Commit
·
9c65b87
1
Parent(s):
6a6d8f6
Model save
Browse files- README.md +65 -0
- adapter_model.safetensors +1 -1
- all_results.json +13 -0
- config_argument.yaml +52 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1196 -0
README.md
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: hllj/Mistral-7B-Vi-Math
|
| 3 |
+
tags:
|
| 4 |
+
- trl
|
| 5 |
+
- sft
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- generator
|
| 9 |
+
model-index:
|
| 10 |
+
- name: sft-mistral-7b-vi-math-v1-clean-valid
|
| 11 |
+
results: []
|
| 12 |
+
library_name: peft
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# sft-mistral-7b-vi-math-v1-clean-valid
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [hllj/Mistral-7B-Vi-Math](https://huggingface.co/hllj/Mistral-7B-Vi-Math) on the generator dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.4370
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 3e-05
|
| 42 |
+
- train_batch_size: 4
|
| 43 |
+
- eval_batch_size: 4
|
| 44 |
+
- seed: 42
|
| 45 |
+
- distributed_type: multi-GPU
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.05
|
| 49 |
+
- num_epochs: 2
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 56 |
+
| 0.2954 | 1.04 | 1000 | 0.4506 |
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
### Framework versions
|
| 60 |
+
|
| 61 |
+
- PEFT 0.5.0
|
| 62 |
+
- Transformers 4.36.2
|
| 63 |
+
- Pytorch 2.1.2
|
| 64 |
+
- Datasets 2.16.0
|
| 65 |
+
- Tokenizers 0.15.0
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 872450448
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73c248137607a1bc2eca838dab3f4a7a482207c5fbad2777d0c18359cf5d848a
|
| 3 |
size 872450448
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_loss": 0.4370269775390625,
|
| 4 |
+
"eval_runtime": 13.746,
|
| 5 |
+
"eval_samples": 140,
|
| 6 |
+
"eval_samples_per_second": 3.201,
|
| 7 |
+
"eval_steps_per_second": 0.8,
|
| 8 |
+
"train_loss": 0.3247208358966101,
|
| 9 |
+
"train_runtime": 7447.4364,
|
| 10 |
+
"train_samples": 8657,
|
| 11 |
+
"train_samples_per_second": 1.032,
|
| 12 |
+
"train_steps_per_second": 0.258
|
| 13 |
+
}
|
config_argument.yaml
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
cache_dir: ./cache
|
| 2 |
+
ddp_find_unused_parameters: false
|
| 3 |
+
ddp_timeout: 30000
|
| 4 |
+
device_map: auto
|
| 5 |
+
do_eval: true
|
| 6 |
+
do_train: true
|
| 7 |
+
eval_steps: 1000
|
| 8 |
+
evaluation_strategy: steps
|
| 9 |
+
fp16: true
|
| 10 |
+
gradient_accumulation_steps: 1
|
| 11 |
+
gradient_checkpointing: true
|
| 12 |
+
gradient_checkpointing_kwargs:
|
| 13 |
+
use_reentrant: false
|
| 14 |
+
hub_model_id: BaoLocTown/sft-mistral-7b-vi-math-v1-clean-valid
|
| 15 |
+
hub_strategy: every_save
|
| 16 |
+
learning_rate: 3.0e-05
|
| 17 |
+
log_level: info
|
| 18 |
+
logging_first_step: true
|
| 19 |
+
logging_steps: 10
|
| 20 |
+
logging_strategy: steps
|
| 21 |
+
lora_alpha: 128
|
| 22 |
+
lora_dropout: 0.05
|
| 23 |
+
lora_r: 256
|
| 24 |
+
lora_target_modules:
|
| 25 |
+
- q_proj
|
| 26 |
+
- k_proj
|
| 27 |
+
- v_proj
|
| 28 |
+
- o_proj
|
| 29 |
+
lr_scheduler_type: cosine
|
| 30 |
+
max_seq_length: 1024
|
| 31 |
+
model_name_or_path: hllj/Mistral-7B-Vi-Math
|
| 32 |
+
model_type: auto
|
| 33 |
+
num_train_epochs: 2
|
| 34 |
+
output_dir: outputs-sft-mistral-7b-vi-math-v1-clean-valid
|
| 35 |
+
overwrite_output_dir: true
|
| 36 |
+
per_device_eval_batch_size: 4
|
| 37 |
+
per_device_train_batch_size: 4
|
| 38 |
+
preprocessing_num_workers: 4
|
| 39 |
+
push_to_hub: true
|
| 40 |
+
report_to: wandb
|
| 41 |
+
run_name: sft-mistral-7b-vi-math-v1-clean-valid
|
| 42 |
+
save_steps: 1000
|
| 43 |
+
save_strategy: steps
|
| 44 |
+
save_total_limit: 13
|
| 45 |
+
seed: 42
|
| 46 |
+
token: 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
|
| 47 |
+
torch_dtype: float16
|
| 48 |
+
train_file_dir: datasets/finetune
|
| 49 |
+
use_peft: true
|
| 50 |
+
validation_file_dir: datasets/validation
|
| 51 |
+
warmup_ratio: 0.05
|
| 52 |
+
weight_decay: 0.05
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_loss": 0.4370269775390625,
|
| 4 |
+
"eval_runtime": 13.746,
|
| 5 |
+
"eval_samples": 140,
|
| 6 |
+
"eval_samples_per_second": 3.201,
|
| 7 |
+
"eval_steps_per_second": 0.8
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 0.3247208358966101,
|
| 4 |
+
"train_runtime": 7447.4364,
|
| 5 |
+
"train_samples": 8657,
|
| 6 |
+
"train_samples_per_second": 1.032,
|
| 7 |
+
"train_steps_per_second": 0.258
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 1922,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 3.0927835051546394e-07,
|
| 14 |
+
