Commit
·
266b399
1
Parent(s):
4e28dc2
Model save
Browse files- README.md +61 -0
- adapter_model.safetensors +1 -1
- all_results.json +13 -0
- config_argument.yaml +50 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1084 -0
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: hllj/mistral-vi-math
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: sft-mistral-7b-v01-v1
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# sft-mistral-7b-v01-v1
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [hllj/mistral-vi-math](https://huggingface.co/hllj/mistral-vi-math) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.4918
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 5e-05
|
| 37 |
+
- train_batch_size: 4
|
| 38 |
+
- eval_batch_size: 4
|
| 39 |
+
- seed: 42
|
| 40 |
+
- distributed_type: multi-GPU
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: cosine
|
| 43 |
+
- lr_scheduler_warmup_ratio: 0.05
|
| 44 |
+
- num_epochs: 2
|
| 45 |
+
- mixed_precision_training: Native AMP
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 0.313 | 0.26 | 500 | 0.5063 |
|
| 52 |
+
| 0.279 | 1.07 | 1000 | 0.4892 |
|
| 53 |
+
| 0.2584 | 1.33 | 1500 | 0.4950 |
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
### Framework versions
|
| 57 |
+
|
| 58 |
+
- Transformers 4.35.2
|
| 59 |
+
- Pytorch 2.1.0
|
| 60 |
+
- Datasets 2.15.0
|
| 61 |
+
- 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 sha256:50f9f18326b14f78e6e5baa1cd8a08bf2c26653a7be354015978e694797c82eb
|
| 3 |
size 872450448
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.45,
|
| 3 |
+
"eval_loss": 0.491791695356369,
|
| 4 |
+
"eval_runtime": 105.74,
|
| 5 |
+
"eval_samples": 852,
|
| 6 |
+
"eval_samples_per_second": 8.058,
|
| 7 |
+
"eval_steps_per_second": 2.014,
|
| 8 |
+
"train_loss": 0.305820442848905,
|
| 9 |
+
"train_runtime": 6666.1209,
|
| 10 |
+
"train_samples": 7665,
|
| 11 |
+
"train_samples_per_second": 2.3,
|
| 12 |
+
"train_steps_per_second": 0.575
|
| 13 |
+
}
|
config_argument.yaml
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: 500
|
| 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-v01-v1
|
| 15 |
+
hub_strategy: every_save
|
| 16 |
+
learning_rate: 5.0e-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-vi-math
|
| 32 |
+
model_type: auto
|
| 33 |
+
num_train_epochs: 2
|
| 34 |
+
output_dir: outputs-sft-mistral-v01-v1
|
| 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-v01-v1
|
| 42 |
+
save_steps: 500
|
| 43 |
+
save_strategy: steps
|
| 44 |
+
save_total_limit: 13
|
| 45 |
+
seed: 42
|
| 46 |
+
torch_dtype: float16
|
| 47 |
+
train_file_dir: datasets/finetune
|
| 48 |
+
use_peft: true
|
| 49 |
+
warmup_ratio: 0.05
|
| 50 |
+
weight_decay: 0.05
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.45,
|
| 3 |
+
"eval_loss": 0.491791695356369,
|
| 4 |
+
"eval_runtime": 105.74,
|
| 5 |
+
"eval_samples": 852,
|
| 6 |
+
"eval_samples_per_second": 8.058,
|
| 7 |
+
"eval_steps_per_second": 2.014
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.45,
|
| 3 |
+
"train_loss": 0.305820442848905,
|
| 4 |
+
"train_runtime": 6666.1209,
|
| 5 |
+
"train_samples": 7665,
|
| 6 |
+
"train_samples_per_second": 2.3,
|
| 7 |
+
"train_steps_per_second": 0.575
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1084 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.4480959833072509,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1718,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 2.604166666666667e-07,
|
| 14 |
+
"loss": 0.7574,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 2.604166666666667e-06,
|
| 20 |
+
"loss": 0.7145,
|
| 21 |
+
"step": 10
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 5.208333333333334e-06,
|
| 26 |
+
"loss": 0.6428,
|
| 27 |
+
"step": 20
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.02,
|
| 31 |
+
"learning_rate": 7.8125e-06,
|
| 32 |
+
"loss": 0.5893,
|
| 33 |
+
"step": 30
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 38 |
+
"loss": 0.537,
|
| 39 |
+
"step": 40
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03,
|
