning_rate": 3.6e-05,
|
| 122 |
+
"loss": 6.4474,
|
| 123 |
+
"step": 19000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 16.16,
|
| 127 |
+
"learning_rate": 3.555555555555555e-05,
|
| 128 |
+
"loss": 6.3968,
|
| 129 |
+
"step": 20000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 16.96,
|
| 133 |
+
"learning_rate": 3.511111111111111e-05,
|
| 134 |
+
"loss": 6.3516,
|
| 135 |
+
"step": 21000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 17.77,
|
| 139 |
+
"learning_rate": 3.466666666666667e-05,
|
| 140 |
+
"loss": 6.311,
|
| 141 |
+
"step": 22000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 18.58,
|
| 145 |
+
"learning_rate": 3.4222222222222224e-05,
|
| 146 |
+
"loss": 6.2707,
|
| 147 |
+
"step": 23000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 19.39,
|
| 151 |
+
"learning_rate": 3.377777777777778e-05,
|
| 152 |
+
"loss": 6.2294,
|
| 153 |
+
"step": 24000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 20.19,
|
| 157 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 158 |
+
"loss": 6.1822,
|
| 159 |
+
"step": 25000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 21.0,
|
| 163 |
+
"learning_rate": 3.288888888888889e-05,
|
| 164 |
+
"loss": 6.1128,
|
| 165 |
+
"step": 26000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 21.81,
|
| 169 |
+
"learning_rate": 3.2444444444444446e-05,
|
| 170 |
+
"loss": 6.0262,
|
| 171 |
+
"step": 27000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 22.62,
|
| 175 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 176 |
+
"loss": 5.9326,
|
| 177 |
+
"step": 28000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 23.42,
|
| 181 |
+
"learning_rate": 3.155555555555556e-05,
|
| 182 |
+
"loss": 5.8051,
|
| 183 |
+
"step": 29000
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 24.23,
|
| 187 |
+
"learning_rate": 3.111111111111112e-05,
|
| 188 |
+
"loss": 5.703,
|
| 189 |
+
"step": 30000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 25.04,
|
| 193 |
+
"learning_rate": 3.066666666666667e-05,
|
| 194 |
+
"loss": 5.6361,
|
| 195 |
+
"step": 31000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 25.85,
|
| 199 |
+
"learning_rate": 3.0222222222222225e-05,
|
| 200 |
+
"loss": 5.5885,
|
| 201 |
+
"step": 32000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 26.66,
|
| 205 |
+
"learning_rate": 2.977777777777778e-05,
|
| 206 |
+
"loss": 5.5487,
|
| 207 |
+
"step": 33000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 27.46,
|
| 211 |
+
"learning_rate": 2.9333333333333333e-05,
|
| 212 |
+
"loss": 5.5163,
|
| 213 |
+
"step": 34000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 28.27,
|
| 217 |
+
"learning_rate": 2.888888888888889e-05,
|
| 218 |
+
"loss": 5.4922,
|
| 219 |
+
"step": 35000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 29.08,
|
| 223 |
+
"learning_rate": 2.8444444444444447e-05,
|
| 224 |
+
"loss": 5.4659,
|
| 225 |
+
"step": 36000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 29.89,
|
| 229 |
+
"learning_rate": 2.8e-05,
|
| 230 |
+
"loss": 5.4453,
|
| 231 |
+
"step": 37000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 30.69,
|
| 235 |
+
"learning_rate": 2.755555555555556e-05,
|
| 236 |
+
"loss": 5.4257,
|
| 237 |
+
"step": 38000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 31.5,
|
| 241 |
+
"learning_rate": 2.7111111111111114e-05,
|
| 242 |
+
"loss": 5.4111,
|
| 243 |
+
"step": 39000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 32.31,
|
| 247 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 248 |
+
"loss": 5.3939,
|
| 249 |
+
"step": 40000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 33.12,
|
| 253 |
+
"learning_rate": 2.6222222222222226e-05,
|
| 254 |
+
"loss": 5.3814,
|
| 255 |
+
"step": 41000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 33.93,
|
| 259 |
+
"learning_rate": 2.577777777777778e-05,
|
| 260 |
+
"loss": 5.3658,
|
| 261 |
+
"step": 42000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 34.73,
|
| 265 |
+
"learning_rate": 2.5333333333333334e-05,
|
| 266 |
+
"loss": 5.353,
|
| 267 |
+
"step": 43000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 35.54,
|
| 271 |
+
"learning_rate": 2.4888888888888893e-05,
|
| 272 |
+
"loss": 5.3419,
|
| 273 |
+
"step": 44000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 36.35,
|
| 277 |
+
"learning_rate": 2.444444444444445e-05,
|
| 278 |
+
"loss": 5.3312,
|
| 279 |
+
"step": 45000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 37.16,
|
| 283 |
+
"learning_rate": 2.4e-05,
|
| 284 |
+
"loss": 5.3217,
|
| 285 |
+
"step": 46000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 37.96,
|
| 289 |
+
"learning_rate": 2.355555555555556e-05,
|
| 290 |
+
"loss": 5.3111,
|
| 291 |
+
"step": 47000
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 38.77,
|
| 295 |
+
"learning_rate": 2.3111111111111112e-05,
|
| 296 |
+
"loss": 5.3013,
|
| 297 |
+
"step": 48000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 39.58,
|
| 301 |
+
"learning_rate": 2.2666666666666668e-05,
|
| 302 |
+
"loss": 5.291,
|
| 303 |
+
"step": 49000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 40.39,
|
| 307 |
+
"learning_rate": 2.2222222222222227e-05,
|
| 308 |
+
"loss": 5.2835,
|
| 309 |
+
"step": 50000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 41.2,
|
| 313 |
+
"learning_rate": 2.177777777777778e-05,
|
| 314 |
+
"loss": 5.2753,
|
| 315 |
+
"step": 51000
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 42.0,
|
| 319 |
+
"learning_rate": 2.1333333333333335e-05,
|
| 320 |
+
"loss": 5.2666,
|
| 321 |
+
"step": 52000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 42.81,
|
| 325 |
+
"learning_rate": 2.088888888888889e-05,
|
| 326 |
+
"loss": 5.2594,
|
| 327 |
+
"step": 53000
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 43.62,
|
| 331 |
+
"learning_rate": 2.0444444444444446e-05,
|
| 332 |
+
"loss": 5.2513,
|
| 333 |
+
"step": 54000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 44.43,
|
| 337 |
+
"learning_rate": 2e-05,
|
| 338 |
+
"loss": 5.2441,
|
| 339 |
+
"step": 55000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 45.23,
|
| 343 |
+
"learning_rate": 1.9555555555555557e-05,
|
| 344 |
+
"loss": 5.2426,
|
| 345 |
+
"step": 56000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 46.04,
|
| 349 |
+
"learning_rate": 1.9111111111111113e-05,
|
| 350 |
+
"loss": 5.2328,
|
| 351 |
+
"step": 57000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 46.85,
|
| 355 |
+
"learning_rate": 1.866666666666667e-05,
|
| 356 |
+
"loss": 5.2278,
|
| 357 |
+
"step": 58000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 47.66,
|
| 361 |
+
"learning_rate": 1.8222222222222224e-05,
|
| 362 |
+
"loss": 5.2213,
|
| 363 |
+
"step": 59000
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 48.47,
|
| 367 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 368 |
+
"loss": 5.2155,
|
| 369 |
+
"step": 60000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 49.27,
|
| 373 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 374 |
+
"loss": 5.2102,
|
| 375 |
+
"step": 61000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 50.08,
|
| 379 |
+
"learning_rate": 1.688888888888889e-05,
|
| 380 |
+
"loss": 5.2048,
|
| 381 |
+
"step": 62000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 50.89,
|
| 385 |
+
"learning_rate": 1.6444444444444444e-05,
|
| 386 |
+
"loss": 5.2008,
|
| 387 |
+
"step": 63000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 51.7,
|
| 391 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 392 |
+
"loss": 5.1975,
|
| 393 |
+
"step": 64000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 52.5,
|
| 397 |
+
"learning_rate": 1.555555555555556e-05,
|
| 398 |
+
"loss": 5.1925,
|
| 399 |
+
"step": 65000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 53.31,
|
| 403 |
+
"learning_rate": 1.5111111111111112e-05,
|
| 404 |
+
"loss": 5.1883,
|
| 405 |
+
"step": 66000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 54.12,
|
| 409 |
+
"learning_rate": 1.4666666666666666e-05,
|
| 410 |
+
"loss": 5.1822,
|
| 411 |
+
"step": 67000
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 54.93,
|
| 415 |
+
"learning_rate": 1.4222222222222224e-05,
|
| 416 |
+
"loss": 5.1806,
|
| 417 |
+
"step": 68000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 55.74,
|
| 421 |
+
"learning_rate": 1.377777777777778e-05,
|
| 422 |
+
"loss": 5.1756,
|
| 423 |
+
"step": 69000
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 56.54,
|
| 427 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 428 |
+
"loss": 5.175,
|
| 429 |
+
"step": 70000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 57.35,
|
| 433 |
+
"learning_rate": 1.288888888888889e-05,
|
| 434 |
+
"loss": 5.1686,
|
| 435 |
+
"step": 71000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 58.16,
|
| 439 |
+
"learning_rate": 1.2444444444444446e-05,
|
| 440 |
+
"loss": 5.1672,
|
| 441 |
+
"step": 72000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 58.97,
|
| 445 |
+
"learning_rate": 1.2e-05,
|
| 446 |
+
"loss": 5.1644,
|
| 447 |
+
"step": 73000
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 59.77,
|
| 451 |
+
"learning_rate": 1.1555555555555556e-05,
|
| 452 |
+
"loss": 5.1609,
|
| 453 |
+
"step": 74000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 60.58,
|
| 457 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 458 |
+
"loss": 5.1582,
|
| 459 |
+
"step": 75000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 61.39,
|
| 463 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 464 |
+
"loss": 5.1539,
|
| 465 |
+
"step": 76000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 62.2,
|
| 469 |
+
"learning_rate": 1.0222222222222223e-05,
|
| 470 |
+
"loss": 5.1535,
|
| 471 |
+
"step": 77000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 63.0,
|
| 475 |
+
"learning_rate": 9.777777777777779e-06,
|
| 476 |
+
"loss": 5.1516,
|
| 477 |
+
"step": 78000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 63.81,
|
| 481 |
+
"learning_rate": 9.333333333333334e-06,
|
| 482 |
+
"loss": 5.1479,
|
| 483 |
+
"step": 79000
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 64.62,
|
| 487 |
+
"learning_rate": 8.888888888888888e-06,
|
| 488 |
+
"loss": 5.1451,
|
| 489 |
+
"step": 80000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 65.43,
|
| 493 |
+
"learning_rate": 8.444444444444446e-06,
|
| 494 |
+
"loss": 5.1439,
|
| 495 |
+
"step": 81000
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 66.24,
|
| 499 |
+
"learning_rate": 8.000000000000001e-06,
|
| 500 |
+
"loss": 5.1429,
|
| 501 |
+
"step": 82000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 67.04,
|
| 505 |
+
"learning_rate": 7.555555555555556e-06,
|
| 506 |
+
"loss": 5.1402,
|
| 507 |
+
"step": 83000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 67.85,
|
| 511 |
+
"learning_rate": 7.111111111111112e-06,
|
| 512 |
+
"loss": 5.1375,
|
| 513 |
+
"step": 84000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 68.66,
|
| 517 |
+
"learning_rate": 6.666666666666667e-06,
|
| 518 |
+
"loss": 5.1348,
|
| 519 |
+
"step": 85000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 69.47,
|
| 523 |
+
"learning_rate": 6.222222222222223e-06,
|
| 524 |
+
"loss": 5.1357,
|
| 525 |
+
"step": 86000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 70.27,
|
| 529 |
+
"learning_rate": 5.777777777777778e-06,
|
| 530 |
+
"loss": 5.1336,
|
| 531 |
+
"step": 87000
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 71.08,
|
| 535 |
+
"learning_rate": 5.333333333333334e-06,
|
| 536 |
+
"loss": 5.1308,
|
| 537 |
+
"step": 88000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 71.89,
|
| 541 |
+
"learning_rate": 4.888888888888889e-06,
|
| 542 |
+
"loss": 5.1304,
|
| 543 |
+
"step": 89000
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 72.7,
|
| 547 |
+
"learning_rate": 4.444444444444444e-06,
|
| 548 |
+
"loss": 5.1285,
|
| 549 |
+
"step": 90000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 73.51,
|
| 553 |
+
"learning_rate": 4.000000000000001e-06,
|
| 554 |
+
"loss": 5.1272,
|
| 555 |
+
"step": 91000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 74.31,
|
| 559 |
+
"learning_rate": 3.555555555555556e-06,
|
| 560 |
+
"loss": 5.1272,
|
| 561 |
+
"step": 92000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 75.12,
|
| 565 |
+
"learning_rate": 3.1111111111111116e-06,
|
| 566 |
+
"loss": 5.1281,
|
| 567 |
+
