Model save
Browse files- README.md +58 -0
- all_results.json +8 -0
- generation_config.json +6 -0
- train_results.json +8 -0
- trainer_state.json +3739 -0
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: allenai/OLMo-2-1124-7B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: OLMo-2-1124-7B-Instruct_SFTv02.08_frozen
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for OLMo-2-1124-7B-Instruct_SFTv02.08_frozen
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [allenai/OLMo-2-1124-7B-Instruct](https://huggingface.co/allenai/OLMo-2-1124-7B-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="Neelectric/OLMo-2-1124-7B-Instruct_SFTv02.08_frozen", 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/neelectric/open-r1_SFT/runs/e4xlmw8h)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
This model was trained with SFT.
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.17.0
|
| 38 |
+
- Transformers: 4.51.3
|
| 39 |
+
- Pytorch: 2.6.0
|
| 40 |
+
- Datasets: 3.5.1
|
| 41 |
+
- Tokenizers: 0.21.1
|
| 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 Gallou{\'e}dec},
|
| 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": 1.8506098969109594e+19,
|
| 3 |
+
"train_loss": 0.3598332001920386,
|
| 4 |
+
"train_runtime": 11724.7761,
|
| 5 |
+
"train_samples": 69132,
|
| 6 |
+
"train_samples_per_second": 17.689,
|
| 7 |
+
"train_steps_per_second": 0.039
|
| 8 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": 100257,
|
| 4 |
+
"pad_token_id": 100277,
|
| 5 |
+
"transformers_version": "4.51.3"
|
| 6 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 1.8506098969109594e+19,
|
| 3 |
+
"train_loss": 0.3598332001920386,
|
| 4 |
+
"train_runtime": 11724.7761,
|
| 5 |
+
"train_samples": 69132,
|
| 6 |
+
"train_samples_per_second": 17.689,
|
| 7 |
+
"train_steps_per_second": 0.039
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3739 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.983818770226537,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 462,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.006472491909385114,
|
| 14 |
+
"grad_norm": 5.066417694091797,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.1501,
|
| 17 |
+
"num_tokens": 963559.0,
|
| 18 |
+
"step": 1
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.012944983818770227,
|
| 22 |
+
"grad_norm": 5.066908359527588,
|
| 23 |
+
"learning_rate": 1.0638297872340427e-06,
|
| 24 |
+
"loss": 1.1455,
|
| 25 |
+
"num_tokens": 1927760.0,
|
| 26 |
+
"step": 2
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.019417475728155338,
|
| 30 |
+
"grad_norm": 4.966612815856934,
|
| 31 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 32 |
+
"loss": 1.1349,
|
| 33 |
+
"num_tokens": 2896369.0,
|
| 34 |
+
"step": 3
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.025889967637540454,
|
| 38 |
+
"grad_norm": 4.637390613555908,
|
| 39 |
+
"learning_rate": 3.1914893617021277e-06,
|
| 40 |
+
"loss": 1.113,
|
| 41 |
+
"num_tokens": 3886583.0,
|
| 42 |
+
"step": 4
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.032362459546925564,
|
| 46 |
+
"grad_norm": 4.048984050750732,
|
| 47 |
+
"learning_rate": 4.255319148936171e-06,
|
| 48 |
+
"loss": 1.0666,
|
| 49 |
+
"num_tokens": 4864476.0,
|
| 50 |
+
"step": 5
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.038834951456310676,
|
| 54 |
+
"grad_norm": 2.996209144592285,
|
| 55 |
+
"learning_rate": 5.319148936170213e-06,
|
| 56 |
+
"loss": 0.978,
|
| 57 |
+
"num_tokens": 5873295.0,
|
| 58 |
+
"step": 6
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.045307443365695796,
|
| 62 |
+
"grad_norm": 1.8425681591033936,
|
| 63 |
+
"learning_rate": 6.3829787234042555e-06,
|
| 64 |
+
"loss": 0.8312,
|
| 65 |
+
"num_tokens": 6876484.0,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.05177993527508091,
|
| 70 |
+
"grad_norm": 1.5959445238113403,
|
| 71 |
+
"learning_rate": 7.446808510638298e-06,
|
| 72 |
+
"loss": 0.8001,
|
| 73 |
+
"num_tokens": 7871664.0,
|
| 74 |
+
"step": 8
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.05825242718446602,
|
| 78 |
+
"grad_norm": 1.3286134004592896,
|
| 79 |
+
"learning_rate": 8.510638297872341e-06,
|
| 80 |
+
"loss": 0.7792,
|
| 81 |
+
"num_tokens": 8869931.0,
|
| 82 |
+
"step": 9
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.06472491909385113,
|
| 86 |
+
"grad_norm": 1.8917397260665894,
|
| 87 |
+
"learning_rate": 9.574468085106383e-06,
|
| 88 |
+
"loss": 0.734,
|
| 89 |
+
"num_tokens": 9874687.0,
|
| 90 |
+
"step": 10
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.07119741100323625,
|
| 94 |
+
"grad_norm": 1.2099961042404175,
|
| 95 |
+
"learning_rate": 1.0638297872340426e-05,
|
| 96 |
+
"loss": 0.6977,
|
| 97 |
+
"num_tokens": 10842628.0,
|
| 98 |
+
"step": 11
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.07766990291262135,
|
| 102 |
+
"grad_norm": 0.9183234572410583,
|
| 103 |
+
"learning_rate": 1.170212765957447e-05,
|
| 104 |
+
"loss": 0.69,
|
| 105 |
+
"num_tokens": 11815438.0,
|
| 106 |
+
"step": 12
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.08414239482200647,
|
| 110 |
+
"grad_norm": 0.7687932252883911,
|
| 111 |
+
"learning_rate": 1.2765957446808511e-05,
|
| 112 |
+
"loss": 0.6501,
|
| 113 |
+
"num_tokens": 12788222.0,
|
| 114 |
+
"step": 13
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.09061488673139159,
|
| 118 |
+
"grad_norm": 0.6621736288070679,
|
| 119 |
+
"learning_rate": 1.3829787234042554e-05,
|
| 120 |
+
"loss": 0.6349,
|
| 121 |
+
"num_tokens": 13756270.0,
|
| 122 |
+
"step": 14
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.0970873786407767,
|
| 126 |
+
"grad_norm": 0.45913347601890564,
|
| 127 |
+
"learning_rate": 1.4893617021276596e-05,
|
| 128 |
+
"loss": 0.609,
|
| 129 |
+
"num_tokens": 14689813.0,
|
| 130 |
+
"step": 15
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.10355987055016182,
|
| 134 |
+
"grad_norm": 0.3547329008579254,
|
| 135 |
+
"learning_rate": 1.595744680851064e-05,
|
| 136 |
+
"loss": 0.5988,
|
| 137 |
+
"num_tokens": 15670657.0,
|
| 138 |
+
"step": 16
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.11003236245954692,
|
| 142 |
+
"grad_norm": 0.3479355573654175,
|
| 143 |
+
"learning_rate": 1.7021276595744682e-05,
|
| 144 |
+
"loss": 0.581,
|
| 145 |
+
"num_tokens": 16640491.0,
|
| 146 |
+
"step": 17
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.11650485436893204,
|
| 150 |
+
"grad_norm": 0.35780686140060425,
|
| 151 |
+
"learning_rate": 1.8085106382978724e-05,
|
| 152 |
+
"loss": 0.5734,
|
| 153 |
+
"num_tokens": 17611388.0,
|
| 154 |
+
"step": 18
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.12297734627831715,
|
| 158 |
+
"grad_norm": 0.27898019552230835,
|
| 159 |
+
"learning_rate": 1.9148936170212766e-05,
|
| 160 |
+
"loss": 0.5658,
|
| 161 |
+
"num_tokens": 18582653.0,
|
| 162 |
+
"step": 19
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.12944983818770225,
|
| 166 |
+
"grad_norm": 0.28641220927238464,
|
| 167 |
+
"learning_rate": 2.0212765957446807e-05,
|
| 168 |
+
"loss": 0.5531,
|
| 169 |
+
"num_tokens": 19557459.0,
|
| 170 |
+
"step": 20
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.13592233009708737,
|
| 174 |
+
"grad_norm": 0.25866761803627014,
|
| 175 |
+
"learning_rate": 2.1276595744680852e-05,
|
| 176 |
+
"loss": 0.5516,
|
| 177 |
+
"num_tokens": 20524158.0,
|
| 178 |
+
"step": 21
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.1423948220064725,
|
| 182 |
+
"grad_norm": 0.23173657059669495,
|
| 183 |
+
"learning_rate": 2.2340425531914894e-05,
|
| 184 |
+
"loss": 0.5331,
|
| 185 |
+
"num_tokens": 21502674.0,
|
| 186 |
+
"step": 22
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.1488673139158576,
|
| 190 |
+
"grad_norm": 0.23649962246418,
|
| 191 |
+
"learning_rate": 2.340425531914894e-05,
|
| 192 |
+
"loss": 0.5297,
|
| 193 |
+
"num_tokens": 22446294.0,
|
| 194 |
+
"step": 23
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.1553398058252427,
|
| 198 |
+
"grad_norm": 0.19479939341545105,
|
| 199 |
+
"learning_rate": 2.446808510638298e-05,
|
| 200 |
+
"loss": 0.5218,
|
| 201 |
+
"num_tokens": 23430225.0,
|
| 202 |
+
"step": 24
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.16181229773462782,
|
| 206 |
+
"grad_norm": 0.22121383249759674,
|
| 207 |
+
"learning_rate": 2.5531914893617022e-05,
|
| 208 |
+
"loss": 0.5162,
|
| 209 |
+
"num_tokens": 24380419.0,
|
| 210 |
+
"step": 25
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.16828478964401294,
|
| 214 |
+
"grad_norm": 0.19796572625637054,
|
| 215 |
+
"learning_rate": 2.6595744680851064e-05,
|
| 216 |
+
"loss": 0.5066,
|
| 217 |
+
"num_tokens": 25343499.0,
|
| 218 |
+
"step": 26
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.17475728155339806,
|
| 222 |
+
"grad_norm": 0.1949160248041153,
|
| 223 |
+
"learning_rate": 2.765957446808511e-05,
|
| 224 |
+
"loss": 0.5027,
|
| 225 |
+
"num_tokens": 26315921.0,
|
| 226 |
+
"step": 27
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.18122977346278318,
|
| 230 |
+
"grad_norm": 0.21131236851215363,
|
| 231 |
+
"learning_rate": 2.8723404255319154e-05,
|
| 232 |
+
"loss": 0.5068,
|
| 233 |
+
"num_tokens": 27255686.0,
|
| 234 |
+
"step": 28
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.18770226537216828,
|
| 238 |
+
"grad_norm": 0.22278958559036255,
|
| 239 |
+
"learning_rate": 2.9787234042553192e-05,
|
| 240 |
+
"loss": 0.4982,
|
| 241 |
+
"num_tokens": 28232449.0,
|
| 242 |
+
"step": 29
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.1941747572815534,
|
| 246 |
+
"grad_norm": 0.2478061467409134,
|
| 247 |
+
"learning_rate": 3.085106382978723e-05,
|
| 248 |
+
"loss": 0.4948,
|
| 249 |
+
"num_tokens": 29213099.0,
|
| 250 |
+
"step": 30
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.20064724919093851,
|
| 254 |
+
"grad_norm": 0.234426811337471,
|
| 255 |
+
"learning_rate": 3.191489361702128e-05,
|
| 256 |
+
"loss": 0.4932,
|
| 257 |
+
"num_tokens": 30210546.0,
|
| 258 |
+
"step": 31
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.20711974110032363,
|
| 262 |
+
"grad_norm": 0.26089921593666077,
|
| 263 |
+
"learning_rate": 3.2978723404255317e-05,
|
| 264 |
+
"loss": 0.4809,
|
| 265 |
+
"num_tokens": 31190215.0,
|
| 266 |
+
"step": 32
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.21359223300970873,
|
| 270 |
+
"grad_norm": 0.21643660962581635,
|
| 271 |
+
"learning_rate": 3.4042553191489365e-05,
|
| 272 |
+
"loss": 0.4772,
|
| 273 |
+
"num_tokens": 32152368.0,
|
| 274 |
+
"step": 33
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.22006472491909385,
|
| 278 |
+
"grad_norm": 0.20244456827640533,
|
| 279 |
+
"learning_rate": 3.5106382978723407e-05,
|
| 280 |
+
"loss": 0.4851,
|
| 281 |
+
"num_tokens": 33138410.0,
|
| 282 |
+
"step": 34
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.22653721682847897,
|
| 286 |
+
"grad_norm": 0.22395862638950348,
|
| 287 |
+
"learning_rate": 3.617021276595745e-05,
|
| 288 |
+
"loss": 0.4766,
|
| 289 |
+
"num_tokens": 34103559.0,
|
| 290 |
+
"step": 35
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.23300970873786409,
|
| 294 |
+
"grad_norm": 0.2538488805294037,
|
| 295 |
+
"learning_rate": 3.723404255319149e-05,
|
| 296 |
+
"loss": 0.4787,
|
| 297 |
+
"num_tokens": 35099702.0,
|
| 298 |
+
"step": 36
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.23948220064724918,
|
| 302 |
+
"grad_norm": 0.2633797824382782,
|
| 303 |
+
"learning_rate": 3.829787234042553e-05,
|
| 304 |
+
"loss": 0.4786,
|
| 305 |
+
"num_tokens": 36067246.0,
|
| 306 |
+
"step": 37
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.2459546925566343,
|
| 310 |
+
"grad_norm": 0.23186658322811127,
|
| 311 |
+
