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 +67 -0
- README.md +60 -0
- all_results.json +16 -0
- checkpoint-100000/config.json +25 -0
- checkpoint-100000/generation_config.json +6 -0
- checkpoint-100000/model.safetensors +3 -0
- checkpoint-100000/optimizer.pt +3 -0
- checkpoint-100000/rng_state_0.pth +3 -0
- checkpoint-100000/rng_state_1.pth +3 -0
- checkpoint-100000/rng_state_2.pth +3 -0
- checkpoint-100000/rng_state_3.pth +3 -0
- checkpoint-100000/rng_state_4.pth +3 -0
- checkpoint-100000/rng_state_5.pth +3 -0
- checkpoint-100000/rng_state_6.pth +3 -0
- checkpoint-100000/rng_state_7.pth +3 -0
- checkpoint-100000/scheduler.pt +3 -0
- checkpoint-100000/trainer_state.json +619 -0
- checkpoint-100000/training_args.bin +3 -0
- checkpoint-91000/config.json +25 -0
- checkpoint-91000/generation_config.json +6 -0
- checkpoint-91000/model.safetensors +3 -0
- checkpoint-91000/optimizer.pt +3 -0
- checkpoint-91000/rng_state_0.pth +3 -0
- checkpoint-91000/rng_state_1.pth +3 -0
- checkpoint-91000/rng_state_2.pth +3 -0
- checkpoint-91000/rng_state_3.pth +3 -0
- checkpoint-91000/rng_state_4.pth +3 -0
- checkpoint-91000/rng_state_5.pth +3 -0
- checkpoint-91000/rng_state_6.pth +3 -0
- checkpoint-91000/rng_state_7.pth +3 -0
- checkpoint-91000/scheduler.pt +3 -0
- checkpoint-91000/trainer_state.json +565 -0
- checkpoint-91000/training_args.bin +3 -0
- checkpoint-92000/config.json +25 -0
- checkpoint-92000/generation_config.json +6 -0
- checkpoint-92000/model.safetensors +3 -0
- checkpoint-92000/optimizer.pt +3 -0
- checkpoint-92000/rng_state_0.pth +3 -0
- checkpoint-92000/rng_state_1.pth +3 -0
- checkpoint-92000/rng_state_2.pth +3 -0
- checkpoint-92000/rng_state_3.pth +3 -0
- checkpoint-92000/rng_state_4.pth +3 -0
- checkpoint-92000/rng_state_5.pth +3 -0
- checkpoint-92000/rng_state_6.pth +3 -0
- checkpoint-92000/rng_state_7.pth +3 -0
- checkpoint-92000/scheduler.pt +3 -0
- checkpoint-92000/trainer_state.json +571 -0
- checkpoint-92000/training_args.bin +3 -0
- checkpoint-93000/config.json +25 -0
- checkpoint-93000/generation_config.json +6 -0
04.pretrain.sh
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env bash
|
| 2 |
+
set -e
|
| 3 |
+
|
| 4 |
+
|
| 5 |
+
# --- initialize conda ---
|
| 6 |
+
source /root/miniconda3/etc/profile.d/conda.sh
|
| 7 |
+
|
| 8 |
+
# --- activate env ---
|
| 9 |
+
conda activate bpe_v2
|
| 10 |
+
|
| 11 |
+
work_dir=/root/NaN/dna-tokenizer
|
| 12 |
+
data_dir=${work_dir}/dna-tokenizer-data
|
| 13 |
+
cache_dir=${data_dir}/cache
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
# runnum=len2_2048
|
| 17 |
+
runnum=len2_5120
|
| 18 |
+
|
| 19 |
+
mkdir -p ${work_dir}/pretrain/models/model_${runnum}
|
| 20 |
+
output_dir=${work_dir}/pretrain/models/model_${runnum}
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
cp 04.pretrain.sh ${output_dir}
|
| 24 |
+
torchrun --nproc_per_node=8 run_mlm.py \
|
| 25 |
+
--output_dir ${output_dir} \
|
| 26 |
+
--model_type bert \
|
| 27 |
+
--tokenizer_name ${work_dir}/merge_bpe/vocab_5120/merge_tokenizer_unigram_len2.json \
|
| 28 |
+
--config_name ${work_dir}/BPE_merge/config_5120.json \
|
| 29 |
+
--project_name token_eval_len2_5120 \
|
| 30 |
+
--do_train True \
|
| 31 |
+
--model_max_length 512 \
|
| 32 |
+
--max_seq_length 512 \
|
| 33 |
+
--line_by_line True \
|
| 34 |
+
--pad_to_max_length True \
|
| 35 |
+
--train_file ${data_dir}/merge_bpe_5120_allchr_all_tokenized_train_chrOnly.tsv \
|
| 36 |
+
--validation_file ${data_dir}/merge_bpe_5120_allchr_all_tokenized_val_chrOnly.tsv \
|
| 37 |
+
--cache_dir ${cache_dir} \
|
| 38 |
+
--use_fast_tokenizer True \
|
| 39 |
+
--do_eval True \
|
| 40 |
+
--gradient_accumulation_steps 1 \
|
| 41 |
+
--per_device_train_batch_size 96 \
|
| 42 |
+
--per_device_eval_batch_size 96 \
|
| 43 |
+
--save_steps 1000 \
|
| 44 |
+
--save_total_limit 10 \
|
| 45 |
+
--max_steps 100000 \
|
| 46 |
+
--logging_steps 1000 \
|
| 47 |
+
--learning_rate 4e-5 \
|
| 48 |
+
--adam_epsilon 1e-6 \
|
| 49 |
+
--weight_decay 0.01 \
|
| 50 |
+
--adam_beta1 0.9 \
|
| 51 |
+
--adam_beta2 0.98 \
|
| 52 |
+
--mlm_probability 0.15 \
|
| 53 |
+
--warmup_steps 10000 \
|
| 54 |
+
--seed 42 \
|
| 55 |
+
--preprocessing_num_workers 8 \
|
| 56 |
+
--overwrite_output_dir True
|
| 57 |
+
#--resume_from_checkpoint /root/NaN/dna-tokenizer/pretrain/models/model_len2_4096/checkpoint-36000
|
| 58 |
+
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
|
README.md
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
model-index:
|
| 7 |
+
- name: model_len2_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 |
+
# model_len2_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: 4.9613
|
| 19 |
+
- Accuracy: 0.2987
|
| 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 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 8
|
| 44 |
+
- total_train_batch_size: 768
|
| 45 |
+
- total_eval_batch_size: 768
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_steps: 10000
|
| 49 |
+
- training_steps: 100000
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
### Framework versions
|
| 56 |
+
|
| 57 |
+
- Transformers 4.35.2
|
| 58 |
+
- Pytorch 2.8.0+cu128
|
| 59 |
+
- Datasets 4.4.1
|
| 60 |
+
- Tokenizers 0.15.2
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 78.12,
|
| 3 |
+
"eval_accuracy": 0.2987443773301591,
|
| 4 |
+
"eval_loss": 4.961287021636963,
|
| 5 |
+
"eval_runtime": 67.6731,
|
| 6 |
+
"eval_samples": 109173,
|
| 7 |
+
"eval_samples_per_second": 1613.241,
|
| 8 |
+
"eval_step": 100000,
|
| 9 |
+
"eval_steps_per_second": 2.113,
|
| 10 |
+
"perplexity": 142.7774353462287,
|
| 11 |
+
"train_loss": 5.5054574072265625,
|
| 12 |
+
"train_runtime": 84130.9868,
|
| 13 |
+
"train_samples": 982503,
|
| 14 |
+
"train_samples_per_second": 912.862,
|
| 15 |
+
"train_steps_per_second": 1.189
|
| 16 |
+
}
|
checkpoint-100000/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-100000/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-100000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b902fc2c7b5437400c89cceec7e8925ba8e5072147d90dda9b78e1be793affda
|
| 3 |
+
size 359944256
|
checkpoint-100000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2753dfcc9064c0201c98f9d878b27a3852c1e23f78a4b4d97fb78505ecc7f3df
|
| 3 |
+
size 720010699
|
checkpoint-100000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4347f2f324af6cbb6239f67b6812731c1c31d7d296d463a8a50f45ee2288bd1
|
| 3 |
+
size 16389
|
checkpoint-100000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd970d89271069031138e76133c80888b1f7c50c586834dffb9ebbe1d50ffc1e
|
| 3 |
+
size 16389
|
checkpoint-100000/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85bbd9e60f855825277b40ecaea7baa9c95bf61ca23fcc8ad0a7583c4b766f32
|
| 3 |
+
size 16389
|
checkpoint-100000/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b458eeddcca50fa20941d38a73e09e20ca0574642482e98a0f412c08fa110b2
|
| 3 |
+
size 16389
|
checkpoint-100000/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d8433c2f9a8a2c330a3361da669809d43bd68e2135f120f3c663e54ff1b5225
|
| 3 |
+
size 16389
|
checkpoint-100000/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f87995019e195a6a049e89004c52b4ed17d8c0c953e72c05e0b56ea9c5323722
|
| 3 |
+
size 16389
|
checkpoint-100000/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66e20881942ec698dbd2cf83a75e065c2978267adf5af53fac58c669d06c1784
|
| 3 |
+
size 16389
|
checkpoint-100000/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc6ab1a614fd6c59a897a8228e859e29ca124538a9c011f6a3bf9cfe80712d4a
|
| 3 |
+
