Model save
Browse files- README.md +58 -0
- all_results.json +8 -0
- generation_config.json +9 -0
- train_results.json +8 -0
- trainer_state.json +684 -0
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-Math-7B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: Qwen2.5-Math-7B-Instruct-SFT
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Qwen2.5-Math-7B-Instruct-SFT
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct).
|
| 15 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
+
|
| 17 |
+
## Quick start
|
| 18 |
+
|
| 19 |
+
```python
|
| 20 |
+
from transformers import pipeline
|
| 21 |
+
|
| 22 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 23 |
+
generator = pipeline("text-generation", model="edbeeching/Qwen2.5-Math-7B-Instruct-SFT", device="cuda")
|
| 24 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 25 |
+
print(output["generated_text"])
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
## Training procedure
|
| 29 |
+
|
| 30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/huggingface/huggingface/runs/ozgbj17k)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
This model was trained with SFT.
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.16.0
|
| 38 |
+
- Transformers: 4.50.0
|
| 39 |
+
- Pytorch: 2.5.1
|
| 40 |
+
- Datasets: 3.2.0
|
| 41 |
+
- Tokenizers: 0.21.0
|
| 42 |
+
|
| 43 |
+
## Citations
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
Cite TRL as:
|
| 48 |
+
|
| 49 |
+
```bibtex
|
| 50 |
+
@misc{vonwerra2022trl,
|
| 51 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 52 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
|
| 53 |
+
year = 2020,
|
| 54 |
+
journal = {GitHub repository},
|
| 55 |
+
publisher = {GitHub},
|
| 56 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 57 |
+
}
|
| 58 |
+
```
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 6.2367671592178156e+19,
|
| 3 |
+
"train_loss": 1.1144484827174477,
|
| 4 |
+
"train_runtime": 39508.3376,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 1.304,
|
| 7 |
+
"train_steps_per_second": 0.01
|
| 8 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645,
|
| 5 |
+
151643
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 151643,
|
| 8 |
+
"transformers_version": "4.50.0"
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 6.2367671592178156e+19,
|
| 3 |
+
"train_loss": 1.1144484827174477,
|
| 4 |
+
"train_runtime": 39508.3376,
|
| 5 |
+
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 1.304,
|
| 7 |
+
"train_steps_per_second": 0.01
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,684 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.983240223463687,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 402,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.037243947858473,
|
| 14 |
+
"grad_norm": 44.700423237162,
|
| 15 |
+
"learning_rate": 1.2195121951219514e-06,
|
| 16 |
+
"loss": 8.9389,
|
| 17 |
+
"num_tokens": 20900161.0,
|
| 18 |
+
"step": 5
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.074487895716946,
|
| 22 |
+
"grad_norm": 39.97441938804836,
|
| 23 |
+
"learning_rate": 2.4390243902439027e-06,
|
| 24 |
+
"loss": 8.6107,
|
| 25 |
+
"num_tokens": 41840347.0,
|
| 26 |
+
"step": 10
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.11173184357541899,
|
| 30 |
+
"grad_norm": 28.68948027128856,
|
| 31 |
+
"learning_rate": 3.6585365853658537e-06,
|
| 32 |
+
"loss": 6.8935,
|
| 33 |
+
"num_tokens": 62811867.0,
|
| 34 |
+
"step": 15