"learning_rate": 3.936170212765958e-05,
|
| 312 |
+
"loss": 0.4671,
|
| 313 |
+
"num_tokens": 37074157.0,
|
| 314 |
+
"step": 38
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.2524271844660194,
|
| 318 |
+
"grad_norm": 0.23708149790763855,
|
| 319 |
+
"learning_rate": 4.0425531914893614e-05,
|
| 320 |
+
"loss": 0.4646,
|
| 321 |
+
"num_tokens": 38026864.0,
|
| 322 |
+
"step": 39
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.2588996763754045,
|
| 326 |
+
"grad_norm": 0.2775563895702362,
|
| 327 |
+
"learning_rate": 4.148936170212766e-05,
|
| 328 |
+
"loss": 0.4607,
|
| 329 |
+
"num_tokens": 39007950.0,
|
| 330 |
+
"step": 40
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.26537216828478966,
|
| 334 |
+
"grad_norm": 0.23539987206459045,
|
| 335 |
+
"learning_rate": 4.2553191489361704e-05,
|
| 336 |
+
"loss": 0.4674,
|
| 337 |
+
"num_tokens": 40004404.0,
|
| 338 |
+
"step": 41
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.27184466019417475,
|
| 342 |
+
"grad_norm": 0.27806609869003296,
|
| 343 |
+
"learning_rate": 4.3617021276595746e-05,
|
| 344 |
+
"loss": 0.4624,
|
| 345 |
+
"num_tokens": 40979367.0,
|
| 346 |
+
"step": 42
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.2783171521035599,
|
| 350 |
+
"grad_norm": 0.2936287522315979,
|
| 351 |
+
"learning_rate": 4.468085106382979e-05,
|
| 352 |
+
"loss": 0.4611,
|
| 353 |
+
"num_tokens": 41954716.0,
|
| 354 |
+
"step": 43
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.284789644012945,
|
| 358 |
+
"grad_norm": 0.2568210959434509,
|
| 359 |
+
"learning_rate": 4.574468085106383e-05,
|
| 360 |
+
"loss": 0.4674,
|
| 361 |
+
"num_tokens": 42927994.0,
|
| 362 |
+
"step": 44
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.2912621359223301,
|
| 366 |
+
"grad_norm": 0.2423561066389084,
|
| 367 |
+
"learning_rate": 4.680851063829788e-05,
|
| 368 |
+
"loss": 0.4556,
|
| 369 |
+
"num_tokens": 43870458.0,
|
| 370 |
+
"step": 45
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.2977346278317152,
|
| 374 |
+
"grad_norm": 0.25109684467315674,
|
| 375 |
+
"learning_rate": 4.787234042553192e-05,
|
| 376 |
+
"loss": 0.4553,
|
| 377 |
+
"num_tokens": 44845205.0,
|
| 378 |
+
"step": 46
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.3042071197411003,
|
| 382 |
+
"grad_norm": 0.3085050582885742,
|
| 383 |
+
"learning_rate": 4.893617021276596e-05,
|
| 384 |
+
"loss": 0.4535,
|
| 385 |
+
"num_tokens": 45817785.0,
|
| 386 |
+
"step": 47
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.3106796116504854,
|
| 390 |
+
"grad_norm": 0.20581719279289246,
|
| 391 |
+
"learning_rate": 5e-05,
|
| 392 |
+
"loss": 0.4556,
|
| 393 |
+
"num_tokens": 46768552.0,
|
| 394 |
+
"step": 48
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.31715210355987056,
|
| 398 |
+
"grad_norm": 0.2908373475074768,
|
| 399 |
+
"learning_rate": 5e-05,
|
| 400 |
+
"loss": 0.4411,
|
| 401 |
+
"num_tokens": 47720390.0,
|
| 402 |
+
"step": 49
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.32362459546925565,
|
| 406 |
+
"grad_norm": 0.39221635460853577,
|
| 407 |
+
"learning_rate": 5e-05,
|
| 408 |
+
"loss": 0.4534,
|
| 409 |
+
"num_tokens": 48659119.0,
|
| 410 |
+
"step": 50
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.3300970873786408,
|
| 414 |
+
"grad_norm": 0.20563775300979614,
|
| 415 |
+
"learning_rate": 5e-05,
|
| 416 |
+
"loss": 0.4503,
|
| 417 |
+
"num_tokens": 49635896.0,
|
| 418 |
+
"step": 51
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.3365695792880259,
|
| 422 |
+
"grad_norm": 0.40220895409584045,
|
| 423 |
+
"learning_rate": 5e-05,
|
| 424 |
+
"loss": 0.4534,
|
| 425 |
+
"num_tokens": 50617481.0,
|
| 426 |
+
"step": 52
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.343042071197411,
|
| 430 |
+
"grad_norm": 0.24856971204280853,
|
| 431 |
+
"learning_rate": 5e-05,
|
| 432 |
+
"loss": 0.446,
|
| 433 |
+
"num_tokens": 51580322.0,
|
| 434 |
+
"step": 53
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.34951456310679613,
|
| 438 |
+
"grad_norm": 0.4208816885948181,
|
| 439 |
+
"learning_rate": 5e-05,
|
| 440 |
+
"loss": 0.4525,
|
| 441 |
+
"num_tokens": 52544983.0,
|
| 442 |
+
"step": 54
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.3559870550161812,
|
| 446 |
+
"grad_norm": 0.26023271679878235,
|
| 447 |
+
"learning_rate": 5e-05,
|
| 448 |
+
"loss": 0.4416,
|
| 449 |
+
"num_tokens": 53538431.0,
|
| 450 |
+
"step": 55
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.36245954692556637,
|
| 454 |
+
"grad_norm": 0.3722991943359375,
|
| 455 |
+
"learning_rate": 5e-05,
|
| 456 |
+
"loss": 0.4458,
|
| 457 |
+
"num_tokens": 54497097.0,
|
| 458 |
+
"step": 56
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.36893203883495146,
|
| 462 |
+
"grad_norm": 0.326428085565567,
|
| 463 |
+
"learning_rate": 5e-05,
|
| 464 |
+
"loss": 0.4348,
|
| 465 |
+
"num_tokens": 55515695.0,
|
| 466 |
+
"step": 57
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.37540453074433655,
|
| 470 |
+
"grad_norm": 0.27920374274253845,
|
| 471 |
+
"learning_rate": 5e-05,
|
| 472 |
+
"loss": 0.4362,
|
| 473 |
+
"num_tokens": 56471100.0,
|
| 474 |
+
"step": 58
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.3818770226537217,
|
| 478 |
+
"grad_norm": 0.325057715177536,
|
| 479 |
+
"learning_rate": 5e-05,
|
| 480 |
+
"loss": 0.4411,
|
| 481 |
+
"num_tokens": 57460948.0,
|
| 482 |
+
"step": 59
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.3883495145631068,
|
| 486 |
+
"grad_norm": 0.2393280267715454,
|
| 487 |
+
"learning_rate": 5e-05,
|
| 488 |
+
"loss": 0.4408,
|
| 489 |
+
"num_tokens": 58450663.0,
|
| 490 |
+
"step": 60
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.3948220064724919,
|
| 494 |
+
"grad_norm": 0.3320794403553009,
|
| 495 |
+
"learning_rate": 5e-05,
|
| 496 |
+
"loss": 0.4352,
|
| 497 |
+
"num_tokens": 59407638.0,
|
| 498 |
+
"step": 61
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.40129449838187703,
|
| 502 |
+
"grad_norm": 0.23197372257709503,
|
| 503 |
+
"learning_rate": 5e-05,
|
| 504 |
+
"loss": 0.4304,
|
| 505 |
+
"num_tokens": 60358388.0,
|
| 506 |
+
"step": 62
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.4077669902912621,
|
| 510 |
+
"grad_norm": 0.30995386838912964,
|
| 511 |
+
"learning_rate": 5e-05,
|
| 512 |
+
"loss": 0.4276,
|
| 513 |
+
"num_tokens": 61306137.0,
|
| 514 |
+
"step": 63
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.41423948220064727,
|
| 518 |
+
"grad_norm": 0.26690706610679626,
|
| 519 |
+
"learning_rate": 5e-05,
|
| 520 |
+
"loss": 0.4383,
|
| 521 |
+
"num_tokens": 62298616.0,
|
| 522 |
+
"step": 64
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.42071197411003236,
|
| 526 |
+
"grad_norm": 0.2964261472225189,
|
| 527 |
+
"learning_rate": 5e-05,
|
| 528 |
+
"loss": 0.4285,
|
| 529 |
+
"num_tokens": 63242620.0,
|
| 530 |
+
"step": 65
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.42718446601941745,
|
| 534 |
+
"grad_norm": 0.25347742438316345,
|
| 535 |
+
"learning_rate": 5e-05,
|
| 536 |
+
"loss": 0.4435,
|
| 537 |
+
"num_tokens": 64231555.0,
|
| 538 |
+
"step": 66
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.4336569579288026,
|
| 542 |
+
"grad_norm": 0.24757370352745056,
|
| 543 |
+
"learning_rate": 5e-05,
|
| 544 |
+
"loss": 0.432,
|
| 545 |
+
"num_tokens": 65190302.0,
|
| 546 |
+
"step": 67
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.4401294498381877,
|
| 550 |
+
"grad_norm": 0.26604801416397095,
|
| 551 |
+
"learning_rate": 5e-05,
|
| 552 |
+
"loss": 0.4315,
|
| 553 |
+
"num_tokens": 66175194.0,
|
| 554 |
+
"step": 68
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.44660194174757284,
|
| 558 |
+
"grad_norm": 0.2248218059539795,
|
| 559 |
+
"learning_rate": 5e-05,
|
| 560 |
+
"loss": 0.4274,
|
| 561 |
+
"num_tokens": 67146659.0,
|
| 562 |
+
"step": 69
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.45307443365695793,
|
| 566 |
+
"grad_norm": 0.2745100259780884,
|
| 567 |
+
"learning_rate": 5e-05,
|
| 568 |
+
"loss": 0.4121,
|
| 569 |
+
"num_tokens": 68115421.0,
|
| 570 |
+
"step": 70
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.459546925566343,
|
| 574 |
+
"grad_norm": 0.2692604064941406,
|
| 575 |
+
"learning_rate": 5e-05,
|
| 576 |
+
"loss": 0.4112,
|
| 577 |
+
"num_tokens": 69078962.0,
|
| 578 |
+
"step": 71
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.46601941747572817,
|
| 582 |
+
"grad_norm": 0.2680717706680298,
|
| 583 |
+
"learning_rate": 5e-05,
|
| 584 |
+
"loss": 0.4353,
|
| 585 |
+
"num_tokens": 70056552.0,
|
| 586 |
+
"step": 72
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.47249190938511326,
|
| 590 |
+
"grad_norm": 0.2345399111509323,
|
| 591 |
+
"learning_rate": 5e-05,
|
| 592 |
+
"loss": 0.428,
|
| 593 |
+
"num_tokens": 71056405.0,
|
| 594 |
+
"step": 73
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.47896440129449835,
|
| 598 |
+
"grad_norm": 0.2474702149629593,
|
| 599 |
+
"learning_rate": 5e-05,
|
| 600 |
+
"loss": 0.4387,
|
| 601 |
+
"num_tokens": 72011963.0,
|
| 602 |
+
"step": 74
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.4854368932038835,
|
| 606 |
+
"grad_norm": 0.23220956325531006,
|
| 607 |
+
"learning_rate": 5e-05,
|
| 608 |
+
"loss": 0.4252,
|
| 609 |
+
"num_tokens": 72974088.0,
|
| 610 |
+
"step": 75
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.4919093851132686,
|
| 614 |
+
"grad_norm": 0.24197089672088623,
|
| 615 |
+
"learning_rate": 5e-05,
|
| 616 |
+
"loss": 0.4206,
|
| 617 |
+
"num_tokens": 73963066.0,
|
| 618 |
+
"step": 76
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.49838187702265374,
|
| 622 |
+
"grad_norm": 0.2226783037185669,
|
| 623 |
+
"learning_rate": 5e-05,
|
| 624 |
+
"loss": 0.4139,
|
| 625 |
+
"num_tokens": 74927507.0,
|
| 626 |
+
"step": 77
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.5048543689320388,
|
| 630 |
+
"grad_norm": 0.2657461166381836,
|
| 631 |
+
"learning_rate": 5e-05,
|
| 632 |
+
"loss": 0.4193,
|
| 633 |
+
"num_tokens": 75913302.0,
|
| 634 |
+
"step": 78
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.511326860841424,
|
| 638 |
+
"grad_norm": 0.24124957621097565,
|
| 639 |
+
"learning_rate": 5e-05,
|
| 640 |
+
"loss": 0.4281,
|
| 641 |
+
"num_tokens": 76871637.0,
|
| 642 |
+
"step": 79
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.517799352750809,
|
| 646 |
+
"grad_norm": 0.23616252839565277,
|
| 647 |
+
"learning_rate": 5e-05,
|
| 648 |
+
"loss": 0.4214,
|
| 649 |
+
"num_tokens": 77844738.0,
|
| 650 |
+
"step": 80
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.5242718446601942,
|
| 654 |
+
"grad_norm": 0.26055875420570374,
|
| 655 |
+
"learning_rate": 5e-05,
|
| 656 |
+
"loss": 0.4155,
|
| 657 |
+
"num_tokens": 78789735.0,
|
| 658 |
+
"step": 81
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.5307443365695793,
|
| 662 |
+
"grad_norm": 0.20040573179721832,
|
| 663 |
+
"learning_rate": 5e-05,
|
| 664 |
+
"loss": 0.4121,
|
| 665 |
+
"num_tokens": 79740057.0,
|
| 666 |
+
"step": 82
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 0.5372168284789643,
|
| 670 |
+
"grad_norm": 0.27394115924835205,
|
| 671 |
+
"learning_rate": 5e-05,
|
| 672 |
+
"loss": 0.42,
|
| 673 |
+
"num_tokens": 80691344.0,
|
| 674 |
+
"step": 83
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.5436893203883495,
|
| 678 |
+
"grad_norm": 0.26746806502342224,
|
| 679 |
+
"learning_rate": 5e-05,
|
| 680 |
+
"loss": 0.4201,
|
| 681 |
+
"num_tokens": 81695065.0,
|
| 682 |
+
"step": 84
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.5501618122977346,
|
| 686 |
+
"grad_norm": 0.19466280937194824,
|
| 687 |
+
"learning_rate": 5e-05,
|
| 688 |
+
"loss": 0.4158,
|
| 689 |
+
"num_tokens": 82670591.0,
|
| 690 |
+