"step": 93000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 75.93,
|
| 571 |
+
"learning_rate": 2.666666666666667e-06,
|
| 572 |
+
"loss": 5.1257,
|
| 573 |
+
"step": 94000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 76.74,
|
| 577 |
+
"learning_rate": 2.222222222222222e-06,
|
| 578 |
+
"loss": 5.1245,
|
| 579 |
+
"step": 95000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 77.54,
|
| 583 |
+
"learning_rate": 1.777777777777778e-06,
|
| 584 |
+
"loss": 5.1244,
|
| 585 |
+
"step": 96000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 78.35,
|
| 589 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 590 |
+
"loss": 5.1229,
|
| 591 |
+
"step": 97000
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 79.16,
|
| 595 |
+
"learning_rate": 8.88888888888889e-07,
|
| 596 |
+
"loss": 5.1223,
|
| 597 |
+
"step": 98000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 79.97,
|
| 601 |
+
"learning_rate": 4.444444444444445e-07,
|
| 602 |
+
"loss": 5.1231,
|
| 603 |
+
"step": 99000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 80.78,
|
| 607 |
+
"learning_rate": 0.0,
|
| 608 |
+
"loss": 5.1203,
|
| 609 |
+
"step": 100000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 10.2,
|
| 613 |
+
"learning_rate": 2.0842105263157895e-05,
|
| 614 |
+
"loss": 5.1411,
|
| 615 |
+
"step": 101000
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 10.3,
|
| 619 |
+
"learning_rate": 2.0631578947368425e-05,
|
| 620 |
+
"loss": 5.1408,
|
| 621 |
+
"step": 102000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 10.4,
|
| 625 |
+
"learning_rate": 2.0421052631578952e-05,
|
| 626 |
+
"loss": 5.1433,
|
| 627 |
+
"step": 103000
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 10.5,
|
| 631 |
+
"learning_rate": 2.0210526315789475e-05,
|
| 632 |
+
"loss": 5.154,
|
| 633 |
+
"step": 104000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 10.6,
|
| 637 |
+
"learning_rate": 2e-05,
|
| 638 |
+
"loss": 5.1553,
|
| 639 |
+
"step": 105000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 10.71,
|
| 643 |
+
"learning_rate": 1.9789473684210528e-05,
|
| 644 |
+
"loss": 5.1442,
|
| 645 |
+
"step": 106000
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 10.81,
|
| 649 |
+
"learning_rate": 1.9578947368421055e-05,
|
| 650 |
+
"loss": 5.1442,
|
| 651 |
+
"step": 107000
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 10.91,
|
| 655 |
+
"learning_rate": 1.936842105263158e-05,
|
| 656 |
+
"loss": 5.147,
|
| 657 |
+
"step": 108000
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 11.01,
|
| 661 |
+
"learning_rate": 1.9157894736842108e-05,
|
| 662 |
+
"loss": 5.1433,
|
| 663 |
+
"step": 109000
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 11.11,
|
| 667 |
+
"learning_rate": 1.894736842105263e-05,
|
| 668 |
+
"loss": 5.1374,
|
| 669 |
+
"step": 110000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 11.21,
|
| 673 |
+
"learning_rate": 1.873684210526316e-05,
|
| 674 |
+
"loss": 5.1411,
|
| 675 |
+
"step": 111000
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 11.31,
|
| 679 |
+
"learning_rate": 1.8526315789473684e-05,
|
| 680 |
+
"loss": 5.1371,
|
| 681 |
+
"step": 112000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 11.41,
|
| 685 |
+
"learning_rate": 1.831578947368421e-05,
|
| 686 |
+
"loss": 5.1379,
|
| 687 |
+
"step": 113000
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 11.51,
|
| 691 |
+
"learning_rate": 1.810526315789474e-05,
|
| 692 |
+
"loss": 5.139,
|
| 693 |
+
"step": 114000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 11.61,
|
| 697 |
+
"learning_rate": 1.7894736842105264e-05,
|
| 698 |
+
"loss": 5.131,
|
| 699 |
+
"step": 115000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 11.72,
|
| 703 |
+
"learning_rate": 1.768421052631579e-05,
|
| 704 |
+
"loss": 5.1313,
|
| 705 |
+
"step": 116000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 11.82,
|
| 709 |
+
"learning_rate": 1.7473684210526317e-05,
|
| 710 |
+
"loss": 5.1287,
|
| 711 |
+
"step": 117000
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 11.92,
|
| 715 |
+
"learning_rate": 1.7263157894736843e-05,
|
| 716 |
+
"loss": 5.1304,
|
| 717 |
+
"step": 118000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 12.02,
|
| 721 |
+
"learning_rate": 1.705263157894737e-05,
|
| 722 |
+
"loss": 5.1309,
|
| 723 |
+
"step": 119000
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 12.12,
|
| 727 |
+
"learning_rate": 1.6842105263157896e-05,
|
| 728 |
+
"loss": 5.1256,
|
| 729 |
+
"step": 120000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 12.22,
|
| 733 |
+
"learning_rate": 1.6631578947368423e-05,
|
| 734 |
+
"loss": 5.1202,
|
| 735 |
+
"step": 121000
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 12.32,
|
| 739 |
+
"learning_rate": 1.642105263157895e-05,
|
| 740 |
+
"loss": 5.125,
|
| 741 |
+
"step": 122000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 12.42,
|
| 745 |
+
"learning_rate": 1.6210526315789473e-05,
|
| 746 |
+
"loss": 5.125,
|
| 747 |
+
"step": 123000
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 12.52,
|
| 751 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 752 |
+
"loss": 5.1259,
|
| 753 |
+
"step": 124000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 12.62,
|
| 757 |
+
"learning_rate": 1.578947368421053e-05,
|
| 758 |
+
"loss": 5.1186,
|
| 759 |
+
"step": 125000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 12.73,
|
| 763 |
+
"learning_rate": 1.5578947368421052e-05,
|
| 764 |
+
"loss": 5.1097,
|
| 765 |
+
"step": 126000
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 12.83,
|
| 769 |
+
"learning_rate": 1.536842105263158e-05,
|
| 770 |
+
"loss": 5.12,
|
| 771 |
+
"step": 127000
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 12.93,
|
| 775 |
+
"learning_rate": 1.5157894736842107e-05,
|
| 776 |
+
"loss": 5.123,
|
| 777 |
+
"step": 128000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 13.03,
|
| 781 |
+
"learning_rate": 1.4947368421052632e-05,
|
| 782 |
+
"loss": 5.1113,
|
| 783 |
+
"step": 129000
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 13.13,
|
| 787 |
+
"learning_rate": 1.4736842105263159e-05,
|
| 788 |
+
"loss": 5.1071,
|
| 789 |
+
"step": 130000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 13.23,
|
| 793 |
+
"learning_rate": 1.4526315789473687e-05,
|
| 794 |
+
"loss": 5.1167,
|
| 795 |
+
"step": 131000
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 13.33,
|
| 799 |
+
"learning_rate": 1.4315789473684212e-05,
|
| 800 |
+
"loss": 5.1153,
|
| 801 |
+
"step": 132000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 13.43,
|
| 805 |
+
"learning_rate": 1.4105263157894738e-05,
|
| 806 |
+
"loss": 5.1171,
|
| 807 |
+
"step": 133000
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 13.53,
|
| 811 |
+
"learning_rate": 1.3894736842105265e-05,
|
| 812 |
+
"loss": 5.1101,
|
| 813 |
+
"step": 134000
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 13.63,
|
| 817 |
+
"learning_rate": 1.3684210526315791e-05,
|
| 818 |
+
"loss": 5.1096,
|
| 819 |
+
"step": 135000
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 13.74,
|
| 823 |
+
"learning_rate": 1.3473684210526316e-05,
|
| 824 |
+
"loss": 5.107,
|
| 825 |
+
"step": 136000
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 13.84,
|
| 829 |
+
"learning_rate": 1.3263157894736843e-05,
|
| 830 |
+
"loss": 5.1048,
|
| 831 |
+
"step": 137000
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 13.94,
|
| 835 |
+
"learning_rate": 1.305263157894737e-05,
|
| 836 |
+
"loss": 5.1077,
|
| 837 |
+
"step": 138000
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 14.04,
|
| 841 |
+
"learning_rate": 1.2842105263157896e-05,
|
| 842 |
+
"loss": 5.0998,
|
| 843 |
+
"step": 139000
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 14.14,
|
| 847 |
+
"learning_rate": 1.263157894736842e-05,
|
| 848 |
+
"loss": 5.1014,
|
| 849 |
+
"step": 140000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 14.24,
|
| 853 |
+
"learning_rate": 1.2421052631578949e-05,
|
| 854 |
+
"loss": 5.1028,
|
| 855 |
+
"step": 141000
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 14.34,
|
| 859 |
+
"learning_rate": 1.2210526315789475e-05,
|
| 860 |
+
"loss": 5.1065,
|
| 861 |
+
"step": 142000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 14.44,
|
| 865 |
+
"learning_rate": 1.2e-05,
|
| 866 |
+
"loss": 5.1024,
|
| 867 |
+
"step": 143000
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 14.54,
|
| 871 |
+
"learning_rate": 1.1789473684210527e-05,
|
| 872 |
+
"loss": 5.1055,
|
| 873 |
+
"step": 144000
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 14.64,
|
| 877 |
+
"learning_rate": 1.1578947368421053e-05,
|
| 878 |
+
"loss": 5.0966,
|
| 879 |
+
"step": 145000
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 14.75,
|
| 883 |
+
"learning_rate": 1.136842105263158e-05,
|
| 884 |
+
"loss": 5.0939,
|
| 885 |
+
"step": 146000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 14.85,
|
| 889 |
+
"learning_rate": 1.1157894736842105e-05,
|
| 890 |
+
"loss": 5.0932,
|
| 891 |
+
"step": 147000
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 14.95,
|
| 895 |
+
"learning_rate": 1.0947368421052633e-05,
|
| 896 |
+
"loss": 5.0971,
|
| 897 |
+
"step": 148000
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 15.05,
|
| 901 |
+
"learning_rate": 1.073684210526316e-05,
|
| 902 |
+
"loss": 5.0802,
|
| 903 |
+
"step": 149000
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 15.15,
|
| 907 |
+
"learning_rate": 1.0526315789473684e-05,
|
| 908 |
+
"loss": 5.0969,
|
| 909 |
+
"step": 150000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 15.25,
|
| 913 |
+
"learning_rate": 1.0315789473684213e-05,
|
| 914 |
+
"loss": 5.0889,
|
| 915 |
+
"step": 151000
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 15.35,
|
| 919 |
+
"learning_rate": 1.0105263157894738e-05,
|
| 920 |
+
"loss": 5.0934,
|
| 921 |
+
"step": 152000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 15.45,
|
| 925 |
+
"learning_rate": 9.894736842105264e-06,
|
| 926 |
+
"loss": 5.0961,
|
| 927 |
+
"step": 153000
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 15.55,
|
| 931 |
+
"learning_rate": 9.68421052631579e-06,
|
| 932 |
+
"loss": 5.0874,
|
| 933 |
+
"step": 154000
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 15.65,
|
| 937 |
+
"learning_rate": 9.473684210526315e-06,
|
| 938 |
+
"loss": 5.0896,
|
| 939 |
+
"step": 155000
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 15.76,
|
| 943 |
+
"learning_rate": 9.263157894736842e-06,
|
| 944 |
+
"loss": 5.0879,
|
| 945 |
+
"step": 156000
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 15.86,
|
| 949 |
+
"learning_rate": 9.05263157894737e-06,
|
| 950 |
+
"loss": 5.0848,
|
| 951 |
+
"step": 157000
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 15.96,
|
| 955 |
+
"learning_rate": 8.842105263157895e-06,
|
| 956 |
+
"loss": 5.0879,
|
| 957 |
+
"step": 158000
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 16.06,
|
| 961 |
+
"learning_rate": 8.631578947368422e-06,
|
| 962 |
+
"loss": 5.0799,
|
| 963 |
+
"step": 159000
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 16.16,
|
| 967 |
+
"learning_rate": 8.421052631578948e-06,
|
| 968 |
+
"loss": 5.0847,
|
| 969 |
+
"step": 160000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 16.26,
|
| 973 |
+
"learning_rate": 8.210526315789475e-06,
|
| 974 |
+
"loss": 5.0897,
|
| 975 |
+
"step": 161000
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 16.36,
|
| 979 |
+
"learning_rate": 8.000000000000001e-06,
|
| 980 |
+
"loss": 5.0799,
|
| 981 |
+
"step": 162000
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 16.46,
|
| 985 |
+
"learning_rate": 7.789473684210526e-06,
|
| 986 |
+
"loss": 5.0847,
|
| 987 |
+
"step": 163000
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 16.56,
|
| 991 |
+
"learning_rate": 7.578947368421054e-06,
|
| 992 |
+
"loss": 5.0764,
|
| 993 |
+
"step": 164000
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 16.66,
|
| 997 |
+
"learning_rate": 7.368421052631579e-06,
|
| 998 |
+
"loss": 5.0756,
|
| 999 |
+
"step": 165000
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 16.77,
|
| 1003 |
+
"learning_rate": 7.157894736842106e-06,
|
| 1004 |
+
"loss": 5.0755,
|
| 1005 |
+
"step": 166000
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 16.87,
|
| 1009 |
+
"learning_rate": 6.947368421052632e-06,
|
| 1010 |
+
"loss": 5.0788,
|
| 1011 |
+
"step": 167000