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.148975791433892,
|
| 38 |
+
"grad_norm": 11.393457880936973,
|
| 39 |
+
"learning_rate": 4.8780487804878055e-06,
|
| 40 |
+
"loss": 5.0942,
|
| 41 |
+
"num_tokens": 83733147.0,
|
| 42 |
+
"step": 20
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.186219739292365,
|
| 46 |
+
"grad_norm": 6.569246393996523,
|
| 47 |
+
"learning_rate": 6.0975609756097564e-06,
|
| 48 |
+
"loss": 4.2535,
|
| 49 |
+
"num_tokens": 104633209.0,
|
| 50 |
+
"step": 25
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.22346368715083798,
|
| 54 |
+
"grad_norm": 3.904749769413194,
|
| 55 |
+
"learning_rate": 7.317073170731707e-06,
|
| 56 |
+
"loss": 3.7968,
|
| 57 |
+
"num_tokens": 125472598.0,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.260707635009311,
|
| 62 |
+
"grad_norm": 2.378812176791007,
|
| 63 |
+
"learning_rate": 8.536585365853658e-06,
|
| 64 |
+
"loss": 3.3338,
|
| 65 |
+
"num_tokens": 146395759.0,
|
| 66 |
+
"step": 35
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.297951582867784,
|
| 70 |
+
"grad_norm": 17.248964649482218,
|
| 71 |
+
"learning_rate": 9.756097560975611e-06,
|
| 72 |
+
"loss": 2.7105,
|
| 73 |
+
"num_tokens": 167334938.0,
|
| 74 |
+
"step": 40
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.33519553072625696,
|
| 78 |
+
"grad_norm": 1.6088393318851981,
|
| 79 |
+
"learning_rate": 9.889196675900278e-06,
|
| 80 |
+
"loss": 2.0834,
|
| 81 |
+
"num_tokens": 188300024.0,
|
| 82 |
+
"step": 45
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.37243947858473,
|
| 86 |
+
"grad_norm": 1.0479372877130533,
|
| 87 |
+
"learning_rate": 9.750692520775623e-06,
|
| 88 |
+
"loss": 1.512,
|
| 89 |
+
"num_tokens": 209250087.0,
|
| 90 |
+
"step": 50
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.409683426443203,
|
| 94 |
+
"grad_norm": 0.5797721215381728,
|
| 95 |
+
"learning_rate": 9.61218836565097e-06,
|
| 96 |
+
"loss": 1.1791,
|
| 97 |
+
"num_tokens": 230103075.0,
|
| 98 |
+
"step": 55
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.44692737430167595,
|
| 102 |
+
"grad_norm": 0.40789177100348467,
|
| 103 |
+
"learning_rate": 9.473684210526315e-06,
|
| 104 |
+
"loss": 1.0089,
|
| 105 |
+
"num_tokens": 250974570.0,
|
| 106 |
+
"step": 60
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.48417132216014896,
|
| 110 |
+
"grad_norm": 0.35568228307746297,
|
| 111 |
+
"learning_rate": 9.335180055401662e-06,
|
| 112 |
+
"loss": 0.9109,
|
| 113 |
+
"num_tokens": 271920522.0,
|
| 114 |
+
"step": 65
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.521415270018622,
|
| 118 |
+
"grad_norm": 0.2773679085093437,
|
| 119 |
+
"learning_rate": 9.19667590027701e-06,
|
| 120 |
+
"loss": 0.8572,
|
| 121 |
+
"num_tokens": 292817720.0,
|
| 122 |
+
"step": 70
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.5586592178770949,
|
| 126 |
+
"grad_norm": 0.23151040916631538,
|
| 127 |
+
"learning_rate": 9.058171745152356e-06,
|
| 128 |
+
"loss": 0.8121,
|
| 129 |
+
"num_tokens": 313711263.0,
|
| 130 |
+
"step": 75
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.595903165735568,
|
| 134 |
+
"grad_norm": 0.21004592737808472,
|
| 135 |
+
"learning_rate": 8.919667590027701e-06,
|
| 136 |
+
"loss": 0.7738,
|
| 137 |
+
"num_tokens": 334628125.0,
|
| 138 |
+
"step": 80
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.633147113594041,
|
| 142 |
+
"grad_norm": 0.18493389037034969,
|
| 143 |
+
"learning_rate": 8.781163434903048e-06,
|
| 144 |
+
"loss": 0.7537,
|
| 145 |
+
"num_tokens": 355507604.0,