size 16389
|
checkpoint-100000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3018e461ce1631f9bf04479faa74b8f3d9fd86bf68d2cd93702db04c8a02131
|
| 3 |
+
size 1465
|
checkpoint-100000/trainer_state.json
ADDED
|
@@ -0,0 +1,619 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 78.125,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 100000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.78,
|
| 13 |
+
"learning_rate": 4.000000000000001e-06,
|
| 14 |
+
"loss": 7.5832,
|
| 15 |
+
"step": 1000
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.56,
|
| 19 |
+
"learning_rate": 8.000000000000001e-06,
|
| 20 |
+
"loss": 6.9724,
|
| 21 |
+
"step": 2000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 2.34,
|
| 25 |
+
"learning_rate": 1.2e-05,
|
| 26 |
+
"loss": 6.7695,
|
| 27 |
+
"step": 3000
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 3.12,
|
| 31 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 32 |
+
"loss": 6.7002,
|
| 33 |
+
"step": 4000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 3.91,
|
| 37 |
+
"learning_rate": 2e-05,
|
| 38 |
+
"loss": 6.666,
|
| 39 |
+
"step": 5000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 4.69,
|
| 43 |
+
"learning_rate": 2.4e-05,
|
| 44 |
+
"loss": 6.6503,
|
| 45 |
+
"step": 6000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 5.47,
|
| 49 |
+
"learning_rate": 2.8e-05,
|
| 50 |
+
"loss": 6.6407,
|
| 51 |
+
"step": 7000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 6.25,
|
| 55 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 56 |
+
"loss": 6.6277,
|
| 57 |
+
"step": 8000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 7.03,
|
| 61 |
+
"learning_rate": 3.6e-05,
|
| 62 |
+
"loss": 6.6209,
|
| 63 |
+
"step": 9000
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 7.81,
|
| 67 |
+
"learning_rate": 4e-05,
|
| 68 |
+
"loss": 6.6135,
|
| 69 |
+
"step": 10000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 8.59,
|
| 73 |
+
"learning_rate": 3.955555555555556e-05,
|
| 74 |
+
"loss": 6.6084,
|
| 75 |
+
"step": 11000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 9.38,
|
| 79 |
+
"learning_rate": 3.9111111111111115e-05,
|
| 80 |
+
"loss": 6.6041,
|
| 81 |
+
"step": 12000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 10.16,
|
| 85 |
+
"learning_rate": 3.866666666666667e-05,
|
| 86 |
+
"loss": 6.6013,
|
| 87 |
+
"step": 13000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 10.94,
|
| 91 |
+
"learning_rate": 3.8222222222222226e-05,
|
| 92 |
+
"loss": 6.5994,
|
| 93 |
+
"step": 14000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 11.72,
|
| 97 |
+
"learning_rate": 3.777777777777778e-05,
|
| 98 |
+
"loss": 6.594,
|
| 99 |
+
"step": 15000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 12.5,
|
| 103 |
+
"learning_rate": 3.733333333333334e-05,
|
| 104 |
+
"loss": 6.5925,
|
| 105 |
+
"step": 16000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 13.28,
|
| 109 |
+
"learning_rate": 3.6888888888888896e-05,
|
| 110 |
+
"loss": 6.5893,
|
| 111 |
+
"step": 17000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 14.06,
|
| 115 |
+
"learning_rate": 3.644444444444445e-05,
|
| 116 |
+
"loss": 6.5875,
|
| 117 |
+
"step": 18000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 14.84,
|
| 121 |
+
"learning_rate": 3.6e-05,
|
| 122 |
+
"loss": 6.5232,
|
| 123 |
+
"step": 19000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 15.62,
|
| 127 |
+
"learning_rate": 3.555555555555555e-05,
|
| 128 |
+
"loss": 6.4358,
|
| 129 |
+
"step": 20000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 16.41,
|
| 133 |
+
"learning_rate": 3.511111111111111e-05,
|
| 134 |
+
"loss": 6.3712,
|
| 135 |
+
"step": 21000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 17.19,
|
| 139 |
+
"learning_rate": 3.466666666666667e-05,
|
| 140 |
+
"loss": 6.311,
|
| 141 |
+
"step": 22000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 17.97,
|
| 145 |
+
"learning_rate": 3.4222222222222224e-05,
|
| 146 |
+
"loss": 6.2493,
|
| 147 |
+
"step": 23000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 18.75,
|
| 151 |
+
"learning_rate": 3.377777777777778e-05,
|
| 152 |
+
"loss": 6.1597,
|
| 153 |
+
"step": 24000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 19.53,
|
| 157 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 158 |
+
"loss": 6.0276,
|
| 159 |
+
"step": 25000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 20.31,
|
| 163 |
+
"learning_rate": 3.288888888888889e-05,
|
| 164 |
+
"loss": 5.8317,
|
| 165 |
+
"step": 26000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 21.09,
|
| 169 |
+
"learning_rate": 3.2444444444444446e-05,
|
| 170 |
+
"loss": 5.6782,
|
| 171 |
+
"step": 27000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 21.88,
|
| 175 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 176 |
+
"loss": 5.5975,
|
| 177 |
+
"step": 28000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 22.66,
|
| 181 |
+
"learning_rate": 3.155555555555556e-05,
|
| 182 |
+
"loss": 5.5369,
|
| 183 |
+
"step": 29000
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 23.44,
|
| 187 |
+
"learning_rate": 3.111111111111112e-05,
|
| 188 |
+
"loss": 5.4921,
|
| 189 |
+
"step": 30000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 24.22,
|
| 193 |
+
"learning_rate": 3.066666666666667e-05,
|
| 194 |
+
"loss": 5.4554,
|
| 195 |
+
"step": 31000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 25.0,
|
| 199 |
+
"learning_rate": 3.0222222222222225e-05,
|
| 200 |
+
"loss": 5.4237,
|
| 201 |
+
"step": 32000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 25.78,
|
| 205 |
+
"learning_rate": 2.977777777777778e-05,
|
| 206 |
+
"loss": 5.3938,
|
| 207 |
+
"step": 33000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 26.56,
|
| 211 |
+
"learning_rate": 2.9333333333333333e-05,
|
| 212 |
+
"loss": 5.3701,
|
| 213 |
+
"step": 34000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 27.34,
|
| 217 |
+
"learning_rate": 2.888888888888889e-05,
|
| 218 |
+
"loss": 5.3452,
|
| 219 |
+
"step": 35000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 28.12,
|
| 223 |
+
"learning_rate": 2.8444444444444447e-05,
|
| 224 |
+
"loss": 5.327,
|
| 225 |
+
"step": 36000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 28.91,
|
| 229 |
+
"learning_rate": 2.8e-05,
|
| 230 |
+
"loss": 5.3063,
|
| 231 |
+
"step": 37000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 29.69,
|
| 235 |
+
"learning_rate": 2.755555555555556e-05,
|
| 236 |
+
"loss": 5.2905,
|
| 237 |
+
"step": 38000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 30.47,
|
| 241 |
+
"learning_rate": 2.7111111111111114e-05,
|
| 242 |
+
"loss": 5.2747,
|
| 243 |
+
"step": 39000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 31.25,
|
| 247 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 248 |
+
"loss": 5.2596,
|
| 249 |
+
"step": 40000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 32.03,
|
| 253 |
+
"learning_rate": 2.6222222222222226e-05,
|
| 254 |
+
"loss": 5.2483,
|
| 255 |
+
"step": 41000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 32.81,
|
| 259 |
+
"learning_rate": 2.577777777777778e-05,
|
| 260 |
+
"loss": 5.2336,
|
| 261 |
+
"step": 42000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 33.59,
|
| 265 |
+
"learning_rate": 2.5333333333333334e-05,
|
| 266 |
+
"loss": 5.2214,
|
| 267 |
+
"step": 43000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 34.38,
|
| 271 |
+
"learning_rate": 2.4888888888888893e-05,
|
| 272 |
+
"loss": 5.2103,
|
| 273 |
+