"step": 85
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.5566343042071198,
|
| 694 |
+
"grad_norm": 0.2403528094291687,
|
| 695 |
+
"learning_rate": 5e-05,
|
| 696 |
+
"loss": 0.416,
|
| 697 |
+
"num_tokens": 83619525.0,
|
| 698 |
+
"step": 86
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.5631067961165048,
|
| 702 |
+
"grad_norm": 0.2280794382095337,
|
| 703 |
+
"learning_rate": 5e-05,
|
| 704 |
+
"loss": 0.4157,
|
| 705 |
+
"num_tokens": 84583829.0,
|
| 706 |
+
"step": 87
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.56957928802589,
|
| 710 |
+
"grad_norm": 0.21896417438983917,
|
| 711 |
+
"learning_rate": 5e-05,
|
| 712 |
+
"loss": 0.4153,
|
| 713 |
+
"num_tokens": 85554557.0,
|
| 714 |
+
"step": 88
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.5760517799352751,
|
| 718 |
+
"grad_norm": 0.19582906365394592,
|
| 719 |
+
"learning_rate": 5e-05,
|
| 720 |
+
"loss": 0.417,
|
| 721 |
+
"num_tokens": 86534800.0,
|
| 722 |
+
"step": 89
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.5825242718446602,
|
| 726 |
+
"grad_norm": 0.23236116766929626,
|
| 727 |
+
"learning_rate": 5e-05,
|
| 728 |
+
"loss": 0.4207,
|
| 729 |
+
"num_tokens": 87479322.0,
|
| 730 |
+
"step": 90
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.5889967637540453,
|
| 734 |
+
"grad_norm": 0.2682839632034302,
|
| 735 |
+
"learning_rate": 5e-05,
|
| 736 |
+
"loss": 0.4193,
|
| 737 |
+
"num_tokens": 88440604.0,
|
| 738 |
+
"step": 91
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.5954692556634305,
|
| 742 |
+
"grad_norm": 0.2160482555627823,
|
| 743 |
+
"learning_rate": 5e-05,
|
| 744 |
+
"loss": 0.4164,
|
| 745 |
+
"num_tokens": 89440902.0,
|
| 746 |
+
"step": 92
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.6019417475728155,
|
| 750 |
+
"grad_norm": 0.23822101950645447,
|
| 751 |
+
"learning_rate": 5e-05,
|
| 752 |
+
"loss": 0.4092,
|
| 753 |
+
"num_tokens": 90420292.0,
|
| 754 |
+
"step": 93
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.6084142394822006,
|
| 758 |
+
"grad_norm": 0.2218194156885147,
|
| 759 |
+
"learning_rate": 5e-05,
|
| 760 |
+
"loss": 0.4166,
|
| 761 |
+
"num_tokens": 91365927.0,
|
| 762 |
+
"step": 94
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.6148867313915858,
|
| 766 |
+
"grad_norm": 0.1841086745262146,
|
| 767 |
+
"learning_rate": 5e-05,
|
| 768 |
+
"loss": 0.4118,
|
| 769 |
+
"num_tokens": 92339481.0,
|
| 770 |
+
"step": 95
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.6213592233009708,
|
| 774 |
+
"grad_norm": 0.22299782931804657,
|
| 775 |
+
"learning_rate": 5e-05,
|
| 776 |
+
"loss": 0.4076,
|
| 777 |
+
"num_tokens": 93277920.0,
|
| 778 |
+
"step": 96
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.627831715210356,
|
| 782 |
+
"grad_norm": 0.297587513923645,
|
| 783 |
+
"learning_rate": 5e-05,
|
| 784 |
+
"loss": 0.408,
|
| 785 |
+
"num_tokens": 94233058.0,
|
| 786 |
+
"step": 97
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.6343042071197411,
|
| 790 |
+
"grad_norm": 0.21505360305309296,
|
| 791 |
+
"learning_rate": 5e-05,
|
| 792 |
+
"loss": 0.4203,
|
| 793 |
+
"num_tokens": 95195865.0,
|
| 794 |
+
"step": 98
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.6407766990291263,
|
| 798 |
+
"grad_norm": 0.2577345371246338,
|
| 799 |
+
"learning_rate": 5e-05,
|
| 800 |
+
"loss": 0.404,
|
| 801 |
+
"num_tokens": 96165533.0,
|
| 802 |
+
"step": 99
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.6472491909385113,
|
| 806 |
+
"grad_norm": 0.23889726400375366,
|
| 807 |
+
"learning_rate": 5e-05,
|
| 808 |
+
"loss": 0.4058,
|
| 809 |
+
"num_tokens": 97128908.0,
|
| 810 |
+
"step": 100
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.6537216828478964,
|
| 814 |
+
"grad_norm": 0.26140421628952026,
|
| 815 |
+
"learning_rate": 5e-05,
|
| 816 |
+
"loss": 0.4071,
|
| 817 |
+
"num_tokens": 98137812.0,
|
| 818 |
+
"step": 101
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.6601941747572816,
|
| 822 |
+
"grad_norm": 0.18511807918548584,
|
| 823 |
+
"learning_rate": 5e-05,
|
| 824 |
+
"loss": 0.4028,
|
| 825 |
+
"num_tokens": 99133445.0,
|
| 826 |
+
"step": 102
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.6666666666666666,
|
| 830 |
+
"grad_norm": 0.22571946680545807,
|
| 831 |
+
"learning_rate": 5e-05,
|
| 832 |
+
"loss": 0.3958,
|
| 833 |
+
"num_tokens": 100106034.0,
|
| 834 |
+
"step": 103
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.6731391585760518,
|
| 838 |
+
"grad_norm": 0.2224554866552353,
|
| 839 |
+
"learning_rate": 5e-05,
|
| 840 |
+
"loss": 0.4228,
|
| 841 |
+
"num_tokens": 101060830.0,
|
| 842 |
+
"step": 104
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.6796116504854369,
|
| 846 |
+
"grad_norm": 0.2639662027359009,
|
| 847 |
+
"learning_rate": 5e-05,
|
| 848 |
+
"loss": 0.4084,
|
| 849 |
+
"num_tokens": 102032708.0,
|
| 850 |
+
"step": 105
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.686084142394822,
|
| 854 |
+
"grad_norm": 0.209217831492424,
|
| 855 |
+
"learning_rate": 5e-05,
|
| 856 |
+
"loss": 0.3914,
|
| 857 |
+
"num_tokens": 103020888.0,
|
| 858 |
+
"step": 106
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.6925566343042071,
|
| 862 |
+
"grad_norm": 0.26654332876205444,
|
| 863 |
+
"learning_rate": 5e-05,
|
| 864 |
+
"loss": 0.4145,
|
| 865 |
+
"num_tokens": 103986883.0,
|
| 866 |
+
"step": 107
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.6990291262135923,
|
| 870 |
+
"grad_norm": 0.21930049359798431,
|
| 871 |
+
"learning_rate": 5e-05,
|
| 872 |
+
"loss": 0.4114,
|
| 873 |
+
"num_tokens": 104978514.0,
|
| 874 |
+
"step": 108
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.7055016181229773,
|
| 878 |
+
"grad_norm": 0.21005888283252716,
|
| 879 |
+
"learning_rate": 5e-05,
|
| 880 |
+
"loss": 0.3988,
|
| 881 |
+
"num_tokens": 105938542.0,
|
| 882 |
+
"step": 109
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.7119741100323624,
|
| 886 |
+
"grad_norm": 0.195763498544693,
|
| 887 |
+
"learning_rate": 5e-05,
|
| 888 |
+
"loss": 0.4007,
|
| 889 |
+
"num_tokens": 106909993.0,
|
| 890 |
+
"step": 110
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.7184466019417476,
|
| 894 |
+
"grad_norm": 0.20811644196510315,
|
| 895 |
+
"learning_rate": 5e-05,
|
| 896 |
+
"loss": 0.4042,
|
| 897 |
+
"num_tokens": 107872313.0,
|
| 898 |
+
"step": 111
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.7249190938511327,
|
| 902 |
+
"grad_norm": 0.238833487033844,
|
| 903 |
+
"learning_rate": 5e-05,
|
| 904 |
+
"loss": 0.3988,
|
| 905 |
+
"num_tokens": 108876000.0,
|
| 906 |
+
"step": 112
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.7313915857605178,
|
| 910 |
+
"grad_norm": 0.24984987080097198,
|
| 911 |
+
"learning_rate": 5e-05,
|
| 912 |
+
"loss": 0.4001,
|
| 913 |
+
"num_tokens": 109857790.0,
|
| 914 |
+
"step": 113
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.7378640776699029,
|
| 918 |
+
"grad_norm": 0.24988315999507904,
|
| 919 |
+
"learning_rate": 5e-05,
|
| 920 |
+
"loss": 0.4011,
|
| 921 |
+
"num_tokens": 110826497.0,
|
| 922 |
+
"step": 114
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.7443365695792881,
|
| 926 |
+
"grad_norm": 0.2496054321527481,
|
| 927 |
+
"learning_rate": 5e-05,
|
| 928 |
+
"loss": 0.3992,
|
| 929 |
+
"num_tokens": 111775780.0,
|
| 930 |
+
"step": 115
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 0.7508090614886731,
|
| 934 |
+
"grad_norm": 0.1960972100496292,
|
| 935 |
+
"learning_rate": 5e-05,
|
| 936 |
+
"loss": 0.4007,
|
| 937 |
+
"num_tokens": 112755203.0,
|
| 938 |
+
"step": 116
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.7572815533980582,
|
| 942 |
+
"grad_norm": 0.22356246411800385,
|
| 943 |
+
"learning_rate": 5e-05,
|
| 944 |
+
"loss": 0.4013,
|
| 945 |
+
"num_tokens": 113720983.0,
|
| 946 |
+
"step": 117
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.7637540453074434,
|
| 950 |
+
"grad_norm": 0.22578826546669006,
|
| 951 |
+
"learning_rate": 5e-05,
|
| 952 |
+
"loss": 0.3926,
|
| 953 |
+
"num_tokens": 114690500.0,
|
| 954 |
+
"step": 118
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.7702265372168284,
|
| 958 |
+
"grad_norm": 0.2602064609527588,
|
| 959 |
+
"learning_rate": 5e-05,
|
| 960 |
+
"loss": 0.3938,
|
| 961 |
+
"num_tokens": 115663752.0,
|
| 962 |
+
"step": 119
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.7766990291262136,
|
| 966 |
+
"grad_norm": 0.1850455105304718,
|
| 967 |
+
"learning_rate": 5e-05,
|
| 968 |
+
"loss": 0.3905,
|
| 969 |
+
"num_tokens": 116656118.0,
|
| 970 |
+
"step": 120
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.7831715210355987,
|
| 974 |
+
"grad_norm": 0.22258904576301575,
|
| 975 |
+
"learning_rate": 5e-05,
|
| 976 |
+
"loss": 0.3996,
|
| 977 |
+
"num_tokens": 117647006.0,
|
| 978 |
+
"step": 121
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.7896440129449838,
|
| 982 |
+
"grad_norm": 0.22703003883361816,
|
| 983 |
+
"learning_rate": 5e-05,
|
| 984 |
+
"loss": 0.3909,
|
| 985 |
+
"num_tokens": 118637898.0,
|
| 986 |
+
"step": 122
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 0.7961165048543689,
|
| 990 |
+
"grad_norm": 0.2309364229440689,
|
| 991 |
+
"learning_rate": 5e-05,
|
| 992 |
+
"loss": 0.3998,
|
| 993 |
+
"num_tokens": 119611539.0,
|
| 994 |
+
"step": 123
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 0.8025889967637541,
|
| 998 |
+
"grad_norm": 0.23023244738578796,
|
| 999 |
+
"learning_rate": 5e-05,
|
| 1000 |
+
"loss": 0.4014,
|
| 1001 |
+
"num_tokens": 120576485.0,
|
| 1002 |
+
"step": 124
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.8090614886731392,
|
| 1006 |
+
"grad_norm": 0.23768304288387299,
|
| 1007 |
+
"learning_rate": 5e-05,
|
| 1008 |
+
"loss": 0.4018,
|
| 1009 |
+
"num_tokens": 121567862.0,
|
| 1010 |
+
"step": 125
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.8155339805825242,
|
| 1014 |
+
"grad_norm": 0.1838195025920868,
|
| 1015 |
+
"learning_rate": 5e-05,
|
| 1016 |
+
"loss": 0.3932,
|
| 1017 |
+
"num_tokens": 122530893.0,
|
| 1018 |
+
"step": 126
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.8220064724919094,
|
| 1022 |
+
"grad_norm": 0.2064729481935501,
|
| 1023 |
+
"learning_rate": 5e-05,
|
| 1024 |
+
"loss": 0.3937,
|
| 1025 |
+
"num_tokens": 123480227.0,
|
| 1026 |
+
"step": 127
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.8284789644012945,
|
| 1030 |
+
"grad_norm": 0.2696620523929596,
|
| 1031 |
+
"learning_rate": 5e-05,
|
| 1032 |
+
"loss": 0.4081,
|
| 1033 |
+
"num_tokens": 124462070.0,
|
| 1034 |
+
"step": 128
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.8349514563106796,
|
| 1038 |
+
"grad_norm": 0.1941477507352829,
|
| 1039 |
+
"learning_rate": 5e-05,
|
| 1040 |
+
"loss": 0.4014,
|
| 1041 |
+
"num_tokens": 125440428.0,
|
| 1042 |
+
"step": 129
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 0.8414239482200647,
|
| 1046 |
+
"grad_norm": 0.22628171741962433,
|
| 1047 |
+
"learning_rate": 5e-05,
|
| 1048 |
+
"loss": 0.3974,
|
| 1049 |
+
"num_tokens": 126416310.0,
|
| 1050 |
+
"step": 130
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.8478964401294499,
|
| 1054 |
+
"grad_norm": 0.21298550069332123,
|
| 1055 |
+
"learning_rate": 5e-05,
|
| 1056 |
+
"loss": 0.3972,
|
| 1057 |
+
"num_tokens": 127406436.0,
|
| 1058 |
+
"step": 131
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 0.8543689320388349,
|
| 1062 |
+
"grad_norm": 0.22063614428043365,
|
| 1063 |
+
"learning_rate": 5e-05,
|
| 1064 |
+
"loss": 0.3963,
|
| 1065 |
+
"num_tokens": 128372197.0,
|
| 1066 |
+
"step": 132
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.86084142394822,
|
| 1070 |
+
"grad_norm": 0.1877291351556778,
|
| 1071 |
+
"learning_rate": 5e-05,