|
| 146 |
+
"step": 85
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.6703910614525139,
|
| 150 |
+
"grad_norm": 0.19478442065788568,
|
| 151 |
+
"learning_rate": 8.642659279778393e-06,
|
| 152 |
+
"loss": 0.7295,
|
| 153 |
+
"num_tokens": 376376000.0,
|
| 154 |
+
"step": 90
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.707635009310987,
|
| 158 |
+
"grad_norm": 0.17818497873491812,
|
| 159 |
+
"learning_rate": 8.50415512465374e-06,
|
| 160 |
+
"loss": 0.7044,
|
| 161 |
+
"num_tokens": 397347520.0,
|
| 162 |
+
"step": 95
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.74487895716946,
|
| 166 |
+
"grad_norm": 0.15661959846871895,
|
| 167 |
+
"learning_rate": 8.365650969529087e-06,
|
| 168 |
+
"loss": 0.6905,
|
| 169 |
+
"num_tokens": 418243978.0,
|
| 170 |
+
"step": 100
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.7821229050279329,
|
| 174 |
+
"grad_norm": 0.1583248766438081,
|
| 175 |
+
"learning_rate": 8.227146814404434e-06,
|
| 176 |
+
"loss": 0.678,
|
| 177 |
+
"num_tokens": 439124783.0,
|
| 178 |
+
"step": 105
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.819366852886406,
|
| 182 |
+
"grad_norm": 0.1385769107129147,
|
| 183 |
+
"learning_rate": 8.088642659279779e-06,
|
| 184 |
+
"loss": 0.6577,
|
| 185 |
+
"num_tokens": 460067060.0,
|
| 186 |
+
"step": 110
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.8566108007448789,
|
| 190 |
+
"grad_norm": 0.1495271309048296,
|
| 191 |
+
"learning_rate": 7.950138504155124e-06,
|
| 192 |
+
"loss": 0.657,
|
| 193 |
+
"num_tokens": 480973564.0,
|
| 194 |
+
"step": 115
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.8938547486033519,
|
| 198 |
+
"grad_norm": 0.14473840607744518,
|
| 199 |
+
"learning_rate": 7.811634349030471e-06,
|
| 200 |
+
"loss": 0.6384,
|
| 201 |
+
"num_tokens": 501920213.0,
|
| 202 |
+
"step": 120
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.931098696461825,
|
| 206 |
+
"grad_norm": 0.1422179408253768,
|
| 207 |
+
"learning_rate": 7.673130193905818e-06,
|
| 208 |
+
"loss": 0.6312,
|
| 209 |
+
"num_tokens": 522882452.0,
|
| 210 |
+
"step": 125
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.9683426443202979,
|
| 214 |
+
"grad_norm": 0.1385480000357401,
|
| 215 |
+
"learning_rate": 7.534626038781164e-06,
|
| 216 |
+
"loss": 0.6267,
|
| 217 |
+
"num_tokens": 543853972.0,
|
| 218 |
+
"step": 130
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.0,
|
| 222 |
+
"grad_norm": 0.11986499724240843,
|
| 223 |
+
"learning_rate": 7.396121883656511e-06,
|
| 224 |
+
"loss": 0.6186,
|
| 225 |
+
"num_tokens": 561623820.0,
|
| 226 |
+
"step": 135
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.037243947858473,
|
| 230 |
+
"grad_norm": 0.12711165190299312,
|
| 231 |
+
"learning_rate": 7.257617728531856e-06,
|
| 232 |
+
"loss": 0.6108,
|
| 233 |
+
"num_tokens": 582493384.0,
|
| 234 |
+
"step": 140
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.074487895716946,
|
| 238 |
+
"grad_norm": 0.13843436006681253,
|
| 239 |
+
"learning_rate": 7.119113573407203e-06,
|
| 240 |
+
"loss": 0.6071,
|
| 241 |
+
"num_tokens": 603371436.0,
|
| 242 |
+
"step": 145
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.111731843575419,
|
| 246 |
+
"grad_norm": 0.12877141358698244,
|
| 247 |
+
"learning_rate": 6.980609418282549e-06,
|
| 248 |
+
"loss": 0.5969,
|
| 249 |
+
"num_tokens": 624211040.0,
|
| 250 |
+
"step": 150
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.148975791433892,
|
| 254 |
+
"grad_norm": 0.11172803837159029,
|