"step": 44000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 35.16,
|
| 277 |
+
"learning_rate": 2.444444444444445e-05,
|
| 278 |
+
"loss": 5.2015,
|
| 279 |
+
"step": 45000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 35.94,
|
| 283 |
+
"learning_rate": 2.4e-05,
|
| 284 |
+
"loss": 5.1907,
|
| 285 |
+
"step": 46000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 36.72,
|
| 289 |
+
"learning_rate": 2.355555555555556e-05,
|
| 290 |
+
"loss": 5.1801,
|
| 291 |
+
"step": 47000
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 37.5,
|
| 295 |
+
"learning_rate": 2.3111111111111112e-05,
|
| 296 |
+
"loss": 5.1713,
|
| 297 |
+
"step": 48000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 38.28,
|
| 301 |
+
"learning_rate": 2.2666666666666668e-05,
|
| 302 |
+
"loss": 5.1645,
|
| 303 |
+
"step": 49000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 39.06,
|
| 307 |
+
"learning_rate": 2.2222222222222227e-05,
|
| 308 |
+
"loss": 5.1548,
|
| 309 |
+
"step": 50000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 39.84,
|
| 313 |
+
"learning_rate": 2.177777777777778e-05,
|
| 314 |
+
"loss": 5.1462,
|
| 315 |
+
"step": 51000
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 40.62,
|
| 319 |
+
"learning_rate": 2.1333333333333335e-05,
|
| 320 |
+
"loss": 5.1417,
|
| 321 |
+
"step": 52000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 41.41,
|
| 325 |
+
"learning_rate": 2.088888888888889e-05,
|
| 326 |
+
"loss": 5.1305,
|
| 327 |
+
"step": 53000
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 42.19,
|
| 331 |
+
"learning_rate": 2.0444444444444446e-05,
|
| 332 |
+
"loss": 5.1287,
|
| 333 |
+
"step": 54000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 42.97,
|
| 337 |
+
"learning_rate": 2e-05,
|
| 338 |
+
"loss": 5.1202,
|
| 339 |
+
"step": 55000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 43.75,
|
| 343 |
+
"learning_rate": 1.9555555555555557e-05,
|
| 344 |
+
"loss": 5.1139,
|
| 345 |
+
"step": 56000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 44.53,
|
| 349 |
+
"learning_rate": 1.9111111111111113e-05,
|
| 350 |
+
"loss": 5.1081,
|
| 351 |
+
"step": 57000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 45.31,
|
| 355 |
+
"learning_rate": 1.866666666666667e-05,
|
| 356 |
+
"loss": 5.1032,
|
| 357 |
+
"step": 58000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 46.09,
|
| 361 |
+
"learning_rate": 1.8222222222222224e-05,
|
| 362 |
+
"loss": 5.0968,
|
| 363 |
+
"step": 59000
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 46.88,
|
| 367 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 368 |
+
"loss": 5.0914,
|
| 369 |
+
"step": 60000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 47.66,
|
| 373 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 374 |
+
"loss": 5.085,
|
| 375 |
+
"step": 61000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 48.44,
|
| 379 |
+
"learning_rate": 1.688888888888889e-05,
|
| 380 |
+
"loss": 5.0806,
|
| 381 |
+
"step": 62000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 49.22,
|
| 385 |
+
"learning_rate": 1.6444444444444444e-05,
|
| 386 |
+
"loss": 5.0769,
|
| 387 |
+
"step": 63000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 50.0,
|
| 391 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 392 |
+
"loss": 5.0728,
|
| 393 |
+
"step": 64000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 50.78,
|
| 397 |
+
"learning_rate": 1.555555555555556e-05,
|
| 398 |
+
"loss": 5.0692,
|
| 399 |
+
"step": 65000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 51.56,
|
| 403 |
+
"learning_rate": 1.5111111111111112e-05,
|
| 404 |
+
"loss": 5.065,
|
| 405 |
+
"step": 66000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 52.34,
|
| 409 |
+
"learning_rate": 1.4666666666666666e-05,
|
| 410 |
+
"loss": 5.0594,
|
| 411 |
+
"step": 67000
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 53.12,
|
| 415 |
+
"learning_rate": 1.4222222222222224e-05,
|
| 416 |
+
"loss": 5.0549,
|
| 417 |
+
"step": 68000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 53.91,
|
| 421 |
+
"learning_rate": 1.377777777777778e-05,
|
| 422 |
+
"loss": 5.0538,
|
| 423 |
+
"step": 69000
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 54.69,
|
| 427 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 428 |
+
"loss": 5.0482,
|
| 429 |
+
"step": 70000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 55.47,
|
| 433 |
+
"learning_rate": 1.288888888888889e-05,
|
| 434 |
+
"loss": 5.0475,
|
| 435 |
+
"step": 71000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 56.25,
|
| 439 |
+
"learning_rate": 1.2444444444444446e-05,
|
| 440 |
+
"loss": 5.0399,
|
| 441 |
+
"step": 72000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 57.03,
|
| 445 |
+
"learning_rate": 1.2e-05,
|
| 446 |
+
"loss": 5.0406,
|
| 447 |
+
"step": 73000
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 57.81,
|
| 451 |
+
"learning_rate": 1.1555555555555556e-05,
|
| 452 |
+
"loss": 5.037,
|
| 453 |
+
"step": 74000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 58.59,
|
| 457 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 458 |
+
"loss": 5.0326,
|
| 459 |
+
"step": 75000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 59.38,
|
| 463 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 464 |
+
"loss": 5.031,
|
| 465 |
+
"step": 76000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 60.16,
|
| 469 |
+
"learning_rate": 1.0222222222222223e-05,
|
| 470 |
+
"loss": 5.0291,
|
| 471 |
+
"step": 77000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 60.94,
|
| 475 |
+
"learning_rate": 9.777777777777779e-06,
|
| 476 |
+
"loss": 5.0266,
|
| 477 |
+
"step": 78000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 61.72,
|
| 481 |
+
"learning_rate": 9.333333333333334e-06,
|
| 482 |
+
"loss": 5.0235,
|
| 483 |
+
"step": 79000
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 62.5,
|
| 487 |
+
"learning_rate": 8.888888888888888e-06,
|
| 488 |
+
"loss": 5.0211,
|
| 489 |
+
"step": 80000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 63.28,
|
| 493 |
+
"learning_rate": 8.444444444444446e-06,
|
| 494 |
+
"loss": 5.0214,
|
| 495 |
+
"step": 81000
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 64.06,
|
| 499 |
+
"learning_rate": 8.000000000000001e-06,
|
| 500 |
+
"loss": 5.0176,
|
| 501 |
+
"step": 82000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 64.84,
|
| 505 |
+
"learning_rate": 7.555555555555556e-06,
|
| 506 |
+
"loss": 5.0157,
|
| 507 |
+
"step": 83000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 65.62,
|
| 511 |
+
"learning_rate": 7.111111111111112e-06,
|
| 512 |
+
"loss": 5.014,
|
| 513 |
+
"step": 84000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 66.41,
|
| 517 |
+
"learning_rate": 6.666666666666667e-06,
|
| 518 |
+
"loss": 5.0115,
|
| 519 |
+
"step": 85000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 67.19,
|
| 523 |
+
"learning_rate": 6.222222222222223e-06,
|
| 524 |
+
"loss": 5.0087,
|
| 525 |
+
"step": 86000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 67.97,
|
| 529 |
+
"learning_rate": 5.777777777777778e-06,
|
| 530 |
+
"loss": 5.0105,
|
| 531 |
+
"step": 87000
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 68.75,
|
| 535 |
+
"learning_rate": 5.333333333333334e-06,
|
| 536 |
+
"loss": 5.0062,
|
| 537 |
+
"step": 88000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 69.53,
|
| 541 |
+
"learning_rate": 4.888888888888889e-06,
|
| 542 |
+
"loss": 5.0028,
|
| 543 |
+
"step": 89000