|
| 1072 |
+
"loss": 0.3928,
|
| 1073 |
+
"num_tokens": 129371264.0,
|
| 1074 |
+
"step": 133
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.8673139158576052,
|
| 1078 |
+
"grad_norm": 0.20851096510887146,
|
| 1079 |
+
"learning_rate": 5e-05,
|
| 1080 |
+
"loss": 0.38,
|
| 1081 |
+
"num_tokens": 130306080.0,
|
| 1082 |
+
"step": 134
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 0.8737864077669902,
|
| 1086 |
+
"grad_norm": 0.2774619162082672,
|
| 1087 |
+
"learning_rate": 5e-05,
|
| 1088 |
+
"loss": 0.4,
|
| 1089 |
+
"num_tokens": 131261937.0,
|
| 1090 |
+
"step": 135
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.8802588996763754,
|
| 1094 |
+
"grad_norm": 0.25149106979370117,
|
| 1095 |
+
"learning_rate": 5e-05,
|
| 1096 |
+
"loss": 0.3933,
|
| 1097 |
+
"num_tokens": 132223182.0,
|
| 1098 |
+
"step": 136
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.8867313915857605,
|
| 1102 |
+
"grad_norm": 0.2103366255760193,
|
| 1103 |
+
"learning_rate": 5e-05,
|
| 1104 |
+
"loss": 0.3967,
|
| 1105 |
+
"num_tokens": 133211562.0,
|
| 1106 |
+
"step": 137
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 0.8932038834951457,
|
| 1110 |
+
"grad_norm": 0.2521952986717224,
|
| 1111 |
+
"learning_rate": 5e-05,
|
| 1112 |
+
"loss": 0.3943,
|
| 1113 |
+
"num_tokens": 134208133.0,
|
| 1114 |
+
"step": 138
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 0.8996763754045307,
|
| 1118 |
+
"grad_norm": 0.23235109448432922,
|
| 1119 |
+
"learning_rate": 5e-05,
|
| 1120 |
+
"loss": 0.3964,
|
| 1121 |
+
"num_tokens": 135194807.0,
|
| 1122 |
+
"step": 139
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.9061488673139159,
|
| 1126 |
+
"grad_norm": 0.31734412908554077,
|
| 1127 |
+
"learning_rate": 5e-05,
|
| 1128 |
+
"loss": 0.3964,
|
| 1129 |
+
"num_tokens": 136175941.0,
|
| 1130 |
+
"step": 140
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.912621359223301,
|
| 1134 |
+
"grad_norm": 0.172586590051651,
|
| 1135 |
+
"learning_rate": 5e-05,
|
| 1136 |
+
"loss": 0.4056,
|
| 1137 |
+
"num_tokens": 137117638.0,
|
| 1138 |
+
"step": 141
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 0.919093851132686,
|
| 1142 |
+
"grad_norm": 0.26154661178588867,
|
| 1143 |
+
"learning_rate": 5e-05,
|
| 1144 |
+
"loss": 0.3848,
|
| 1145 |
+
"num_tokens": 138102412.0,
|
| 1146 |
+
"step": 142
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.9255663430420712,
|
| 1150 |
+
"grad_norm": 0.30846381187438965,
|
| 1151 |
+
"learning_rate": 5e-05,
|
| 1152 |
+
"loss": 0.3881,
|
| 1153 |
+
"num_tokens": 139056304.0,
|
| 1154 |
+
"step": 143
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.9320388349514563,
|
| 1158 |
+
"grad_norm": 0.17311494052410126,
|
| 1159 |
+
"learning_rate": 5e-05,
|
| 1160 |
+
"loss": 0.392,
|
| 1161 |
+
"num_tokens": 140002988.0,
|
| 1162 |
+
"step": 144
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 0.9385113268608414,
|
| 1166 |
+
"grad_norm": 0.25492337346076965,
|
| 1167 |
+
"learning_rate": 5e-05,
|
| 1168 |
+
"loss": 0.3952,
|
| 1169 |
+
"num_tokens": 140939323.0,
|
| 1170 |
+
"step": 145
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 0.9449838187702265,
|
| 1174 |
+
"grad_norm": 0.2816878855228424,
|
| 1175 |
+
"learning_rate": 5e-05,
|
| 1176 |
+
"loss": 0.3903,
|
| 1177 |
+
"num_tokens": 141898246.0,
|
| 1178 |
+
"step": 146
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.9514563106796117,
|
| 1182 |
+
"grad_norm": 0.19545646011829376,
|
| 1183 |
+
"learning_rate": 5e-05,
|
| 1184 |
+
"loss": 0.3967,
|
| 1185 |
+
"num_tokens": 142861118.0,
|
| 1186 |
+
"step": 147
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.9579288025889967,
|
| 1190 |
+
"grad_norm": 0.2272789180278778,
|
| 1191 |
+
"learning_rate": 5e-05,
|
| 1192 |
+
"loss": 0.391,
|
| 1193 |
+
"num_tokens": 143845628.0,
|
| 1194 |
+
"step": 148
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.9644012944983819,
|
| 1198 |
+
"grad_norm": 0.180133655667305,
|
| 1199 |
+
"learning_rate": 5e-05,
|
| 1200 |
+
"loss": 0.401,
|
| 1201 |
+
"num_tokens": 144816454.0,
|
| 1202 |
+
"step": 149
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.970873786407767,
|
| 1206 |
+
"grad_norm": 0.1802646517753601,
|
| 1207 |
+
"learning_rate": 5e-05,
|
| 1208 |
+
"loss": 0.3902,
|
| 1209 |
+
"num_tokens": 145791528.0,
|
| 1210 |
+
"step": 150
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.9773462783171522,
|
| 1214 |
+
"grad_norm": 0.20655637979507446,
|
| 1215 |
+
"learning_rate": 5e-05,
|
| 1216 |
+
"loss": 0.4024,
|
| 1217 |
+
"num_tokens": 146776225.0,
|
| 1218 |
+
"step": 151
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 0.9838187702265372,
|
| 1222 |
+
"grad_norm": 0.18897205591201782,
|
| 1223 |
+
"learning_rate": 5e-05,
|
| 1224 |
+
"loss": 0.3858,
|
| 1225 |
+
"num_tokens": 147716038.0,
|
| 1226 |
+
"step": 152
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 0.9902912621359223,
|
| 1230 |
+
"grad_norm": 0.18271128833293915,
|
| 1231 |
+
"learning_rate": 5e-05,
|
| 1232 |
+
"loss": 0.3826,
|
| 1233 |
+
"num_tokens": 148641036.0,
|
| 1234 |
+
"step": 153
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.9967637540453075,
|
| 1238 |
+
"grad_norm": 0.19371099770069122,
|
| 1239 |
+
"learning_rate": 5e-05,
|
| 1240 |
+
"loss": 0.3863,
|
| 1241 |
+
"num_tokens": 149611850.0,
|
| 1242 |
+
"step": 154
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.0,
|
| 1246 |
+
"grad_norm": 0.19371099770069122,
|
| 1247 |
+
"learning_rate": 5e-05,
|
| 1248 |
+
"loss": 0.3883,
|
| 1249 |
+
"num_tokens": 150082857.0,
|
| 1250 |
+
"step": 155
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 1.006472491909385,
|
| 1254 |
+
"grad_norm": 0.3387119472026825,
|
| 1255 |
+
"learning_rate": 5e-05,
|
| 1256 |
+
"loss": 0.3457,
|
| 1257 |
+
"num_tokens": 151065207.0,
|
| 1258 |
+
"step": 156
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 1.0129449838187703,
|
| 1262 |
+
"grad_norm": 0.20606622099876404,
|
| 1263 |
+
"learning_rate": 5e-05,
|
| 1264 |
+
"loss": 0.3373,
|
| 1265 |
+
"num_tokens": 152046682.0,
|
| 1266 |
+
"step": 157
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 1.0194174757281553,
|
| 1270 |
+
"grad_norm": 0.19748540222644806,
|
| 1271 |
+
"learning_rate": 5e-05,
|
| 1272 |
+
"loss": 0.3398,
|
| 1273 |
+
"num_tokens": 153014543.0,
|
| 1274 |
+
"step": 158
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 1.0258899676375404,
|
| 1278 |
+
"grad_norm": 0.226538747549057,
|
| 1279 |
+
"learning_rate": 5e-05,
|
| 1280 |
+
"loss": 0.3434,
|
| 1281 |
+
"num_tokens": 153988434.0,
|
| 1282 |
+
"step": 159
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 1.0323624595469256,
|
| 1286 |
+
"grad_norm": 0.20436212420463562,
|
| 1287 |
+
"learning_rate": 5e-05,
|
| 1288 |
+
"loss": 0.3441,
|
| 1289 |
+
"num_tokens": 154938356.0,
|
| 1290 |
+
"step": 160
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.0388349514563107,
|
| 1294 |
+
"grad_norm": 0.20210999250411987,
|
| 1295 |
+
"learning_rate": 5e-05,
|
| 1296 |
+
"loss": 0.3442,
|
| 1297 |
+
"num_tokens": 155920665.0,
|
| 1298 |
+
"step": 161
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.0453074433656957,
|
| 1302 |
+
"grad_norm": 0.26638829708099365,
|
| 1303 |
+
"learning_rate": 5e-05,
|
| 1304 |
+
"loss": 0.3448,
|
| 1305 |
+
"num_tokens": 156878844.0,
|
| 1306 |
+
"step": 162
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 1.051779935275081,
|
| 1310 |
+
"grad_norm": 0.25940850377082825,
|
| 1311 |
+
"learning_rate": 5e-05,
|
| 1312 |
+
"loss": 0.3388,
|
| 1313 |
+
"num_tokens": 157852056.0,
|
| 1314 |
+
"step": 163
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 1.058252427184466,
|
| 1318 |
+
"grad_norm": 0.18894004821777344,
|
| 1319 |
+
"learning_rate": 5e-05,
|
| 1320 |
+
"loss": 0.3451,
|
| 1321 |
+
"num_tokens": 158847308.0,
|
| 1322 |
+
"step": 164
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 1.064724919093851,
|
| 1326 |
+
"grad_norm": 0.20138530433177948,
|
| 1327 |
+
"learning_rate": 5e-05,
|
| 1328 |
+
"loss": 0.3471,
|
| 1329 |
+
"num_tokens": 159815676.0,
|
| 1330 |
+
"step": 165
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 1.0711974110032363,
|
| 1334 |
+
"grad_norm": 0.2081957310438156,
|
| 1335 |
+
"learning_rate": 5e-05,
|
| 1336 |
+
"loss": 0.3437,
|
| 1337 |
+
"num_tokens": 160783247.0,
|
| 1338 |
+
"step": 166
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 1.0776699029126213,
|
| 1342 |
+
"grad_norm": 0.20640355348587036,
|
| 1343 |
+
"learning_rate": 5e-05,
|
| 1344 |
+
"loss": 0.3387,
|
| 1345 |
+
"num_tokens": 161757978.0,
|
| 1346 |
+
"step": 167
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.0841423948220066,
|
| 1350 |
+
"grad_norm": 0.1982601284980774,
|
| 1351 |
+
"learning_rate": 5e-05,
|
| 1352 |
+
"loss": 0.3358,
|
| 1353 |
+
"num_tokens": 162697927.0,
|
| 1354 |
+
"step": 168
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.0906148867313916,
|
| 1358 |
+
"grad_norm": 0.20576398074626923,
|
| 1359 |
+
"learning_rate": 5e-05,
|
| 1360 |
+
"loss": 0.3436,
|
| 1361 |
+
"num_tokens": 163662092.0,
|
| 1362 |
+
"step": 169
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 1.0970873786407767,
|
| 1366 |
+
"grad_norm": 0.2331991046667099,
|
| 1367 |
+
"learning_rate": 5e-05,
|
| 1368 |
+
"loss": 0.3358,
|
| 1369 |
+
"num_tokens": 164636005.0,
|
| 1370 |
+
"step": 170
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 1.103559870550162,
|
| 1374 |
+
"grad_norm": 0.25516974925994873,
|
| 1375 |
+
"learning_rate": 5e-05,
|
| 1376 |
+
"loss": 0.3428,
|
| 1377 |
+
"num_tokens": 165575709.0,
|
| 1378 |
+
"step": 171
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 1.110032362459547,
|
| 1382 |
+
"grad_norm": 0.21340486407279968,
|
| 1383 |
+
"learning_rate": 5e-05,
|
| 1384 |
+
"loss": 0.3299,
|
| 1385 |
+
"num_tokens": 166581172.0,
|
| 1386 |
+
"step": 172
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 1.116504854368932,
|
| 1390 |
+
"grad_norm": 0.18883739411830902,
|
| 1391 |
+
"learning_rate": 5e-05,
|
| 1392 |
+
"loss": 0.3393,
|
| 1393 |
+
"num_tokens": 167529454.0,
|
| 1394 |
+
"step": 173
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 1.1229773462783172,
|
| 1398 |
+
"grad_norm": 0.19975334405899048,
|
| 1399 |
+
"learning_rate": 5e-05,
|
| 1400 |
+
"loss": 0.3322,
|
| 1401 |
+
"num_tokens": 168484414.0,
|
| 1402 |
+
"step": 174
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.1294498381877023,
|
| 1406 |
+
"grad_norm": 0.2676781117916107,
|
| 1407 |
+
"learning_rate": 5e-05,
|
| 1408 |
+
"loss": 0.3429,
|
| 1409 |
+
"num_tokens": 169452401.0,
|
| 1410 |
+
"step": 175
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.1359223300970873,
|
| 1414 |
+
"grad_norm": 0.1652645617723465,
|
| 1415 |
+
"learning_rate": 5e-05,
|
| 1416 |
+
"loss": 0.3349,
|
| 1417 |
+
"num_tokens": 170407712.0,
|
| 1418 |
+
"step": 176
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 1.1423948220064726,
|
| 1422 |
+
"grad_norm": 0.19614100456237793,
|
| 1423 |
+
"learning_rate": 5e-05,
|
| 1424 |
+
"loss": 0.3434,
|
| 1425 |
+
"num_tokens": 171418075.0,
|
| 1426 |
+
"step": 177
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 1.1488673139158576,
|
| 1430 |
+
"grad_norm": 0.23959225416183472,
|
| 1431 |
+
"learning_rate": 5e-05,
|
| 1432 |
+
"loss": 0.3395,
|
| 1433 |
+
"num_tokens": 172409907.0,
|
| 1434 |
+
"step": 178
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 1.1553398058252426,
|
| 1438 |
+
"grad_norm": 0.2018483281135559,
|
| 1439 |
+
"learning_rate": 5e-05,
|
| 1440 |
+
"loss": 0.3367,
|
| 1441 |
+
"num_tokens": 173368352.0,
|
| 1442 |
+
"step": 179
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 1.161812297734628,