| 255 |
+
"learning_rate": 6.842105263157896e-06,
|
| 256 |
+
"loss": 0.5961,
|
| 257 |
+
"num_tokens": 645080464.0,
|
| 258 |
+
"step": 155
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.186219739292365,
|
| 262 |
+
"grad_norm": 0.12257878721308095,
|
| 263 |
+
"learning_rate": 6.703601108033242e-06,
|
| 264 |
+
"loss": 0.5961,
|
| 265 |
+
"num_tokens": 665984359.0,
|
| 266 |
+
"step": 160
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.223463687150838,
|
| 270 |
+
"grad_norm": 0.12182656514914046,
|
| 271 |
+
"learning_rate": 6.565096952908588e-06,
|
| 272 |
+
"loss": 0.5903,
|
| 273 |
+
"num_tokens": 686922696.0,
|
| 274 |
+
"step": 165
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.260707635009311,
|
| 278 |
+
"grad_norm": 0.11249855500170149,
|
| 279 |
+
"learning_rate": 6.426592797783934e-06,
|
| 280 |
+
"loss": 0.5844,
|
| 281 |
+
"num_tokens": 707833603.0,
|
| 282 |
+
"step": 170
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.2979515828677841,
|
| 286 |
+
"grad_norm": 0.12449747176048374,
|
| 287 |
+
"learning_rate": 6.2880886426592805e-06,
|
| 288 |
+
"loss": 0.5803,
|
| 289 |
+
"num_tokens": 728796956.0,
|
| 290 |
+
"step": 175
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.3351955307262569,
|
| 294 |
+
"grad_norm": 0.12431311388507522,
|
| 295 |
+
"learning_rate": 6.1495844875346266e-06,
|
| 296 |
+
"loss": 0.5769,
|
| 297 |
+
"num_tokens": 749639247.0,
|
| 298 |
+
"step": 180
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.37243947858473,
|
| 302 |
+
"grad_norm": 0.11884858911346256,
|
| 303 |
+
"learning_rate": 6.011080332409973e-06,
|
| 304 |
+
"loss": 0.5769,
|
| 305 |
+
"num_tokens": 770548626.0,
|
| 306 |
+
"step": 185
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.409683426443203,
|
| 310 |
+
"grad_norm": 0.12315392451802569,
|
| 311 |
+
"learning_rate": 5.8725761772853194e-06,
|
| 312 |
+
"loss": 0.5738,
|
| 313 |
+
"num_tokens": 791439887.0,
|
| 314 |
+
"step": 190
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.446927374301676,
|
| 318 |
+
"grad_norm": 0.14923588588117534,
|
| 319 |
+
"learning_rate": 5.734072022160665e-06,
|
| 320 |
+
"loss": 0.5666,
|
| 321 |
+
"num_tokens": 812411407.0,
|
| 322 |
+
"step": 195
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.484171322160149,
|
| 326 |
+
"grad_norm": 0.12273387220504116,
|
| 327 |
+
"learning_rate": 5.5955678670360115e-06,
|
| 328 |
+
"loss": 0.5685,
|
| 329 |
+
"num_tokens": 833361095.0,
|
| 330 |
+
"step": 200
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.5214152700186219,
|
| 334 |
+
"grad_norm": 0.11370568104002803,
|
| 335 |
+
"learning_rate": 5.4570637119113575e-06,
|
| 336 |
+
"loss": 0.5675,
|
| 337 |
+
"num_tokens": 854291659.0,
|
| 338 |
+
"step": 205
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.558659217877095,
|
| 342 |
+
"grad_norm": 0.11804662768074886,
|
| 343 |
+
"learning_rate": 5.318559556786704e-06,
|
| 344 |
+
"loss": 0.5638,
|
| 345 |
+
"num_tokens": 875218064.0,
|
| 346 |
+
"step": 210
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.595903165735568,
|
| 350 |
+
"grad_norm": 0.11044864275419868,
|
| 351 |
+
"learning_rate": 5.180055401662051e-06,
|
| 352 |
+
"loss": 0.5625,
|
| 353 |
+
"num_tokens": 896144111.0,
|
| 354 |
+
"step": 215
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.633147113594041,
|
| 358 |
+
"grad_norm": 0.1185174239784444,
|
| 359 |
+
"learning_rate": 5.041551246537396e-06,
|
| 360 |
+
"loss": 0.564,
|
| 361 |
+
"num_tokens": 917103979.0,