"loss": 0.5665,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 3.092783505154639e-06,
|
| 20 |
+
"loss": 0.7248,
|
| 21 |
+
"step": 10
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.02,
|
| 25 |
+
"learning_rate": 6.185567010309278e-06,
|
| 26 |
+
"loss": 0.7059,
|
| 27 |
+
"step": 20
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.03,
|
| 31 |
+
"learning_rate": 9.278350515463918e-06,
|
| 32 |
+
"loss": 0.6139,
|
| 33 |
+
"step": 30
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.04,
|
| 37 |
+
"learning_rate": 1.2371134020618556e-05,
|
| 38 |
+
"loss": 0.5087,
|
| 39 |
+
"step": 40
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.05,
|
| 43 |
+
"learning_rate": 1.5463917525773194e-05,
|
| 44 |
+
"loss": 0.4724,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06,
|
| 49 |
+
"learning_rate": 1.8556701030927837e-05,
|
| 50 |
+
"loss": 0.4124,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07,
|
| 55 |
+
"learning_rate": 2.1649484536082473e-05,
|
| 56 |
+
"loss": 0.4254,
|
| 57 |
+
"step": 70
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.08,
|
| 61 |
+
"learning_rate": 2.4742268041237112e-05,
|
| 62 |
+
"loss": 0.3885,
|
| 63 |
+
"step": 80
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.09,
|
| 67 |
+
"learning_rate": 2.7835051546391755e-05,
|
| 68 |
+
"loss": 0.3624,
|
| 69 |
+
"step": 90
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.1,
|
| 73 |
+
"learning_rate": 2.999979997843754e-05,
|
| 74 |
+
"loss": 0.4005,
|
| 75 |
+
"step": 100
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.11,
|
| 79 |
+
"learning_rate": 2.999624418794702e-05,
|
| 80 |
+
"loss": 0.3947,
|
| 81 |
+
"step": 110
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.12,
|
| 85 |
+
"learning_rate": 2.998824468665815e-05,
|
| 86 |
+
"loss": 0.383,
|
| 87 |
+
"step": 120
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.14,
|
| 91 |
+
"learning_rate": 2.997580384499581e-05,
|
| 92 |
+
"loss": 0.3477,
|
| 93 |
+
"step": 130
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.15,
|
| 97 |
+
"learning_rate": 2.9958925349449884e-05,
|
| 98 |
+
"loss": 0.3627,
|
| 99 |
+
"step": 140
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.16,
|
| 103 |
+
"learning_rate": 2.9937614201482864e-05,
|
| 104 |
+
"loss": 0.3744,
|
| 105 |
+
"step": 150
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.17,
|
| 109 |
+
"learning_rate": 2.9911876716047828e-05,
|
| 110 |
+
"loss": 0.3545,
|
| 111 |
+
"step": 160
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.18,
|
| 115 |
+
"learning_rate": 2.988172051971717e-05,
|
| 116 |
+
"loss": 0.3598,
|
| 117 |
+
"step": 170
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.19,
|
| 121 |
+
"learning_rate": 2.9847154548422685e-05,
|
| 122 |
+
"loss": 0.336,
|
| 123 |
+
"step": 180
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.2,
|
| 127 |
+
"learning_rate": 2.9808189044807664e-05,
|
| 128 |
+
"loss": 0.3482,
|
| 129 |
+
"step": 190
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.21,
|
| 133 |
+
"learning_rate": 2.976483555519177e-05,
|
| 134 |
+
"loss": 0.3675,
|
| 135 |
+
"step": 200
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.22,
|
| 139 |
+
"learning_rate": 2.9717106926149626e-05,
|
| 140 |
+
"loss": 0.3417,
|
| 141 |
+
"step": 210
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.23,
|
| 145 |
+
"learning_rate": 2.9665017300704087e-05,
|
| 146 |
+
"loss": 0.3401,
|
| 147 |
+
"step": 220
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.24,
|
| 151 |
+
"learning_rate": 2.9608582114135352e-05,
|
| 152 |
+
"loss": 0.3315,
|
| 153 |
+
"step": 230
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.25,
|
| 157 |
+
"learning_rate": 2.954781808940717e-05,
|
| 158 |
+
"loss": 0.366,
|
| 159 |
+
"step": 240
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.26,
|
| 163 |
+
"learning_rate": 2.9482743232211473e-05,
|
| 164 |
+
"loss": 0.3604,
|
| 165 |
+
"step": 250
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.27,
|
| 169 |
+
"learning_rate": 2.9413376825632873e-05,
|
| 170 |
+
"loss": 0.3548,
|
| 171 |
+
"step": 260
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.28,
|
| 175 |
+
"learning_rate": 2.9339739424434687e-05,
|
| 176 |
+
"loss": 0.3615,
|
| 177 |
+
"step": 270
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.29,
|
| 181 |
+
"learning_rate": 2.9261852848968123e-05,
|
| 182 |
+
"loss": 0.3681,
|
| 183 |
+
"step": 280
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.3,
|
| 187 |
+
"learning_rate": 2.9179740178706412e-05,
|
| 188 |
+
"loss": 0.368,
|
| 189 |
+
"step": 290
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.31,