| 43 |
+
"learning_rate": 1.3020833333333334e-05,
|
| 44 |
+
"loss": 0.4432,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03,
|
| 49 |
+
"learning_rate": 1.5625e-05,
|
| 50 |
+
"loss": 0.4239,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04,
|
| 55 |
+
"learning_rate": 1.8229166666666668e-05,
|
| 56 |
+
"loss": 0.3672,
|
| 57 |
+
"step": 70
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.04,
|
| 61 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 62 |
+
"loss": 0.3798,
|
| 63 |
+
"step": 80
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.05,
|
| 67 |
+
"learning_rate": 2.34375e-05,
|
| 68 |
+
"loss": 0.3666,
|
| 69 |
+
"step": 90
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.05,
|
| 73 |
+
"learning_rate": 2.604166666666667e-05,
|
| 74 |
+
"loss": 0.341,
|
| 75 |
+
"step": 100
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.06,
|
| 79 |
+
"learning_rate": 2.8645833333333333e-05,
|
| 80 |
+
"loss": 0.3855,
|
| 81 |
+
"step": 110
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.06,
|
| 85 |
+
"learning_rate": 3.125e-05,
|
| 86 |
+
"loss": 0.3517,
|
| 87 |
+
"step": 120
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.07,
|
| 91 |
+
"learning_rate": 3.385416666666667e-05,
|
| 92 |
+
"loss": 0.3482,
|
| 93 |
+
"step": 130
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.07,
|
| 97 |
+
"learning_rate": 3.6458333333333336e-05,
|
| 98 |
+
"loss": 0.3465,
|
| 99 |
+
"step": 140
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.08,
|
| 103 |
+
"learning_rate": 3.90625e-05,
|
| 104 |
+
"loss": 0.3455,
|
| 105 |
+
"step": 150
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.08,
|
| 109 |
+
"learning_rate": 4.166666666666667e-05,
|
| 110 |
+
"loss": 0.3418,
|
| 111 |
+
"step": 160
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.09,
|
| 115 |
+
"learning_rate": 4.4270833333333337e-05,
|
| 116 |
+
"loss": 0.338,
|
| 117 |
+
"step": 170
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.09,
|
| 121 |
+
"learning_rate": 4.6875e-05,
|
| 122 |
+
"loss": 0.3419,
|
| 123 |
+
"step": 180
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.1,
|
| 127 |
+
"learning_rate": 4.947916666666667e-05,
|
| 128 |
+
"loss": 0.3593,
|
| 129 |
+
"step": 190
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1,
|
| 133 |
+
"learning_rate": 4.99994047380455e-05,
|
| 134 |
+
"loss": 0.3421,
|
| 135 |
+
"step": 200
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.11,
|
| 139 |
+
"learning_rate": 4.999698653493815e-05,
|
| 140 |
+
"loss": 0.3433,
|
| 141 |
+
"step": 210
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.11,
|
| 145 |
+
"learning_rate": 4.999270836660003e-05,
|
| 146 |
+
"loss": 0.3644,
|
| 147 |
+
"step": 220
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.12,
|
| 151 |
+
"learning_rate": 4.998657055135927e-05,
|
| 152 |
+
"loss": 0.3415,
|
| 153 |
+
"step": 230
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.13,
|
| 157 |
+
"learning_rate": 4.9978573545915854e-05,
|
| 158 |
+
"loss": 0.337,
|
| 159 |
+
"step": 240
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.13,
|
| 163 |
+
"learning_rate": 4.996871794530757e-05,
|
| 164 |
+
"loss": 0.3445,
|
| 165 |
+
"step": 250
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.14,
|
| 169 |
+
"learning_rate": 4.9957004482865796e-05,
|
| 170 |
+
"loss": 0.3434,
|
| 171 |
+
"step": 260
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.14,
|
| 175 |
+
"learning_rate": 4.994343403016093e-05,
|
| 176 |
+
"loss": 0.3308,
|
| 177 |
+
"step": 270
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.15,
|
| 181 |
+
"learning_rate": 4.992800759693746e-05,
|
| 182 |
+
"loss": 0.3223,
|
| 183 |
+
"step": 280
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.15,
|
| 187 |
+
"learning_rate": 4.9910726331038935e-05,
|
| 188 |
+
"loss": 0.3283,
|
| 189 |
+
"step": 290
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.16,
|
| 193 |
+
"learning_rate": 4.989159151832251e-05,
|
| 194 |
+
"loss": 0.3344,
|
| 195 |
+
"step": 300
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.16,