|
| 1446 |
+
"grad_norm": 0.2409161776304245,
|
| 1447 |
+
"learning_rate": 5e-05,
|
| 1448 |
+
"loss": 0.3415,
|
| 1449 |
+
"num_tokens": 174328021.0,
|
| 1450 |
+
"step": 180
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 1.168284789644013,
|
| 1454 |
+
"grad_norm": 0.2707282602787018,
|
| 1455 |
+
"learning_rate": 5e-05,
|
| 1456 |
+
"loss": 0.3385,
|
| 1457 |
+
"num_tokens": 175328614.0,
|
| 1458 |
+
"step": 181
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 1.174757281553398,
|
| 1462 |
+
"grad_norm": 0.1754923313856125,
|
| 1463 |
+
"learning_rate": 5e-05,
|
| 1464 |
+
"loss": 0.339,
|
| 1465 |
+
"num_tokens": 176287442.0,
|
| 1466 |
+
"step": 182
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.1812297734627832,
|
| 1470 |
+
"grad_norm": 0.20444481074810028,
|
| 1471 |
+
"learning_rate": 5e-05,
|
| 1472 |
+
"loss": 0.3444,
|
| 1473 |
+
"num_tokens": 177272590.0,
|
| 1474 |
+
"step": 183
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 1.1877022653721683,
|
| 1478 |
+
"grad_norm": 0.2513251006603241,
|
| 1479 |
+
"learning_rate": 5e-05,
|
| 1480 |
+
"loss": 0.3458,
|
| 1481 |
+
"num_tokens": 178243495.0,
|
| 1482 |
+
"step": 184
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 1.1941747572815533,
|
| 1486 |
+
"grad_norm": 0.1885911375284195,
|
| 1487 |
+
"learning_rate": 5e-05,
|
| 1488 |
+
"loss": 0.3414,
|
| 1489 |
+
"num_tokens": 179230835.0,
|
| 1490 |
+
"step": 185
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 1.2006472491909386,
|
| 1494 |
+
"grad_norm": 0.2212754189968109,
|
| 1495 |
+
"learning_rate": 5e-05,
|
| 1496 |
+
"loss": 0.3372,
|
| 1497 |
+
"num_tokens": 180197716.0,
|
| 1498 |
+
"step": 186
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 1.2071197411003236,
|
| 1502 |
+
"grad_norm": 0.19679434597492218,
|
| 1503 |
+
"learning_rate": 5e-05,
|
| 1504 |
+
"loss": 0.3481,
|
| 1505 |
+
"num_tokens": 181168136.0,
|
| 1506 |
+
"step": 187
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 1.2135922330097086,
|
| 1510 |
+
"grad_norm": 0.1955721527338028,
|
| 1511 |
+
"learning_rate": 5e-05,
|
| 1512 |
+
"loss": 0.3381,
|
| 1513 |
+
"num_tokens": 182127126.0,
|
| 1514 |
+
"step": 188
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 1.220064724919094,
|
| 1518 |
+
"grad_norm": 0.20957227051258087,
|
| 1519 |
+
"learning_rate": 5e-05,
|
| 1520 |
+
"loss": 0.3423,
|
| 1521 |
+
"num_tokens": 183085892.0,
|
| 1522 |
+
"step": 189
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.226537216828479,
|
| 1526 |
+
"grad_norm": 0.20260438323020935,
|
| 1527 |
+
"learning_rate": 5e-05,
|
| 1528 |
+
"loss": 0.3381,
|
| 1529 |
+
"num_tokens": 184057299.0,
|
| 1530 |
+
"step": 190
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 1.233009708737864,
|
| 1534 |
+
"grad_norm": 0.1949196457862854,
|
| 1535 |
+
"learning_rate": 5e-05,
|
| 1536 |
+
"loss": 0.3357,
|
| 1537 |
+
"num_tokens": 184998791.0,
|
| 1538 |
+
"step": 191
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 1.2394822006472492,
|
| 1542 |
+
"grad_norm": 0.19839757680892944,
|
| 1543 |
+
"learning_rate": 5e-05,
|
| 1544 |
+
"loss": 0.333,
|
| 1545 |
+
"num_tokens": 185986785.0,
|
| 1546 |
+
"step": 192
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 1.2459546925566343,
|
| 1550 |
+
"grad_norm": 0.20561406016349792,
|
| 1551 |
+
"learning_rate": 5e-05,
|
| 1552 |
+
"loss": 0.3293,
|
| 1553 |
+
"num_tokens": 186929881.0,
|
| 1554 |
+
"step": 193
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 1.2524271844660193,
|
| 1558 |
+
"grad_norm": 0.2009248435497284,
|
| 1559 |
+
"learning_rate": 5e-05,
|
| 1560 |
+
"loss": 0.3435,
|
| 1561 |
+
"num_tokens": 187902972.0,
|
| 1562 |
+
"step": 194
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 1.2588996763754046,
|
| 1566 |
+
"grad_norm": 0.2801060378551483,
|
| 1567 |
+
"learning_rate": 5e-05,
|
| 1568 |
+
"loss": 0.3313,
|
| 1569 |
+
"num_tokens": 188884007.0,
|
| 1570 |
+
"step": 195
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 1.2653721682847896,
|
| 1574 |
+
"grad_norm": 0.1825418472290039,
|
| 1575 |
+
"learning_rate": 5e-05,
|
| 1576 |
+
"loss": 0.3318,
|
| 1577 |
+
"num_tokens": 189812757.0,
|
| 1578 |
+
"step": 196
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.2718446601941746,
|
| 1582 |
+
"grad_norm": 0.23952046036720276,
|
| 1583 |
+
"learning_rate": 5e-05,
|
| 1584 |
+
"loss": 0.3343,
|
| 1585 |
+
"num_tokens": 190775296.0,
|
| 1586 |
+
"step": 197
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 1.27831715210356,
|
| 1590 |
+
"grad_norm": 0.213717520236969,
|
| 1591 |
+
"learning_rate": 5e-05,
|
| 1592 |
+
"loss": 0.3383,
|
| 1593 |
+
"num_tokens": 191750113.0,
|
| 1594 |
+
"step": 198
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 1.284789644012945,
|
| 1598 |
+
"grad_norm": 0.23496580123901367,
|
| 1599 |
+
"learning_rate": 5e-05,
|
| 1600 |
+
"loss": 0.3381,
|
| 1601 |
+
"num_tokens": 192691419.0,
|
| 1602 |
+
"step": 199
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 1.29126213592233,
|
| 1606 |
+
"grad_norm": 0.21562671661376953,
|
| 1607 |
+
"learning_rate": 5e-05,
|
| 1608 |
+
"loss": 0.3414,
|
| 1609 |
+
"num_tokens": 193680379.0,
|
| 1610 |
+
"step": 200
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 1.2977346278317152,
|
| 1614 |
+
"grad_norm": 0.19444721937179565,
|
| 1615 |
+
"learning_rate": 5e-05,
|
| 1616 |
+
"loss": 0.334,
|
| 1617 |
+
"num_tokens": 194655500.0,
|
| 1618 |
+
"step": 201
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 1.3042071197411003,
|
| 1622 |
+
"grad_norm": 0.16557656228542328,
|
| 1623 |
+
"learning_rate": 5e-05,
|
| 1624 |
+
"loss": 0.3392,
|
| 1625 |
+
"num_tokens": 195598008.0,
|
| 1626 |
+
"step": 202
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 1.3106796116504853,
|
| 1630 |
+
"grad_norm": 0.18384099006652832,
|
| 1631 |
+
"learning_rate": 5e-05,
|
| 1632 |
+
"loss": 0.3414,
|
| 1633 |
+
"num_tokens": 196583549.0,
|
| 1634 |
+
"step": 203
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.3171521035598706,
|
| 1638 |
+
"grad_norm": 0.2008940875530243,
|
| 1639 |
+
"learning_rate": 5e-05,
|
| 1640 |
+
"loss": 0.3387,
|
| 1641 |
+
"num_tokens": 197555491.0,
|
| 1642 |
+
"step": 204
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 1.3236245954692556,
|
| 1646 |
+
"grad_norm": 0.18595947325229645,
|
| 1647 |
+
"learning_rate": 5e-05,
|
| 1648 |
+
"loss": 0.3335,
|
| 1649 |
+
"num_tokens": 198552040.0,
|
| 1650 |
+
"step": 205
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 1.3300970873786409,
|
| 1654 |
+
"grad_norm": 0.21683627367019653,
|
| 1655 |
+
"learning_rate": 5e-05,
|
| 1656 |
+
"loss": 0.3328,
|
| 1657 |
+
"num_tokens": 199517007.0,
|
| 1658 |
+
"step": 206
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 1.3365695792880259,
|
| 1662 |
+
"grad_norm": 0.19960325956344604,
|
| 1663 |
+
"learning_rate": 5e-05,
|
| 1664 |
+
"loss": 0.3398,
|
| 1665 |
+
"num_tokens": 200490485.0,
|
| 1666 |
+
"step": 207
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 1.343042071197411,
|
| 1670 |
+
"grad_norm": 0.18728888034820557,
|
| 1671 |
+
"learning_rate": 5e-05,
|
| 1672 |
+
"loss": 0.3437,
|
| 1673 |
+
"num_tokens": 201459121.0,
|
| 1674 |
+
"step": 208
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 1.3495145631067962,
|
| 1678 |
+
"grad_norm": 0.19551408290863037,
|
| 1679 |
+
"learning_rate": 5e-05,
|
| 1680 |
+
"loss": 0.3339,
|
| 1681 |
+
"num_tokens": 202378391.0,
|
| 1682 |
+
"step": 209
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 1.3559870550161812,
|
| 1686 |
+
"grad_norm": 0.19920724630355835,
|
| 1687 |
+
"learning_rate": 5e-05,
|
| 1688 |
+
"loss": 0.3421,
|
| 1689 |
+
"num_tokens": 203389991.0,
|
| 1690 |
+
"step": 210
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 1.3624595469255665,
|
| 1694 |
+
"grad_norm": 0.22347542643547058,
|
| 1695 |
+
"learning_rate": 5e-05,
|
| 1696 |
+
"loss": 0.3417,
|
| 1697 |
+
"num_tokens": 204350028.0,
|
| 1698 |
+
"step": 211
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 1.3689320388349515,
|
| 1702 |
+
"grad_norm": 0.21298804879188538,
|
| 1703 |
+
"learning_rate": 5e-05,
|
| 1704 |
+
"loss": 0.3412,
|
| 1705 |
+
"num_tokens": 205321725.0,
|
| 1706 |
+
"step": 212
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 1.3754045307443366,
|
| 1710 |
+
"grad_norm": 0.2074659764766693,
|
| 1711 |
+
"learning_rate": 5e-05,
|
| 1712 |
+
"loss": 0.3414,
|
| 1713 |
+
"num_tokens": 206300400.0,
|
| 1714 |
+
"step": 213
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 1.3818770226537218,
|
| 1718 |
+
"grad_norm": 0.17087648808956146,
|
| 1719 |
+
"learning_rate": 5e-05,
|
| 1720 |
+
"loss": 0.3351,
|
| 1721 |
+
"num_tokens": 207269349.0,
|
| 1722 |
+
"step": 214
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 1.3883495145631068,
|
| 1726 |
+
"grad_norm": 0.18093572556972504,
|
| 1727 |
+
"learning_rate": 5e-05,
|
| 1728 |
+
"loss": 0.3366,
|
| 1729 |
+
"num_tokens": 208239995.0,
|
| 1730 |
+
"step": 215
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 1.3948220064724919,
|
| 1734 |
+
"grad_norm": 0.23184221982955933,
|
| 1735 |
+
"learning_rate": 5e-05,
|
| 1736 |
+
"loss": 0.3428,
|
| 1737 |
+
"num_tokens": 209197405.0,
|
| 1738 |
+
"step": 216
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 1.4012944983818771,
|
| 1742 |
+
"grad_norm": 0.23396241664886475,
|
| 1743 |
+
"learning_rate": 5e-05,
|
| 1744 |
+
"loss": 0.3359,
|
| 1745 |
+
"num_tokens": 210173069.0,
|
| 1746 |
+
"step": 217
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 1.4077669902912622,
|
| 1750 |
+
"grad_norm": 0.18798178434371948,
|
| 1751 |
+
"learning_rate": 5e-05,
|
| 1752 |
+
"loss": 0.3336,
|
| 1753 |
+
"num_tokens": 211140476.0,
|
| 1754 |
+
"step": 218
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 1.4142394822006472,
|
| 1758 |
+
"grad_norm": 0.17764322459697723,
|
| 1759 |
+
"learning_rate": 5e-05,
|
| 1760 |
+
"loss": 0.3339,
|
| 1761 |
+
"num_tokens": 212101096.0,
|
| 1762 |
+
"step": 219
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 1.4207119741100325,
|
| 1766 |
+
"grad_norm": 0.16891926527023315,
|
| 1767 |
+
"learning_rate": 5e-05,
|
| 1768 |
+
"loss": 0.3395,
|
| 1769 |
+
"num_tokens": 213068720.0,
|
| 1770 |
+
"step": 220
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 1.4271844660194175,
|
| 1774 |
+
"grad_norm": 0.1684737652540207,
|
| 1775 |
+
"learning_rate": 5e-05,
|
| 1776 |
+
"loss": 0.3393,
|
| 1777 |
+
"num_tokens": 214020099.0,
|
| 1778 |
+
"step": 221
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 1.4336569579288025,
|
| 1782 |
+
"grad_norm": 0.17267465591430664,
|
| 1783 |
+
"learning_rate": 5e-05,
|
| 1784 |
+
"loss": 0.3339,
|
| 1785 |
+
"num_tokens": 214947806.0,
|
| 1786 |
+
"step": 222
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 1.4401294498381878,
|
| 1790 |
+
"grad_norm": 0.1806415170431137,
|
| 1791 |
+
"learning_rate": 5e-05,
|
| 1792 |
+
"loss": 0.3359,
|
| 1793 |
+
"num_tokens": 215925598.0,
|
| 1794 |
+
"step": 223
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 1.4466019417475728,
|
| 1798 |
+
"grad_norm": 0.178355872631073,
|
| 1799 |
+
"learning_rate": 5e-05,
|
| 1800 |
+
"loss": 0.3328,
|
| 1801 |
+
"num_tokens": 216915650.0,
|
| 1802 |
+
"step": 224
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 1.4530744336569579,
|
| 1806 |
+
"grad_norm": 0.16551369428634644,
|
| 1807 |
+
"learning_rate": 5e-05,
|
| 1808 |
+
"loss": 0.3389,
|
| 1809 |
+
"num_tokens": 217865373.0,
|
| 1810 |
+
"step": 225
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 1.4595469255663431,
|
| 1814 |
+
"grad_norm": 0.17925454676151276,
|
| 1815 |
+
"learning_rate": 5e-05,