|
| 193 |
+
"learning_rate": 2.9093425745405897e-05,
|
| 194 |
+
"loss": 0.3509,
|
| 195 |
+
"step": 300
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.32,
|
| 199 |
+
"learning_rate": 2.9012171361681493e-05,
|
| 200 |
+
"loss": 0.3321,
|
| 201 |
+
"step": 310
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.33,
|
| 205 |
+
"learning_rate": 2.8917945065723644e-05,
|
| 206 |
+
"loss": 0.3653,
|
| 207 |
+
"step": 320
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.34,
|
| 211 |
+
"learning_rate": 2.8819594582268972e-05,
|
| 212 |
+
"loss": 0.3548,
|
| 213 |
+
"step": 330
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.35,
|
| 217 |
+
"learning_rate": 2.8717149054688286e-05,
|
| 218 |
+
"loss": 0.3602,
|
| 219 |
+
"step": 340
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.36,
|
| 223 |
+
"learning_rate": 2.8610638839802383e-05,
|
| 224 |
+
"loss": 0.3333,
|
| 225 |
+
"step": 350
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.37,
|
| 229 |
+
"learning_rate": 2.85000954988866e-05,
|
| 230 |
+
"loss": 0.3642,
|
| 231 |
+
"step": 360
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.39,
|
| 235 |
+
"learning_rate": 2.838555178831857e-05,
|
| 236 |
+
"loss": 0.346,
|
| 237 |
+
"step": 370
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.4,
|
| 241 |
+
"learning_rate": 2.8267041649871796e-05,
|
| 242 |
+
"loss": 0.3542,
|
| 243 |
+
"step": 380
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.41,
|
| 247 |
+
"learning_rate": 2.8144600200657953e-05,
|
| 248 |
+
"loss": 0.3364,
|
| 249 |
+
"step": 390
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.42,
|
| 253 |
+
"learning_rate": 2.8018263722720953e-05,
|
| 254 |
+
"loss": 0.3526,
|
| 255 |
+
"step": 400
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.43,
|
| 259 |
+
"learning_rate": 2.7888069652285765e-05,
|
| 260 |
+
"loss": 0.3457,
|
| 261 |
+
"step": 410
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.44,
|
| 265 |
+
"learning_rate": 2.775405656866529e-05,
|
| 266 |
+
"loss": 0.328,
|
| 267 |
+
"step": 420
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.45,
|
| 271 |
+
"learning_rate": 2.7616264182828423e-05,
|
| 272 |
+
"loss": 0.3445,
|
| 273 |
+
"step": 430
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.46,
|
| 277 |
+
"learning_rate": 2.747473332563291e-05,
|
| 278 |
+
"loss": 0.3503,
|
| 279 |
+
"step": 440
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.47,
|
| 283 |
+
"learning_rate": 2.7329505935726215e-05,
|
| 284 |
+
"loss": 0.3631,
|
| 285 |
+
"step": 450
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.48,
|
| 289 |
+
"learning_rate": 2.718062504711823e-05,
|
| 290 |
+
"loss": 0.3456,
|
| 291 |
+
"step": 460
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.49,
|
| 295 |
+
"learning_rate": 2.7028134776429372e-05,
|
| 296 |
+
"loss": 0.3373,
|
| 297 |
+
"step": 470
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.5,
|
| 301 |
+
"learning_rate": 2.6872080309817844e-05,
|
| 302 |
+
"loss": 0.3477,
|
| 303 |
+
"step": 480
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.51,
|
| 307 |
+
"learning_rate": 2.6712507889590042e-05,
|
| 308 |
+
"loss": 0.3603,
|
| 309 |
+
"step": 490
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.52,
|
| 313 |
+
"learning_rate": 2.654946480049793e-05,
|
| 314 |
+
"loss": 0.3242,
|
| 315 |
+
"step": 500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.53,
|
| 319 |
+
"learning_rate": 2.6382999355727565e-05,
|
| 320 |
+
"loss": 0.3277,
|
| 321 |
+
"step": 510
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.54,
|
| 325 |
+
"learning_rate": 2.6213160882582855e-05,
|
| 326 |
+
"loss": 0.3424,
|
| 327 |
+
"step": 520
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.55,
|
| 331 |
+
"learning_rate": 2.6039999707868797e-05,
|
| 332 |
+
"loss": 0.3277,
|
| 333 |
+
"step": 530
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.56,
|
| 337 |
+
"learning_rate": 2.5863567142978596e-05,
|
| 338 |
+
"loss": 0.34,
|
| 339 |
+
"step": 540
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.57,
|
| 343 |
+
"learning_rate": 2.5683915468688945e-05,
|
| 344 |
+
"loss": 0.3086,
|
| 345 |
+
"step": 550
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.58,
|
| 349 |
+
"learning_rate": 2.5501097919668147e-05,
|
| 350 |
+
"loss": 0.3462,
|
| 351 |
+
"step": 560
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.59,
|
| 355 |
+
"learning_rate": 2.531516866870149e-05,
|
| 356 |
+
"loss": 0.3497,
|
| 357 |
+
"step": 570
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.6,
|
| 361 |
+
"learning_rate": 2.512618281063873e-05,