|
| 199 |
+
"learning_rate": 4.987060458256324e-05,
|
| 200 |
+
"loss": 0.3395,
|
| 201 |
+
"step": 310
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.17,
|
| 205 |
+
"learning_rate": 4.98477670853482e-05,
|
| 206 |
+
"loss": 0.3255,
|
| 207 |
+
"step": 320
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.17,
|
| 211 |
+
"learning_rate": 4.982308072596025e-05,
|
| 212 |
+
"loss": 0.3075,
|
| 213 |
+
"step": 330
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.18,
|
| 217 |
+
"learning_rate": 4.979654734125161e-05,
|
| 218 |
+
"loss": 0.3294,
|
| 219 |
+
"step": 340
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.18,
|
| 223 |
+
"learning_rate": 4.976816890550717e-05,
|
| 224 |
+
"loss": 0.3196,
|
| 225 |
+
"step": 350
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.19,
|
| 229 |
+
"learning_rate": 4.9737947530297606e-05,
|
| 230 |
+
"loss": 0.3436,
|
| 231 |
+
"step": 360
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.19,
|
| 235 |
+
"learning_rate": 4.9705885464322266e-05,
|
| 236 |
+
"loss": 0.3114,
|
| 237 |
+
"step": 370
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.2,
|
| 241 |
+
"learning_rate": 4.967198509324183e-05,
|
| 242 |
+
"loss": 0.3257,
|
| 243 |
+
"step": 380
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.2,
|
| 247 |
+
"learning_rate": 4.9636248939500805e-05,
|
| 248 |
+
"loss": 0.3062,
|
| 249 |
+
"step": 390
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.21,
|
| 253 |
+
"learning_rate": 4.959867966213986e-05,
|
| 254 |
+
"loss": 0.3381,
|
| 255 |
+
"step": 400
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.21,
|
| 259 |
+
"learning_rate": 4.955928005659792e-05,
|
| 260 |
+
"loss": 0.3234,
|
| 261 |
+
"step": 410
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.22,
|
| 265 |
+
"learning_rate": 4.951805305450422e-05,
|
| 266 |
+
"loss": 0.3345,
|
| 267 |
+
"step": 420
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.22,
|
| 271 |
+
"learning_rate": 4.947500172346016e-05,
|
| 272 |
+
"loss": 0.317,
|
| 273 |
+
"step": 430
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.23,
|
| 277 |
+
"learning_rate": 4.9430129266811e-05,
|
| 278 |
+
"loss": 0.3306,
|
| 279 |
+
"step": 440
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.23,
|
| 283 |
+
"learning_rate": 4.9383439023407585e-05,
|
| 284 |
+
"loss": 0.3393,
|
| 285 |
+
"step": 450
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.24,
|
| 289 |
+
"learning_rate": 4.933493446735784e-05,
|
| 290 |
+
"loss": 0.3143,
|
| 291 |
+
"step": 460
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.25,
|
| 295 |
+
"learning_rate": 4.928461920776832e-05,
|
| 296 |
+
"loss": 0.3322,
|
| 297 |
+
"step": 470
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.25,
|
| 301 |
+
"learning_rate": 4.923249698847564e-05,
|
| 302 |
+
"loss": 0.2923,
|
| 303 |
+
"step": 480
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.26,
|
| 307 |
+
"learning_rate": 4.91785716877679e-05,
|
| 308 |
+
"loss": 0.3197,
|
| 309 |
+
"step": 490
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.26,
|
| 313 |
+
"learning_rate": 4.912284731809614e-05,
|
| 314 |
+
"loss": 0.313,
|
| 315 |
+
"step": 500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.26,
|
| 319 |
+
"eval_loss": 0.5063315629959106,
|
| 320 |
+
"eval_runtime": 105.7257,
|
| 321 |
+
"eval_samples_per_second": 8.059,
|
| 322 |
+
"eval_steps_per_second": 2.015,
|
| 323 |
+
"step": 500
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.27,
|
| 327 |
+
"learning_rate": 4.906532802577575e-05,
|
| 328 |
+
"loss": 0.3151,
|
| 329 |
+
"step": 510
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.27,
|
| 333 |
+
"learning_rate": 4.9006018090677974e-05,
|
| 334 |
+
"loss": 0.3121,
|
| 335 |
+
"step": 520
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.28,
|
| 339 |
+
"learning_rate": 4.8944921925911444e-05,
|
| 340 |
+
"loss": 0.3254,
|
| 341 |
+
"step": 530
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 0.28,
|
| 345 |
+
"learning_rate": 4.888204407749382e-05,
|
| 346 |
+
"loss": 0.3487,