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 16.97,
|
| 1015 |
+
"learning_rate": 6.736842105263158e-06,
|
| 1016 |
+
"loss": 5.0793,
|
| 1017 |
+
"step": 168000
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 17.07,
|
| 1021 |
+
"learning_rate": 6.526315789473685e-06,
|
| 1022 |
+
"loss": 5.0768,
|
| 1023 |
+
"step": 169000
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 17.17,
|
| 1027 |
+
"learning_rate": 6.31578947368421e-06,
|
| 1028 |
+
"loss": 5.0746,
|
| 1029 |
+
"step": 170000
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 17.27,
|
| 1033 |
+
"learning_rate": 6.105263157894738e-06,
|
| 1034 |
+
"loss": 5.075,
|
| 1035 |
+
"step": 171000
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 17.37,
|
| 1039 |
+
"learning_rate": 5.8947368421052634e-06,
|
| 1040 |
+
"loss": 5.0799,
|
| 1041 |
+
"step": 172000
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 17.47,
|
| 1045 |
+
"learning_rate": 5.68421052631579e-06,
|
| 1046 |
+
"loss": 5.0684,
|
| 1047 |
+
"step": 173000
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 17.57,
|
| 1051 |
+
"learning_rate": 5.4736842105263165e-06,
|
| 1052 |
+
"loss": 5.0741,
|
| 1053 |
+
"step": 174000
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 17.67,
|
| 1057 |
+
"learning_rate": 5.263157894736842e-06,
|
| 1058 |
+
"loss": 5.0756,
|
| 1059 |
+
"step": 175000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 17.78,
|
| 1063 |
+
"learning_rate": 5.052631578947369e-06,
|
| 1064 |
+
"loss": 5.0711,
|
| 1065 |
+
"step": 176000
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 17.88,
|
| 1069 |
+
"learning_rate": 4.842105263157895e-06,
|
| 1070 |
+
"loss": 5.0701,
|
| 1071 |
+
"step": 177000
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 17.98,
|
| 1075 |
+
"learning_rate": 4.631578947368421e-06,
|
| 1076 |
+
"loss": 5.0724,
|
| 1077 |
+
"step": 178000
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 18.08,
|
| 1081 |
+
"learning_rate": 4.4210526315789476e-06,
|
| 1082 |
+
"loss": 5.0729,
|
| 1083 |
+
"step": 179000
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 18.18,
|
| 1087 |
+
"learning_rate": 4.210526315789474e-06,
|
| 1088 |
+
"loss": 5.0667,
|
| 1089 |
+
"step": 180000
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 18.28,
|
| 1093 |
+
"learning_rate": 4.000000000000001e-06,
|
| 1094 |
+
"loss": 5.0692,
|
| 1095 |
+
"step": 181000
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 18.38,
|
| 1099 |
+
"learning_rate": 3.789473684210527e-06,
|
| 1100 |
+
"loss": 5.0714,
|
| 1101 |
+
"step": 182000
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 18.48,
|
| 1105 |
+
"learning_rate": 3.578947368421053e-06,
|
| 1106 |
+
"loss": 5.0662,
|
| 1107 |
+
"step": 183000
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 18.58,
|
| 1111 |
+
"learning_rate": 3.368421052631579e-06,
|
| 1112 |
+
"loss": 5.0726,
|
| 1113 |
+
"step": 184000
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 18.68,
|
| 1117 |
+
"learning_rate": 3.157894736842105e-06,
|
| 1118 |
+
"loss": 5.0743,
|
| 1119 |
+
"step": 185000
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 18.79,
|
| 1123 |
+
"learning_rate": 2.9473684210526317e-06,
|
| 1124 |
+
"loss": 5.059,
|
| 1125 |
+
"step": 186000
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 18.89,
|
| 1129 |
+
"learning_rate": 2.7368421052631583e-06,
|
| 1130 |
+
"loss": 5.064,
|
| 1131 |
+
"step": 187000
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 18.99,
|
| 1135 |
+
"learning_rate": 2.5263157894736844e-06,
|
| 1136 |
+
"loss": 5.0659,
|
| 1137 |
+
"step": 188000
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 19.09,
|
| 1141 |
+
"learning_rate": 2.3157894736842105e-06,
|
| 1142 |
+
"loss": 5.0645,
|
| 1143 |
+
"step": 189000
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 19.19,
|
| 1147 |
+
"learning_rate": 2.105263157894737e-06,
|
| 1148 |
+
"loss": 5.0657,
|
| 1149 |
+
"step": 190000
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 19.29,
|
| 1153 |
+
"learning_rate": 1.8947368421052634e-06,
|
| 1154 |
+
"loss": 5.0674,
|
| 1155 |
+
"step": 191000
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 19.39,
|
| 1159 |
+
"learning_rate": 1.6842105263157895e-06,
|
| 1160 |
+
"loss": 5.0609,
|
| 1161 |
+
"step": 192000
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 19.49,
|
| 1165 |
+
"learning_rate": 1.4736842105263159e-06,
|
| 1166 |
+
"loss": 5.0594,
|
| 1167 |
+
"step": 193000
|
| 1168 |
+
}
|
| 1169 |
+
],
|
| 1170 |
+
"logging_steps": 1000,
|
| 1171 |
+
"max_steps": 200000,
|
| 1172 |
+
"num_train_epochs": 21,
|
| 1173 |
+
"save_steps": 1000,
|
| 1174 |
+
"total_flos": 2.255722180734432e+19,
|
| 1175 |
+
"trial_name": null,
|
| 1176 |
+
"trial_params": null
|
| 1177 |
+
}
|
checkpoint-193000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f7b759ef851ee3a68e8c9ad880cbb1bc393f7d811df1a445efe7298474f0c09
|
| 3 |
+
size 5137
|
checkpoint-194000/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 12 |
+
"layer_norm_eps": 1e-12,
|
| 13 |
+
"max_length": 512,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.35.2",
|
| 22 |
+
"type_vocab_size": 2,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 5120
|
| 25 |
+
}
|
checkpoint-194000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"max_length": 512,
|
| 4 |
+
"pad_token_id": 0,
|
| 5 |
+
"transformers_version": "4.35.2"
|
| 6 |
+
}
|
checkpoint-194000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ac827f5a006581a23a735f6c2b2eec7d0684a75ec47a409a6aeb3a8518f9a2f
|
| 3 |
+
size 359944256
|
checkpoint-194000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1746782d4b1dc063e47255dcbe78f3ed6853bbaeba691267c9cc6946f844a50e
|
| 3 |
+
size 720010699
|
checkpoint-194000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6034fc1ea03e5f948d22b1d408b68f117ba507f29466abf9104ff7cb0299524
|
| 3 |
+
size 14645
|
checkpoint-194000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9aa460464675e9f0593bb3962bdd48c1f52b25c8c8bf257806850efc7689aa1
|
| 3 |
+
size 1465
|
checkpoint-194000/trainer_state.json
ADDED
|
@@ -0,0 +1,1183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 19.593980406019593,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 194000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.81,
|
| 13 |
+
"learning_rate": 4.000000000000001e-06,
|
| 14 |
+
"loss": 7.87,
|
| 15 |
+
"step": 1000
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.62,
|
| 19 |
+
"learning_rate": 8.000000000000001e-06,
|
| 20 |
+
"loss": 6.8831,
|
| 21 |
+
"step": 2000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 2.42,
|
| 25 |
+
"learning_rate": 1.2e-05,
|
| 26 |
+
"loss": 6.7256,
|
| 27 |
+
"step": 3000
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 3.23,
|
| 31 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 32 |
+
"loss": 6.6605,
|
| 33 |
+
"step": 4000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 4.04,
|
| 37 |
+
"learning_rate": 2e-05,
|
| 38 |
+
"loss": 6.6243,
|
| 39 |
+
"step": 5000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 4.85,
|
| 43 |
+
"learning_rate": 2.4e-05,
|
| 44 |
+
"loss": 6.6033,
|
| 45 |
+
"step": 6000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 5.65,
|
| 49 |
+
"learning_rate": 2.8e-05,
|
| 50 |
+
"loss": 6.5906,
|
| 51 |
+
"step": 7000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 6.46,
|
| 55 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 56 |
+
"loss": 6.5772,
|
| 57 |
+
"step": 8000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 7.27,
|
| 61 |
+
"learning_rate": 3.6e-05,
|
| 62 |
+
"loss": 6.5718,
|
| 63 |
+
"step": 9000
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 8.08,
|
| 67 |
+
"learning_rate": 4e-05,
|
| 68 |
+
"loss": 6.5653,
|
| 69 |
+
"step": 10000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 8.89,
|
| 73 |
+
"learning_rate": 3.955555555555556e-05,
|
| 74 |
+
"loss": 6.5602,
|
| 75 |
+
"step": 11000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 9.69,
|
| 79 |
+
"learning_rate": 3.9111111111111115e-05,
|
| 80 |
+
"loss": 6.5572,
|
| 81 |
+
"step": 12000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 10.5,
|
| 85 |
+
"learning_rate": 3.866666666666667e-05,
|
| 86 |
+
"loss": 6.5534,
|
| 87 |
+
"step": 13000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 11.31,
|
| 91 |
+
"learning_rate": 3.8222222222222226e-05,
|
| 92 |
+
"loss": 6.5533,
|
| 93 |
+
"step": 14000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 12.12,
|
| 97 |
+
"learning_rate": 3.777777777777778e-05,
|
| 98 |
+
"loss": 6.547,
|
| 99 |
+
"step": 15000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 12.92,
|
| 103 |
+
"learning_rate": 3.733333333333334e-05,
|
| 104 |
+
"loss": 6.5463,
|
| 105 |
+
"step": 16000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 13.73,
|
| 109 |
+
"learning_rate": 3.6888888888888896e-05,
|
| 110 |
+
"loss": 6.5437,
|
| 111 |
+
"step": 17000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 14.54,
|
| 115 |
+
"learning_rate": 3.644444444444445e-05,
|
| 116 |
+
"loss": 6.5322,
|
| 117 |
+
"step": 18000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 15.35,
|
| 121 |
+
"learning_rate": 3.6e-05,
|
| 122 |
+
"loss": 6.4474,
|
| 123 |
+
"step": 19000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 16.16,
|
| 127 |
+
"learning_rate": 3.555555555555555e-05,
|
| 128 |
+
"loss": 6.3968,
|
| 129 |
+
"step": 20000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 16.96,
|
| 133 |
+
"learning_rate": 3.511111111111111e-05,
|
| 134 |
+
"loss": 6.3516,
|
| 135 |
+
"step": 21000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 17.77,
|
| 139 |
+
"learning_rate": 3.466666666666667e-05,
|
| 140 |
+
"loss": 6.311,
|
| 141 |
+
"step": 22000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 18.58,
|
| 145 |
+
"learning_rate": 3.4222222222222224e-05,
|
| 146 |
+
"loss": 6.2707,
|
| 147 |
+
"step": 23000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 19.39,
|
| 151 |
+
"learning_rate": 3.377777777777778e-05,
|
| 152 |
+
"loss": 6.2294,
|
| 153 |
+
"step": 24000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 20.19,
|
| 157 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 158 |
+
"loss": 6.1822,
|
| 159 |
+
"step": 25000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 21.0,
|
| 163 |
+
"learning_rate": 3.288888888888889e-05,
|
| 164 |
+
"loss": 6.1128,
|
| 165 |
+
"step": 26000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 21.81,
|
| 169 |
+
"learning_rate": 3.2444444444444446e-05,
|
| 170 |
+
"loss": 6.0262,
|
| 171 |
+
"step": 27000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 22.62,
|
| 175 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 176 |
+
"loss": 5.9326,
|
| 177 |
+
"step": 28000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 23.42,
|
| 181 |
+
"learning_rate": 3.155555555555556e-05,
|
| 182 |
+
"loss": 5.8051,
|
| 183 |
+
"step": 29000
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 24.23,
|
| 187 |
+
"learning_rate": 3.111111111111112e-05,
|
| 188 |
+
"loss": 5.703,
|
| 189 |
+
"step": 30000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 25.04,
|
| 193 |
+
"learning_rate": 3.066666666666667e-05,
|
| 194 |
+
"loss": 5.6361,
|
| 195 |
+
"step": 31000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 25.85,
|
| 199 |
+
"learning_rate": 3.0222222222222225e-05,
|
| 200 |
+
"loss": 5.5885,
|
| 201 |
+
"step": 32000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 26.66,
|
| 205 |
+
"learning_rate": 2.977777777777778e-05,
|
| 206 |
+
"loss": 5.5487,
|
| 207 |
+
"step": 33000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 27.46,
|
| 211 |
+
"learning_rate": 2.9333333333333333e-05,
|
| 212 |
+
"loss": 5.5163,
|
| 213 |
+
"step": 34000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 28.27,
|
| 217 |
+
"learning_rate": 2.888888888888889e-05,
|
| 218 |
+
"loss": 5.4922,
|
| 219 |
+
"step": 35000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 29.08,
|
| 223 |
+
"learning_rate": 2.8444444444444447e-05,
|
| 224 |
+
"loss": 5.4659,
|
| 225 |
+
"step": 36000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 29.89,
|
| 229 |
+
"learning_rate": 2.8e-05,
|
| 230 |
+
"loss": 5.4453,
|
| 231 |
+
"step": 37000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 30.69,
|
| 235 |
+
"learning_rate": 2.755555555555556e-05,
|
| 236 |
+
"loss": 5.4257,
|
| 237 |
+
"step": 38000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 31.5,