|
| 362 |
+
"loss": 0.3328,
|
| 363 |
+
"step": 580
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.61,
|
| 367 |
+
"learning_rate": 2.4934196346068248e-05,
|
| 368 |
+
"loss": 0.339,
|
| 369 |
+
"step": 590
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.62,
|
| 373 |
+
"learning_rate": 2.4739266164722916e-05,
|
| 374 |
+
"loss": 0.3323,
|
| 375 |
+
"step": 600
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.63,
|
| 379 |
+
"learning_rate": 2.4541450028622397e-05,
|
| 380 |
+
"loss": 0.344,
|
| 381 |
+
"step": 610
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.65,
|
| 385 |
+
"learning_rate": 2.4340806554957033e-05,
|
| 386 |
+
"loss": 0.3494,
|
| 387 |
+
"step": 620
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.66,
|
| 391 |
+
"learning_rate": 2.413739519871833e-05,
|
| 392 |
+
"loss": 0.3224,
|
| 393 |
+
"step": 630
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.67,
|
| 397 |
+
"learning_rate": 2.39312762350811e-05,
|
| 398 |
+
"loss": 0.3296,
|
| 399 |
+
"step": 640
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.68,
|
| 403 |
+
"learning_rate": 2.372251074154269e-05,
|
| 404 |
+
"loss": 0.3324,
|
| 405 |
+
"step": 650
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.69,
|
| 409 |
+
"learning_rate": 2.351116057982436e-05,
|
| 410 |
+
"loss": 0.3217,
|
| 411 |
+
"step": 660
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.7,
|
| 415 |
+
"learning_rate": 2.329728837754034e-05,
|
| 416 |
+
"loss": 0.344,
|
| 417 |
+
"step": 670
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.71,
|
| 421 |
+
"learning_rate": 2.3080957509639908e-05,
|
| 422 |
+
"loss": 0.3426,
|
| 423 |
+
"step": 680
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.72,
|
| 427 |
+
"learning_rate": 2.286223207962802e-05,
|
| 428 |
+
"loss": 0.3166,
|
| 429 |
+
"step": 690
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.73,
|
| 433 |
+
"learning_rate": 2.264117690057007e-05,
|
| 434 |
+
"loss": 0.3145,
|
| 435 |
+
"step": 700
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.74,
|
| 439 |
+
"learning_rate": 2.2417857475886383e-05,
|
| 440 |
+
"loss": 0.342,
|
| 441 |
+
"step": 710
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.75,
|
| 445 |
+
"learning_rate": 2.219233997994211e-05,
|
| 446 |
+
"loss": 0.3259,
|
| 447 |
+
"step": 720
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.76,
|
| 451 |
+
"learning_rate": 2.1964691238438374e-05,
|
| 452 |
+
"loss": 0.3195,
|
| 453 |
+
"step": 730
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.77,
|
| 457 |
+
"learning_rate": 2.173497870861034e-05,
|
| 458 |
+
"loss": 0.3442,
|
| 459 |
+
"step": 740
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.78,
|
| 463 |
+
"learning_rate": 2.1503270459238204e-05,
|
| 464 |
+
"loss": 0.3387,
|
| 465 |
+
"step": 750
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.79,
|
| 469 |
+
"learning_rate": 2.1269635150476917e-05,
|
| 470 |
+
"loss": 0.337,
|
| 471 |
+
"step": 760
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.8,
|
| 475 |
+
"learning_rate": 2.1034142013510735e-05,
|
| 476 |
+
"loss": 0.32,
|
| 477 |
+
"step": 770
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.81,
|
| 481 |
+
"learning_rate": 2.0796860830038506e-05,
|
| 482 |
+
"loss": 0.3168,
|
| 483 |
+
"step": 780
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.82,
|
| 487 |
+
"learning_rate": 2.055786191159583e-05,
|
| 488 |
+
"loss": 0.3229,
|
| 489 |
+
"step": 790
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.83,
|
| 493 |
+
"learning_rate": 2.0317216078720264e-05,
|
| 494 |
+
"loss": 0.3341,
|
| 495 |
+
"step": 800
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.84,
|
| 499 |
+
"learning_rate": 2.0074994639965654e-05,
|
| 500 |
+
"loss": 0.3204,
|
| 501 |
+
"step": 810
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.85,
|
| 505 |
+
"learning_rate": 1.9831269370771864e-05,
|
| 506 |
+
"loss": 0.3518,
|
| 507 |
+
"step": 820
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.86,
|
| 511 |
+
"learning_rate": 1.9586112492196187e-05,
|
| 512 |
+
"loss": 0.317,
|
| 513 |
+
"step": 830
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.87,
|
| 517 |
+
"learning_rate": 1.9339596649512653e-05,
|
| 518 |
+
"loss": 0.3297,
|
| 519 |
+
"step": 840
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.88,
|
| 523 |
+
"learning_rate": 1.9091794890685704e-05,
|
| 524 |
+
"loss": 0.3332,
|
| 525 |
+
"step": 850
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.89,
|
| 529 |
+
"learning_rate": 1.884278064472448e-05,
|
| 530 |
+
"loss": 0.3375,
|
| 531 |
+
"step": 860