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 70.31,
|
| 547 |
+
"learning_rate": 4.444444444444444e-06,
|
| 548 |
+
"loss": 5.0066,
|
| 549 |
+
"step": 90000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 71.09,
|
| 553 |
+
"learning_rate": 4.000000000000001e-06,
|
| 554 |
+
"loss": 5.0032,
|
| 555 |
+
"step": 91000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 71.88,
|
| 559 |
+
"learning_rate": 3.555555555555556e-06,
|
| 560 |
+
"loss": 5.0022,
|
| 561 |
+
"step": 92000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 72.66,
|
| 565 |
+
"learning_rate": 3.1111111111111116e-06,
|
| 566 |
+
"loss": 5.0024,
|
| 567 |
+
"step": 93000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 73.44,
|
| 571 |
+
"learning_rate": 2.666666666666667e-06,
|
| 572 |
+
"loss": 5.0007,
|
| 573 |
+
"step": 94000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 74.22,
|
| 577 |
+
"learning_rate": 2.222222222222222e-06,
|
| 578 |
+
"loss": 5.0008,
|
| 579 |
+
"step": 95000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 75.0,
|
| 583 |
+
"learning_rate": 1.777777777777778e-06,
|
| 584 |
+
"loss": 4.9978,
|
| 585 |
+
"step": 96000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 75.78,
|
| 589 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 590 |
+
"loss": 4.9966,
|
| 591 |
+
"step": 97000
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 76.56,
|
| 595 |
+
"learning_rate": 8.88888888888889e-07,
|
| 596 |
+
"loss": 4.9994,
|
| 597 |
+
"step": 98000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 77.34,
|
| 601 |
+
"learning_rate": 4.444444444444445e-07,
|
| 602 |
+
"loss": 4.9966,
|
| 603 |
+
"step": 99000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 78.12,
|
| 607 |
+
"learning_rate": 0.0,
|
| 608 |
+
"loss": 4.9976,
|
| 609 |
+
"step": 100000
|
| 610 |
+
}
|
| 611 |
+
],
|
| 612 |
+
"logging_steps": 1000,
|
| 613 |
+
"max_steps": 100000,
|
| 614 |
+
"num_train_epochs": 79,
|
| 615 |
+
"save_steps": 1000,
|
| 616 |
+
"total_flos": 2.0208137237272986e+19,
|
| 617 |
+
"trial_name": null,
|
| 618 |
+
"trial_params": null
|
| 619 |
+
}
|
checkpoint-100000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0745aace4da4e1b77980fbb19c691aeee604fd28b68564cdb7a5c2f63c40987
|
| 3 |
+
size 5073
|
checkpoint-91000/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-91000/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-91000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c41b92507de8a0067f60a30b57caba6f48e2b1ddfdc55d955b7261cbe88c026a
|
| 3 |
+
size 359944256
|
checkpoint-91000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8831e04123eec5ca084798ce90cee5d7f6950a5473711bbf719989954acd3d3c
|
| 3 |
+
size 720010699
|
checkpoint-91000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a24ee5b251e4383f6b59bb318701533f5cd37be013923c6ae7c9d39b30b2e04a
|
| 3 |
+
size 16389
|
checkpoint-91000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe502f4b2f689f96242626c849a42a3c4d9b40f7b9c11f970d9a97a18550169b
|
| 3 |
+
size 16389
|
checkpoint-91000/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:655c95a0efb71c6832937b8175e741ceeea86350ab1143d9d13d7726920ac50a
|
| 3 |
+
size 16389
|
checkpoint-91000/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70f85ab7ca493f5d32f0a4551a0606c262045b916b5d3197705fd1886ce4e60f
|
| 3 |
+
size 16389
|
checkpoint-91000/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52e5f68d34799624db6594b85778ce69385257e4c1c07811da5f695ab59f01e1
|
| 3 |
+
size 16389
|
checkpoint-91000/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fae7bd357c7fee45c2d23a0b3e55a3cad9d0b6866b7c93d05e2dd5fbb885cc4
|
| 3 |
+
size 16389
|
checkpoint-91000/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c365b6f4f2f969f75fbf860ef04abd14d7bde6f770da2fab6c811007f808335
|
| 3 |
+
size 16389
|
checkpoint-91000/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51fb12135a2607bcd562b0aeee3f546753ee869ab497c0bb5c2cc414b8d5d584
|
| 3 |
+
size 16389
|
checkpoint-91000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12d90c9e4c6eaab6503615c6b976f9f1a3bb26b48aff77762de6e4dfcc6477d4
|
| 3 |
+
size 1465
|
checkpoint-91000/trainer_state.json
ADDED
|
@@ -0,0 +1,565 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 71.09375,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 91000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.78,
|
| 13 |
+
"learning_rate": 4.000000000000001e-06,
|
| 14 |
+
"loss": 7.5832,
|
| 15 |
+
"step": 1000
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.56,
|
| 19 |
+
"learning_rate": 8.000000000000001e-06,
|
| 20 |
+
"loss": 6.9724,
|
| 21 |
+
"step": 2000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 2.34,
|
| 25 |
+
"learning_rate": 1.2e-05,
|
| 26 |
+
"loss": 6.7695,
|
| 27 |
+
"step": 3000
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 3.12,
|
| 31 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 32 |
+
"loss": 6.7002,
|
| 33 |
+
"step": 4000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 3.91,
|
| 37 |
+
"learning_rate": 2e-05,
|
| 38 |
+
"loss": 6.666,
|
| 39 |
+
"step": 5000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 4.69,
|
| 43 |
+
"learning_rate": 2.4e-05,
|
| 44 |
+
"loss": 6.6503,
|
| 45 |
+
"step": 6000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 5.47,
|
| 49 |
+
"learning_rate": 2.8e-05,
|
| 50 |
+
"loss": 6.6407,
|
| 51 |
+
"step": 7000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 6.25,
|
| 55 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 56 |
+
"loss": 6.6277,
|
| 57 |
+
"step": 8000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 7.03,
|
| 61 |
+
"learning_rate": 3.6e-05,
|
| 62 |
+
"loss": 6.6209,
|
| 63 |
+
"step": 9000
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 7.81,
|
| 67 |
+
"learning_rate": 4e-05,
|
| 68 |
+
"loss": 6.6135,
|
| 69 |
+
"step": 10000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 8.59,
|
| 73 |
+
"learning_rate": 3.955555555555556e-05,
|
| 74 |
+
"loss": 6.6084,
|
| 75 |
+
"step": 11000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 9.38,
|
| 79 |
+
"learning_rate": 3.9111111111111115e-05,
|
| 80 |
+
"loss": 6.6041,
|
| 81 |
+
"step": 12000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 10.16,
|
| 85 |
+
"learning_rate": 3.866666666666667e-05,
|
| 86 |
+
"loss": 6.6013,
|
| 87 |
+
"step": 13000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 10.94,
|
| 91 |
+
"learning_rate": 3.8222222222222226e-05,
|
| 92 |
+
"loss": 6.5994,
|
| 93 |
+
"step": 14000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 11.72,
|
| 97 |
+
"learning_rate": 3.777777777777778e-05,
|
| 98 |
+
"loss": 6.594,
|
| 99 |
+
"step": 15000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 12.5,
|
| 103 |
+
"learning_rate": 3.733333333333334e-05,
|
| 104 |
+
"loss": 6.5925,
|
| 105 |
+
"step": 16000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 13.28,
|
| 109 |
+
"learning_rate": 3.6888888888888896e-05,
|
| 110 |
+
"loss": 6.5893,
|
| 111 |
+
"step": 17000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 14.06,
|
| 115 |
+
"learning_rate": 3.644444444444445e-05,
|
| 116 |
+
"loss": 6.5875,
|
| 117 |
+
"step": 18000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 14.84,
|
| 121 |
+
"learning_rate": 3.6e-05,
|
| 122 |
+
"loss": 6.5232,
|
| 123 |
+
"step": 19000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 15.62,
|
| 127 |
+
"learning_rate": 3.555555555555555e-05,
|
| 128 |
+
"loss": 6.4358,
|
| 129 |
+
"step": 20000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 16.41,