|
| 241 |
+
"learning_rate": 2.7111111111111114e-05,
|
| 242 |
+
"loss": 5.4111,
|
| 243 |
+
"step": 39000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 32.31,
|
| 247 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 248 |
+
"loss": 5.3939,
|
| 249 |
+
"step": 40000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 33.12,
|
| 253 |
+
"learning_rate": 2.6222222222222226e-05,
|
| 254 |
+
"loss": 5.3814,
|
| 255 |
+
"step": 41000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 33.93,
|
| 259 |
+
"learning_rate": 2.577777777777778e-05,
|
| 260 |
+
"loss": 5.3658,
|
| 261 |
+
"step": 42000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 34.73,
|
| 265 |
+
"learning_rate": 2.5333333333333334e-05,
|
| 266 |
+
"loss": 5.353,
|
| 267 |
+
"step": 43000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 35.54,
|
| 271 |
+
"learning_rate": 2.4888888888888893e-05,
|
| 272 |
+
"loss": 5.3419,
|
| 273 |
+
"step": 44000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 36.35,
|
| 277 |
+
"learning_rate": 2.444444444444445e-05,
|
| 278 |
+
"loss": 5.3312,
|
| 279 |
+
"step": 45000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 37.16,
|
| 283 |
+
"learning_rate": 2.4e-05,
|
| 284 |
+
"loss": 5.3217,
|
| 285 |
+
"step": 46000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 37.96,
|
| 289 |
+
"learning_rate": 2.355555555555556e-05,
|
| 290 |
+
"loss": 5.3111,
|
| 291 |
+
"step": 47000
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 38.77,
|
| 295 |
+
"learning_rate": 2.3111111111111112e-05,
|
| 296 |
+
"loss": 5.3013,
|
| 297 |
+
"step": 48000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 39.58,
|
| 301 |
+
"learning_rate": 2.2666666666666668e-05,
|
| 302 |
+
"loss": 5.291,
|
| 303 |
+
"step": 49000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 40.39,
|
| 307 |
+
"learning_rate": 2.2222222222222227e-05,
|
| 308 |
+
"loss": 5.2835,
|
| 309 |
+
"step": 50000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 41.2,
|
| 313 |
+
"learning_rate": 2.177777777777778e-05,
|
| 314 |
+
"loss": 5.2753,
|
| 315 |
+
"step": 51000
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 42.0,
|
| 319 |
+
"learning_rate": 2.1333333333333335e-05,
|
| 320 |
+
"loss": 5.2666,
|
| 321 |
+
"step": 52000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 42.81,
|
| 325 |
+
"learning_rate": 2.088888888888889e-05,
|
| 326 |
+
"loss": 5.2594,
|
| 327 |
+
"step": 53000
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 43.62,
|
| 331 |
+
"learning_rate": 2.0444444444444446e-05,
|
| 332 |
+
"loss": 5.2513,
|
| 333 |
+
"step": 54000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 44.43,
|
| 337 |
+
"learning_rate": 2e-05,
|
| 338 |
+
"loss": 5.2441,
|
| 339 |
+
"step": 55000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 45.23,
|
| 343 |
+
"learning_rate": 1.9555555555555557e-05,
|
| 344 |
+
"loss": 5.2426,
|
| 345 |
+
"step": 56000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 46.04,
|
| 349 |
+
"learning_rate": 1.9111111111111113e-05,
|
| 350 |
+
"loss": 5.2328,
|
| 351 |
+
"step": 57000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 46.85,
|
| 355 |
+
"learning_rate": 1.866666666666667e-05,
|
| 356 |
+
"loss": 5.2278,
|
| 357 |
+
"step": 58000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 47.66,
|
| 361 |
+
"learning_rate": 1.8222222222222224e-05,
|
| 362 |
+
"loss": 5.2213,
|
| 363 |
+
"step": 59000
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 48.47,
|
| 367 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 368 |
+
"loss": 5.2155,
|
| 369 |
+
"step": 60000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 49.27,
|
| 373 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 374 |
+
"loss": 5.2102,
|
| 375 |
+
"step": 61000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 50.08,
|
| 379 |
+
"learning_rate": 1.688888888888889e-05,
|
| 380 |
+
"loss": 5.2048,
|
| 381 |
+
"step": 62000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 50.89,
|
| 385 |
+
"learning_rate": 1.6444444444444444e-05,
|
| 386 |
+
"loss": 5.2008,
|
| 387 |
+
"step": 63000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 51.7,
|
| 391 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 392 |
+
"loss": 5.1975,
|
| 393 |
+
"step": 64000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 52.5,
|
| 397 |
+
"learning_rate": 1.555555555555556e-05,
|
| 398 |
+
"loss": 5.1925,
|
| 399 |
+
"step": 65000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 53.31,
|
| 403 |
+
"learning_rate": 1.5111111111111112e-05,
|
| 404 |
+
"loss": 5.1883,
|
| 405 |
+
"step": 66000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 54.12,
|
| 409 |
+
"learning_rate": 1.4666666666666666e-05,
|
| 410 |
+
"loss": 5.1822,
|
| 411 |
+
"step": 67000
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 54.93,
|
| 415 |
+
"learning_rate": 1.4222222222222224e-05,
|
| 416 |
+
"loss": 5.1806,
|
| 417 |
+
"step": 68000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 55.74,
|
| 421 |
+
"learning_rate": 1.377777777777778e-05,
|
| 422 |
+
"loss": 5.1756,
|
| 423 |
+
"step": 69000
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 56.54,
|
| 427 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 428 |
+
"loss": 5.175,
|
| 429 |
+
"step": 70000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 57.35,
|
| 433 |
+
"learning_rate": 1.288888888888889e-05,
|
| 434 |
+
"loss": 5.1686,
|
| 435 |
+
"step": 71000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 58.16,
|
| 439 |
+
"learning_rate": 1.2444444444444446e-05,
|
| 440 |
+
"loss": 5.1672,
|
| 441 |
+
"step": 72000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 58.97,
|
| 445 |
+
"learning_rate": 1.2e-05,
|
| 446 |
+
"loss": 5.1644,
|
| 447 |
+
"step": 73000
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 59.77,
|
| 451 |
+
"learning_rate": 1.1555555555555556e-05,
|
| 452 |
+
"loss": 5.1609,
|
| 453 |
+
"step": 74000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 60.58,
|
| 457 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 458 |
+
"loss": 5.1582,
|
| 459 |
+
"step": 75000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 61.39,
|
| 463 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 464 |
+
"loss": 5.1539,
|
| 465 |
+
"step": 76000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 62.2,
|
| 469 |
+
"learning_rate": 1.0222222222222223e-05,
|
| 470 |
+
"loss": 5.1535,
|
| 471 |
+
"step": 77000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 63.0,
|
| 475 |
+
"learning_rate": 9.777777777777779e-06,
|
| 476 |
+
"loss": 5.1516,
|
| 477 |
+
"step": 78000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 63.81,
|
| 481 |
+
"learning_rate": 9.333333333333334e-06,
|
| 482 |
+
"loss": 5.1479,
|
| 483 |
+
"step": 79000
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 64.62,
|
| 487 |
+
"learning_rate": 8.888888888888888e-06,
|
| 488 |
+
"loss": 5.1451,
|
| 489 |
+
"step": 80000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 65.43,
|
| 493 |
+
"learning_rate": 8.444444444444446e-06,
|
| 494 |
+
"loss": 5.1439,
|
| 495 |
+
"step": 81000
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 66.24,
|
| 499 |
+
"learning_rate": 8.000000000000001e-06,
|
| 500 |
+
"loss": 5.1429,
|
| 501 |
+
"step": 82000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 67.04,
|
| 505 |
+
"learning_rate": 7.555555555555556e-06,
|
| 506 |
+
"loss": 5.1402,
|
| 507 |
+
"step": 83000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 67.85,
|
| 511 |
+
"learning_rate": 7.111111111111112e-06,
|
| 512 |
+
"loss": 5.1375,
|
| 513 |
+
"step": 84000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 68.66,
|
| 517 |
+
"learning_rate": 6.666666666666667e-06,
|
| 518 |
+
"loss": 5.1348,
|
| 519 |
+
"step": 85000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 69.47,
|
| 523 |
+
"learning_rate": 6.222222222222223e-06,
|
| 524 |
+
"loss": 5.1357,
|
| 525 |
+
"step": 86000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 70.27,
|
| 529 |
+
"learning_rate": 5.777777777777778e-06,
|
| 530 |
+
"loss": 5.1336,
|
| 531 |
+
"step": 87000
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 71.08,
|
| 535 |
+
"learning_rate": 5.333333333333334e-06,
|
| 536 |
+
"loss": 5.1308,
|
| 537 |
+
"step": 88000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 71.89,
|
| 541 |
+
"learning_rate": 4.888888888888889e-06,
|
| 542 |
+
"loss": 5.1304,
|
| 543 |
+
"step": 89000
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 72.7,
|
| 547 |
+
"learning_rate": 4.444444444444444e-06,
|
| 548 |
+
"loss": 5.1285,
|
| 549 |
+
"step": 90000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 73.51,
|
| 553 |
+
"learning_rate": 4.000000000000001e-06,
|
| 554 |
+
"loss": 5.1272,
|
| 555 |
+
"step": 91000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 74.31,
|
| 559 |
+
"learning_rate": 3.555555555555556e-06,
|
| 560 |
+
"loss": 5.1272,
|
| 561 |
+
"step": 92000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 75.12,
|
| 565 |
+
"learning_rate": 3.1111111111111116e-06,
|
| 566 |
+
"loss": 5.1281,
|
| 567 |
+
"step": 93000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 75.93,
|
| 571 |
+
"learning_rate": 2.666666666666667e-06,
|
| 572 |
+
"loss": 5.1257,
|
| 573 |
+
"step": 94000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 76.74,
|
| 577 |
+
"learning_rate": 2.222222222222222e-06,
|
| 578 |
+
"loss": 5.1245,
|
| 579 |
+
"step": 95000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 77.54,
|
| 583 |
+
"learning_rate": 1.777777777777778e-06,
|
| 584 |
+
"loss": 5.1244,
|
| 585 |
+
"step": 96000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 78.35,
|
| 589 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 590 |
+
"loss": 5.1229,
|
| 591 |
+
"step": 97000
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 79.16,
|
| 595 |
+
"learning_rate": 8.88888888888889e-07,
|
| 596 |
+
"loss": 5.1223,
|
| 597 |
+
"step": 98000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 79.97,
|
| 601 |
+
"learning_rate": 4.444444444444445e-07,
|
| 602 |
+
"loss": 5.1231,
|
| 603 |
+
"step": 99000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 80.78,
|
| 607 |
+
"learning_rate": 0.0,
|
| 608 |
+
"loss": 5.1203,
|
| 609 |
+
"step": 100000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 10.2,
|
| 613 |
+
"learning_rate": 2.0842105263157895e-05,
|
| 614 |
+
"loss": 5.1411,
|
| 615 |
+
"step": 101000
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 10.3,
|
| 619 |
+
"learning_rate": 2.0631578947368425e-05,
|
| 620 |
+
"loss": 5.1408,
|
| 621 |
+
"step": 102000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 10.4,
|
| 625 |
+
"learning_rate": 2.0421052631578952e-05,
|
| 626 |
+
"loss": 5.1433,
|
| 627 |
+
"step": 103000
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 10.5,
|
| 631 |
+
"learning_rate": 2.0210526315789475e-05,
|
| 632 |
+
"loss": 5.154,
|
| 633 |
+
"step": 104000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 10.6,
|
| 637 |
+
"learning_rate": 2e-05,
|
| 638 |
+
"loss": 5.1553,
|
| 639 |
+
"step": 105000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 10.71,
|
| 643 |
+
"learning_rate": 1.9789473684210528e-05,
|
| 644 |
+
"loss": 5.1442,
|
| 645 |
+
"step": 106000
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 10.81,
|
| 649 |
+
"learning_rate": 1.9578947368421055e-05,
|
| 650 |
+
"loss": 5.1442,
|
| 651 |
+
"step": 107000
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 10.91,
|
| 655 |
+
"learning_rate": 1.936842105263158e-05,
|
| 656 |
+
"loss": 5.147,
|
| 657 |
+
"step": 108000
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 11.01,
|
| 661 |
+
"learning_rate": 1.9157894736842108e-05,
|
| 662 |
+
"loss": 5.1433,
|
| 663 |
+
"step": 109000
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 11.11,
|
| 667 |
+
"learning_rate": 1.894736842105263e-05,
|
| 668 |
+
"loss": 5.1374,
|
| 669 |
+
"step": 110000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 11.21,
|
| 673 |
+
"learning_rate": 1.873684210526316e-05,
|
| 674 |
+
"loss": 5.1411,
|
| 675 |
+
"step": 111000
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 11.31,
|
| 679 |
+
"learning_rate": 1.8526315789473684e-05,
|
| 680 |
+
"loss": 5.1371,
|
| 681 |
+
"step": 112000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 11.41,
|
| 685 |
+
"learning_rate": 1.831578947368421e-05,
|
| 686 |
+