|
| 1816 |
+
"loss": 0.3309,
|
| 1817 |
+
"num_tokens": 218823612.0,
|
| 1818 |
+
"step": 226
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 1.4660194174757282,
|
| 1822 |
+
"grad_norm": 0.1850486695766449,
|
| 1823 |
+
"learning_rate": 5e-05,
|
| 1824 |
+
"loss": 0.3314,
|
| 1825 |
+
"num_tokens": 219799962.0,
|
| 1826 |
+
"step": 227
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 1.4724919093851132,
|
| 1830 |
+
"grad_norm": 0.18899139761924744,
|
| 1831 |
+
"learning_rate": 5e-05,
|
| 1832 |
+
"loss": 0.3401,
|
| 1833 |
+
"num_tokens": 220771199.0,
|
| 1834 |
+
"step": 228
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 1.4789644012944985,
|
| 1838 |
+
"grad_norm": 0.19012326002120972,
|
| 1839 |
+
"learning_rate": 5e-05,
|
| 1840 |
+
"loss": 0.3359,
|
| 1841 |
+
"num_tokens": 221736326.0,
|
| 1842 |
+
"step": 229
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 1.4854368932038835,
|
| 1846 |
+
"grad_norm": 0.19176773726940155,
|
| 1847 |
+
"learning_rate": 5e-05,
|
| 1848 |
+
"loss": 0.3365,
|
| 1849 |
+
"num_tokens": 222710609.0,
|
| 1850 |
+
"step": 230
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 1.4919093851132685,
|
| 1854 |
+
"grad_norm": 0.21373401582241058,
|
| 1855 |
+
"learning_rate": 5e-05,
|
| 1856 |
+
"loss": 0.3326,
|
| 1857 |
+
"num_tokens": 223688658.0,
|
| 1858 |
+
"step": 231
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 1.4983818770226538,
|
| 1862 |
+
"grad_norm": 0.1788434386253357,
|
| 1863 |
+
"learning_rate": 5e-05,
|
| 1864 |
+
"loss": 0.3366,
|
| 1865 |
+
"num_tokens": 224689265.0,
|
| 1866 |
+
"step": 232
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 1.5048543689320388,
|
| 1870 |
+
"grad_norm": 0.16676850616931915,
|
| 1871 |
+
"learning_rate": 5e-05,
|
| 1872 |
+
"loss": 0.3345,
|
| 1873 |
+
"num_tokens": 225643475.0,
|
| 1874 |
+
"step": 233
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 1.5113268608414239,
|
| 1878 |
+
"grad_norm": 0.1769399642944336,
|
| 1879 |
+
"learning_rate": 5e-05,
|
| 1880 |
+
"loss": 0.3378,
|
| 1881 |
+
"num_tokens": 226617652.0,
|
| 1882 |
+
"step": 234
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 1.5177993527508091,
|
| 1886 |
+
"grad_norm": 0.17505072057247162,
|
| 1887 |
+
"learning_rate": 5e-05,
|
| 1888 |
+
"loss": 0.3349,
|
| 1889 |
+
"num_tokens": 227553267.0,
|
| 1890 |
+
"step": 235
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 1.5242718446601942,
|
| 1894 |
+
"grad_norm": 0.20999805629253387,
|
| 1895 |
+
"learning_rate": 5e-05,
|
| 1896 |
+
"loss": 0.3366,
|
| 1897 |
+
"num_tokens": 228538404.0,
|
| 1898 |
+
"step": 236
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 1.5307443365695792,
|
| 1902 |
+
"grad_norm": 0.20305493474006653,
|
| 1903 |
+
"learning_rate": 5e-05,
|
| 1904 |
+
"loss": 0.3345,
|
| 1905 |
+
"num_tokens": 229526832.0,
|
| 1906 |
+
"step": 237
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 1.5372168284789645,
|
| 1910 |
+
"grad_norm": 0.20696744322776794,
|
| 1911 |
+
"learning_rate": 5e-05,
|
| 1912 |
+
"loss": 0.3392,
|
| 1913 |
+
"num_tokens": 230514566.0,
|
| 1914 |
+
"step": 238
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 1.5436893203883495,
|
| 1918 |
+
"grad_norm": 0.21763259172439575,
|
| 1919 |
+
"learning_rate": 5e-05,
|
| 1920 |
+
"loss": 0.3362,
|
| 1921 |
+
"num_tokens": 231499488.0,
|
| 1922 |
+
"step": 239
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 1.5501618122977345,
|
| 1926 |
+
"grad_norm": 0.16580604016780853,
|
| 1927 |
+
"learning_rate": 5e-05,
|
| 1928 |
+
"loss": 0.3456,
|
| 1929 |
+
"num_tokens": 232467260.0,
|
| 1930 |
+
"step": 240
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 1.5566343042071198,
|
| 1934 |
+
"grad_norm": 0.17884966731071472,
|
| 1935 |
+
"learning_rate": 5e-05,
|
| 1936 |
+
"loss": 0.3379,
|
| 1937 |
+
"num_tokens": 233453448.0,
|
| 1938 |
+
"step": 241
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 1.5631067961165048,
|
| 1942 |
+
"grad_norm": 0.17534446716308594,
|
| 1943 |
+
"learning_rate": 5e-05,
|
| 1944 |
+
"loss": 0.3327,
|
| 1945 |
+
"num_tokens": 234468336.0,
|
| 1946 |
+
"step": 242
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 1.5695792880258899,
|
| 1950 |
+
"grad_norm": 0.19182085990905762,
|
| 1951 |
+
"learning_rate": 5e-05,
|
| 1952 |
+
"loss": 0.3401,
|
| 1953 |
+
"num_tokens": 235437157.0,
|
| 1954 |
+
"step": 243
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 1.5760517799352751,
|
| 1958 |
+
"grad_norm": 0.17959745228290558,
|
| 1959 |
+
"learning_rate": 5e-05,
|
| 1960 |
+
"loss": 0.3427,
|
| 1961 |
+
"num_tokens": 236420720.0,
|
| 1962 |
+
"step": 244
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 1.5825242718446602,
|
| 1966 |
+
"grad_norm": 0.19488820433616638,
|
| 1967 |
+
"learning_rate": 5e-05,
|
| 1968 |
+
"loss": 0.3384,
|
| 1969 |
+
"num_tokens": 237408717.0,
|
| 1970 |
+
"step": 245
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 1.5889967637540452,
|
| 1974 |
+
"grad_norm": 0.18275916576385498,
|
| 1975 |
+
"learning_rate": 5e-05,
|
| 1976 |
+
"loss": 0.3415,
|
| 1977 |
+
"num_tokens": 238399497.0,
|
| 1978 |
+
"step": 246
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"epoch": 1.5954692556634305,
|
| 1982 |
+
"grad_norm": 0.17819155752658844,
|
| 1983 |
+
"learning_rate": 5e-05,
|
| 1984 |
+
"loss": 0.3437,
|
| 1985 |
+
"num_tokens": 239341614.0,
|
| 1986 |
+
"step": 247
|
| 1987 |
+
},
|
| 1988 |
+
{
|
| 1989 |
+
"epoch": 1.6019417475728155,
|
| 1990 |
+
"grad_norm": 0.20477968454360962,
|
| 1991 |
+
"learning_rate": 5e-05,
|
| 1992 |
+
"loss": 0.3374,
|
| 1993 |
+
"num_tokens": 240303758.0,
|
| 1994 |
+
"step": 248
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 1.6084142394822005,
|
| 1998 |
+
"grad_norm": 0.2054113894701004,
|
| 1999 |
+
"learning_rate": 5e-05,
|
| 2000 |
+
"loss": 0.3375,
|
| 2001 |
+
"num_tokens": 241254594.0,
|
| 2002 |
+
"step": 249
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 1.6148867313915858,
|
| 2006 |
+
"grad_norm": 0.16167765855789185,
|
| 2007 |
+
"learning_rate": 5e-05,
|
| 2008 |
+
"loss": 0.3417,
|
| 2009 |
+
"num_tokens": 242199383.0,
|
| 2010 |
+
"step": 250
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 1.6213592233009708,
|
| 2014 |
+
"grad_norm": 0.18958935141563416,
|
| 2015 |
+
"learning_rate": 5e-05,
|
| 2016 |
+
"loss": 0.3358,
|
| 2017 |
+
"num_tokens": 243205373.0,
|
| 2018 |
+
"step": 251
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 1.6278317152103559,
|
| 2022 |
+
"grad_norm": 0.1921786665916443,
|
| 2023 |
+
"learning_rate": 5e-05,
|
| 2024 |
+
"loss": 0.3299,
|
| 2025 |
+
"num_tokens": 244177909.0,
|
| 2026 |
+
"step": 252
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 1.6343042071197411,
|
| 2030 |
+
"grad_norm": 0.1913369745016098,
|
| 2031 |
+
"learning_rate": 5e-05,
|
| 2032 |
+
"loss": 0.3428,
|
| 2033 |
+
"num_tokens": 245165218.0,
|
| 2034 |
+
"step": 253
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 1.6407766990291264,
|
| 2038 |
+
"grad_norm": 0.2190655767917633,
|
| 2039 |
+
"learning_rate": 5e-05,
|
| 2040 |
+
"loss": 0.3325,
|
| 2041 |
+
"num_tokens": 246106607.0,
|
| 2042 |
+
"step": 254
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 1.6472491909385112,
|
| 2046 |
+
"grad_norm": 0.196571484208107,
|
| 2047 |
+
"learning_rate": 5e-05,
|
| 2048 |
+
"loss": 0.3381,
|
| 2049 |
+
"num_tokens": 247086207.0,
|
| 2050 |
+
"step": 255
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"epoch": 1.6537216828478964,
|
| 2054 |
+
"grad_norm": 0.21676744520664215,
|
| 2055 |
+
"learning_rate": 5e-05,
|
| 2056 |
+
"loss": 0.3398,
|
| 2057 |
+
"num_tokens": 248068946.0,
|
| 2058 |
+
"step": 256
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 1.6601941747572817,
|
| 2062 |
+
"grad_norm": 0.18862760066986084,
|
| 2063 |
+
"learning_rate": 5e-05,
|
| 2064 |
+
"loss": 0.3333,
|
| 2065 |
+
"num_tokens": 249047854.0,
|
| 2066 |
+
"step": 257
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 1.6666666666666665,
|
| 2070 |
+
"grad_norm": 0.18911020457744598,
|
| 2071 |
+
"learning_rate": 5e-05,
|
| 2072 |
+
"loss": 0.3437,
|
| 2073 |
+
"num_tokens": 250033293.0,
|
| 2074 |
+
"step": 258
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 1.6731391585760518,
|
| 2078 |
+
"grad_norm": 0.17415007948875427,
|
| 2079 |
+
"learning_rate": 5e-05,
|
| 2080 |
+
"loss": 0.3399,
|
| 2081 |
+
"num_tokens": 251008614.0,
|
| 2082 |
+
"step": 259
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 1.679611650485437,
|
| 2086 |
+
"grad_norm": 0.1821623295545578,
|
| 2087 |
+
"learning_rate": 5e-05,
|
| 2088 |
+
"loss": 0.333,
|
| 2089 |
+
"num_tokens": 251959677.0,
|
| 2090 |
+
"step": 260
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 1.6860841423948218,
|
| 2094 |
+
"grad_norm": 0.19831088185310364,
|
| 2095 |
+
"learning_rate": 5e-05,
|
| 2096 |
+
"loss": 0.3416,
|
| 2097 |
+
"num_tokens": 252935571.0,
|
| 2098 |
+
"step": 261
|
| 2099 |
+
},
|
| 2100 |
+
{
|
| 2101 |
+
"epoch": 1.692556634304207,
|
| 2102 |
+
"grad_norm": 0.19969160854816437,
|
| 2103 |
+
"learning_rate": 5e-05,
|
| 2104 |
+
"loss": 0.34,
|
| 2105 |
+
"num_tokens": 253879032.0,
|
| 2106 |
+
"step": 262
|
| 2107 |
+
},
|
| 2108 |
+
{
|
| 2109 |
+
"epoch": 1.6990291262135924,
|
| 2110 |
+
"grad_norm": 0.17339688539505005,
|
| 2111 |
+
"learning_rate": 5e-05,
|
| 2112 |
+
"loss": 0.3266,
|
| 2113 |
+
"num_tokens": 254826418.0,
|
| 2114 |
+
"step": 263
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 1.7055016181229772,
|
| 2118 |
+
"grad_norm": 0.1652975082397461,
|
| 2119 |
+
"learning_rate": 5e-05,
|
| 2120 |
+
"loss": 0.3397,
|
| 2121 |
+
"num_tokens": 255785864.0,
|
| 2122 |
+
"step": 264
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 1.7119741100323624,
|
| 2126 |
+
"grad_norm": 0.18107086420059204,
|
| 2127 |
+
"learning_rate": 5e-05,
|
| 2128 |
+
"loss": 0.3347,
|
| 2129 |
+
"num_tokens": 256751813.0,
|
| 2130 |
+
"step": 265
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 1.7184466019417477,
|
| 2134 |
+
"grad_norm": 0.23111234605312347,
|
| 2135 |
+
"learning_rate": 5e-05,
|
| 2136 |
+
"loss": 0.3419,
|
| 2137 |
+
"num_tokens": 257721834.0,
|
| 2138 |
+
"step": 266
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 1.7249190938511327,
|
| 2142 |
+
"grad_norm": 0.19649353623390198,
|
| 2143 |
+
"learning_rate": 5e-05,
|
| 2144 |
+
"loss": 0.3398,
|
| 2145 |
+
"num_tokens": 258673121.0,
|
| 2146 |
+
"step": 267
|
| 2147 |
+
},
|
| 2148 |
+
{
|
| 2149 |
+
"epoch": 1.7313915857605178,
|
| 2150 |
+
"grad_norm": 0.18504799902439117,
|
| 2151 |
+
"learning_rate": 5e-05,
|
| 2152 |
+
"loss": 0.3437,
|
| 2153 |
+
"num_tokens": 259660088.0,
|
| 2154 |
+
"step": 268
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 1.737864077669903,
|
| 2158 |
+
"grad_norm": 0.172653466463089,
|
| 2159 |
+
"learning_rate": 5e-05,
|
| 2160 |
+
"loss": 0.3438,
|
| 2161 |
+
"num_tokens": 260659515.0,
|
| 2162 |
+
"step": 269
|
| 2163 |
+
},
|
| 2164 |
+
{
|
| 2165 |
+
"epoch": 1.744336569579288,
|
| 2166 |
+
"grad_norm": 0.180886372923851,
|
| 2167 |
+
"learning_rate": 5e-05,
|
| 2168 |
+
"loss": 0.3386,
|
| 2169 |
+
"num_tokens": 261673283.0,
|
| 2170 |
+
"step": 270
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 1.750809061488673,
|
| 2174 |
+
"grad_norm": 0.19707052409648895,
|
| 2175 |
+
"learning_rate": 5e-05,
|
| 2176 |
+
"loss": 0.3318,
|
| 2177 |
+
"num_tokens": 262663793.0,
|
| 2178 |
+
"step": 271
|
| 2179 |
+
},
|
| 2180 |
+
{
|
| 2181 |
+
"epoch": 1.7572815533980584,
|
| 2182 |
+
"grad_norm": 0.21546867489814758,
|
| 2183 |
+
"learning_rate": 5e-05,
|
| 2184 |
+
"loss": 0.3382,
|
| 2185 |
+
"num_tokens": 263631573.0,
|