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.91,
|
| 535 |
+
"learning_rate": 1.8592627699924218e-05,
|
| 536 |
+
"loss": 0.3372,
|
| 537 |
+
"step": 870
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.92,
|
| 541 |
+
"learning_rate": 1.8341410182001225e-05,
|
| 542 |
+
"loss": 0.3291,
|
| 543 |
+
"step": 880
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.93,
|
| 547 |
+
"learning_rate": 1.8089202532127756e-05,
|
| 548 |
+
"loss": 0.33,
|
| 549 |
+
"step": 890
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.94,
|
| 553 |
+
"learning_rate": 1.783607948487357e-05,
|
| 554 |
+
"loss": 0.3214,
|
| 555 |
+
"step": 900
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.95,
|
| 559 |
+
"learning_rate": 1.758211604606041e-05,
|
| 560 |
+
"loss": 0.3423,
|
| 561 |
+
"step": 910
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.96,
|
| 565 |
+
"learning_rate": 1.7327387470536174e-05,
|
| 566 |
+
"loss": 0.3171,
|
| 567 |
+
"step": 920
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.97,
|
| 571 |
+
"learning_rate": 1.7071969239875282e-05,
|
| 572 |
+
"loss": 0.3308,
|
| 573 |
+
"step": 930
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.98,
|
| 577 |
+
"learning_rate": 1.6815937040011855e-05,
|
| 578 |
+
"loss": 0.3234,
|
| 579 |
+
"step": 940
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.99,
|
| 583 |
+
"learning_rate": 1.6559366738812345e-05,
|
| 584 |
+
"loss": 0.3103,
|
| 585 |
+
"step": 950
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.0,
|
| 589 |
+
"learning_rate": 1.6302334363594227e-05,
|
| 590 |
+
"loss": 0.3305,
|
| 591 |
+
"step": 960
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.01,
|
| 595 |
+
"learning_rate": 1.6044916078597505e-05,
|
| 596 |
+
"loss": 0.289,
|
| 597 |
+
"step": 970
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.02,
|
| 601 |
+
"learning_rate": 1.578718816241556e-05,
|
| 602 |
+
"loss": 0.3036,
|
| 603 |
+
"step": 980
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.03,
|
| 607 |
+
"learning_rate": 1.5529226985392172e-05,
|
| 608 |
+
"loss": 0.2895,
|
| 609 |
+
"step": 990
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.04,
|
| 613 |
+
"learning_rate": 1.527110898699136e-05,
|
| 614 |
+
"loss": 0.2954,
|
| 615 |
+
"step": 1000
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.04,
|
| 619 |
+
"eval_loss": 0.450633704662323,
|
| 620 |
+
"eval_runtime": 13.7441,
|
| 621 |
+
"eval_samples_per_second": 3.201,
|
| 622 |
+
"eval_steps_per_second": 0.8,
|
| 623 |
+
"step": 1000
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 1.05,
|
| 627 |
+
"learning_rate": 1.5012910653146696e-05,
|
| 628 |
+
"loss": 0.2868,
|
| 629 |
+
"step": 1010
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.06,
|
| 633 |
+
"learning_rate": 1.475470849359687e-05,
|
| 634 |
+
"loss": 0.3139,
|
| 635 |
+
"step": 1020
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 1.07,
|
| 639 |
+
"learning_rate": 1.449657901921421e-05,
|
| 640 |
+
"loss": 0.2902,
|
| 641 |
+
"step": 1030
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 1.08,
|
| 645 |
+
"learning_rate": 1.4238598719332875e-05,
|
| 646 |
+
"loss": 0.3213,
|
| 647 |
+
"step": 1040
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.09,
|
| 651 |
+
"learning_rate": 1.398084403908339e-05,
|
| 652 |
+
"loss": 0.2874,
|
| 653 |
+
"step": 1050
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.1,
|
| 657 |
+
"learning_rate": 1.372339135674031e-05,
|
| 658 |
+
"loss": 0.3001,
|
| 659 |
+
"step": 1060
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 1.11,
|
| 663 |
+
"learning_rate": 1.3466316961089692e-05,
|
| 664 |
+
"loss": 0.3068,
|
| 665 |
+
"step": 1070
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 1.12,
|
| 669 |
+
"learning_rate": 1.3209697028823101e-05,
|
| 670 |
+
"loss": 0.281,
|
| 671 |
+
"step": 1080
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 1.13,
|
| 675 |
+
"learning_rate": 1.295360760196477e-05,
|
| 676 |
+
"loss": 0.2817,
|
| 677 |
+
"step": 1090
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 1.14,
|
| 681 |
+
"learning_rate": 1.2698124565338744e-05,
|
| 682 |
+
"loss": 0.2874,
|
| 683 |
+
"step": 1100
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 1.16,
|
| 687 |
+
"learning_rate": 1.244332362408255e-05,
|
| 688 |
+
"loss": 0.2759,
|
| 689 |
+
"step": 1110
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.17,
|
| 693 |
+
"learning_rate": 1.2189280281214128e-05,
|
| 694 |
+
"loss": 0.289,
|
| 695 |
+
"step": 1120
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.18,
|
| 699 |
+
"learning_rate": 1.193606981525869e-05,