"loss": 5.1379,
|
| 687 |
+
"step": 113000
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 11.51,
|
| 691 |
+
"learning_rate": 1.810526315789474e-05,
|
| 692 |
+
"loss": 5.139,
|
| 693 |
+
"step": 114000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 11.61,
|
| 697 |
+
"learning_rate": 1.7894736842105264e-05,
|
| 698 |
+
"loss": 5.131,
|
| 699 |
+
"step": 115000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 11.72,
|
| 703 |
+
"learning_rate": 1.768421052631579e-05,
|
| 704 |
+
"loss": 5.1313,
|
| 705 |
+
"step": 116000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 11.82,
|
| 709 |
+
"learning_rate": 1.7473684210526317e-05,
|
| 710 |
+
"loss": 5.1287,
|
| 711 |
+
"step": 117000
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 11.92,
|
| 715 |
+
"learning_rate": 1.7263157894736843e-05,
|
| 716 |
+
"loss": 5.1304,
|
| 717 |
+
"step": 118000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 12.02,
|
| 721 |
+
"learning_rate": 1.705263157894737e-05,
|
| 722 |
+
"loss": 5.1309,
|
| 723 |
+
"step": 119000
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 12.12,
|
| 727 |
+
"learning_rate": 1.6842105263157896e-05,
|
| 728 |
+
"loss": 5.1256,
|
| 729 |
+
"step": 120000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 12.22,
|
| 733 |
+
"learning_rate": 1.6631578947368423e-05,
|
| 734 |
+
"loss": 5.1202,
|
| 735 |
+
"step": 121000
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 12.32,
|
| 739 |
+
"learning_rate": 1.642105263157895e-05,
|
| 740 |
+
"loss": 5.125,
|
| 741 |
+
"step": 122000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 12.42,
|
| 745 |
+
"learning_rate": 1.6210526315789473e-05,
|
| 746 |
+
"loss": 5.125,
|
| 747 |
+
"step": 123000
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 12.52,
|
| 751 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 752 |
+
"loss": 5.1259,
|
| 753 |
+
"step": 124000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 12.62,
|
| 757 |
+
"learning_rate": 1.578947368421053e-05,
|
| 758 |
+
"loss": 5.1186,
|
| 759 |
+
"step": 125000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 12.73,
|
| 763 |
+
"learning_rate": 1.5578947368421052e-05,
|
| 764 |
+
"loss": 5.1097,
|
| 765 |
+
"step": 126000
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 12.83,
|
| 769 |
+
"learning_rate": 1.536842105263158e-05,
|
| 770 |
+
"loss": 5.12,
|
| 771 |
+
"step": 127000
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 12.93,
|
| 775 |
+
"learning_rate": 1.5157894736842107e-05,
|
| 776 |
+
"loss": 5.123,
|
| 777 |
+
"step": 128000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 13.03,
|
| 781 |
+
"learning_rate": 1.4947368421052632e-05,
|
| 782 |
+
"loss": 5.1113,
|
| 783 |
+
"step": 129000
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 13.13,
|
| 787 |
+
"learning_rate": 1.4736842105263159e-05,
|
| 788 |
+
"loss": 5.1071,
|
| 789 |
+
"step": 130000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 13.23,
|
| 793 |
+
"learning_rate": 1.4526315789473687e-05,
|
| 794 |
+
"loss": 5.1167,
|
| 795 |
+
"step": 131000
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 13.33,
|
| 799 |
+
"learning_rate": 1.4315789473684212e-05,
|
| 800 |
+
"loss": 5.1153,
|
| 801 |
+
"step": 132000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 13.43,
|
| 805 |
+
"learning_rate": 1.4105263157894738e-05,
|
| 806 |
+
"loss": 5.1171,
|
| 807 |
+
"step": 133000
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 13.53,
|
| 811 |
+
"learning_rate": 1.3894736842105265e-05,
|
| 812 |
+
"loss": 5.1101,
|
| 813 |
+
"step": 134000
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 13.63,
|
| 817 |
+
"learning_rate": 1.3684210526315791e-05,
|
| 818 |
+
"loss": 5.1096,
|
| 819 |
+
"step": 135000
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 13.74,
|
| 823 |
+
"learning_rate": 1.3473684210526316e-05,
|
| 824 |
+
"loss": 5.107,
|
| 825 |
+
"step": 136000
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 13.84,
|
| 829 |
+
"learning_rate": 1.3263157894736843e-05,
|
| 830 |
+
"loss": 5.1048,
|
| 831 |
+
"step": 137000
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 13.94,
|
| 835 |
+
"learning_rate": 1.305263157894737e-05,
|
| 836 |
+
"loss": 5.1077,
|
| 837 |
+
"step": 138000
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 14.04,
|
| 841 |
+
"learning_rate": 1.2842105263157896e-05,
|
| 842 |
+
"loss": 5.0998,
|
| 843 |
+
"step": 139000
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 14.14,
|
| 847 |
+
"learning_rate": 1.263157894736842e-05,
|
| 848 |
+
"loss": 5.1014,
|
| 849 |
+
"step": 140000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 14.24,
|
| 853 |
+
"learning_rate": 1.2421052631578949e-05,
|
| 854 |
+
"loss": 5.1028,
|
| 855 |
+
"step": 141000
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 14.34,
|
| 859 |
+
"learning_rate": 1.2210526315789475e-05,
|
| 860 |
+
"loss": 5.1065,
|
| 861 |
+
"step": 142000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 14.44,
|
| 865 |
+
"learning_rate": 1.2e-05,
|
| 866 |
+
"loss": 5.1024,
|
| 867 |
+
"step": 143000
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 14.54,
|
| 871 |
+
"learning_rate": 1.1789473684210527e-05,
|
| 872 |
+
"loss": 5.1055,
|
| 873 |
+
"step": 144000
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 14.64,
|
| 877 |
+
"learning_rate": 1.1578947368421053e-05,
|
| 878 |
+
"loss": 5.0966,
|
| 879 |
+
"step": 145000
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 14.75,
|
| 883 |
+
"learning_rate": 1.136842105263158e-05,
|
| 884 |
+
"loss": 5.0939,
|
| 885 |
+
"step": 146000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 14.85,
|
| 889 |
+
"learning_rate": 1.1157894736842105e-05,
|
| 890 |
+
"loss": 5.0932,
|
| 891 |
+
"step": 147000
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 14.95,
|
| 895 |
+
"learning_rate": 1.0947368421052633e-05,
|
| 896 |
+
"loss": 5.0971,
|
| 897 |
+
"step": 148000
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 15.05,
|
| 901 |
+
"learning_rate": 1.073684210526316e-05,
|
| 902 |
+
"loss": 5.0802,
|
| 903 |
+
"step": 149000
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 15.15,
|
| 907 |
+
"learning_rate": 1.0526315789473684e-05,
|
| 908 |
+
"loss": 5.0969,
|
| 909 |
+
"step": 150000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 15.25,
|
| 913 |
+
"learning_rate": 1.0315789473684213e-05,
|
| 914 |
+
"loss": 5.0889,
|
| 915 |
+
"step": 151000
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 15.35,
|
| 919 |
+
"learning_rate": 1.0105263157894738e-05,
|
| 920 |
+
"loss": 5.0934,
|
| 921 |
+
"step": 152000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 15.45,
|
| 925 |
+
"learning_rate": 9.894736842105264e-06,
|
| 926 |
+
"loss": 5.0961,
|
| 927 |
+
"step": 153000
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 15.55,
|
| 931 |
+
"learning_rate": 9.68421052631579e-06,
|
| 932 |
+
"loss": 5.0874,
|
| 933 |
+
"step": 154000
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 15.65,
|
| 937 |
+
"learning_rate": 9.473684210526315e-06,
|
| 938 |
+
"loss": 5.0896,
|
| 939 |
+
"step": 155000
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 15.76,
|
| 943 |
+
"learning_rate": 9.263157894736842e-06,
|
| 944 |
+
"loss": 5.0879,
|
| 945 |
+
"step": 156000
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 15.86,
|
| 949 |
+
"learning_rate": 9.05263157894737e-06,
|
| 950 |
+
"loss": 5.0848,
|
| 951 |
+
"step": 157000
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 15.96,
|
| 955 |
+
"learning_rate": 8.842105263157895e-06,
|
| 956 |
+
"loss": 5.0879,
|
| 957 |
+
"step": 158000
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 16.06,
|
| 961 |
+
"learning_rate": 8.631578947368422e-06,
|
| 962 |
+
"loss": 5.0799,
|
| 963 |
+
"step": 159000
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 16.16,
|
| 967 |
+
"learning_rate": 8.421052631578948e-06,
|
| 968 |
+
"loss": 5.0847,
|
| 969 |
+
"step": 160000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 16.26,
|
| 973 |
+
"learning_rate": 8.210526315789475e-06,
|
| 974 |
+
"loss": 5.0897,
|
| 975 |
+
"step": 161000
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 16.36,
|
| 979 |
+
"learning_rate": 8.000000000000001e-06,
|
| 980 |
+
"loss": 5.0799,
|
| 981 |
+
"step": 162000
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 16.46,
|
| 985 |
+
"learning_rate": 7.789473684210526e-06,
|
| 986 |
+
"loss": 5.0847,
|
| 987 |
+
"step": 163000
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 16.56,
|
| 991 |
+
"learning_rate": 7.578947368421054e-06,
|
| 992 |
+
"loss": 5.0764,
|
| 993 |
+
"step": 164000
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 16.66,
|
| 997 |
+
"learning_rate": 7.368421052631579e-06,
|
| 998 |
+
"loss": 5.0756,
|
| 999 |
+
"step": 165000
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 16.77,
|
| 1003 |
+
"learning_rate": 7.157894736842106e-06,
|
| 1004 |
+
"loss": 5.0755,
|
| 1005 |
+
"step": 166000
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 16.87,
|
| 1009 |
+
"learning_rate": 6.947368421052632e-06,
|
| 1010 |
+
"loss": 5.0788,
|
| 1011 |
+
"step": 167000
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 16.97,
|
| 1015 |
+
"learning_rate": 6.736842105263158e-06,
|
| 1016 |
+
"loss": 5.0793,
|
| 1017 |
+
"step": 168000
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 17.07,
|
| 1021 |
+
"learning_rate": 6.526315789473685e-06,
|
| 1022 |
+
"loss": 5.0768,
|
| 1023 |
+
"step": 169000
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 17.17,
|
| 1027 |
+
"learning_rate": 6.31578947368421e-06,
|
| 1028 |
+
"loss": 5.0746,
|
| 1029 |
+
"step": 170000
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 17.27,
|
| 1033 |
+
"learning_rate": 6.105263157894738e-06,
|
| 1034 |
+
"loss": 5.075,
|
| 1035 |
+
"step": 171000
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 17.37,
|
| 1039 |
+
"learning_rate": 5.8947368421052634e-06,
|
| 1040 |
+
"loss": 5.0799,
|
| 1041 |
+
"step": 172000
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 17.47,
|
| 1045 |
+
"learning_rate": 5.68421052631579e-06,
|
| 1046 |
+
"loss": 5.0684,
|
| 1047 |
+
"step": 173000
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 17.57,
|
| 1051 |
+
"learning_rate": 5.4736842105263165e-06,
|
| 1052 |
+
"loss": 5.0741,
|
| 1053 |
+
"step": 174000
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 17.67,
|
| 1057 |
+
"learning_rate": 5.263157894736842e-06,
|
| 1058 |
+
"loss": 5.0756,
|
| 1059 |
+
"step": 175000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 17.78,
|
| 1063 |
+
"learning_rate": 5.052631578947369e-06,
|
| 1064 |
+
"loss": 5.0711,
|
| 1065 |
+
"step": 176000
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 17.88,
|
| 1069 |
+
"learning_rate": 4.842105263157895e-06,
|
| 1070 |
+
"loss": 5.0701,
|
| 1071 |
+
"step": 177000
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 17.98,
|
| 1075 |
+
"learning_rate": 4.631578947368421e-06,
|
| 1076 |
+
"loss": 5.0724,
|
| 1077 |
+
"step": 178000
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 18.08,
|
| 1081 |
+
"learning_rate": 4.4210526315789476e-06,
|
| 1082 |
+
"loss": 5.0729,
|
| 1083 |
+
"step": 179000
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 18.18,
|
| 1087 |
+
"learning_rate": 4.210526315789474e-06,
|
| 1088 |
+
"loss": 5.0667,
|
| 1089 |
+
"step": 180000
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 18.28,
|
| 1093 |
+
"learning_rate": 4.000000000000001e-06,
|
| 1094 |
+
"loss": 5.0692,
|
| 1095 |
+
"step": 181000
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 18.38,
|
| 1099 |
+
"learning_rate": 3.789473684210527e-06,
|
| 1100 |
+
"loss": 5.0714,
|
| 1101 |
+
"step": 182000
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 18.48,
|
| 1105 |
+
"learning_rate": 3.578947368421053e-06,
|
| 1106 |
+
"loss": 5.0662,
|
| 1107 |
+
"step": 183000
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 18.58,
|
| 1111 |
+
"learning_rate": 3.368421052631579e-06,
|
| 1112 |
+
"loss": 5.0726,
|
| 1113 |
+
"step": 184000
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 18.68,
|
| 1117 |
+
"learning_rate": 3.157894736842105e-06,
|
| 1118 |
+
"loss": 5.0743,
|
| 1119 |
+
"step": 185000
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 18.79,
|
| 1123 |
+
"learning_rate": 2.9473684210526317e-06,
|
| 1124 |
+
"loss": 5.059,
|
| 1125 |
+
"step": 186000