|
| 133 |
+
"learning_rate": 3.511111111111111e-05,
|
| 134 |
+
"loss": 6.3712,
|
| 135 |
+
"step": 21000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 17.19,
|
| 139 |
+
"learning_rate": 3.466666666666667e-05,
|
| 140 |
+
"loss": 6.311,
|
| 141 |
+
"step": 22000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 17.97,
|
| 145 |
+
"learning_rate": 3.4222222222222224e-05,
|
| 146 |
+
"loss": 6.2493,
|
| 147 |
+
"step": 23000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 18.75,
|
| 151 |
+
"learning_rate": 3.377777777777778e-05,
|
| 152 |
+
"loss": 6.1597,
|
| 153 |
+
"step": 24000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 19.53,
|
| 157 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 158 |
+
"loss": 6.0276,
|
| 159 |
+
"step": 25000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 20.31,
|
| 163 |
+
"learning_rate": 3.288888888888889e-05,
|
| 164 |
+
"loss": 5.8317,
|
| 165 |
+
"step": 26000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 21.09,
|
| 169 |
+
"learning_rate": 3.2444444444444446e-05,
|
| 170 |
+
"loss": 5.6782,
|
| 171 |
+
"step": 27000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 21.88,
|
| 175 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 176 |
+
"loss": 5.5975,
|
| 177 |
+
"step": 28000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 22.66,
|
| 181 |
+
"learning_rate": 3.155555555555556e-05,
|
| 182 |
+
"loss": 5.5369,
|
| 183 |
+
"step": 29000
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 23.44,
|
| 187 |
+
"learning_rate": 3.111111111111112e-05,
|
| 188 |
+
"loss": 5.4921,
|
| 189 |
+
"step": 30000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 24.22,
|
| 193 |
+
"learning_rate": 3.066666666666667e-05,
|
| 194 |
+
"loss": 5.4554,
|
| 195 |
+
"step": 31000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 25.0,
|
| 199 |
+
"learning_rate": 3.0222222222222225e-05,
|
| 200 |
+
"loss": 5.4237,
|
| 201 |
+
"step": 32000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 25.78,
|
| 205 |
+
"learning_rate": 2.977777777777778e-05,
|
| 206 |
+
"loss": 5.3938,
|
| 207 |
+
"step": 33000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 26.56,
|
| 211 |
+
"learning_rate": 2.9333333333333333e-05,
|
| 212 |
+
"loss": 5.3701,
|
| 213 |
+
"step": 34000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 27.34,
|
| 217 |
+
"learning_rate": 2.888888888888889e-05,
|
| 218 |
+
"loss": 5.3452,
|
| 219 |
+
"step": 35000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 28.12,
|
| 223 |
+
"learning_rate": 2.8444444444444447e-05,
|
| 224 |
+
"loss": 5.327,
|
| 225 |
+
"step": 36000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 28.91,
|
| 229 |
+
"learning_rate": 2.8e-05,
|
| 230 |
+
"loss": 5.3063,
|
| 231 |
+
"step": 37000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 29.69,
|
| 235 |
+
"learning_rate": 2.755555555555556e-05,
|
| 236 |
+
"loss": 5.2905,
|
| 237 |
+
"step": 38000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 30.47,
|
| 241 |
+
"learning_rate": 2.7111111111111114e-05,
|
| 242 |
+
"loss": 5.2747,
|
| 243 |
+
"step": 39000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 31.25,
|
| 247 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 248 |
+
"loss": 5.2596,
|
| 249 |
+
"step": 40000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 32.03,
|
| 253 |
+
"learning_rate": 2.6222222222222226e-05,
|
| 254 |
+
"loss": 5.2483,
|
| 255 |
+
"step": 41000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 32.81,
|
| 259 |
+
"learning_rate": 2.577777777777778e-05,
|
| 260 |
+
"loss": 5.2336,
|
| 261 |
+
"step": 42000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 33.59,
|
| 265 |
+
"learning_rate": 2.5333333333333334e-05,
|
| 266 |
+
"loss": 5.2214,
|
| 267 |
+
"step": 43000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 34.38,
|
| 271 |
+
"learning_rate": 2.4888888888888893e-05,
|
| 272 |
+
"loss": 5.2103,
|
| 273 |
+
"step": 44000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 35.16,
|
| 277 |
+
"learning_rate": 2.444444444444445e-05,
|
| 278 |
+
"loss": 5.2015,
|
| 279 |
+
"step": 45000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 35.94,
|
| 283 |
+
"learning_rate": 2.4e-05,
|
| 284 |
+
"loss": 5.1907,
|
| 285 |
+
"step": 46000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 36.72,
|
| 289 |
+
"learning_rate": 2.355555555555556e-05,
|
| 290 |
+
"loss": 5.1801,
|
| 291 |
+
"step": 47000
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 37.5,
|
| 295 |
+
"learning_rate": 2.3111111111111112e-05,
|
| 296 |
+
"loss": 5.1713,
|
| 297 |
+
"step": 48000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 38.28,
|
| 301 |
+
"learning_rate": 2.2666666666666668e-05,
|
| 302 |
+
"loss": 5.1645,
|
| 303 |
+
"step": 49000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 39.06,
|
| 307 |
+
"learning_rate": 2.2222222222222227e-05,
|
| 308 |
+
"loss": 5.1548,
|
| 309 |
+
"step": 50000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 39.84,
|
| 313 |
+
"learning_rate": 2.177777777777778e-05,
|
| 314 |
+
"loss": 5.1462,
|
| 315 |
+
"step": 51000
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 40.62,
|
| 319 |
+
"learning_rate": 2.1333333333333335e-05,
|
| 320 |
+
"loss": 5.1417,
|
| 321 |
+
"step": 52000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 41.41,
|
| 325 |
+
"learning_rate": 2.088888888888889e-05,
|
| 326 |
+
"loss": 5.1305,
|
| 327 |
+
"step": 53000
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 42.19,
|
| 331 |
+
"learning_rate": 2.0444444444444446e-05,
|
| 332 |
+
"loss": 5.1287,
|
| 333 |
+
"step": 54000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 42.97,
|
| 337 |
+
"learning_rate": 2e-05,
|
| 338 |
+
"loss": 5.1202,
|
| 339 |
+
"step": 55000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 43.75,
|
| 343 |
+
"learning_rate": 1.9555555555555557e-05,
|
| 344 |
+
"loss": 5.1139,
|
| 345 |
+
"step": 56000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 44.53,
|
| 349 |
+
"learning_rate": 1.9111111111111113e-05,
|
| 350 |
+
"loss": 5.1081,
|
| 351 |
+
"step": 57000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 45.31,
|
| 355 |
+
"learning_rate": 1.866666666666667e-05,
|
| 356 |
+
"loss": 5.1032,
|
| 357 |
+
"step": 58000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 46.09,
|
| 361 |
+
"learning_rate": 1.8222222222222224e-05,
|
| 362 |
+
"loss": 5.0968,
|
| 363 |
+
"step": 59000
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 46.88,
|
| 367 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 368 |
+
"loss": 5.0914,
|
| 369 |
+
"step": 60000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 47.66,
|
| 373 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 374 |
+
"loss": 5.085,
|
| 375 |
+
"step": 61000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 48.44,
|
| 379 |
+
"learning_rate": 1.688888888888889e-05,
|
| 380 |
+
"loss": 5.0806,
|
| 381 |
+
"step": 62000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 49.22,
|
| 385 |
+
"learning_rate": 1.6444444444444444e-05,
|
| 386 |
+
"loss": 5.0769,
|
| 387 |
+
"step": 63000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 50.0,
|
| 391 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 392 |
+
"loss": 5.0728,
|
| 393 |
+
"step": 64000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 50.78,
|
| 397 |
+
"learning_rate": 1.555555555555556e-05,
|
| 398 |
+
"loss": 5.0692,
|
| 399 |
+
"step": 65000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 51.56,