|
| 700 |
+
"loss": 0.3084,
|
| 701 |
+
"step": 1130
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 1.19,
|
| 705 |
+
"learning_rate": 1.1683767257942017e-05,
|
| 706 |
+
"loss": 0.27,
|
| 707 |
+
"step": 1140
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 1.2,
|
| 711 |
+
"learning_rate": 1.143244737195698e-05,
|
| 712 |
+
"loss": 0.3034,
|
| 713 |
+
"step": 1150
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.21,
|
| 717 |
+
"learning_rate": 1.1182184628809725e-05,
|
| 718 |
+
"loss": 0.3149,
|
| 719 |
+
"step": 1160
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 1.22,
|
| 723 |
+
"learning_rate": 1.093305318675215e-05,
|
| 724 |
+
"loss": 0.3223,
|
| 725 |
+
"step": 1170
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 1.23,
|
| 729 |
+
"learning_rate": 1.068512686880725e-05,
|
| 730 |
+
"loss": 0.2817,
|
| 731 |
+
"step": 1180
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.24,
|
| 735 |
+
"learning_rate": 1.0438479140893711e-05,
|
| 736 |
+
"loss": 0.2904,
|
| 737 |
+
"step": 1190
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.25,
|
| 741 |
+
"learning_rate": 1.0193183090056407e-05,
|
| 742 |
+
"loss": 0.3009,
|
| 743 |
+
"step": 1200
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 1.26,
|
| 747 |
+
"learning_rate": 9.949311402809125e-06,
|
| 748 |
+
"loss": 0.2932,
|
| 749 |
+
"step": 1210
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 1.27,
|
| 753 |
+
"learning_rate": 9.706936343595973e-06,
|
| 754 |
+
"loss": 0.3013,
|
| 755 |
+
"step": 1220
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 1.28,
|
| 759 |
+
"learning_rate": 9.466129733377887e-06,
|
| 760 |
+
"loss": 0.2935,
|
| 761 |
+
"step": 1230
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.29,
|
| 765 |
+
"learning_rate": 9.226962928350503e-06,
|
| 766 |
+
"loss": 0.289,
|
| 767 |
+
"step": 1240
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 1.3,
|
| 771 |
+
"learning_rate": 8.989506798799793e-06,
|
| 772 |
+
"loss": 0.2822,
|
| 773 |
+
"step": 1250
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.31,
|
| 777 |
+
"learning_rate": 8.753831708101669e-06,
|
| 778 |
+
"loss": 0.3064,
|
| 779 |
+
"step": 1260
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.32,
|
| 783 |
+
"learning_rate": 8.520007491871777e-06,
|
| 784 |
+
"loss": 0.3173,
|
| 785 |
+
"step": 1270
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 1.33,
|
| 789 |
+
"learning_rate": 8.288103437271743e-06,
|
| 790 |
+
"loss": 0.2797,
|
| 791 |
+
"step": 1280
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 1.34,
|
| 795 |
+
"learning_rate": 8.058188262477835e-06,
|
| 796 |
+
"loss": 0.2604,
|
| 797 |
+
"step": 1290
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 1.35,
|
| 801 |
+
"learning_rate": 7.830330096318326e-06,
|
| 802 |
+
"loss": 0.2976,
|
| 803 |
+
"step": 1300
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 1.36,
|
| 807 |
+
"learning_rate": 7.604596458085425e-06,
|
| 808 |
+
"loss": 0.2776,
|
| 809 |
+
"step": 1310
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 1.37,
|
| 813 |
+
"learning_rate": 7.381054237527869e-06,
|
| 814 |
+
"loss": 0.288,
|
| 815 |
+
"step": 1320
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.38,
|
| 819 |
+
"learning_rate": 7.159769675030054e-06,
|
| 820 |
+
"loss": 0.2975,
|
| 821 |
+
"step": 1330
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.39,
|
| 825 |
+
"learning_rate": 6.940808341983558e-06,
|
| 826 |
+
"loss": 0.2845,
|
| 827 |
+
"step": 1340
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 1.4,
|
| 831 |
+
"learning_rate": 6.724235121356932e-06,
|
| 832 |
+
"loss": 0.2831,
|
| 833 |
+
"step": 1350
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.42,
|
| 837 |
+
"learning_rate": 6.510114188469482e-06,
|
| 838 |
+
"loss": 0.2933,
|
| 839 |
+
"step": 1360
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 1.43,
|
| 843 |
+
"learning_rate": 6.298508991974726e-06,
|
| 844 |
+
"loss": 0.2913,
|
| 845 |
+
"step": 1370
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 1.44,
|
| 849 |
+
"learning_rate": 6.089482235059209e-06,
|
| 850 |
+
"loss": 0.2855,
|
| 851 |
+
"step": 1380
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 1.45,
|
| 855 |
+
"learning_rate": 5.8830958568621676e-06,
|
| 856 |
+
"loss": 0.3165,
|
| 857 |
+
"step": 1390
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.46,
|
| 861 |
+
"learning_rate": 5.679411014121645e-06,
|
| 862 |
+
"loss": 0.2847,
|
| 863 |
+
"step": 1400
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.47,
|
| 867 |
+
"learning_rate": 5.478488063052423e-06,
|
| 868 |
+