|
| 347 |
+
"step": 540
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.29,
|
| 351 |
+
"learning_rate": 4.881738922401353e-05,
|
| 352 |
+
"loss": 0.3261,
|
| 353 |
+
"step": 550
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.29,
|
| 357 |
+
"learning_rate": 4.8750962176281635e-05,
|
| 358 |
+
"loss": 0.334,
|
| 359 |
+
"step": 560
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.3,
|
| 363 |
+
"learning_rate": 4.868276787697389e-05,
|
| 364 |
+
"loss": 0.3191,
|
| 365 |
+
"step": 570
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.3,
|
| 369 |
+
"learning_rate": 4.861281140026296e-05,
|
| 370 |
+
"loss": 0.3118,
|
| 371 |
+
"step": 580
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.31,
|
| 375 |
+
"learning_rate": 4.854109795144084e-05,
|
| 376 |
+
"loss": 0.3249,
|
| 377 |
+
"step": 590
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.31,
|
| 381 |
+
"learning_rate": 4.8467632866531596e-05,
|
| 382 |
+
"loss": 0.3095,
|
| 383 |
+
"step": 600
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.32,
|
| 387 |
+
"learning_rate": 4.8392421611894275e-05,
|
| 388 |
+
"loss": 0.3334,
|
| 389 |
+
"step": 610
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.32,
|
| 393 |
+
"learning_rate": 4.83154697838162e-05,
|
| 394 |
+
"loss": 0.3193,
|
| 395 |
+
"step": 620
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.33,
|
| 399 |
+
"learning_rate": 4.8236783108096514e-05,
|
| 400 |
+
"loss": 0.297,
|
| 401 |
+
"step": 630
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.33,
|
| 405 |
+
"learning_rate": 4.815636743962022e-05,
|
| 406 |
+
"loss": 0.3232,
|
| 407 |
+
"step": 640
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.34,
|
| 411 |
+
"learning_rate": 4.8074228761922444e-05,
|
| 412 |
+
"loss": 0.3348,
|
| 413 |
+
"step": 650
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.34,
|
| 417 |
+
"learning_rate": 4.799037318674329e-05,
|
| 418 |
+
"loss": 0.3401,
|
| 419 |
+
"step": 660
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.35,
|
| 423 |
+
"learning_rate": 4.7904806953573e-05,
|
| 424 |
+
"loss": 0.3299,
|
| 425 |
+
"step": 670
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.35,
|
| 429 |
+
"learning_rate": 4.781753642918778e-05,
|
| 430 |
+
"loss": 0.3152,
|
| 431 |
+
"step": 680
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.36,
|
| 435 |
+
"learning_rate": 4.772856810717599e-05,
|
| 436 |
+
"loss": 0.3104,
|
| 437 |
+
"step": 690
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.37,
|
| 441 |
+
"learning_rate": 4.763790860745502e-05,
|
| 442 |
+
"loss": 0.3331,
|
| 443 |
+
"step": 700
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.37,
|
| 447 |
+
"learning_rate": 4.7545564675778677e-05,
|
| 448 |
+
"loss": 0.332,
|
| 449 |
+
"step": 710
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.38,
|
| 453 |
+
"learning_rate": 4.745154318323528e-05,
|
| 454 |
+
"loss": 0.3318,
|
| 455 |
+
"step": 720
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 0.38,
|
| 459 |
+
"learning_rate": 4.7355851125736394e-05,
|
| 460 |
+
"loss": 0.3166,
|
| 461 |
+
"step": 730
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 0.39,
|
| 465 |
+
"learning_rate": 4.725849562349627e-05,
|
| 466 |
+
"loss": 0.3055,
|
| 467 |
+
"step": 740
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.39,
|
| 471 |
+
"learning_rate": 4.715948392050206e-05,
|
| 472 |
+
"loss": 0.3213,
|
| 473 |
+
"step": 750
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.4,
|
| 477 |
+
"learning_rate": 4.7058823383974794e-05,
|
| 478 |
+
"loss": 0.315,
|
| 479 |
+
"step": 760
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.4,
|
| 483 |
+
"learning_rate": 4.6956521503821215e-05,
|
| 484 |
+
"loss": 0.3525,
|
| 485 |
+
"step": 770
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.41,
|
| 489 |
+
"learning_rate": 4.685258589207648e-05,
|
| 490 |
+
"loss": 0.3089,
|
| 491 |
+
"step": 780
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.41,
|
| 495 |
+
"learning_rate": 4.6747024282337735e-05,
|
| 496 |
+
"loss": 0.3047,
|