|
| 403 |
+
"learning_rate": 1.5111111111111112e-05,
|
| 404 |
+
"loss": 5.065,
|
| 405 |
+
"step": 66000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 52.34,
|
| 409 |
+
"learning_rate": 1.4666666666666666e-05,
|
| 410 |
+
"loss": 5.0594,
|
| 411 |
+
"step": 67000
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 53.12,
|
| 415 |
+
"learning_rate": 1.4222222222222224e-05,
|
| 416 |
+
"loss": 5.0549,
|
| 417 |
+
"step": 68000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 53.91,
|
| 421 |
+
"learning_rate": 1.377777777777778e-05,
|
| 422 |
+
"loss": 5.0538,
|
| 423 |
+
"step": 69000
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 54.69,
|
| 427 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 428 |
+
"loss": 5.0482,
|
| 429 |
+
"step": 70000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 55.47,
|
| 433 |
+
"learning_rate": 1.288888888888889e-05,
|
| 434 |
+
"loss": 5.0475,
|
| 435 |
+
"step": 71000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 56.25,
|
| 439 |
+
"learning_rate": 1.2444444444444446e-05,
|
| 440 |
+
"loss": 5.0399,
|
| 441 |
+
"step": 72000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 57.03,
|
| 445 |
+
"learning_rate": 1.2e-05,
|
| 446 |
+
"loss": 5.0406,
|
| 447 |
+
"step": 73000
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 57.81,
|
| 451 |
+
"learning_rate": 1.1555555555555556e-05,
|
| 452 |
+
"loss": 5.037,
|
| 453 |
+
"step": 74000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 58.59,
|
| 457 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 458 |
+
"loss": 5.0326,
|
| 459 |
+
"step": 75000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 59.38,
|
| 463 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 464 |
+
"loss": 5.031,
|
| 465 |
+
"step": 76000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 60.16,
|
| 469 |
+
"learning_rate": 1.0222222222222223e-05,
|
| 470 |
+
"loss": 5.0291,
|
| 471 |
+
"step": 77000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 60.94,
|
| 475 |
+
"learning_rate": 9.777777777777779e-06,
|
| 476 |
+
"loss": 5.0266,
|
| 477 |
+
"step": 78000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 61.72,
|
| 481 |
+
"learning_rate": 9.333333333333334e-06,
|
| 482 |
+
"loss": 5.0235,
|
| 483 |
+
"step": 79000
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 62.5,
|
| 487 |
+
"learning_rate": 8.888888888888888e-06,
|
| 488 |
+
"loss": 5.0211,
|
| 489 |
+
"step": 80000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 63.28,
|
| 493 |
+
"learning_rate": 8.444444444444446e-06,
|
| 494 |
+
"loss": 5.0214,
|
| 495 |
+
"step": 81000
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 64.06,
|
| 499 |
+
"learning_rate": 8.000000000000001e-06,
|
| 500 |
+
"loss": 5.0176,
|
| 501 |
+
"step": 82000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 64.84,
|
| 505 |
+
"learning_rate": 7.555555555555556e-06,
|
| 506 |
+
"loss": 5.0157,
|
| 507 |
+
"step": 83000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 65.62,
|
| 511 |
+
"learning_rate": 7.111111111111112e-06,
|
| 512 |
+
"loss": 5.014,
|
| 513 |
+
"step": 84000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 66.41,
|
| 517 |
+
"learning_rate": 6.666666666666667e-06,
|
| 518 |
+
"loss": 5.0115,
|
| 519 |
+
"step": 85000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 67.19,
|
| 523 |
+
"learning_rate": 6.222222222222223e-06,
|
| 524 |
+
"loss": 5.0087,
|
| 525 |
+
"step": 86000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 67.97,
|
| 529 |
+
"learning_rate": 5.777777777777778e-06,
|
| 530 |
+
"loss": 5.0105,
|
| 531 |
+
"step": 87000
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 68.75,
|
| 535 |
+
"learning_rate": 5.333333333333334e-06,
|
| 536 |
+
"loss": 5.0062,
|
| 537 |
+
"step": 88000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 69.53,
|
| 541 |
+
"learning_rate": 4.888888888888889e-06,
|
| 542 |
+
"loss": 5.0028,
|
| 543 |
+
"step": 89000
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 70.31,
|
| 547 |
+
"learning_rate": 4.444444444444444e-06,
|
| 548 |
+
"loss": 5.0066,
|
| 549 |
+
"step": 90000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 71.09,
|
| 553 |
+
"learning_rate": 4.000000000000001e-06,
|
| 554 |
+
"loss": 5.0032,
|
| 555 |
+
"step": 91000
|
| 556 |
+
}
|
| 557 |
+
],
|
| 558 |
+
"logging_steps": 1000,
|
| 559 |
+
"max_steps": 100000,
|
| 560 |
+
"num_train_epochs": 79,
|
| 561 |
+
"save_steps": 1000,
|
| 562 |
+
"total_flos": 1.8389404885918417e+19,
|
| 563 |
+
"trial_name": null,
|
| 564 |
+
"trial_params": null
|
| 565 |
+
}
|
checkpoint-91000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0745aace4da4e1b77980fbb19c691aeee604fd28b68564cdb7a5c2f63c40987
|
| 3 |
+
size 5073
|
checkpoint-92000/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-92000/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-92000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d47e8051ca7bc578765f5ef9125bef83c2b01c6bc9690a0ca43237e07304c66
|
| 3 |
+
size 359944256
|
checkpoint-92000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:254601789ac7766cb5bac76584f6ed7783dcc47ee674e1ebcda7f9708d72599e
|
| 3 |
+
size 720010699
|
checkpoint-92000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b25758867e28c02986ed3ea251734c7d0c3fadd4e163accae4b1764e9fd2a1db
|
| 3 |
+
size 16389
|
checkpoint-92000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a8d99f3f6e4a39877cb631c961a1dbd51bbec73c3ad9eb65a468a76bead900d
|
| 3 |
+
size 16389
|
checkpoint-92000/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d953a1d7075324c1e1c7490779c4d4834082c963e4c2d3c5d4d03d673db9dfae
|
| 3 |
+
size 16389
|
checkpoint-92000/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a93d4a96838d8f130db6202a3e39fb86ac37115f5ef367cb4a598b0acc91cdaf
|
| 3 |
+
size 16389
|
checkpoint-92000/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f031c7bb312cc0aa8e79146431b09ab8a3100e82573da2c5a886e308b711d799
|
| 3 |
+
size 16389
|
checkpoint-92000/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b51b54e79c4f69ec244d55c2816b424abba7f9db6d4bba2b4941e498ff8c551
|
| 3 |
+
size 16389
|
checkpoint-92000/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:edcf70d4551b194c15939491674efd35aca28d0fd63ed0ee53b973310dce7df6
|
| 3 |
+
size 16389
|
checkpoint-92000/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a433b99af629a6bc5d208f5286ca162963c65057db36c90994406fc5b013575c
|
| 3 |
+
size 16389
|
checkpoint-92000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fcbadb39f9f32ff4728925c7f60b2e1aa81047b2c2b0e24dd13f530e77605a0
|
| 3 |
+
size 1465
|
checkpoint-92000/trainer_state.json
ADDED
|
@@ -0,0 +1,571 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 71.875,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 92000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.78,
|
| 13 |
+
"learning_rate": 4.000000000000001e-06,
|
| 14 |
+
"loss": 7.5832,
|
| 15 |
+
"step": 1000
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.56,
|
| 19 |
+
"learning_rate": 8.000000000000001e-06,
|
| 20 |
+
"loss": 6.9724,
|
| 21 |
+
"step": 2000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 2.34,
|
| 25 |
+
"learning_rate": 1.2e-05,
|
| 26 |
+
"loss": 6.7695,
|
| 27 |
+
"step": 3000
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 3.12,
|
| 31 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 32 |
+
"loss": 6.7002,
|
| 33 |
+
"step": 4000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 3.91,
|
| 37 |
+
"learning_rate": 2e-05,
|