|
| 362 |
+
"step": 220
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.670391061452514,
|
| 366 |
+
"grad_norm": 0.12026499691941232,
|
| 367 |
+
"learning_rate": 4.903047091412742e-06,
|
| 368 |
+
"loss": 0.5554,
|
| 369 |
+
"num_tokens": 938069583.0,
|
| 370 |
+
"step": 225
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.7076350093109869,
|
| 374 |
+
"grad_norm": 0.11487320551484248,
|
| 375 |
+
"learning_rate": 4.764542936288089e-06,
|
| 376 |
+
"loss": 0.5498,
|
| 377 |
+
"num_tokens": 958987689.0,
|
| 378 |
+
"step": 230
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.74487895716946,
|
| 382 |
+
"grad_norm": 0.121932717620048,
|
| 383 |
+
"learning_rate": 4.626038781163435e-06,
|
| 384 |
+
"loss": 0.558,
|
| 385 |
+
"num_tokens": 979951299.0,
|
| 386 |
+
"step": 235
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.7821229050279328,
|
| 390 |
+
"grad_norm": 0.11603410597547152,
|
| 391 |
+
"learning_rate": 4.487534626038781e-06,
|
| 392 |
+
"loss": 0.5568,
|
| 393 |
+
"num_tokens": 1000838678.0,
|
| 394 |
+
"step": 240
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.819366852886406,
|
| 398 |
+
"grad_norm": 0.10726484051752529,
|
| 399 |
+
"learning_rate": 4.349030470914128e-06,
|
| 400 |
+
"loss": 0.5485,
|
| 401 |
+
"num_tokens": 1021747806.0,
|
| 402 |
+
"step": 245
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.856610800744879,
|
| 406 |
+
"grad_norm": 0.13127354938696664,
|
| 407 |
+
"learning_rate": 4.210526315789474e-06,
|
| 408 |
+
"loss": 0.551,
|
| 409 |
+
"num_tokens": 1042682828.0,
|
| 410 |
+
"step": 250
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.893854748603352,
|
| 414 |
+
"grad_norm": 0.13042928050538638,
|
| 415 |
+
"learning_rate": 4.07202216066482e-06,
|
| 416 |
+
"loss": 0.5482,
|
| 417 |
+
"num_tokens": 1063637713.0,
|
| 418 |
+
"step": 255
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.931098696461825,
|
| 422 |
+
"grad_norm": 0.10378281749835497,
|
| 423 |
+
"learning_rate": 3.933518005540167e-06,
|
| 424 |
+
"loss": 0.5492,
|
| 425 |
+
"num_tokens": 1084551621.0,
|
| 426 |
+
"step": 260
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.9683426443202978,
|
| 430 |
+
"grad_norm": 0.11405027703876851,
|
| 431 |
+
"learning_rate": 3.7950138504155126e-06,
|
| 432 |
+
"loss": 0.5432,
|
| 433 |
+
"num_tokens": 1105456616.0,
|
| 434 |
+
"step": 265
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.0,
|
| 438 |
+
"grad_norm": 0.1188033142047116,
|
| 439 |
+
"learning_rate": 3.656509695290859e-06,
|
| 440 |
+
"loss": 0.5457,
|
| 441 |
+
"num_tokens": 1123247640.0,
|
| 442 |
+
"step": 270
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 2.037243947858473,
|
| 446 |
+
"grad_norm": 0.11511290129075778,
|
| 447 |
+
"learning_rate": 3.5180055401662054e-06,
|
| 448 |
+
"loss": 0.5416,
|
| 449 |
+
"num_tokens": 1144178840.0,
|
| 450 |
+
"step": 275
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.074487895716946,
|
| 454 |
+
"grad_norm": 0.11812786472280946,
|
| 455 |
+
"learning_rate": 3.3795013850415515e-06,
|
| 456 |
+
"loss": 0.5418,
|
| 457 |
+
"num_tokens": 1165088860.0,
|
| 458 |
+
"step": 280
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.111731843575419,
|
| 462 |
+
"grad_norm": 0.10270714280099584,
|
| 463 |
+
"learning_rate": 3.240997229916898e-06,
|
| 464 |
+
"loss": 0.5409,
|
| 465 |
+
"num_tokens": 1185985413.0,
|
| 466 |
+
"step": 285
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 2.148975791433892,
|
| 470 |
+
"grad_norm": 0.1096828174375488,