| 497 |
+
"step": 790
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.42,
|
| 501 |
+
"learning_rate": 4.6639844529188734e-05,
|
| 502 |
+
"loss": 0.3192,
|
| 503 |
+
"step": 800
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.42,
|
| 507 |
+
"learning_rate": 4.653105460761533e-05,
|
| 508 |
+
"loss": 0.319,
|
| 509 |
+
"step": 810
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.43,
|
| 513 |
+
"learning_rate": 4.642066261241212e-05,
|
| 514 |
+
"loss": 0.3179,
|
| 515 |
+
"step": 820
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.43,
|
| 519 |
+
"learning_rate": 4.630867675758013e-05,
|
| 520 |
+
"loss": 0.3061,
|
| 521 |
+
"step": 830
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.44,
|
| 525 |
+
"learning_rate": 4.61951053757156e-05,
|
| 526 |
+
"loss": 0.3123,
|
| 527 |
+
"step": 840
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.44,
|
| 531 |
+
"learning_rate": 4.6079956917390024e-05,
|
| 532 |
+
"loss": 0.2952,
|
| 533 |
+
"step": 850
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.0,
|
| 537 |
+
"learning_rate": 4.5963239950521306e-05,
|
| 538 |
+
"loss": 0.2996,
|
| 539 |
+
"step": 860
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.01,
|
| 543 |
+
"learning_rate": 4.5844963159736303e-05,
|
| 544 |
+
"loss": 0.285,
|
| 545 |
+
"step": 870
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.01,
|
| 549 |
+
"learning_rate": 4.572513534572457e-05,
|
| 550 |
+
"loss": 0.2925,
|
| 551 |
+
"step": 880
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 1.02,
|
| 555 |
+
"learning_rate": 4.560376542458354e-05,
|
| 556 |
+
"loss": 0.2836,
|
| 557 |
+
"step": 890
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 1.02,
|
| 561 |
+
"learning_rate": 4.5480862427155134e-05,
|
| 562 |
+
"loss": 0.2824,
|
| 563 |
+
"step": 900
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.03,
|
| 567 |
+
"learning_rate": 4.535643549835373e-05,
|
| 568 |
+
"loss": 0.2814,
|
| 569 |
+
"step": 910
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.03,
|
| 573 |
+
"learning_rate": 4.5230493896485774e-05,
|
| 574 |
+
"loss": 0.2838,
|
| 575 |
+
"step": 920
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.04,
|
| 579 |
+
"learning_rate": 4.5103046992560855e-05,
|
| 580 |
+
"loss": 0.2802,
|
| 581 |
+
"step": 930
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.04,
|
| 585 |
+
"learning_rate": 4.4974104269594444e-05,
|
| 586 |
+
"loss": 0.3026,
|
| 587 |
+
"step": 940
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.05,
|
| 591 |
+
"learning_rate": 4.484367532190228e-05,
|
| 592 |
+
"loss": 0.2613,
|
| 593 |
+
"step": 950
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.05,
|
| 597 |
+
"learning_rate": 4.47117698543865e-05,
|
| 598 |
+
"loss": 0.276,
|
| 599 |
+
"step": 960
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 1.06,
|
| 603 |
+
"learning_rate": 4.457839768181349e-05,
|
| 604 |
+
"loss": 0.2865,
|
| 605 |
+
"step": 970
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.06,
|
| 609 |
+
"learning_rate": 4.444356872808362e-05,
|
| 610 |
+
"loss": 0.2705,
|
| 611 |
+
"step": 980
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.07,
|
| 615 |
+
"learning_rate": 4.43072930254928e-05,
|
| 616 |
+
"loss": 0.2942,
|
| 617 |
+
"step": 990
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 1.07,
|
| 621 |
+
"learning_rate": 4.4169580713986037e-05,
|
| 622 |
+
"loss": 0.279,
|
| 623 |
+
"step": 1000
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 1.07,
|
| 627 |
+
"eval_loss": 0.48916903138160706,
|
| 628 |
+
"eval_runtime": 106.4721,
|
| 629 |
+
"eval_samples_per_second": 8.002,
|
| 630 |
+
"eval_steps_per_second": 2.001,
|
| 631 |
+
"step": 1000
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 1.08,
|
| 635 |
+
"learning_rate": 4.4030442040402915e-05,
|
| 636 |
+
"loss": 0.2714,
|
| 637 |
+
"step": 1010
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 1.08,
|
| 641 |
+
"learning_rate": 4.388988735771518e-05,
|
| 642 |
+
"loss": 0.2521,
|
| 643 |
+
"step": 1020
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 1.09,