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 18.89,
|
| 1129 |
+
"learning_rate": 2.7368421052631583e-06,
|
| 1130 |
+
"loss": 5.064,
|
| 1131 |
+
"step": 187000
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 18.99,
|
| 1135 |
+
"learning_rate": 2.5263157894736844e-06,
|
| 1136 |
+
"loss": 5.0659,
|
| 1137 |
+
"step": 188000
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 19.09,
|
| 1141 |
+
"learning_rate": 2.3157894736842105e-06,
|
| 1142 |
+
"loss": 5.0645,
|
| 1143 |
+
"step": 189000
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 19.19,
|
| 1147 |
+
"learning_rate": 2.105263157894737e-06,
|
| 1148 |
+
"loss": 5.0657,
|
| 1149 |
+
"step": 190000
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 19.29,
|
| 1153 |
+
"learning_rate": 1.8947368421052634e-06,
|
| 1154 |
+
"loss": 5.0674,
|
| 1155 |
+
"step": 191000
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 19.39,
|
| 1159 |
+
"learning_rate": 1.6842105263157895e-06,
|
| 1160 |
+
"loss": 5.0609,
|
| 1161 |
+
"step": 192000
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 19.49,
|
| 1165 |
+
"learning_rate": 1.4736842105263159e-06,
|
| 1166 |
+
"loss": 5.0594,
|
| 1167 |
+
"step": 193000
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 19.59,
|
| 1171 |
+
"learning_rate": 1.2631578947368422e-06,
|
| 1172 |
+
"loss": 5.0675,
|
| 1173 |
+
"step": 194000
|
| 1174 |
+
}
|
| 1175 |
+
],
|
| 1176 |
+
"logging_steps": 1000,
|
| 1177 |
+
"max_steps": 200000,
|
| 1178 |
+
"num_train_epochs": 21,
|
| 1179 |
+
"save_steps": 1000,
|
| 1180 |
+
"total_flos": 2.2582481978018497e+19,
|
| 1181 |
+
"trial_name": null,
|
| 1182 |
+
"trial_params": null
|
| 1183 |
+
}
|
checkpoint-194000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f7b759ef851ee3a68e8c9ad880cbb1bc393f7d811df1a445efe7298474f0c09
|
| 3 |
+
size 5137
|
checkpoint-195000/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 12 |
+
"layer_norm_eps": 1e-12,
|
| 13 |
+
"max_length": 512,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.35.2",
|
| 22 |
+
"type_vocab_size": 2,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 5120
|
| 25 |
+
}
|
checkpoint-195000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"max_length": 512,
|
| 4 |
+
"pad_token_id": 0,
|
| 5 |
+
"transformers_version": "4.35.2"
|
| 6 |
+
}
|
checkpoint-195000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03bcd5fc4e87aec74b7df0d6323e4d10d78527c308195fd6e3a43072524f6f1c
|
| 3 |
+
size 359944256
|
checkpoint-195000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b176cd6fac9c28e4076115050e528c3581bfacf5b44c261f0300102a653a612
|
| 3 |
+
size 720010699
|
checkpoint-195000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a5f7f056d5301090fef0d131fa1eea2bee14507e236c442bee7f36ee1f93b7d
|
| 3 |
+
size 14645
|
checkpoint-195000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac3001d5dd025a8da6bc02910e07eb74e4b31d248926c79f2143788adccb7d21
|
| 3 |
+
size 1465
|
checkpoint-195000/trainer_state.json
ADDED
|
@@ -0,0 +1,1189 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 19.694980305019694,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 195000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.81,
|
| 13 |
+
"learning_rate": 4.000000000000001e-06,
|
| 14 |
+
"loss": 7.87,
|
| 15 |
+
"step": 1000
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.62,
|
| 19 |
+
"learning_rate": 8.000000000000001e-06,
|
| 20 |
+
"loss": 6.8831,
|
| 21 |
+
"step": 2000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 2.42,
|
| 25 |
+
"learning_rate": 1.2e-05,
|
| 26 |
+
"loss": 6.7256,
|
| 27 |
+
"step": 3000
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 3.23,
|
| 31 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 32 |
+
"loss": 6.6605,
|
| 33 |
+
"step": 4000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 4.04,
|
| 37 |
+
"learning_rate": 2e-05,
|
| 38 |
+
"loss": 6.6243,
|
| 39 |
+
"step": 5000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 4.85,
|
| 43 |
+
"learning_rate": 2.4e-05,
|
| 44 |
+
"loss": 6.6033,
|
| 45 |
+
"step": 6000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 5.65,
|
| 49 |
+
"learning_rate": 2.8e-05,
|
| 50 |
+
"loss": 6.5906,
|
| 51 |
+
"step": 7000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 6.46,
|
| 55 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 56 |
+
"loss": 6.5772,
|
| 57 |
+
"step": 8000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 7.27,
|
| 61 |
+
"learning_rate": 3.6e-05,
|
| 62 |
+
"loss": 6.5718,
|
| 63 |
+
"step": 9000
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 8.08,
|
| 67 |
+
"learning_rate": 4e-05,
|
| 68 |
+
"loss": 6.5653,
|
| 69 |
+
"step": 10000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 8.89,
|
| 73 |
+
"learning_rate": 3.955555555555556e-05,
|
| 74 |
+
"loss": 6.5602,
|
| 75 |
+
"step": 11000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 9.69,
|
| 79 |
+
"learning_rate": 3.9111111111111115e-05,
|
| 80 |
+
"loss": 6.5572,
|
| 81 |
+
"step": 12000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 10.5,
|
| 85 |
+
"learning_rate": 3.866666666666667e-05,
|
| 86 |
+
"loss": 6.5534,
|
| 87 |
+
"step": 13000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 11.31,
|
| 91 |
+
"learning_rate": 3.8222222222222226e-05,
|
| 92 |
+
"loss": 6.5533,
|
| 93 |
+
"step": 14000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 12.12,
|
| 97 |
+
"learning_rate": 3.777777777777778e-05,
|
| 98 |
+
"loss": 6.547,
|
| 99 |
+
"step": 15000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 12.92,
|
| 103 |
+
"learning_rate": 3.733333333333334e-05,
|
| 104 |
+
"loss": 6.5463,
|
| 105 |
+
"step": 16000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 13.73,
|
| 109 |
+
"learning_rate": 3.6888888888888896e-05,
|
| 110 |
+
"loss": 6.5437,
|
| 111 |
+
"step": 17000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 14.54,
|
| 115 |
+
"learning_rate": 3.644444444444445e-05,
|
| 116 |
+
"loss": 6.5322,
|
| 117 |
+
"step": 18000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 15.35,
|
| 121 |
+
"learning_rate": 3.6e-05,
|
| 122 |
+
"loss": 6.4474,
|
| 123 |
+
"step": 19000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 16.16,
|
| 127 |
+
"learning_rate": 3.555555555555555e-05,
|
| 128 |
+
"loss": 6.3968,
|
| 129 |
+
"step": 20000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 16.96,
|
| 133 |
+
"learning_rate": 3.511111111111111e-05,
|
| 134 |
+
"loss": 6.3516,
|
| 135 |
+
"step": 21000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 17.77,
|
| 139 |
+
"learning_rate": 3.466666666666667e-05,
|
| 140 |
+
"loss": 6.311,
|
| 141 |
+
"step": 22000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 18.58,
|
| 145 |
+
"learning_rate": 3.4222222222222224e-05,
|
| 146 |
+
"loss": 6.2707,
|
| 147 |
+
"step": 23000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 19.39,
|
| 151 |
+
"learning_rate": 3.377777777777778e-05,
|
| 152 |
+
"loss": 6.2294,
|
| 153 |
+
"step": 24000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 20.19,
|
| 157 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 158 |
+
"loss": 6.1822,
|
| 159 |
+
"step": 25000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 21.0,
|
| 163 |
+
"learning_rate": 3.288888888888889e-05,
|
| 164 |
+
"loss": 6.1128,
|
| 165 |
+
"step": 26000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 21.81,
|
| 169 |
+
"learning_rate": 3.2444444444444446e-05,
|
| 170 |
+
"loss": 6.0262,
|
| 171 |
+
"step": 27000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 22.62,
|
| 175 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 176 |
+
"loss": 5.9326,
|
| 177 |
+
"step": 28000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 23.42,
|
| 181 |
+
"learning_rate": 3.155555555555556e-05,
|
| 182 |
+
"loss": 5.8051,
|
| 183 |
+
"step": 29000
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 24.23,
|
| 187 |
+
"learning_rate": 3.111111111111112e-05,
|
| 188 |
+
"loss": 5.703,
|
| 189 |
+
"step": 30000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 25.04,
|
| 193 |
+
"learning_rate": 3.066666666666667e-05,
|
| 194 |
+
"loss": 5.6361,
|
| 195 |
+
"step": 31000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 25.85,
|
| 199 |
+
"learning_rate": 3.0222222222222225e-05,
|
| 200 |
+
"loss": 5.5885,
|
| 201 |
+
"step": 32000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 26.66,
|
| 205 |
+
"learning_rate": 2.977777777777778e-05,
|
| 206 |
+
"loss": 5.5487,
|
| 207 |
+
"step": 33000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 27.46,
|
| 211 |
+
"learning_rate": 2.9333333333333333e-05,
|
| 212 |
+
"loss": 5.5163,
|
| 213 |
+
"step": 34000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 28.27,
|
| 217 |
+
"learning_rate": 2.888888888888889e-05,
|
| 218 |
+
"loss": 5.4922,
|
| 219 |
+
"step": 35000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 29.08,
|
| 223 |
+
"learning_rate": 2.8444444444444447e-05,
|
| 224 |
+
"loss": 5.4659,
|
| 225 |
+
"step": 36000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 29.89,
|
| 229 |
+
"learning_rate": 2.8e-05,
|
| 230 |
+
"loss": 5.4453,
|
| 231 |
+
"step": 37000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 30.69,
|
| 235 |
+
"learning_rate": 2.755555555555556e-05,
|
| 236 |
+
"loss": 5.4257,
|
| 237 |
+
"step": 38000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 31.5,
|
| 241 |
+
"learning_rate": 2.7111111111111114e-05,
|
| 242 |
+
"loss": 5.4111,
|
| 243 |
+
"step": 39000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 32.31,
|
| 247 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 248 |
+
"loss": 5.3939,
|
| 249 |
+
"step": 40000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 33.12,
|
| 253 |
+
"learning_rate": 2.6222222222222226e-05,
|
| 254 |
+
"loss": 5.3814,
|
| 255 |
+
"step": 41000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 33.93,
|
| 259 |
+
"learning_rate": 2.577777777777778e-05,
|
| 260 |
+
"loss": 5.3658,
|
| 261 |
+
"step": 42000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 34.73,
|
| 265 |
+
"learning_rate": 2.5333333333333334e-05,
|
| 266 |
+
"loss": 5.353,
|
| 267 |
+
"step": 43000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 35.54,
|
| 271 |
+
"learning_rate": 2.4888888888888893e-05,
|
| 272 |
+
"loss": 5.3419,
|
| 273 |
+
"step": 44000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 36.35,
|
| 277 |
+
"learning_rate": 2.444444444444445e-05,
|
| 278 |
+
"loss": 5.3312,
|
| 279 |
+
"step": 45000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 37.16,
|
| 283 |
+
"learning_rate": 2.4e-05,
|
| 284 |
+
"loss": 5.3217,
|
| 285 |
+
"step": 46000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 37.96,
|
| 289 |
+
"learning_rate": 2.355555555555556e-05,
|
| 290 |
+
"loss": 5.3111,
|
| 291 |
+
"step": 47000
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 38.77,
|
| 295 |
+
"learning_rate": 2.3111111111111112e-05,
|
| 296 |
+
"loss": 5.3013,
|
| 297 |
+
"step": 48000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 39.58,
|
| 301 |
+
"learning_rate": 2.2666666666666668e-05,
|
| 302 |
+
"loss": 5.291,
|
| 303 |
+
"step": 49000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 40.39,
|
| 307 |
+
"learning_rate": 2.2222222222222227e-05,
|
| 308 |
+
"loss": 5.2835,
|
| 309 |
+
"step": 50000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 41.2,
|
| 313 |
+
"learning_rate": 2.177777777777778e-05,
|
| 314 |
+
"loss": 5.2753,
|
| 315 |
+
"step": 51000
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 42.0,
|
| 319 |
+
"learning_rate": 2.1333333333333335e-05,
|
| 320 |
+
"loss": 5.2666,
|
| 321 |
+
"step": 52000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 42.81,
|
| 325 |
+
"learning_rate": 2.088888888888889e-05,
|
| 326 |
+
"loss": 5.2594,
|
| 327 |
+
"step": 53000
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 43.62,
|
| 331 |
+
"learning_rate": 2.0444444444444446e-05,
|
| 332 |
+
"loss": 5.2513,
|
| 333 |
+
"step": 54000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 44.43,
|
| 337 |
+
"learning_rate": 2e-05,
|
| 338 |
+
"loss": 5.2441,
|
| 339 |
+
"step": 55000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 45.23,
|
| 343 |
+
"learning_rate": 1.9555555555555557e-05,
|
| 344 |
+
"loss": 5.2426,
|
| 345 |
+
"step": 56000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 46.04,
|
| 349 |
+
"learning_rate": 1.9111111111111113e-05,
|
| 350 |
+
"loss": 5.2328,
|
| 351 |