|
| 471 |
+
"learning_rate": 3.102493074792244e-06,
|
| 472 |
+
"loss": 0.5389,
|
| 473 |
+
"num_tokens": 1206900439.0,
|
| 474 |
+
"step": 290
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.186219739292365,
|
| 478 |
+
"grad_norm": 0.12117958971385849,
|
| 479 |
+
"learning_rate": 2.9639889196675903e-06,
|
| 480 |
+
"loss": 0.5373,
|
| 481 |
+
"num_tokens": 1227788909.0,
|
| 482 |
+
"step": 295
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.223463687150838,
|
| 486 |
+
"grad_norm": 0.10303636082477868,
|
| 487 |
+
"learning_rate": 2.8254847645429368e-06,
|
| 488 |
+
"loss": 0.5422,
|
| 489 |
+
"num_tokens": 1248631579.0,
|
| 490 |
+
"step": 300
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 2.260707635009311,
|
| 494 |
+
"grad_norm": 0.1055723015177993,
|
| 495 |
+
"learning_rate": 2.686980609418283e-06,
|
| 496 |
+
"loss": 0.5338,
|
| 497 |
+
"num_tokens": 1269568695.0,
|
| 498 |
+
"step": 305
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 2.297951582867784,
|
| 502 |
+
"grad_norm": 0.09853558468957078,
|
| 503 |
+
"learning_rate": 2.5484764542936292e-06,
|
| 504 |
+
"loss": 0.5331,
|
| 505 |
+
"num_tokens": 1290448726.0,
|
| 506 |
+
"step": 310
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.335195530726257,
|
| 510 |
+
"grad_norm": 0.09780439525165775,
|
| 511 |
+
"learning_rate": 2.4099722991689752e-06,
|
| 512 |
+
"loss": 0.5373,
|
| 513 |
+
"num_tokens": 1311374206.0,
|
| 514 |
+
"step": 315
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 2.37243947858473,
|
| 518 |
+
"grad_norm": 0.11343316486691782,
|
| 519 |
+
"learning_rate": 2.2714681440443217e-06,
|
| 520 |
+
"loss": 0.5324,
|
| 521 |
+
"num_tokens": 1332316908.0,
|
| 522 |
+
"step": 320
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.4096834264432028,
|
| 526 |
+
"grad_norm": 0.09861823968974112,
|
| 527 |
+
"learning_rate": 2.1329639889196677e-06,
|
| 528 |
+
"loss": 0.5291,
|
| 529 |
+
"num_tokens": 1353285538.0,
|
| 530 |
+
"step": 325
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 2.446927374301676,
|
| 534 |
+
"grad_norm": 0.09761284938648966,
|
| 535 |
+
"learning_rate": 1.994459833795014e-06,
|
| 536 |
+
"loss": 0.5284,
|
| 537 |
+
"num_tokens": 1374171123.0,
|
| 538 |
+
"step": 330
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 2.484171322160149,
|
| 542 |
+
"grad_norm": 0.10068212333923239,
|
| 543 |
+
"learning_rate": 1.8559556786703603e-06,
|
| 544 |
+
"loss": 0.5315,
|
| 545 |
+
"num_tokens": 1395101851.0,
|
| 546 |
+
"step": 335
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 2.521415270018622,
|
| 550 |
+
"grad_norm": 0.09595198002866547,
|
| 551 |
+
"learning_rate": 1.7174515235457066e-06,
|
| 552 |
+
"loss": 0.5274,
|
| 553 |
+
"num_tokens": 1416073371.0,
|
| 554 |
+
"step": 340
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 2.558659217877095,
|
| 558 |
+
"grad_norm": 0.09486136119692574,
|
| 559 |
+
"learning_rate": 1.5789473684210526e-06,
|
| 560 |
+
"loss": 0.5308,
|
| 561 |
+
"num_tokens": 1437018467.0,
|
| 562 |
+
"step": 345
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 2.5959031657355682,
|
| 566 |
+
"grad_norm": 0.09700270169515557,
|
| 567 |
+
"learning_rate": 1.4404432132963992e-06,
|
| 568 |
+
"loss": 0.5268,
|
| 569 |
+
"num_tokens": 1457919336.0,
|
| 570 |
+
"step": 350
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.633147113594041,
|
| 574 |
+
"grad_norm": 0.09888912058958187,
|
| 575 |
+
"learning_rate": 1.3019390581717452e-06,
|
| 576 |
+