|
| 647 |
+
"learning_rate": 4.374792712425637e-05,
|
| 648 |
+
"loss": 0.2797,
|
| 649 |
+
"step": 1030
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 1.09,
|
| 653 |
+
"learning_rate": 4.360457190294366e-05,
|
| 654 |
+
"loss": 0.2666,
|
| 655 |
+
"step": 1040
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 1.1,
|
| 659 |
+
"learning_rate": 4.345983236049189e-05,
|
| 660 |
+
"loss": 0.2916,
|
| 661 |
+
"step": 1050
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.1,
|
| 665 |
+
"learning_rate": 4.33137192666199e-05,
|
| 666 |
+
"loss": 0.2758,
|
| 667 |
+
"step": 1060
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.11,
|
| 671 |
+
"learning_rate": 4.3166243493249136e-05,
|
| 672 |
+
"loss": 0.2632,
|
| 673 |
+
"step": 1070
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 1.12,
|
| 677 |
+
"learning_rate": 4.301741601369475e-05,
|
| 678 |
+
"loss": 0.2913,
|
| 679 |
+
"step": 1080
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 1.12,
|
| 683 |
+
"learning_rate": 4.286724790184906e-05,
|
| 684 |
+
"loss": 0.2753,
|
| 685 |
+
"step": 1090
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 1.13,
|
| 689 |
+
"learning_rate": 4.27157503313576e-05,
|
| 690 |
+
"loss": 0.2565,
|
| 691 |
+
"step": 1100
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 1.13,
|
| 695 |
+
"learning_rate": 4.256293457478769e-05,
|
| 696 |
+
"loss": 0.2745,
|
| 697 |
+
"step": 1110
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 1.14,
|
| 701 |
+
"learning_rate": 4.24088120027897e-05,
|
| 702 |
+
"loss": 0.2663,
|
| 703 |
+
"step": 1120
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.14,
|
| 707 |
+
"learning_rate": 4.2253394083250946e-05,
|
| 708 |
+
"loss": 0.2836,
|
| 709 |
+
"step": 1130
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.15,
|
| 713 |
+
"learning_rate": 4.209669238044245e-05,
|
| 714 |
+
"loss": 0.2894,
|
| 715 |
+
"step": 1140
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 1.15,
|
| 719 |
+
"learning_rate": 4.19387185541584e-05,
|
| 720 |
+
"loss": 0.2705,
|
| 721 |
+
"step": 1150
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 1.16,
|
| 725 |
+
"learning_rate": 4.1779484358848644e-05,
|
| 726 |
+
"loss": 0.275,
|
| 727 |
+
"step": 1160
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 1.16,
|
| 731 |
+
"learning_rate": 4.161900164274403e-05,
|
| 732 |
+
"loss": 0.2566,
|
| 733 |
+
"step": 1170
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 1.17,
|
| 737 |
+
"learning_rate": 4.145728234697479e-05,
|
| 738 |
+
"loss": 0.2475,
|
| 739 |
+
"step": 1180
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 1.17,
|
| 743 |
+
"learning_rate": 4.12943385046821e-05,
|
| 744 |
+
"loss": 0.2853,
|
| 745 |
+
"step": 1190
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.18,
|
| 749 |
+
"learning_rate": 4.113018224012262e-05,
|
| 750 |
+
"loss": 0.2749,
|
| 751 |
+
"step": 1200
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.18,
|
| 755 |
+
"learning_rate": 4.0964825767766465e-05,
|
| 756 |
+
"loss": 0.2693,
|
| 757 |
+
"step": 1210
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 1.19,
|
| 761 |
+
"learning_rate": 4.079828139138827e-05,
|
| 762 |
+
"loss": 0.2938,
|
| 763 |
+
"step": 1220
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 1.19,
|
| 767 |
+
"learning_rate": 4.063056150315177e-05,
|
| 768 |
+
"loss": 0.2793,
|
| 769 |
+
"step": 1230
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 1.2,
|
| 773 |
+
"learning_rate": 4.046167858268766e-05,
|
| 774 |
+
"loss": 0.2647,
|
| 775 |
+
"step": 1240
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 1.2,
|
| 779 |
+
"learning_rate": 4.0291645196165026e-05,
|
| 780 |
+
"loss": 0.2764,
|
| 781 |
+
"step": 1250
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 1.21,
|
| 785 |
+
"learning_rate": 4.012047399535642e-05,
|
| 786 |
+
"loss": 0.2802,
|
| 787 |
+
"step": 1260
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.21,
|
| 791 |
+
"learning_rate": 3.9948177716696324e-05,
|
| 792 |
+
"loss": 0.278,
|
| 793 |
+
"step": 1270