"loss": 0.2904,
|
| 869 |
+
"step": 1410
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 1.48,
|
| 873 |
+
"learning_rate": 5.280386541461171e-06,
|
| 874 |
+
"loss": 0.2815,
|
| 875 |
+
"step": 1420
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 1.49,
|
| 879 |
+
"learning_rate": 5.085165151104125e-06,
|
| 880 |
+
"loss": 0.3055,
|
| 881 |
+
"step": 1430
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 1.5,
|
| 885 |
+
"learning_rate": 4.892881740292471e-06,
|
| 886 |
+
"loss": 0.2837,
|
| 887 |
+
"step": 1440
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 1.51,
|
| 891 |
+
"learning_rate": 4.7035932867506446e-06,
|
| 892 |
+
"loss": 0.2791,
|
| 893 |
+
"step": 1450
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 1.52,
|
| 897 |
+
"learning_rate": 4.51735588073261e-06,
|
| 898 |
+
"loss": 0.2597,
|
| 899 |
+
"step": 1460
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.53,
|
| 903 |
+
"learning_rate": 4.334224708401099e-06,
|
| 904 |
+
"loss": 0.2961,
|
| 905 |
+
"step": 1470
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.54,
|
| 909 |
+
"learning_rate": 4.154254035474777e-06,
|
| 910 |
+
"loss": 0.2974,
|
| 911 |
+
"step": 1480
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 1.55,
|
| 915 |
+
"learning_rate": 3.977497191148111e-06,
|
| 916 |
+
"loss": 0.2864,
|
| 917 |
+
"step": 1490
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 1.56,
|
| 921 |
+
"learning_rate": 3.804006552288802e-06,
|
| 922 |
+
"loss": 0.2961,
|
| 923 |
+
"step": 1500
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 1.57,
|
| 927 |
+
"learning_rate": 3.633833527917379e-06,
|
| 928 |
+
"loss": 0.2924,
|
| 929 |
+
"step": 1510
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 1.58,
|
| 933 |
+
"learning_rate": 3.467028543973591e-06,
|
| 934 |
+
"loss": 0.2942,
|
| 935 |
+
"step": 1520
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 1.59,
|
| 939 |
+
"learning_rate": 3.303641028374138e-06,
|
| 940 |
+
"loss": 0.2837,
|
| 941 |
+
"step": 1530
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.6,
|
| 945 |
+
"learning_rate": 3.1437193963660797e-06,
|
| 946 |
+
"loss": 0.3026,
|
| 947 |
+
"step": 1540
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.61,
|
| 951 |
+
"learning_rate": 2.987311036180369e-06,
|
| 952 |
+
"loss": 0.2928,
|
| 953 |
+
"step": 1550
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 1.62,
|
| 957 |
+
"learning_rate": 2.8344622949896986e-06,
|
| 958 |
+
"loss": 0.2862,
|
| 959 |
+
"step": 1560
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 1.63,
|
| 963 |
+
"learning_rate": 2.685218465174828e-06,
|
| 964 |
+
"loss": 0.2872,
|
| 965 |
+
"step": 1570
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 1.64,
|
| 969 |
+
"learning_rate": 2.5396237709034816e-06,
|
| 970 |
+
"loss": 0.3098,
|
| 971 |
+
"step": 1580
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 1.65,
|
| 975 |
+
"learning_rate": 2.3977213550257583e-06,
|
| 976 |
+
"loss": 0.2866,
|
| 977 |
+
"step": 1590
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 1.66,
|
| 981 |
+
"learning_rate": 2.2595532662899915e-06,
|
| 982 |
+
"loss": 0.3035,
|
| 983 |
+
"step": 1600
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.68,
|
| 987 |
+
"learning_rate": 2.1251604468827823e-06,
|
| 988 |
+
"loss": 0.3049,
|
| 989 |
+
"step": 1610
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.69,
|
| 993 |
+
"learning_rate": 1.994582720296954e-06,
|
| 994 |
+
"loss": 0.2678,
|
| 995 |
+
"step": 1620
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 1.7,
|
| 999 |
+
"learning_rate": 1.8678587795309971e-06,
|
| 1000 |
+
"loss": 0.2966,
|
| 1001 |
+
"step": 1630
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 1.71,
|
| 1005 |
+
"learning_rate": 1.7450261756234849e-06,
|
| 1006 |
+
"loss": 0.2787,
|
| 1007 |
+
"step": 1640
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 1.72,
|
| 1011 |
+
"learning_rate": 1.6261213065258984e-06,
|
| 1012 |
+
"loss": 0.2957,
|
| 1013 |
+
"step": 1650
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 1.73,
|
| 1017 |
+
"learning_rate": 1.511179406317131e-06,
|
| 1018 |
+
"loss": 0.2747,
|
| 1019 |
+
"step": 1660
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 1.74,
|
| 1023 |
+
"learning_rate": 1.4002345347628598e-06,
|
| 1024 |
+
"loss": 0.2764,
|
| 1025 |
+
"step": 1670
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.75,
|
| 1029 |
+
"learning_rate": 1.293319567222918e-06,
|
| 1030 |
+
"loss": 0.2983,
|
| 1031 |
+
"step": 1680
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.76,
|
| 1035 |
+
"learning_rate": 1.1904661849095993e-06,