| 38 |
+
"loss": 6.666,
|
| 39 |
+
"step": 5000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 4.69,
|
| 43 |
+
"learning_rate": 2.4e-05,
|
| 44 |
+
"loss": 6.6503,
|
| 45 |
+
"step": 6000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 5.47,
|
| 49 |
+
"learning_rate": 2.8e-05,
|
| 50 |
+
"loss": 6.6407,
|
| 51 |
+
"step": 7000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 6.25,
|
| 55 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 56 |
+
"loss": 6.6277,
|
| 57 |
+
"step": 8000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 7.03,
|
| 61 |
+
"learning_rate": 3.6e-05,
|
| 62 |
+
"loss": 6.6209,
|
| 63 |
+
"step": 9000
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 7.81,
|
| 67 |
+
"learning_rate": 4e-05,
|
| 68 |
+
"loss": 6.6135,
|
| 69 |
+
"step": 10000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 8.59,
|
| 73 |
+
"learning_rate": 3.955555555555556e-05,
|
| 74 |
+
"loss": 6.6084,
|
| 75 |
+
"step": 11000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 9.38,
|
| 79 |
+
"learning_rate": 3.9111111111111115e-05,
|
| 80 |
+
"loss": 6.6041,
|
| 81 |
+
"step": 12000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 10.16,
|
| 85 |
+
"learning_rate": 3.866666666666667e-05,
|
| 86 |
+
"loss": 6.6013,
|
| 87 |
+
"step": 13000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 10.94,
|
| 91 |
+
"learning_rate": 3.8222222222222226e-05,
|
| 92 |
+
"loss": 6.5994,
|
| 93 |
+
"step": 14000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 11.72,
|
| 97 |
+
"learning_rate": 3.777777777777778e-05,
|
| 98 |
+
"loss": 6.594,
|
| 99 |
+
"step": 15000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 12.5,
|
| 103 |
+
"learning_rate": 3.733333333333334e-05,
|
| 104 |
+
"loss": 6.5925,
|
| 105 |
+
"step": 16000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 13.28,
|
| 109 |
+
"learning_rate": 3.6888888888888896e-05,
|
| 110 |
+
"loss": 6.5893,
|
| 111 |
+
"step": 17000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 14.06,
|
| 115 |
+
"learning_rate": 3.644444444444445e-05,
|
| 116 |
+
"loss": 6.5875,
|
| 117 |
+
"step": 18000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 14.84,
|
| 121 |
+
"learning_rate": 3.6e-05,
|
| 122 |
+
"loss": 6.5232,
|
| 123 |
+
"step": 19000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 15.62,
|
| 127 |
+
"learning_rate": 3.555555555555555e-05,
|
| 128 |
+
"loss": 6.4358,
|
| 129 |
+
"step": 20000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 16.41,
|
| 133 |
+
"learning_rate": 3.511111111111111e-05,
|
| 134 |
+
"loss": 6.3712,
|
| 135 |
+
"step": 21000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 17.19,
|
| 139 |
+
"learning_rate": 3.466666666666667e-05,
|
| 140 |
+
"loss": 6.311,
|
| 141 |
+
"step": 22000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 17.97,
|
| 145 |
+
"learning_rate": 3.4222222222222224e-05,
|
| 146 |
+
"loss": 6.2493,
|
| 147 |
+
"step": 23000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 18.75,
|
| 151 |
+
"learning_rate": 3.377777777777778e-05,
|
| 152 |
+
"loss": 6.1597,
|
| 153 |
+
"step": 24000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 19.53,
|
| 157 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 158 |
+
"loss": 6.0276,
|
| 159 |
+
"step": 25000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 20.31,
|
| 163 |
+
"learning_rate": 3.288888888888889e-05,
|
| 164 |
+
"loss": 5.8317,
|
| 165 |
+
"step": 26000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 21.09,
|
| 169 |
+
"learning_rate": 3.2444444444444446e-05,
|
| 170 |
+
"loss": 5.6782,
|
| 171 |
+
"step": 27000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 21.88,
|
| 175 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 176 |
+
"loss": 5.5975,
|
| 177 |
+
"step": 28000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 22.66,
|
| 181 |
+
"learning_rate": 3.155555555555556e-05,
|
| 182 |
+
"loss": 5.5369,
|
| 183 |
+
"step": 29000
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 23.44,
|
| 187 |
+
"learning_rate": 3.111111111111112e-05,
|
| 188 |
+
"loss": 5.4921,
|
| 189 |
+
"step": 30000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 24.22,
|
| 193 |
+
"learning_rate": 3.066666666666667e-05,
|
| 194 |
+
"loss": 5.4554,
|
| 195 |
+
"step": 31000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 25.0,
|
| 199 |
+
"learning_rate": 3.0222222222222225e-05,
|
| 200 |
+
"loss": 5.4237,
|
| 201 |
+
"step": 32000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 25.78,
|
| 205 |
+
"learning_rate": 2.977777777777778e-05,
|
| 206 |
+
"loss": 5.3938,
|
| 207 |
+
"step": 33000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 26.56,
|
| 211 |
+
"learning_rate": 2.9333333333333333e-05,
|
| 212 |
+
"loss": 5.3701,
|
| 213 |
+
"step": 34000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 27.34,
|
| 217 |
+
"learning_rate": 2.888888888888889e-05,
|
| 218 |
+
"loss": 5.3452,
|
| 219 |
+
"step": 35000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 28.12,
|
| 223 |
+
"learning_rate": 2.8444444444444447e-05,
|
| 224 |
+
"loss": 5.327,
|
| 225 |
+
"step": 36000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 28.91,
|
| 229 |
+
"learning_rate": 2.8e-05,
|
| 230 |
+
"loss": 5.3063,
|
| 231 |
+
"step": 37000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 29.69,
|
| 235 |
+
"learning_rate": 2.755555555555556e-05,
|
| 236 |
+
"loss": 5.2905,
|
| 237 |
+
"step": 38000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 30.47,
|
| 241 |
+
"learning_rate": 2.7111111111111114e-05,
|
| 242 |
+
"loss": 5.2747,
|
| 243 |
+
"step": 39000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 31.25,
|
| 247 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 248 |
+
"loss": 5.2596,
|
| 249 |
+
"step": 40000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 32.03,
|
| 253 |
+
"learning_rate": 2.6222222222222226e-05,
|
| 254 |
+
"loss": 5.2483,
|
| 255 |
+
"step": 41000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 32.81,
|
| 259 |
+
"learning_rate": 2.577777777777778e-05,
|
| 260 |
+
"loss": 5.2336,
|
| 261 |
+
"step": 42000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 33.59,
|
| 265 |
+
"learning_rate": 2.5333333333333334e-05,
|
| 266 |
+
"loss": 5.2214,
|
| 267 |
+
"step": 43000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 34.38,
|
| 271 |
+
"learning_rate": 2.4888888888888893e-05,
|
| 272 |
+
"loss": 5.2103,
|
| 273 |
+
"step": 44000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 35.16,
|
| 277 |
+
"learning_rate": 2.444444444444445e-05,
|
| 278 |
+
"loss": 5.2015,
|
| 279 |
+
"step": 45000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 35.94,
|
| 283 |
+
"learning_rate": 2.4e-05,
|
| 284 |
+
"loss": 5.1907,
|
| 285 |
+
"step": 46000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 36.72,
|
| 289 |
+
"learning_rate": 2.355555555555556e-05,
|
| 290 |
+
"loss": 5.1801,
|
| 291 |
+
"step": 47000
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 37.5,
|
| 295 |
+
"learning_rate": 2.3111111111111112e-05,
|
| 296 |
+
"loss": 5.1713,
|
| 297 |
+
"step": 48000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 38.28,
|
| 301 |
+
"learning_rate": 2.2666666666666668e-05,
|
| 302 |
+
"loss": 5.1645,
|
| 303 |
+
"step": 49000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 39.06,
|
| 307 |
+
"learning_rate": 2.2222222222222227e-05,
|
| 308 |
+
"loss": 5.1548,
|
| 309 |
+
"step": 50000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 39.84,
|
| 313 |
+