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.22,
|
| 797 |
+
"learning_rate": 3.977476918033357e-05,
|
| 798 |
+
"loss": 0.275,
|
| 799 |
+
"step": 1280
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 1.22,
|
| 803 |
+
"learning_rate": 3.960026128917741e-05,
|
| 804 |
+
"loss": 0.2548,
|
| 805 |
+
"step": 1290
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 1.23,
|
| 809 |
+
"learning_rate": 3.942466702793738e-05,
|
| 810 |
+
"loss": 0.2629,
|
| 811 |
+
"step": 1300
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 1.24,
|
| 815 |
+
"learning_rate": 3.924799946215723e-05,
|
| 816 |
+
"loss": 0.2776,
|
| 817 |
+
"step": 1310
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 1.24,
|
| 821 |
+
"learning_rate": 3.9070271737242656e-05,
|
| 822 |
+
"loss": 0.2868,
|
| 823 |
+
"step": 1320
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 1.25,
|
| 827 |
+
"learning_rate": 3.889149707748327e-05,
|
| 828 |
+
"loss": 0.2874,
|
| 829 |
+
"step": 1330
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.25,
|
| 833 |
+
"learning_rate": 3.8711688785068555e-05,
|
| 834 |
+
"loss": 0.2624,
|
| 835 |
+
"step": 1340
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.26,
|
| 839 |
+
"learning_rate": 3.853086023909808e-05,
|
| 840 |
+
"loss": 0.2674,
|
| 841 |
+
"step": 1350
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 1.26,
|
| 845 |
+
"learning_rate": 3.8349024894586014e-05,
|
| 846 |
+
"loss": 0.2613,
|
| 847 |
+
"step": 1360
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.27,
|
| 851 |
+
"learning_rate": 3.816619628146e-05,
|
| 852 |
+
"loss": 0.2559,
|
| 853 |
+
"step": 1370
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 1.27,
|
| 857 |
+
"learning_rate": 3.798238800355436e-05,
|
| 858 |
+
"loss": 0.2713,
|
| 859 |
+
"step": 1380
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 1.28,
|
| 863 |
+
"learning_rate": 3.77976137375979e-05,
|
| 864 |
+
"loss": 0.2493,
|
| 865 |
+
"step": 1390
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 1.28,
|
| 869 |
+
"learning_rate": 3.761188723219628e-05,
|
| 870 |
+
"loss": 0.2425,
|
| 871 |
+
"step": 1400
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.29,
|
| 875 |
+
"learning_rate": 3.742522230680896e-05,
|
| 876 |
+
"loss": 0.2541,
|
| 877 |
+
"step": 1410
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.29,
|
| 881 |
+
"learning_rate": 3.7237632850720995e-05,
|
| 882 |
+
"loss": 0.278,
|
| 883 |
+
"step": 1420
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 1.3,
|
| 887 |
+
"learning_rate": 3.70491328220095e-05,
|
| 888 |
+
"loss": 0.2362,
|
| 889 |
+
"step": 1430
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 1.3,
|
| 893 |
+
"learning_rate": 3.685973624650511e-05,
|
| 894 |
+
"loss": 0.255,
|
| 895 |
+
"step": 1440
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 1.31,
|
| 899 |
+
"learning_rate": 3.6669457216748326e-05,
|
| 900 |
+
"loss": 0.2668,
|
| 901 |
+
"step": 1450
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 1.31,
|
| 905 |
+
"learning_rate": 3.647830989094095e-05,
|
| 906 |
+
"loss": 0.2416,
|
| 907 |
+
"step": 1460
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 1.32,
|
| 911 |
+
"learning_rate": 3.6286308491892565e-05,
|
| 912 |
+
"loss": 0.2492,
|
| 913 |
+
"step": 1470
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.32,
|
| 917 |
+
"learning_rate": 3.609346730596229e-05,
|
| 918 |
+
"loss": 0.2546,
|
| 919 |
+
"step": 1480
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.33,
|
| 923 |
+
"learning_rate": 3.589980068199575e-05,
|
| 924 |
+
"loss": 0.2502,
|
| 925 |
+
"step": 1490
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 1.33,
|
| 929 |
+
"learning_rate": 3.570532303025742e-05,
|
| 930 |
+
"loss": 0.2584,
|
| 931 |
+
"step": 1500
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 1.33,
|
| 935 |
+
"eval_loss": 0.4950372576713562,
|
| 936 |
+
"eval_runtime": 105.7937,
|
| 937 |
+
"eval_samples_per_second": 8.053,
|
| 938 |
+
"eval_steps_per_second": 2.013,
|
| 939 |
+
"step": 1500
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 1.34,