|
| 1036 |
+
"loss": 0.2981,
|
| 1037 |
+
"step": 1690
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 1.77,
|
| 1041 |
+
"learning_rate": 1.0917048654998407e-06,
|
| 1042 |
+
"loss": 0.3148,
|
| 1043 |
+
"step": 1700
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 1.78,
|
| 1047 |
+
"learning_rate": 9.970648741040273e-07,
|
| 1048 |
+
"loss": 0.3123,
|
| 1049 |
+
"step": 1710
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 1.79,
|
| 1053 |
+
"learning_rate": 9.065742545941052e-07,
|
| 1054 |
+
"loss": 0.2972,
|
| 1055 |
+
"step": 1720
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 1.8,
|
| 1059 |
+
"learning_rate": 8.202598212935897e-07,
|
| 1060 |
+
"loss": 0.271,
|
| 1061 |
+
"step": 1730
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 1.81,
|
| 1065 |
+
"learning_rate": 7.381471510318799e-07,
|
| 1066 |
+
"loss": 0.2761,
|
| 1067 |
+
"step": 1740
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.82,
|
| 1071 |
+
"learning_rate": 6.602605755653124e-07,
|
| 1072 |
+
"loss": 0.3004,
|
| 1073 |
+
"step": 1750
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.83,
|
| 1077 |
+
"learning_rate": 5.866231743671296e-07,
|
| 1078 |
+
"loss": 0.2771,
|
| 1079 |
+
"step": 1760
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 1.84,
|
| 1083 |
+
"learning_rate": 5.172567677885276e-07,
|
| 1084 |
+
"loss": 0.2985,
|
| 1085 |
+
"step": 1770
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 1.85,
|
| 1089 |
+
"learning_rate": 4.521819105928293e-07,
|
| 1090 |
+
"loss": 0.2873,
|
| 1091 |
+
"step": 1780
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.86,
|
| 1095 |
+
"learning_rate": 3.9141788586465224e-07,
|
| 1096 |
+
"loss": 0.2869,
|
| 1097 |
+
"step": 1790
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 1.87,
|
| 1101 |
+
"learning_rate": 3.349826992959154e-07,
|
| 1102 |
+
"loss": 0.2814,
|
| 1103 |
+
"step": 1800
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 1.88,
|
| 1107 |
+
"learning_rate": 2.828930738503727e-07,
|
| 1108 |
+
"loss": 0.2875,
|
| 1109 |
+
"step": 1810
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.89,
|
| 1113 |
+
"learning_rate": 2.3516444480822962e-07,
|
| 1114 |
+
"loss": 0.3106,
|
| 1115 |
+
"step": 1820
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.9,
|
| 1119 |
+
"learning_rate": 1.9181095519233748e-07,
|
| 1120 |
+
"loss": 0.2933,
|
| 1121 |
+
"step": 1830
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 1.91,
|
| 1125 |
+
"learning_rate": 1.52845451577317e-07,
|
| 1126 |
+
"loss": 0.2798,
|
| 1127 |
+
"step": 1840
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 1.93,
|
| 1131 |
+
"learning_rate": 1.1827948028283353e-07,
|
| 1132 |
+
"loss": 0.3051,
|
| 1133 |
+
"step": 1850
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 1.94,
|
| 1137 |
+
"learning_rate": 8.812328395217395e-08,
|
| 1138 |
+
"loss": 0.2644,
|
| 1139 |
+
"step": 1860
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 1.95,
|
| 1143 |
+
"learning_rate": 6.238579851713611e-08,
|
| 1144 |
+
"loss": 0.3041,
|
| 1145 |
+
"step": 1870
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 1.96,
|
| 1149 |
+
"learning_rate": 4.1074650550116946e-08,
|
| 1150 |
+
"loss": 0.2848,
|
| 1151 |
+
"step": 1880
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.97,
|
| 1155 |
+
"learning_rate": 2.4196155004190256e-08,
|
| 1156 |
+
"loss": 0.2695,
|
| 1157 |
+
"step": 1890
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.98,
|
| 1161 |
+
"learning_rate": 1.175531334185187e-08,
|
| 1162 |
+
"loss": 0.2958,
|
| 1163 |
+
"step": 1900
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 1.99,
|
| 1167 |
+
"learning_rate": 3.755812052983476e-09,
|
| 1168 |
+
"loss": 0.2994,
|
| 1169 |
+
"step": 1910
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 2.0,
|
| 1173 |
+
"learning_rate": 2.0002156246146096e-10,
|
| 1174 |
+
"loss": 0.2929,
|
| 1175 |
+
"step": 1920
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 2.0,
|
| 1179 |
+
"step": 1922,
|
| 1180 |
+
"total_flos": 3.4599459174219776e+17,
|
| 1181 |
+
"train_loss": 0.3247208358966101,
|
| 1182 |
+
"train_runtime": 7447.4364,
|
| 1183 |
+
"train_samples_per_second": 1.032,
|
| 1184 |
+
"train_steps_per_second": 0.258
|
| 1185 |
+
}
|
| 1186 |
+
],
|
| 1187 |
+
"logging_steps": 10,
|
| 1188 |
+
"max_steps": 1922,
|
| 1189 |
+
"num_input_tokens_seen": 0,
|
| 1190 |
+
"num_train_epochs": 2,
|
| 1191 |
+
"save_steps": 1000,
|
| 1192 |
+
"total_flos": 3.4599459174219776e+17,
|
| 1193 |
+
"train_batch_size": 4,
|
| 1194 |
+
"trial_name": null,
|
| 1195 |
+
"trial_params": null
|
| 1196 |
+
}
|