| 2186 |
+
"step": 272
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 1.7637540453074434,
|
| 2190 |
+
"grad_norm": 0.19814084470272064,
|
| 2191 |
+
"learning_rate": 5e-05,
|
| 2192 |
+
"loss": 0.3427,
|
| 2193 |
+
"num_tokens": 264625690.0,
|
| 2194 |
+
"step": 273
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 1.7702265372168284,
|
| 2198 |
+
"grad_norm": 0.19324062764644623,
|
| 2199 |
+
"learning_rate": 5e-05,
|
| 2200 |
+
"loss": 0.3279,
|
| 2201 |
+
"num_tokens": 265585386.0,
|
| 2202 |
+
"step": 274
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 1.7766990291262137,
|
| 2206 |
+
"grad_norm": 0.16428862512111664,
|
| 2207 |
+
"learning_rate": 5e-05,
|
| 2208 |
+
"loss": 0.3455,
|
| 2209 |
+
"num_tokens": 266565331.0,
|
| 2210 |
+
"step": 275
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 1.7831715210355987,
|
| 2214 |
+
"grad_norm": 0.20684756338596344,
|
| 2215 |
+
"learning_rate": 5e-05,
|
| 2216 |
+
"loss": 0.3357,
|
| 2217 |
+
"num_tokens": 267570388.0,
|
| 2218 |
+
"step": 276
|
| 2219 |
+
},
|
| 2220 |
+
{
|
| 2221 |
+
"epoch": 1.7896440129449838,
|
| 2222 |
+
"grad_norm": 0.18957240879535675,
|
| 2223 |
+
"learning_rate": 5e-05,
|
| 2224 |
+
"loss": 0.3364,
|
| 2225 |
+
"num_tokens": 268536852.0,
|
| 2226 |
+
"step": 277
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"epoch": 1.796116504854369,
|
| 2230 |
+
"grad_norm": 0.17509396374225616,
|
| 2231 |
+
"learning_rate": 5e-05,
|
| 2232 |
+
"loss": 0.3422,
|
| 2233 |
+
"num_tokens": 269499895.0,
|
| 2234 |
+
"step": 278
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 1.802588996763754,
|
| 2238 |
+
"grad_norm": 0.16740205883979797,
|
| 2239 |
+
"learning_rate": 5e-05,
|
| 2240 |
+
"loss": 0.3325,
|
| 2241 |
+
"num_tokens": 270449454.0,
|
| 2242 |
+
"step": 279
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 1.809061488673139,
|
| 2246 |
+
"grad_norm": 0.1855873316526413,
|
| 2247 |
+
"learning_rate": 5e-05,
|
| 2248 |
+
"loss": 0.3315,
|
| 2249 |
+
"num_tokens": 271445748.0,
|
| 2250 |
+
"step": 280
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 1.8155339805825244,
|
| 2254 |
+
"grad_norm": 0.15973623096942902,
|
| 2255 |
+
"learning_rate": 5e-05,
|
| 2256 |
+
"loss": 0.3382,
|
| 2257 |
+
"num_tokens": 272437678.0,
|
| 2258 |
+
"step": 281
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 1.8220064724919094,
|
| 2262 |
+
"grad_norm": 0.17084303498268127,
|
| 2263 |
+
"learning_rate": 5e-05,
|
| 2264 |
+
"loss": 0.3408,
|
| 2265 |
+
"num_tokens": 273421632.0,
|
| 2266 |
+
"step": 282
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 1.8284789644012944,
|
| 2270 |
+
"grad_norm": 0.1683521568775177,
|
| 2271 |
+
"learning_rate": 5e-05,
|
| 2272 |
+
"loss": 0.3305,
|
| 2273 |
+
"num_tokens": 274382121.0,
|
| 2274 |
+
"step": 283
|
| 2275 |
+
},
|
| 2276 |
+
{
|
| 2277 |
+
"epoch": 1.8349514563106797,
|
| 2278 |
+
"grad_norm": 0.18775099515914917,
|
| 2279 |
+
"learning_rate": 5e-05,
|
| 2280 |
+
"loss": 0.3277,
|
| 2281 |
+
"num_tokens": 275355409.0,
|
| 2282 |
+
"step": 284
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 1.8414239482200647,
|
| 2286 |
+
"grad_norm": 0.19409479200839996,
|
| 2287 |
+
"learning_rate": 5e-05,
|
| 2288 |
+
"loss": 0.3323,
|
| 2289 |
+
"num_tokens": 276363366.0,
|
| 2290 |
+
"step": 285
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"epoch": 1.8478964401294498,
|
| 2294 |
+
"grad_norm": 0.19770023226737976,
|
| 2295 |
+
"learning_rate": 5e-05,
|
| 2296 |
+
"loss": 0.3379,
|
| 2297 |
+
"num_tokens": 277316291.0,
|
| 2298 |
+
"step": 286
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 1.854368932038835,
|
| 2302 |
+
"grad_norm": 0.19350184500217438,
|
| 2303 |
+
"learning_rate": 5e-05,
|
| 2304 |
+
"loss": 0.3375,
|
| 2305 |
+
"num_tokens": 278277485.0,
|
| 2306 |
+
"step": 287
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 1.86084142394822,
|
| 2310 |
+
"grad_norm": 0.17950181663036346,
|
| 2311 |
+
"learning_rate": 5e-05,
|
| 2312 |
+
"loss": 0.3298,
|
| 2313 |
+
"num_tokens": 279263638.0,
|
| 2314 |
+
"step": 288
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 1.867313915857605,
|
| 2318 |
+
"grad_norm": 0.1721695512533188,
|
| 2319 |
+
"learning_rate": 5e-05,
|
| 2320 |
+
"loss": 0.3304,
|
| 2321 |
+
"num_tokens": 280229543.0,
|
| 2322 |
+
"step": 289
|
| 2323 |
+
},
|
| 2324 |
+
{
|
| 2325 |
+
"epoch": 1.8737864077669903,
|
| 2326 |
+
"grad_norm": 0.15675385296344757,
|
| 2327 |
+
"learning_rate": 5e-05,
|
| 2328 |
+
"loss": 0.3299,
|
| 2329 |
+
"num_tokens": 281207364.0,
|
| 2330 |
+
"step": 290
|
| 2331 |
+
},
|
| 2332 |
+
{
|
| 2333 |
+
"epoch": 1.8802588996763754,
|
| 2334 |
+
"grad_norm": 0.1917867511510849,
|
| 2335 |
+
"learning_rate": 5e-05,
|
| 2336 |
+
"loss": 0.3291,
|
| 2337 |
+
"num_tokens": 282156358.0,
|
| 2338 |
+
"step": 291
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 1.8867313915857604,
|
| 2342 |
+
"grad_norm": 0.18502658605575562,
|
| 2343 |
+
"learning_rate": 5e-05,
|
| 2344 |
+
"loss": 0.3324,
|
| 2345 |
+
"num_tokens": 283119435.0,
|
| 2346 |
+
"step": 292
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 1.8932038834951457,
|
| 2350 |
+
"grad_norm": 0.17235122621059418,
|
| 2351 |
+
"learning_rate": 5e-05,
|
| 2352 |
+
"loss": 0.3393,
|
| 2353 |
+
"num_tokens": 284084676.0,
|
| 2354 |
+
"step": 293
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 1.8996763754045307,
|
| 2358 |
+
"grad_norm": 0.18662425875663757,
|
| 2359 |
+
"learning_rate": 5e-05,
|
| 2360 |
+
"loss": 0.3507,
|
| 2361 |
+
"num_tokens": 285051682.0,
|
| 2362 |
+
"step": 294
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 1.9061488673139158,
|
| 2366 |
+
"grad_norm": 0.1718778908252716,
|
| 2367 |
+
"learning_rate": 5e-05,
|
| 2368 |
+
"loss": 0.3358,
|
| 2369 |
+
"num_tokens": 286037634.0,
|
| 2370 |
+
"step": 295
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 1.912621359223301,
|
| 2374 |
+
"grad_norm": 0.16769616305828094,
|
| 2375 |
+
"learning_rate": 5e-05,
|
| 2376 |
+
"loss": 0.3305,
|
| 2377 |
+
"num_tokens": 287028258.0,
|
| 2378 |
+
"step": 296
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 1.919093851132686,
|
| 2382 |
+
"grad_norm": 0.1893540471792221,
|
| 2383 |
+
"learning_rate": 5e-05,
|
| 2384 |
+
"loss": 0.3333,
|
| 2385 |
+
"num_tokens": 287996979.0,
|
| 2386 |
+
"step": 297
|
| 2387 |
+
},
|
| 2388 |
+
{
|
| 2389 |
+
"epoch": 1.925566343042071,
|
| 2390 |
+
"grad_norm": 0.20489463210105896,
|
| 2391 |
+
"learning_rate": 5e-05,
|
| 2392 |
+
"loss": 0.3336,
|
| 2393 |
+
"num_tokens": 288984893.0,
|
| 2394 |
+
"step": 298
|
| 2395 |
+
},
|
| 2396 |
+
{
|
| 2397 |
+
"epoch": 1.9320388349514563,
|
| 2398 |
+
"grad_norm": 0.17792005836963654,
|
| 2399 |
+
"learning_rate": 5e-05,
|
| 2400 |
+
"loss": 0.3354,
|
| 2401 |
+
"num_tokens": 289948988.0,
|
| 2402 |
+
"step": 299
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 1.9385113268608414,
|
| 2406 |
+
"grad_norm": 0.1810276359319687,
|
| 2407 |
+
"learning_rate": 5e-05,
|
| 2408 |
+
"loss": 0.3408,
|
| 2409 |
+
"num_tokens": 290947258.0,
|
| 2410 |
+
"step": 300
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 1.9449838187702264,
|
| 2414 |
+
"grad_norm": 0.19058284163475037,
|
| 2415 |
+
"learning_rate": 5e-05,
|
| 2416 |
+
"loss": 0.3366,
|
| 2417 |
+
"num_tokens": 291896825.0,
|
| 2418 |
+
"step": 301
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 1.9514563106796117,
|
| 2422 |
+
"grad_norm": 0.19804033637046814,
|
| 2423 |
+
"learning_rate": 5e-05,
|
| 2424 |
+
"loss": 0.3272,
|
| 2425 |
+
"num_tokens": 292874918.0,
|
| 2426 |
+
"step": 302
|
| 2427 |
+
},
|
| 2428 |
+
{
|
| 2429 |
+
"epoch": 1.9579288025889967,
|
| 2430 |
+
"grad_norm": 0.2071111500263214,
|
| 2431 |
+
"learning_rate": 5e-05,
|
| 2432 |
+
"loss": 0.3388,
|
| 2433 |
+
"num_tokens": 293858095.0,
|
| 2434 |
+
"step": 303
|
| 2435 |
+
},
|
| 2436 |
+
{
|
| 2437 |
+
"epoch": 1.9644012944983817,
|
| 2438 |
+
"grad_norm": 0.18215212225914001,
|
| 2439 |
+
"learning_rate": 5e-05,
|
| 2440 |
+
"loss": 0.3403,
|
| 2441 |
+
"num_tokens": 294831363.0,
|
| 2442 |
+
"step": 304
|
| 2443 |
+
},
|
| 2444 |
+
{
|
| 2445 |
+
"epoch": 1.970873786407767,
|
| 2446 |
+
"grad_norm": 0.15112967789173126,
|
| 2447 |
+
"learning_rate": 5e-05,
|
| 2448 |
+
"loss": 0.3299,
|
| 2449 |
+
"num_tokens": 295815029.0,
|
| 2450 |
+
"step": 305
|
| 2451 |
+
},
|
| 2452 |
+
{
|
| 2453 |
+
"epoch": 1.9773462783171523,
|
| 2454 |
+
"grad_norm": 0.17273668944835663,
|
| 2455 |
+
"learning_rate": 5e-05,
|
| 2456 |
+
"loss": 0.3428,
|
| 2457 |
+
"num_tokens": 296783225.0,
|
| 2458 |
+
"step": 306
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 1.983818770226537,
|
| 2462 |
+
"grad_norm": 0.17477214336395264,
|
| 2463 |
+
"learning_rate": 5e-05,
|
| 2464 |
+
"loss": 0.3337,
|
| 2465 |
+
"num_tokens": 297740638.0,
|
| 2466 |
+
"step": 307
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 1.9902912621359223,
|
| 2470 |
+
"grad_norm": 0.183084636926651,
|
| 2471 |
+
"learning_rate": 5e-05,
|
| 2472 |
+
"loss": 0.3443,
|
| 2473 |
+
"num_tokens": 298713508.0,
|
| 2474 |
+
"step": 308
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 1.9967637540453076,
|
| 2478 |
+
"grad_norm": 0.1524902880191803,
|
| 2479 |
+
"learning_rate": 5e-05,
|
| 2480 |
+
"loss": 0.3363,
|
| 2481 |
+
"num_tokens": 299687136.0,
|
| 2482 |
+
"step": 309
|
| 2483 |
+
},
|
| 2484 |
+
{
|
| 2485 |
+
"epoch": 2.0,
|
| 2486 |
+
"grad_norm": 0.2531540095806122,
|
| 2487 |
+
"learning_rate": 5e-05,
|
| 2488 |
+
"loss": 0.3098,
|
| 2489 |
+
"num_tokens": 300160844.0,
|
| 2490 |
+
"step": 310
|
| 2491 |
+
},
|
| 2492 |
+
{
|
| 2493 |
+
"epoch": 2.0064724919093853,
|
| 2494 |
+
"grad_norm": 0.22765809297561646,
|
| 2495 |
+
"learning_rate": 5e-05,
|
| 2496 |
+
"loss": 0.2614,
|
| 2497 |
+
"num_tokens": 301102396.0,
|
| 2498 |
+
"step": 311
|
| 2499 |
+
},
|
| 2500 |
+
{
|
| 2501 |
+
"epoch": 2.01294498381877,
|
| 2502 |
+
"grad_norm": 0.2378404140472412,
|
| 2503 |
+
"learning_rate": 5e-05,
|
| 2504 |
+
"loss": 0.2622,
|
| 2505 |
+
"num_tokens": 302075156.0,
|
| 2506 |
+
"step": 312
|
| 2507 |
+
},
|
| 2508 |
+
{
|
| 2509 |
+
"epoch": 2.0194174757281553,
|
| 2510 |
+
"grad_norm": 0.22973977029323578,
|
| 2511 |
+
"learning_rate": 5e-05,
|
| 2512 |
+
"loss": 0.2604,
|
| 2513 |
+
"num_tokens": 303057420.0,
|
| 2514 |
+
"step": 313
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 2.0258899676375406,
|
| 2518 |
+
"grad_norm": 0.21607546508312225,
|
| 2519 |
+
"learning_rate": 5e-05,
|
| 2520 |
+
"loss": 0.2571,
|
| 2521 |
+
"num_tokens": 304035012.0,
|
| 2522 |
+
"step": 314
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 2.0323624595469254,
|
| 2526 |
+
"grad_norm": 0.25009459257125854,
|
| 2527 |
+
"learning_rate": 5e-05,
|
| 2528 |
+
"loss": 0.2624,
|
| 2529 |
+
"num_tokens": 305020171.0,
|
| 2530 |
+
"step": 315
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 2.0388349514563107,
|
| 2534 |
+
"grad_norm": 0.2218926101922989,
|
| 2535 |
+
"learning_rate": 5e-05,
|
| 2536 |
+
"loss": 0.2611,
|
| 2537 |
+
"num_tokens": 305997805.0,
|
| 2538 |
+
"step": 316
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 2.045307443365696,
|
| 2542 |
+
"grad_norm": 0.19613030552864075,
|
| 2543 |
+
"learning_rate": 5e-05,
|
| 2544 |
+
"loss": 0.2594,
|
| 2545 |
+
"num_tokens": 306946495.0,
|
| 2546 |
+
"step": 317
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 2.0517799352750807,
|
| 2550 |
+
"grad_norm": 0.23204907774925232,
|
| 2551 |
+
"learning_rate": 5e-05,
|
| 2552 |
+
"loss": 0.2636,
|
| 2553 |
+
"num_tokens": 307898930.0,
|
| 2554 |
+
"step": 318
|
| 2555 |
+
},
|
| 2556 |
+
{
|
| 2557 |
+
"epoch": 2.058252427184466,
|
| 2558 |
+