+
"step": 57000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 46.85,
|
| 355 |
+
"learning_rate": 1.866666666666667e-05,
|
| 356 |
+
"loss": 5.2278,
|
| 357 |
+
"step": 58000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 47.66,
|
| 361 |
+
"learning_rate": 1.8222222222222224e-05,
|
| 362 |
+
"loss": 5.2213,
|
| 363 |
+
"step": 59000
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 48.47,
|
| 367 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 368 |
+
"loss": 5.2155,
|
| 369 |
+
"step": 60000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 49.27,
|
| 373 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 374 |
+
"loss": 5.2102,
|
| 375 |
+
"step": 61000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 50.08,
|
| 379 |
+
"learning_rate": 1.688888888888889e-05,
|
| 380 |
+
"loss": 5.2048,
|
| 381 |
+
"step": 62000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 50.89,
|
| 385 |
+
"learning_rate": 1.6444444444444444e-05,
|
| 386 |
+
"loss": 5.2008,
|
| 387 |
+
"step": 63000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 51.7,
|
| 391 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 392 |
+
"loss": 5.1975,
|
| 393 |
+
"step": 64000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 52.5,
|
| 397 |
+
"learning_rate": 1.555555555555556e-05,
|
| 398 |
+
"loss": 5.1925,
|
| 399 |
+
"step": 65000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 53.31,
|
| 403 |
+
"learning_rate": 1.5111111111111112e-05,
|
| 404 |
+
"loss": 5.1883,
|
| 405 |
+
"step": 66000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 54.12,
|
| 409 |
+
"learning_rate": 1.4666666666666666e-05,
|
| 410 |
+
"loss": 5.1822,
|
| 411 |
+
"step": 67000
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 54.93,
|
| 415 |
+
"learning_rate": 1.4222222222222224e-05,
|
| 416 |
+
"loss": 5.1806,
|
| 417 |
+
"step": 68000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 55.74,
|
| 421 |
+
"learning_rate": 1.377777777777778e-05,
|
| 422 |
+
"loss": 5.1756,
|
| 423 |
+
"step": 69000
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 56.54,
|
| 427 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 428 |
+
"loss": 5.175,
|
| 429 |
+
"step": 70000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 57.35,
|
| 433 |
+
"learning_rate": 1.288888888888889e-05,
|
| 434 |
+
"loss": 5.1686,
|
| 435 |
+
"step": 71000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 58.16,
|
| 439 |
+
"learning_rate": 1.2444444444444446e-05,
|
| 440 |
+
"loss": 5.1672,
|
| 441 |
+
"step": 72000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 58.97,
|
| 445 |
+
"learning_rate": 1.2e-05,
|
| 446 |
+
"loss": 5.1644,
|
| 447 |
+
"step": 73000
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 59.77,
|
| 451 |
+
"learning_rate": 1.1555555555555556e-05,
|
| 452 |
+
"loss": 5.1609,
|
| 453 |
+
"step": 74000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 60.58,
|
| 457 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 458 |
+
"loss": 5.1582,
|
| 459 |
+
"step": 75000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 61.39,
|
| 463 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 464 |
+
"loss": 5.1539,
|
| 465 |
+
"step": 76000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 62.2,
|
| 469 |
+
"learning_rate": 1.0222222222222223e-05,
|
| 470 |
+
"loss": 5.1535,
|
| 471 |
+
"step": 77000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 63.0,
|
| 475 |
+
"learning_rate": 9.777777777777779e-06,
|
| 476 |
+
"loss": 5.1516,
|
| 477 |
+
"step": 78000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 63.81,
|
| 481 |
+
"learning_rate": 9.333333333333334e-06,
|
| 482 |
+
"loss": 5.1479,
|
| 483 |
+
"step": 79000
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 64.62,
|
| 487 |
+
"learning_rate": 8.888888888888888e-06,
|
| 488 |
+
"loss": 5.1451,
|
| 489 |
+
"step": 80000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 65.43,
|
| 493 |
+
"learning_rate": 8.444444444444446e-06,
|
| 494 |
+
"loss": 5.1439,
|
| 495 |
+
"step": 81000
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 66.24,
|
| 499 |
+
"learning_rate": 8.000000000000001e-06,
|
| 500 |
+
"loss": 5.1429,
|
| 501 |
+
"step": 82000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 67.04,
|
| 505 |
+
"learning_rate": 7.555555555555556e-06,
|
| 506 |
+
"loss": 5.1402,
|
| 507 |
+
"step": 83000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 67.85,
|
| 511 |
+
"learning_rate": 7.111111111111112e-06,
|
| 512 |
+
"loss": 5.1375,
|
| 513 |
+
"step": 84000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 68.66,
|
| 517 |
+
"learning_rate": 6.666666666666667e-06,
|
| 518 |
+
"loss": 5.1348,
|
| 519 |
+
"step": 85000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 69.47,
|
| 523 |
+
"learning_rate": 6.222222222222223e-06,
|
| 524 |
+
"loss": 5.1357,
|
| 525 |
+
"step": 86000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 70.27,
|
| 529 |
+
"learning_rate": 5.777777777777778e-06,
|
| 530 |
+
"loss": 5.1336,
|
| 531 |
+
"step": 87000
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 71.08,
|
| 535 |
+
"learning_rate": 5.333333333333334e-06,
|
| 536 |
+
"loss": 5.1308,
|
| 537 |
+
"step": 88000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 71.89,
|
| 541 |
+
"learning_rate": 4.888888888888889e-06,
|
| 542 |
+
"loss": 5.1304,
|
| 543 |
+
"step": 89000
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 72.7,
|
| 547 |
+
"learning_rate": 4.444444444444444e-06,
|
| 548 |
+
"loss": 5.1285,
|
| 549 |
+
"step": 90000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 73.51,
|
| 553 |
+
"learning_rate": 4.000000000000001e-06,
|
| 554 |
+
"loss": 5.1272,
|
| 555 |
+
"step": 91000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 74.31,
|
| 559 |
+
"learning_rate": 3.555555555555556e-06,
|
| 560 |
+
"loss": 5.1272,
|
| 561 |
+
"step": 92000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 75.12,
|
| 565 |
+
"learning_rate": 3.1111111111111116e-06,
|
| 566 |
+
"loss": 5.1281,
|
| 567 |
+
"step": 93000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 75.93,
|
| 571 |
+
"learning_rate": 2.666666666666667e-06,
|
| 572 |
+
"loss": 5.1257,
|
| 573 |
+
"step": 94000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 76.74,
|
| 577 |
+
"learning_rate": 2.222222222222222e-06,
|
| 578 |
+
"loss": 5.1245,
|
| 579 |
+
"step": 95000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 77.54,
|
| 583 |
+
"learning_rate": 1.777777777777778e-06,
|
| 584 |
+
"loss": 5.1244,
|
| 585 |
+
"step": 96000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 78.35,
|
| 589 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 590 |
+
"loss": 5.1229,
|
| 591 |
+
"step": 97000
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 79.16,
|
| 595 |
+
"learning_rate": 8.88888888888889e-07,
|
| 596 |
+
"loss": 5.1223,
|
| 597 |
+
"step": 98000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 79.97,
|
| 601 |
+
"learning_rate": 4.444444444444445e-07,
|
| 602 |
+
"loss": 5.1231,
|
| 603 |
+
"step": 99000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 80.78,
|
| 607 |
+
"learning_rate": 0.0,
|
| 608 |
+
"loss": 5.1203,
|
| 609 |
+
"step": 100000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 10.2,
|
| 613 |
+
"learning_rate": 2.0842105263157895e-05,
|
| 614 |
+
"loss": 5.1411,
|
| 615 |
+
"step": 101000
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 10.3,
|
| 619 |
+
"learning_rate": 2.0631578947368425e-05,
|
| 620 |
+
"loss": 5.1408,
|
| 621 |
+
"step": 102000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 10.4,
|
| 625 |
+
"learning_rate": 2.0421052631578952e-05,
|
| 626 |
+
"loss": 5.1433,
|
| 627 |
+
"step": 103000
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 10.5,
|
| 631 |
+
"learning_rate": 2.0210526315789475e-05,
|
| 632 |
+
"loss": 5.154,
|
| 633 |
+
"step": 104000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 10.6,
|
| 637 |
+
"learning_rate": 2e-05,
|
| 638 |
+
"loss": 5.1553,
|
| 639 |
+
"step": 105000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 10.71,
|
| 643 |
+
"learning_rate": 1.9789473684210528e-05,
|
| 644 |
+
"loss": 5.1442,
|
| 645 |
+
"step": 106000
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 10.81,
|
| 649 |
+
"learning_rate": 1.9578947368421055e-05,
|
| 650 |
+
"loss": 5.1442,
|
| 651 |
+
"step": 107000
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 10.91,
|
| 655 |
+
"learning_rate": 1.936842105263158e-05,
|
| 656 |
+
"loss": 5.147,
|
| 657 |
+
"step": 108000
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 11.01,
|
| 661 |
+
"learning_rate": 1.9157894736842108e-05,
|
| 662 |
+
"loss": 5.1433,
|
| 663 |
+
"step": 109000
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 11.11,
|
| 667 |
+
"learning_rate": 1.894736842105263e-05,
|
| 668 |
+
"loss": 5.1374,
|
| 669 |
+
"step": 110000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 11.21,
|
| 673 |
+
"learning_rate": 1.873684210526316e-05,
|
| 674 |
+
"loss": 5.1411,
|
| 675 |
+
"step": 111000
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 11.31,
|
| 679 |
+
"learning_rate": 1.8526315789473684e-05,
|
| 680 |
+
"loss": 5.1371,
|
| 681 |
+
"step": 112000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 11.41,
|
| 685 |
+
"learning_rate": 1.831578947368421e-05,
|
| 686 |
+
"loss": 5.1379,
|
| 687 |
+
"step": 113000
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 11.51,
|
| 691 |
+
"learning_rate": 1.810526315789474e-05,
|
| 692 |
+
"loss": 5.139,
|
| 693 |
+
"step": 114000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 11.61,
|
| 697 |
+
"learning_rate": 1.7894736842105264e-05,
|
| 698 |
+
"loss": 5.131,
|
| 699 |
+
"step": 115000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 11.72,
|
| 703 |
+
"learning_rate": 1.768421052631579e-05,
|
| 704 |
+
"loss": 5.1313,
|
| 705 |
+
"step": 116000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 11.82,
|
| 709 |
+
"learning_rate": 1.7473684210526317e-05,
|
| 710 |
+
"loss": 5.1287,
|
| 711 |
+
"step": 117000
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 11.92,
|
| 715 |
+
"learning_rate": 1.7263157894736843e-05,
|
| 716 |
+
"loss": 5.1304,
|
| 717 |
+
"step": 118000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 12.02,
|
| 721 |
+
"learning_rate": 1.705263157894737e-05,
|
| 722 |
+
"loss": 5.1309,
|
| 723 |
+
"step": 119000
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 12.12,
|
| 727 |
+
"learning_rate": 1.6842105263157896e-05,
|
| 728 |
+
"loss": 5.1256,
|
| 729 |
+
"step": 120000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 12.22,
|
| 733 |
+
"learning_rate": 1.6631578947368423e-05,
|
| 734 |
+
"loss": 5.1202,
|
| 735 |
+
"step": 121000
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 12.32,
|
| 739 |
+
"learning_rate": 1.642105263157895e-05,
|
| 740 |
+
"loss": 5.125,
|
| 741 |
+
"step": 122000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 12.42,
|
| 745 |
+
"learning_rate": 1.6210526315789473e-05,
|
| 746 |
+
"loss": 5.125,
|
| 747 |
+
"step": 123000
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 12.52,
|
| 751 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 752 |
+
"loss": 5.1259,
|
| 753 |
+
"step": 124000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 12.62,
|
| 757 |
+
"learning_rate": 1.578947368421053e-05,
|
| 758 |
+
"loss": 5.1186,
|
| 759 |
+
"step": 125000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 12.73,
|
| 763 |
+
"learning_rate": 1.5578947368421052e-05,
|
| 764 |
+
"loss": 5.1097,
|
| 765 |
+
"step": 126000
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 12.83,
|
| 769 |
+
"learning_rate": 1.536842105263158e-05,
|
| 770 |
+
"loss": 5.12,
|
| 771 |
+
"step": 127000
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 12.93,
|
| 775 |
+
"learning_rate": 1.5157894736842107e-05,
|
| 776 |
+
"loss": 5.123,
|
| 777 |
+
"step": 128000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 13.03,
|
| 781 |
+
"learning_rate": 1.4947368421052632e-05,
|
| 782 |
+
"loss": 5.1113,
|
| 783 |
+
"step": 129000
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 13.13,
|
| 787 |
+
"learning_rate": 1.4736842105263159e-05,
|
| 788 |
+
"loss": 5.1071,
|
| 789 |
+
"step": 130000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 13.23,
|
| 793 |
+
"learning_rate": 1.4526315789473687e-05,
|
| 794 |
+
"loss": 5.1167,
|
| 795 |
+
"step": 131000