"loss": 0.5296,
|
| 577 |
+
"num_tokens": 1478880064.0,
|
| 578 |
+
"step": 355
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.6703910614525137,
|
| 582 |
+
"grad_norm": 0.09588099838616412,
|
| 583 |
+
"learning_rate": 1.1634349030470915e-06,
|
| 584 |
+
"loss": 0.5336,
|
| 585 |
+
"num_tokens": 1499763351.0,
|
| 586 |
+
"step": 360
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 2.707635009310987,
|
| 590 |
+
"grad_norm": 0.08937394796037,
|
| 591 |
+
"learning_rate": 1.024930747922438e-06,
|
| 592 |
+
"loss": 0.528,
|
| 593 |
+
"num_tokens": 1520641603.0,
|
| 594 |
+
"step": 365
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 2.74487895716946,
|
| 598 |
+
"grad_norm": 0.09490522714269171,
|
| 599 |
+
"learning_rate": 8.86426592797784e-07,
|
| 600 |
+
"loss": 0.5307,
|
| 601 |
+
"num_tokens": 1541584460.0,
|
| 602 |
+
"step": 370
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.782122905027933,
|
| 606 |
+
"grad_norm": 0.09709816809585911,
|
| 607 |
+
"learning_rate": 7.479224376731302e-07,
|
| 608 |
+
"loss": 0.5262,
|
| 609 |
+
"num_tokens": 1562543224.0,
|
| 610 |
+
"step": 375
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 2.819366852886406,
|
| 614 |
+
"grad_norm": 0.0908607538920962,
|
| 615 |
+
"learning_rate": 6.094182825484765e-07,
|
| 616 |
+
"loss": 0.5284,
|
| 617 |
+
"num_tokens": 1583428775.0,
|
| 618 |
+
"step": 380
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.856610800744879,
|
| 622 |
+
"grad_norm": 0.08729376484195411,
|
| 623 |
+
"learning_rate": 4.7091412742382274e-07,
|
| 624 |
+
"loss": 0.5311,
|
| 625 |
+
"num_tokens": 1604332118.0,
|
| 626 |
+
"step": 385
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.893854748603352,
|
| 630 |
+
"grad_norm": 0.08813530444241563,
|
| 631 |
+
"learning_rate": 3.32409972299169e-07,
|
| 632 |
+
"loss": 0.5274,
|
| 633 |
+
"num_tokens": 1625289686.0,
|
| 634 |
+
"step": 390
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.931098696461825,
|
| 638 |
+
"grad_norm": 0.08717195128913408,
|
| 639 |
+
"learning_rate": 1.9390581717451524e-07,
|
| 640 |
+
"loss": 0.5278,
|
| 641 |
+
"num_tokens": 1646192159.0,
|
| 642 |
+
"step": 395
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 2.968342644320298,
|
| 646 |
+
"grad_norm": 0.08486932600724212,
|
| 647 |
+
"learning_rate": 5.54016620498615e-08,
|
| 648 |
+
"loss": 0.5278,
|
| 649 |
+
"num_tokens": 1667121360.0,
|
| 650 |
+
"step": 400
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 2.983240223463687,
|
| 654 |
+
"num_tokens": 1675463706.0,
|
| 655 |
+
"step": 402,
|
| 656 |
+
"total_flos": 6.2367671592178156e+19,
|
| 657 |
+
"train_loss": 1.1144484827174477,
|
| 658 |
+
"train_runtime": 39508.3376,
|
| 659 |
+
"train_samples_per_second": 1.304,
|
| 660 |
+
"train_steps_per_second": 0.01
|
| 661 |
+
}
|
| 662 |
+
],
|
| 663 |
+
"logging_steps": 5,
|
| 664 |
+
"max_steps": 402,
|
| 665 |
+
"num_input_tokens_seen": 0,
|
| 666 |
+
"num_train_epochs": 3,
|
| 667 |
+
"save_steps": 500,
|
| 668 |
+
"stateful_callbacks": {
|
| 669 |
+
"TrainerControl": {
|
| 670 |
+
"args": {
|
| 671 |
+
"should_epoch_stop": false,
|
| 672 |
+
"should_evaluate": false,
|
| 673 |
+
"should_log": false,
|
| 674 |
+
"should_save": true,
|
| 675 |
+
"should_training_stop": true
|
| 676 |
+
},
|
| 677 |
+
"attributes": {}
|
| 678 |
+
}
|
| 679 |
+
},
|
| 680 |
+
"total_flos": 6.2367671592178156e+19,
|
| 681 |
+
"train_batch_size": 2,
|
| 682 |
+
"trial_name": null,
|
| 683 |
+
"trial_params": null
|
| 684 |
+
}
|