"learning_rate": 2.177777777777778e-05,
|
| 314 |
+
"loss": 5.1462,
|
| 315 |
+
"step": 51000
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 40.62,
|
| 319 |
+
"learning_rate": 2.1333333333333335e-05,
|
| 320 |
+
"loss": 5.1417,
|
| 321 |
+
"step": 52000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 41.41,
|
| 325 |
+
"learning_rate": 2.088888888888889e-05,
|
| 326 |
+
"loss": 5.1305,
|
| 327 |
+
"step": 53000
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 42.19,
|
| 331 |
+
"learning_rate": 2.0444444444444446e-05,
|
| 332 |
+
"loss": 5.1287,
|
| 333 |
+
"step": 54000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 42.97,
|
| 337 |
+
"learning_rate": 2e-05,
|
| 338 |
+
"loss": 5.1202,
|
| 339 |
+
"step": 55000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 43.75,
|
| 343 |
+
"learning_rate": 1.9555555555555557e-05,
|
| 344 |
+
"loss": 5.1139,
|
| 345 |
+
"step": 56000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 44.53,
|
| 349 |
+
"learning_rate": 1.9111111111111113e-05,
|
| 350 |
+
"loss": 5.1081,
|
| 351 |
+
"step": 57000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 45.31,
|
| 355 |
+
"learning_rate": 1.866666666666667e-05,
|
| 356 |
+
"loss": 5.1032,
|
| 357 |
+
"step": 58000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 46.09,
|
| 361 |
+
"learning_rate": 1.8222222222222224e-05,
|
| 362 |
+
"loss": 5.0968,
|
| 363 |
+
"step": 59000
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 46.88,
|
| 367 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 368 |
+
"loss": 5.0914,
|
| 369 |
+
"step": 60000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 47.66,
|
| 373 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 374 |
+
"loss": 5.085,
|
| 375 |
+
"step": 61000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 48.44,
|
| 379 |
+
"learning_rate": 1.688888888888889e-05,
|
| 380 |
+
"loss": 5.0806,
|
| 381 |
+
"step": 62000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 49.22,
|
| 385 |
+
"learning_rate": 1.6444444444444444e-05,
|
| 386 |
+
"loss": 5.0769,
|
| 387 |
+
"step": 63000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 50.0,
|
| 391 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 392 |
+
"loss": 5.0728,
|
| 393 |
+
"step": 64000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 50.78,
|
| 397 |
+
"learning_rate": 1.555555555555556e-05,
|
| 398 |
+
"loss": 5.0692,
|
| 399 |
+
"step": 65000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 51.56,
|
| 403 |
+
"learning_rate": 1.5111111111111112e-05,
|
| 404 |
+
"loss": 5.065,
|
| 405 |
+
"step": 66000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 52.34,
|
| 409 |
+
"learning_rate": 1.4666666666666666e-05,
|
| 410 |
+
"loss": 5.0594,
|
| 411 |
+
"step": 67000
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 53.12,
|
| 415 |
+
"learning_rate": 1.4222222222222224e-05,
|
| 416 |
+
"loss": 5.0549,
|
| 417 |
+
"step": 68000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 53.91,
|
| 421 |
+
"learning_rate": 1.377777777777778e-05,
|
| 422 |
+
"loss": 5.0538,
|
| 423 |
+
"step": 69000
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 54.69,
|
| 427 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 428 |
+
"loss": 5.0482,
|
| 429 |
+
"step": 70000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 55.47,
|
| 433 |
+
"learning_rate": 1.288888888888889e-05,
|
| 434 |
+
"loss": 5.0475,
|
| 435 |
+
"step": 71000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 56.25,
|
| 439 |
+
"learning_rate": 1.2444444444444446e-05,
|
| 440 |
+
"loss": 5.0399,
|
| 441 |
+
"step": 72000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 57.03,
|
| 445 |
+
"learning_rate": 1.2e-05,
|
| 446 |
+
"loss": 5.0406,
|
| 447 |
+
"step": 73000
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 57.81,
|
| 451 |
+
"learning_rate": 1.1555555555555556e-05,
|
| 452 |
+
"loss": 5.037,
|
| 453 |
+
"step": 74000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 58.59,
|
| 457 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 458 |
+
"loss": 5.0326,
|
| 459 |
+
"step": 75000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 59.38,
|
| 463 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 464 |
+
"loss": 5.031,
|
| 465 |
+
"step": 76000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 60.16,
|
| 469 |
+
"learning_rate": 1.0222222222222223e-05,
|
| 470 |
+
"loss": 5.0291,
|
| 471 |
+
"step": 77000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 60.94,
|
| 475 |
+
"learning_rate": 9.777777777777779e-06,
|
| 476 |
+
"loss": 5.0266,
|
| 477 |
+
"step": 78000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 61.72,
|
| 481 |
+
"learning_rate": 9.333333333333334e-06,
|
| 482 |
+
"loss": 5.0235,
|
| 483 |
+
"step": 79000
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 62.5,
|
| 487 |
+
"learning_rate": 8.888888888888888e-06,
|
| 488 |
+
"loss": 5.0211,
|
| 489 |
+
"step": 80000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 63.28,
|
| 493 |
+
"learning_rate": 8.444444444444446e-06,
|
| 494 |
+
"loss": 5.0214,
|
| 495 |
+
"step": 81000
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 64.06,
|
| 499 |
+
"learning_rate": 8.000000000000001e-06,
|
| 500 |
+
"loss": 5.0176,
|
| 501 |
+
"step": 82000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 64.84,
|
| 505 |
+
"learning_rate": 7.555555555555556e-06,
|
| 506 |
+
"loss": 5.0157,
|
| 507 |
+
"step": 83000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 65.62,
|
| 511 |
+
"learning_rate": 7.111111111111112e-06,
|
| 512 |
+
"loss": 5.014,
|
| 513 |
+
"step": 84000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 66.41,
|
| 517 |
+
"learning_rate": 6.666666666666667e-06,
|
| 518 |
+
"loss": 5.0115,
|
| 519 |
+
"step": 85000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 67.19,
|
| 523 |
+
"learning_rate": 6.222222222222223e-06,
|
| 524 |
+
"loss": 5.0087,
|
| 525 |
+
"step": 86000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 67.97,
|
| 529 |
+
"learning_rate": 5.777777777777778e-06,
|
| 530 |
+
"loss": 5.0105,
|
| 531 |
+
"step": 87000
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 68.75,
|
| 535 |
+
"learning_rate": 5.333333333333334e-06,
|
| 536 |
+
"loss": 5.0062,
|
| 537 |
+
"step": 88000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 69.53,
|
| 541 |
+
"learning_rate": 4.888888888888889e-06,
|
| 542 |
+
"loss": 5.0028,
|
| 543 |
+
"step": 89000
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 70.31,
|
| 547 |
+
"learning_rate": 4.444444444444444e-06,
|
| 548 |
+
"loss": 5.0066,
|
| 549 |
+
"step": 90000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 71.09,
|
| 553 |
+
"learning_rate": 4.000000000000001e-06,
|
| 554 |
+
"loss": 5.0032,
|
| 555 |
+
"step": 91000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 71.88,
|
| 559 |
+
"learning_rate": 3.555555555555556e-06,
|
| 560 |
+
"loss": 5.0022,
|
| 561 |
+
"step": 92000
|
| 562 |
+
}
|
| 563 |
+
],
|
| 564 |
+
"logging_steps": 1000,
|
| 565 |
+
"max_steps": 100000,
|
| 566 |
+
"num_train_epochs": 79,
|
| 567 |
+
"save_steps": 1000,
|
| 568 |
+
"total_flos": 1.8591486258291147e+19,
|
| 569 |
+
"trial_name": null,
|
| 570 |
+
"trial_params": null
|
| 571 |
+
}
|
checkpoint-92000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0745aace4da4e1b77980fbb19c691aeee604fd28b68564cdb7a5c2f63c40987
|
| 3 |
+
size 5073
|
checkpoint-93000/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-93000/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 |
+
}
|