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 13.33,
|
| 799 |
+
"learning_rate": 1.4315789473684212e-05,
|
| 800 |
+
"loss": 5.1153,
|
| 801 |
+
"step": 132000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 13.43,
|
| 805 |
+
"learning_rate": 1.4105263157894738e-05,
|
| 806 |
+
"loss": 5.1171,
|
| 807 |
+
"step": 133000
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 13.53,
|
| 811 |
+
"learning_rate": 1.3894736842105265e-05,
|
| 812 |
+
"loss": 5.1101,
|
| 813 |
+
"step": 134000
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 13.63,
|
| 817 |
+
"learning_rate": 1.3684210526315791e-05,
|
| 818 |
+
"loss": 5.1096,
|
| 819 |
+
"step": 135000
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 13.74,
|
| 823 |
+
"learning_rate": 1.3473684210526316e-05,
|
| 824 |
+
"loss": 5.107,
|
| 825 |
+
"step": 136000
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 13.84,
|
| 829 |
+
"learning_rate": 1.3263157894736843e-05,
|
| 830 |
+
"loss": 5.1048,
|
| 831 |
+
"step": 137000
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 13.94,
|
| 835 |
+
"learning_rate": 1.305263157894737e-05,
|
| 836 |
+
"loss": 5.1077,
|
| 837 |
+
"step": 138000
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 14.04,
|
| 841 |
+
"learning_rate": 1.2842105263157896e-05,
|
| 842 |
+
"loss": 5.0998,
|
| 843 |
+
"step": 139000
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 14.14,
|
| 847 |
+
"learning_rate": 1.263157894736842e-05,
|
| 848 |
+
"loss": 5.1014,
|
| 849 |
+
"step": 140000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 14.24,
|
| 853 |
+
"learning_rate": 1.2421052631578949e-05,
|
| 854 |
+
"loss": 5.1028,
|
| 855 |
+
"step": 141000
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 14.34,
|
| 859 |
+
"learning_rate": 1.2210526315789475e-05,
|
| 860 |
+
"loss": 5.1065,
|
| 861 |
+
"step": 142000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 14.44,
|
| 865 |
+
"learning_rate": 1.2e-05,
|
| 866 |
+
"loss": 5.1024,
|
| 867 |
+
"step": 143000
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 14.54,
|
| 871 |
+
"learning_rate": 1.1789473684210527e-05,
|
| 872 |
+
"loss": 5.1055,
|
| 873 |
+
"step": 144000
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 14.64,
|
| 877 |
+
"learning_rate": 1.1578947368421053e-05,
|
| 878 |
+
"loss": 5.0966,
|
| 879 |
+
"step": 145000
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 14.75,
|
| 883 |
+
"learning_rate": 1.136842105263158e-05,
|
| 884 |
+
"loss": 5.0939,
|
| 885 |
+
"step": 146000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 14.85,
|
| 889 |
+
"learning_rate": 1.1157894736842105e-05,
|
| 890 |
+
"loss": 5.0932,
|
| 891 |
+
"step": 147000
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 14.95,
|
| 895 |
+
"learning_rate": 1.0947368421052633e-05,
|
| 896 |
+
"loss": 5.0971,
|
| 897 |
+
"step": 148000
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 15.05,
|
| 901 |
+
"learning_rate": 1.073684210526316e-05,
|
| 902 |
+
"loss": 5.0802,
|
| 903 |
+
"step": 149000
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 15.15,
|
| 907 |
+
"learning_rate": 1.0526315789473684e-05,
|
| 908 |
+
"loss": 5.0969,
|
| 909 |
+
"step": 150000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 15.25,
|
| 913 |
+
"learning_rate": 1.0315789473684213e-05,
|
| 914 |
+
"loss": 5.0889,
|
| 915 |
+
"step": 151000
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 15.35,
|
| 919 |
+
"learning_rate": 1.0105263157894738e-05,
|
| 920 |
+
"loss": 5.0934,
|
| 921 |
+
"step": 152000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 15.45,
|
| 925 |
+
"learning_rate": 9.894736842105264e-06,
|
| 926 |
+
"loss": 5.0961,
|
| 927 |
+
"step": 153000
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 15.55,
|
| 931 |
+
"learning_rate": 9.68421052631579e-06,
|
| 932 |
+
"loss": 5.0874,
|
| 933 |
+
"step": 154000
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 15.65,
|
| 937 |
+
"learning_rate": 9.473684210526315e-06,
|
| 938 |
+
"loss": 5.0896,
|
| 939 |
+
"step": 155000
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 15.76,
|
| 943 |
+
"learning_rate": 9.263157894736842e-06,
|
| 944 |
+
"loss": 5.0879,
|
| 945 |
+
"step": 156000
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 15.86,
|
| 949 |
+
"learning_rate": 9.05263157894737e-06,
|
| 950 |
+
"loss": 5.0848,
|
| 951 |
+
"step": 157000
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 15.96,
|
| 955 |
+
"learning_rate": 8.842105263157895e-06,
|
| 956 |
+
"loss": 5.0879,
|
| 957 |
+
"step": 158000
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 16.06,
|
| 961 |
+
"learning_rate": 8.631578947368422e-06,
|
| 962 |
+
"loss": 5.0799,
|
| 963 |
+
"step": 159000
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 16.16,
|
| 967 |
+
"learning_rate": 8.421052631578948e-06,
|
| 968 |
+
"loss": 5.0847,
|
| 969 |
+
"step": 160000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 16.26,
|
| 973 |
+
"learning_rate": 8.210526315789475e-06,
|
| 974 |
+
"loss": 5.0897,
|
| 975 |
+
"step": 161000
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 16.36,
|
| 979 |
+
"learning_rate": 8.000000000000001e-06,
|
| 980 |
+
"loss": 5.0799,
|
| 981 |
+
"step": 162000
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 16.46,
|
| 985 |
+
"learning_rate": 7.789473684210526e-06,
|
| 986 |
+
"loss": 5.0847,
|
| 987 |
+
"step": 163000
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 16.56,
|
| 991 |
+
"learning_rate": 7.578947368421054e-06,
|
| 992 |
+
"loss": 5.0764,
|
| 993 |
+
"step": 164000
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 16.66,
|
| 997 |
+
"learning_rate": 7.368421052631579e-06,
|
| 998 |
+
"loss": 5.0756,
|
| 999 |
+
"step": 165000
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 16.77,
|
| 1003 |
+
"learning_rate": 7.157894736842106e-06,
|
| 1004 |
+
"loss": 5.0755,
|
| 1005 |
+
"step": 166000
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 16.87,
|
| 1009 |
+
"learning_rate": 6.947368421052632e-06,
|
| 1010 |
+
"loss": 5.0788,
|
| 1011 |
+
"step": 167000
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 16.97,
|
| 1015 |
+
"learning_rate": 6.736842105263158e-06,
|
| 1016 |
+
"loss": 5.0793,
|
| 1017 |
+
"step": 168000
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 17.07,
|
| 1021 |
+
"learning_rate": 6.526315789473685e-06,
|
| 1022 |
+
"loss": 5.0768,
|
| 1023 |
+
"step": 169000
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 17.17,
|
| 1027 |
+
"learning_rate": 6.31578947368421e-06,
|
| 1028 |
+
"loss": 5.0746,
|
| 1029 |
+
"step": 170000
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 17.27,
|
| 1033 |
+
"learning_rate": 6.105263157894738e-06,
|
| 1034 |
+
"loss": 5.075,
|
| 1035 |
+
"step": 171000
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 17.37,
|
| 1039 |
+
"learning_rate": 5.8947368421052634e-06,
|
| 1040 |
+
"loss": 5.0799,
|
| 1041 |
+
"step": 172000
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 17.47,
|
| 1045 |
+
"learning_rate": 5.68421052631579e-06,
|
| 1046 |
+
"loss": 5.0684,
|
| 1047 |
+
"step": 173000
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 17.57,
|
| 1051 |
+
"learning_rate": 5.4736842105263165e-06,
|
| 1052 |
+
"loss": 5.0741,
|
| 1053 |
+
"step": 174000
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 17.67,
|
| 1057 |
+
"learning_rate": 5.263157894736842e-06,
|
| 1058 |
+
"loss": 5.0756,
|
| 1059 |
+
"step": 175000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 17.78,
|
| 1063 |
+
"learning_rate": 5.052631578947369e-06,
|
| 1064 |
+
"loss": 5.0711,
|
| 1065 |
+
"step": 176000
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 17.88,
|
| 1069 |
+
"learning_rate": 4.842105263157895e-06,
|
| 1070 |
+
"loss": 5.0701,
|
| 1071 |
+
"step": 177000
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 17.98,
|
| 1075 |
+
"learning_rate": 4.631578947368421e-06,
|
| 1076 |
+
"loss": 5.0724,
|
| 1077 |
+
"step": 178000
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 18.08,
|
| 1081 |
+
"learning_rate": 4.4210526315789476e-06,
|
| 1082 |
+
"loss": 5.0729,
|
| 1083 |
+
"step": 179000
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 18.18,
|
| 1087 |
+
"learning_rate": 4.210526315789474e-06,
|
| 1088 |
+
"loss": 5.0667,
|
| 1089 |
+
"step": 180000
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 18.28,
|
| 1093 |
+
"learning_rate": 4.000000000000001e-06,
|
| 1094 |
+
"loss": 5.0692,
|
| 1095 |
+
"step": 181000
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 18.38,
|
| 1099 |
+
"learning_rate": 3.789473684210527e-06,
|
| 1100 |
+
"loss": 5.0714,
|
| 1101 |
+
"step": 182000
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 18.48,
|
| 1105 |
+
"learning_rate": 3.578947368421053e-06,
|
| 1106 |
+
"loss": 5.0662,
|
| 1107 |
+
"step": 183000
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 18.58,
|
| 1111 |
+
"learning_rate": 3.368421052631579e-06,
|
| 1112 |
+
"loss": 5.0726,
|
| 1113 |
+
"step": 184000
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 18.68,
|
| 1117 |
+
"learning_rate": 3.157894736842105e-06,
|
| 1118 |
+
"loss": 5.0743,
|
| 1119 |
+
"step": 185000
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 18.79,
|
| 1123 |
+
"learning_rate": 2.9473684210526317e-06,
|
| 1124 |
+
"loss": 5.059,
|
| 1125 |
+
"step": 186000
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 18.89,
|
| 1129 |
+
"learning_rate": 2.7368421052631583e-06,
|
| 1130 |
+
"loss": 5.064,
|
| 1131 |
+
"step": 187000
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 18.99,
|
| 1135 |
+
"learning_rate": 2.5263157894736844e-06,
|
| 1136 |
+
"loss": 5.0659,
|
| 1137 |
+
"step": 188000
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 19.09,
|
| 1141 |
+
"learning_rate": 2.3157894736842105e-06,
|
| 1142 |
+
"loss": 5.0645,
|
| 1143 |
+
"step": 189000
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 19.19,
|
| 1147 |
+
"learning_rate": 2.105263157894737e-06,
|
| 1148 |
+
"loss": 5.0657,
|
| 1149 |
+
"step": 190000
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 19.29,
|
| 1153 |
+
"learning_rate": 1.8947368421052634e-06,
|
| 1154 |
+
"loss": 5.0674,
|
| 1155 |
+
"step": 191000
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 19.39,
|
| 1159 |
+
"learning_rate": 1.6842105263157895e-06,
|
| 1160 |
+
"loss": 5.0609,
|
| 1161 |
+
"step": 192000
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 19.49,
|
| 1165 |
+
"learning_rate": 1.4736842105263159e-06,
|
| 1166 |
+
"loss": 5.0594,
|
| 1167 |
+
"step": 193000
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 19.59,
|
| 1171 |
+
"learning_rate": 1.2631578947368422e-06,
|
| 1172 |
+
"loss": 5.0675,
|
| 1173 |
+
"step": 194000
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 19.69,
|
| 1177 |
+
"learning_rate": 1.0526315789473685e-06,
|
| 1178 |
+
"loss": 5.0665,
|
| 1179 |
+
"step": 195000
|
| 1180 |
+
}
|
| 1181 |
+
],
|
| 1182 |
+
"logging_steps": 1000,
|
| 1183 |
+
"max_steps": 200000,
|
| 1184 |
+
"num_train_epochs": 21,
|
| 1185 |
+
"save_steps": 1000,
|
| 1186 |
+
"total_flos": 2.2607742148692673e+19,
|
| 1187 |
+
"trial_name": null,
|
| 1188 |
+
"trial_params": null
|
| 1189 |
+
}
|
checkpoint-195000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f7b759ef851ee3a68e8c9ad880cbb1bc393f7d811df1a445efe7298474f0c09
|
| 3 |
+
size 5137
|
checkpoint-196000/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 12 |
+
"layer_norm_eps": 1e-12,
|
| 13 |
+
"max_length": 512,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.35.2",
|
| 22 |
+
"type_vocab_size": 2,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 5120
|
| 25 |
+
}
|
checkpoint-196000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"max_length": 512,
|
| 4 |
+
"pad_token_id": 0,
|
| 5 |
+
"transformers_version": "4.35.2"
|
| 6 |
+
}
|
checkpoint-196000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d4cb0beb8fd1739031e032ebfe7714af7779d282fbc78c4d5bfaf6a9989bf1b
|
| 3 |
+
size 359944256
|
checkpoint-196000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f3b80bb6488b70b91aa55b45a496839e7ac5676f76813ab352a72343b1f0902
|
| 3 |
+
size 720010699
|
checkpoint-196000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f6a4e29e6e8d29c81f2831d5a3e4d30574ff6372a9483152598e2a505a73ecf
|
| 3 |
+
size 14645
|
checkpoint-196000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5811ac92ade8f505f0886ccc4ac5ddf97e3250649855fc9b12115faa6921b77
|
| 3 |
+
size 1465
|