|
| 943 |
+
"learning_rate": 3.551004882135839e-05,
|
| 944 |
+
"loss": 0.2638,
|
| 945 |
+
"step": 1510
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 1.34,
|
| 949 |
+
"learning_rate": 3.531399258517962e-05,
|
| 950 |
+
"loss": 0.2383,
|
| 951 |
+
"step": 1520
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 1.35,
|
| 955 |
+
"learning_rate": 3.511716890979084e-05,
|
| 956 |
+
"loss": 0.2677,
|
| 957 |
+
"step": 1530
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 1.36,
|
| 961 |
+
"learning_rate": 3.4919592440365085e-05,
|
| 962 |
+
"loss": 0.255,
|
| 963 |
+
"step": 1540
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 1.36,
|
| 967 |
+
"learning_rate": 3.472127787808893e-05,
|
| 968 |
+
"loss": 0.2474,
|
| 969 |
+
"step": 1550
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.37,
|
| 973 |
+
"learning_rate": 3.452223997906871e-05,
|
| 974 |
+
"loss": 0.2474,
|
| 975 |
+
"step": 1560
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.37,
|
| 979 |
+
"learning_rate": 3.432249355323244e-05,
|
| 980 |
+
"loss": 0.2632,
|
| 981 |
+
"step": 1570
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 1.38,
|
| 985 |
+
"learning_rate": 3.412205346322794e-05,
|
| 986 |
+
"loss": 0.2338,
|
| 987 |
+
"step": 1580
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 1.38,
|
| 991 |
+
"learning_rate": 3.392093462331688e-05,
|
| 992 |
+
"loss": 0.2553,
|
| 993 |
+
"step": 1590
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 1.39,
|
| 997 |
+
"learning_rate": 3.371915199826506e-05,
|
| 998 |
+
"loss": 0.2519,
|
| 999 |
+
"step": 1600
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 1.39,
|
| 1003 |
+
"learning_rate": 3.3516720602228945e-05,
|
| 1004 |
+
"loss": 0.2549,
|
| 1005 |
+
"step": 1610
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 1.4,
|
| 1009 |
+
"learning_rate": 3.331365549763848e-05,
|
| 1010 |
+
"loss": 0.2802,
|
| 1011 |
+
"step": 1620
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.4,
|
| 1015 |
+
"learning_rate": 3.310997179407631e-05,
|
| 1016 |
+
"loss": 0.2734,
|
| 1017 |
+
"step": 1630
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.41,
|
| 1021 |
+
"learning_rate": 3.2905684647153536e-05,
|
| 1022 |
+
"loss": 0.2609,
|
| 1023 |
+
"step": 1640
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 1.41,
|
| 1027 |
+
"learning_rate": 3.270080925738202e-05,
|
| 1028 |
+
"loss": 0.2383,
|
| 1029 |
+
"step": 1650
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 1.42,
|
| 1033 |
+
"learning_rate": 3.2495360869043354e-05,
|
| 1034 |
+
"loss": 0.2576,
|
| 1035 |
+
"step": 1660
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 1.42,
|
| 1039 |
+
"learning_rate": 3.2289354769054556e-05,
|
| 1040 |
+
"loss": 0.2305,
|
| 1041 |
+
"step": 1670
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 1.43,
|
| 1045 |
+
"learning_rate": 3.2082806285830645e-05,
|
| 1046 |
+
"loss": 0.2508,
|
| 1047 |
+
"step": 1680
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 1.43,
|
| 1051 |
+
"learning_rate": 3.187573078814402e-05,
|
| 1052 |
+
"loss": 0.2367,
|
| 1053 |
+
"step": 1690
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.44,
|
| 1057 |
+
"learning_rate": 3.166814368398098e-05,
|
| 1058 |
+
"loss": 0.2335,
|
| 1059 |
+
"step": 1700
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.44,
|
| 1063 |
+
"learning_rate": 3.146006041939522e-05,
|
| 1064 |
+
"loss": 0.2523,
|
| 1065 |
+
"step": 1710
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 1.45,
|
| 1069 |
+
"step": 1718,
|
| 1070 |
+
"total_flos": 3.091617473007452e+17,
|
| 1071 |
+
"train_loss": 0.305820442848905,
|
| 1072 |
+
"train_runtime": 6666.1209,
|
| 1073 |
+
"train_samples_per_second": 2.3,
|
| 1074 |
+
"train_steps_per_second": 0.575
|
| 1075 |
+
}
|
| 1076 |
+
],
|
| 1077 |
+
"logging_steps": 10,
|
| 1078 |
+
"max_steps": 3834,
|
| 1079 |
+
"num_train_epochs": 2,
|
| 1080 |
+
"save_steps": 500,
|
| 1081 |
+
"total_flos": 3.091617473007452e+17,
|
| 1082 |
+
"trial_name": null,
|
| 1083 |
+
"trial_params": null
|
| 1084 |
+
}
|