"grad_norm": 0.20592013001441956,
|
| 2559 |
+
"learning_rate": 5e-05,
|
| 2560 |
+
"loss": 0.2554,
|
| 2561 |
+
"num_tokens": 308853869.0,
|
| 2562 |
+
"step": 319
|
| 2563 |
+
},
|
| 2564 |
+
{
|
| 2565 |
+
"epoch": 2.0647249190938513,
|
| 2566 |
+
"grad_norm": 0.2031695544719696,
|
| 2567 |
+
"learning_rate": 5e-05,
|
| 2568 |
+
"loss": 0.2584,
|
| 2569 |
+
"num_tokens": 309835585.0,
|
| 2570 |
+
"step": 320
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"epoch": 2.071197411003236,
|
| 2574 |
+
"grad_norm": 0.2156866490840912,
|
| 2575 |
+
"learning_rate": 5e-05,
|
| 2576 |
+
"loss": 0.2544,
|
| 2577 |
+
"num_tokens": 310815130.0,
|
| 2578 |
+
"step": 321
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 2.0776699029126213,
|
| 2582 |
+
"grad_norm": 0.21014027297496796,
|
| 2583 |
+
"learning_rate": 5e-05,
|
| 2584 |
+
"loss": 0.2644,
|
| 2585 |
+
"num_tokens": 311797693.0,
|
| 2586 |
+
"step": 322
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 2.0841423948220066,
|
| 2590 |
+
"grad_norm": 0.19828633964061737,
|
| 2591 |
+
"learning_rate": 5e-05,
|
| 2592 |
+
"loss": 0.2569,
|
| 2593 |
+
"num_tokens": 312741860.0,
|
| 2594 |
+
"step": 323
|
| 2595 |
+
},
|
| 2596 |
+
{
|
| 2597 |
+
"epoch": 2.0906148867313914,
|
| 2598 |
+
"grad_norm": 0.24393822252750397,
|
| 2599 |
+
"learning_rate": 5e-05,
|
| 2600 |
+
"loss": 0.259,
|
| 2601 |
+
"num_tokens": 313699114.0,
|
| 2602 |
+
"step": 324
|
| 2603 |
+
},
|
| 2604 |
+
{
|
| 2605 |
+
"epoch": 2.0970873786407767,
|
| 2606 |
+
"grad_norm": 0.2079489678144455,
|
| 2607 |
+
"learning_rate": 5e-05,
|
| 2608 |
+
"loss": 0.2603,
|
| 2609 |
+
"num_tokens": 314676353.0,
|
| 2610 |
+
"step": 325
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 2.103559870550162,
|
| 2614 |
+
"grad_norm": 0.19386853277683258,
|
| 2615 |
+
"learning_rate": 5e-05,
|
| 2616 |
+
"loss": 0.2632,
|
| 2617 |
+
"num_tokens": 315619556.0,
|
| 2618 |
+
"step": 326
|
| 2619 |
+
},
|
| 2620 |
+
{
|
| 2621 |
+
"epoch": 2.1100323624595467,
|
| 2622 |
+
"grad_norm": 0.20605434477329254,
|
| 2623 |
+
"learning_rate": 5e-05,
|
| 2624 |
+
"loss": 0.2628,
|
| 2625 |
+
"num_tokens": 316593419.0,
|
| 2626 |
+
"step": 327
|
| 2627 |
+
},
|
| 2628 |
+
{
|
| 2629 |
+
"epoch": 2.116504854368932,
|
| 2630 |
+
"grad_norm": 0.17503254115581512,
|
| 2631 |
+
"learning_rate": 5e-05,
|
| 2632 |
+
"loss": 0.2505,
|
| 2633 |
+
"num_tokens": 317586062.0,
|
| 2634 |
+
"step": 328
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 2.1229773462783172,
|
| 2638 |
+
"grad_norm": 0.19255898892879486,
|
| 2639 |
+
"learning_rate": 5e-05,
|
| 2640 |
+
"loss": 0.2579,
|
| 2641 |
+
"num_tokens": 318557320.0,
|
| 2642 |
+
"step": 329
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 2.129449838187702,
|
| 2646 |
+
"grad_norm": 0.18474873900413513,
|
| 2647 |
+
"learning_rate": 5e-05,
|
| 2648 |
+
"loss": 0.2572,
|
| 2649 |
+
"num_tokens": 319521712.0,
|
| 2650 |
+
"step": 330
|
| 2651 |
+
},
|
| 2652 |
+
{
|
| 2653 |
+
"epoch": 2.1359223300970873,
|
| 2654 |
+
"grad_norm": 0.1876448690891266,
|
| 2655 |
+
"learning_rate": 5e-05,
|
| 2656 |
+
"loss": 0.263,
|
| 2657 |
+
"num_tokens": 320503248.0,
|
| 2658 |
+
"step": 331
|
| 2659 |
+
},
|
| 2660 |
+
{
|
| 2661 |
+
"epoch": 2.1423948220064726,
|
| 2662 |
+
"grad_norm": 0.1980055868625641,
|
| 2663 |
+
"learning_rate": 5e-05,
|
| 2664 |
+
"loss": 0.2625,
|
| 2665 |
+
"num_tokens": 321501454.0,
|
| 2666 |
+
"step": 332
|
| 2667 |
+
},
|
| 2668 |
+
{
|
| 2669 |
+
"epoch": 2.148867313915858,
|
| 2670 |
+
"grad_norm": 0.19981230795383453,
|
| 2671 |
+
"learning_rate": 5e-05,
|
| 2672 |
+
"loss": 0.26,
|
| 2673 |
+
"num_tokens": 322456831.0,
|
| 2674 |
+
"step": 333
|
| 2675 |
+
},
|
| 2676 |
+
{
|
| 2677 |
+
"epoch": 2.1553398058252426,
|
| 2678 |
+
"grad_norm": 0.20402458310127258,
|
| 2679 |
+
"learning_rate": 5e-05,
|
| 2680 |
+
"loss": 0.2591,
|
| 2681 |
+
"num_tokens": 323415821.0,
|
| 2682 |
+
"step": 334
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 2.161812297734628,
|
| 2686 |
+
"grad_norm": 0.25081008672714233,
|
| 2687 |
+
"learning_rate": 5e-05,
|
| 2688 |
+
"loss": 0.2628,
|
| 2689 |
+
"num_tokens": 324385718.0,
|
| 2690 |
+
"step": 335
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 2.168284789644013,
|
| 2694 |
+
"grad_norm": 0.18330006301403046,
|
| 2695 |
+
"learning_rate": 5e-05,
|
| 2696 |
+
"loss": 0.2585,
|
| 2697 |
+
"num_tokens": 325330934.0,
|
| 2698 |
+
"step": 336
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 2.174757281553398,
|
| 2702 |
+
"grad_norm": 0.17511707544326782,
|
| 2703 |
+
"learning_rate": 5e-05,
|
| 2704 |
+
"loss": 0.2609,
|
| 2705 |
+
"num_tokens": 326277294.0,
|
| 2706 |
+
"step": 337
|
| 2707 |
+
},
|
| 2708 |
+
{
|
| 2709 |
+
"epoch": 2.1812297734627832,
|
| 2710 |
+
"grad_norm": 0.19182541966438293,
|
| 2711 |
+
"learning_rate": 5e-05,
|
| 2712 |
+
"loss": 0.2561,
|
| 2713 |
+
"num_tokens": 327249393.0,
|
| 2714 |
+
"step": 338
|
| 2715 |
+
},
|
| 2716 |
+
{
|
| 2717 |
+
"epoch": 2.1877022653721685,
|
| 2718 |
+
"grad_norm": 0.1984628140926361,
|
| 2719 |
+
"learning_rate": 5e-05,
|
| 2720 |
+
"loss": 0.2603,
|
| 2721 |
+
"num_tokens": 328230895.0,
|
| 2722 |
+
"step": 339
|
| 2723 |
+
},
|
| 2724 |
+
{
|
| 2725 |
+
"epoch": 2.1941747572815533,
|
| 2726 |
+
"grad_norm": 0.2331947386264801,
|
| 2727 |
+
"learning_rate": 5e-05,
|
| 2728 |
+
"loss": 0.263,
|
| 2729 |
+
"num_tokens": 329211471.0,
|
| 2730 |
+
"step": 340
|
| 2731 |
+
},
|
| 2732 |
+
{
|
| 2733 |
+
"epoch": 2.2006472491909386,
|
| 2734 |
+
"grad_norm": 0.2167729288339615,
|
| 2735 |
+
"learning_rate": 5e-05,
|
| 2736 |
+
"loss": 0.2618,
|
| 2737 |
+
"num_tokens": 330165352.0,
|
| 2738 |
+
"step": 341
|
| 2739 |
+
},
|
| 2740 |
+
{
|
| 2741 |
+
"epoch": 2.207119741100324,
|
| 2742 |
+
"grad_norm": 0.1731816977262497,
|
| 2743 |
+
"learning_rate": 5e-05,
|
| 2744 |
+
"loss": 0.2577,
|
| 2745 |
+
"num_tokens": 331112466.0,
|
| 2746 |
+
"step": 342
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 2.2135922330097086,
|
| 2750 |
+
"grad_norm": 0.1722971647977829,
|
| 2751 |
+
"learning_rate": 5e-05,
|
| 2752 |
+
"loss": 0.2543,
|
| 2753 |
+
"num_tokens": 332076946.0,
|
| 2754 |
+
"step": 343
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 2.220064724919094,
|
| 2758 |
+
"grad_norm": 0.20503529906272888,
|
| 2759 |
+
"learning_rate": 5e-05,
|
| 2760 |
+
"loss": 0.2554,
|
| 2761 |
+
"num_tokens": 333063256.0,
|
| 2762 |
+
"step": 344
|
| 2763 |
+
},
|
| 2764 |
+
{
|
| 2765 |
+
"epoch": 2.226537216828479,
|
| 2766 |
+
"grad_norm": 0.2305249273777008,
|
| 2767 |
+
"learning_rate": 5e-05,
|
| 2768 |
+
"loss": 0.2647,
|
| 2769 |
+
"num_tokens": 334026829.0,
|
| 2770 |
+
"step": 345
|
| 2771 |
+
},
|
| 2772 |
+
{
|
| 2773 |
+
"epoch": 2.233009708737864,
|
| 2774 |
+
"grad_norm": 0.19918742775917053,
|
| 2775 |
+
"learning_rate": 5e-05,
|
| 2776 |
+
"loss": 0.258,
|
| 2777 |
+
"num_tokens": 335023881.0,
|
| 2778 |
+
"step": 346
|
| 2779 |
+
},
|
| 2780 |
+
{
|
| 2781 |
+
"epoch": 2.2394822006472492,
|
| 2782 |
+
"grad_norm": 0.1792277842760086,
|
| 2783 |
+
"learning_rate": 5e-05,
|
| 2784 |
+
"loss": 0.26,
|
| 2785 |
+
"num_tokens": 336010678.0,
|
| 2786 |
+
"step": 347
|
| 2787 |
+
},
|
| 2788 |
+
{
|
| 2789 |
+
"epoch": 2.2459546925566345,
|
| 2790 |
+
"grad_norm": 0.20549416542053223,
|
| 2791 |
+
"learning_rate": 5e-05,
|
| 2792 |
+
"loss": 0.2617,
|
| 2793 |
+
"num_tokens": 336975057.0,
|
| 2794 |
+
"step": 348
|
| 2795 |
+
},
|
| 2796 |
+
{
|
| 2797 |
+
"epoch": 2.2524271844660193,
|
| 2798 |
+
"grad_norm": 0.18338747322559357,
|
| 2799 |
+
"learning_rate": 5e-05,
|
| 2800 |
+
"loss": 0.2614,
|
| 2801 |
+
"num_tokens": 337918498.0,
|
| 2802 |
+
"step": 349
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 2.2588996763754046,
|
| 2806 |
+
"grad_norm": 0.2006232738494873,
|
| 2807 |
+
"learning_rate": 5e-05,
|
| 2808 |
+
"loss": 0.2567,
|
| 2809 |
+
"num_tokens": 338909441.0,
|
| 2810 |
+
"step": 350
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 2.26537216828479,
|
| 2814 |
+
"grad_norm": 0.18148912489414215,
|
| 2815 |
+
"learning_rate": 5e-05,
|
| 2816 |
+
"loss": 0.2633,
|
| 2817 |
+
"num_tokens": 339884565.0,
|
| 2818 |
+
"step": 351
|
| 2819 |
+
},
|
| 2820 |
+
{
|
| 2821 |
+
"epoch": 2.2718446601941746,
|
| 2822 |
+
"grad_norm": 0.19440388679504395,
|
| 2823 |
+
"learning_rate": 5e-05,
|
| 2824 |
+
"loss": 0.2589,
|
| 2825 |
+
"num_tokens": 340849615.0,
|
| 2826 |
+
"step": 352
|
| 2827 |
+
},
|
| 2828 |
+
{
|
| 2829 |
+
"epoch": 2.27831715210356,
|
| 2830 |
+
"grad_norm": 0.22656117379665375,
|
| 2831 |
+
"learning_rate": 5e-05,
|
| 2832 |
+
"loss": 0.265,
|
| 2833 |
+
"num_tokens": 341812130.0,
|
| 2834 |
+
"step": 353
|
| 2835 |
+
},
|
| 2836 |
+
{
|
| 2837 |
+
"epoch": 2.284789644012945,
|
| 2838 |
+
"grad_norm": 0.1865127980709076,
|
| 2839 |
+
"learning_rate": 5e-05,
|
| 2840 |
+
"loss": 0.267,
|
| 2841 |
+
"num_tokens": 342798689.0,
|
| 2842 |
+
"step": 354
|
| 2843 |
+
},
|
| 2844 |
+
{
|
| 2845 |
+
"epoch": 2.29126213592233,
|
| 2846 |
+
"grad_norm": 0.18646317720413208,
|
| 2847 |
+
"learning_rate": 5e-05,
|
| 2848 |
+
"loss": 0.2627,
|
| 2849 |
+
"num_tokens": 343777378.0,
|
| 2850 |
+
"step": 355
|
| 2851 |
+
},
|
| 2852 |
+
{
|
| 2853 |
+
"epoch": 2.2977346278317152,
|
| 2854 |
+
"grad_norm": 0.1813158243894577,
|
| 2855 |
+
"learning_rate": 5e-05,
|
| 2856 |
+
"loss": 0.2663,
|
| 2857 |
+
"num_tokens": 344722430.0,
|
| 2858 |
+
"step": 356
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 2.3042071197411005,
|
| 2862 |
+
"grad_norm": 0.1691797971725464,
|
| 2863 |
+
"learning_rate": 5e-05,
|
| 2864 |
+
"loss": 0.2591,
|
| 2865 |
+
"num_tokens": 345692509.0,
|
| 2866 |
+
"step": 357
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 2.3106796116504853,
|
| 2870 |
+
"grad_norm": 0.1962641179561615,
|
| 2871 |
+
"learning_rate": 5e-05,
|
| 2872 |
+
"loss": 0.2595,
|
| 2873 |
+
"num_tokens": 346680167.0,
|
| 2874 |
+
"step": 358
|
| 2875 |
+
},
|
| 2876 |
+
{
|
| 2877 |
+
"epoch": 2.3171521035598706,
|
| 2878 |
+
"grad_norm": 0.17452265322208405,
|
| 2879 |
+
"learning_rate": 5e-05,
|
| 2880 |
+
"loss": 0.2669,
|
| 2881 |
+
"num_tokens": 347684225.0,
|
| 2882 |
+
"step": 359
|
| 2883 |
+
},
|
| 2884 |
+
{
|
| 2885 |
+
"epoch": 2.323624595469256,
|
| 2886 |
+
"grad_norm": 0.1666034311056137,
|
| 2887 |
+
"learning_rate": 5e-05,
|
| 2888 |
+
"loss": 0.2614,
|
| 2889 |
+
"num_tokens": 348650945.0,
|
| 2890 |
+
"step": 360
|
| 2891 |
+
},
|
| 2892 |
+
{
|
| 2893 |
+
"epoch": 2.3300970873786406,
|
| 2894 |
+
"grad_norm": 0.19067111611366272,
|
| 2895 |
+
"learning_rate": 5e-05,
|
| 2896 |
+
"loss": 0.2624,
|
| 2897 |
+
"num_tokens": 349609701.0,
|
| 2898 |
+
"step": 361
|
| 2899 |
+
},
|
| 2900 |
+
{
|
| 2901 |
+
"epoch": 2.336569579288026,
|
| 2902 |
+
"grad_norm": 0.20523084700107574,
|
| 2903 |
+
"learning_rate": 5e-05,
|
| 2904 |
+
"loss": 0.2638,
|
| 2905 |
+
"num_tokens": 350570434.0,
|
| 2906 |
+
"step": 362
|
| 2907 |
+
},
|
| 2908 |
+
{
|
| 2909 |
+
"epoch": 2.343042071197411,
|
| 2910 |
+
"grad_norm": 0.2024819701910019,
|
| 2911 |
+
"learning_rate": 5e-05,
|
| 2912 |
+
"loss": 0.2648,
|
| 2913 |
+
"num_tokens": 351557109.0,
|
| 2914 |
+
"step": 363
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 2.349514563106796,
|
| 2918 |
+
"grad_norm": 0.211598739027977,
|
| 2919 |
+
"learning_rate": 5e-05,
|
| 2920 |
+
"loss": 0.2664,
|
| 2921 |
+
"num_tokens": 352535505.0,
|
| 2922 |
+
"step": 364
|
| 2923 |
+
},
|
| 2924 |
+
{
|
| 2925 |
+
"epoch": 2.355987055016181,
|
| 2926 |
+
"grad_norm": 0.17019622027873993,
|
| 2927 |
+
"learning_rate": 5e-05,
|
| 2928 |
+
"loss": 0.2639,
|
| 2929 |
+
"num_tokens": 353532460.0,
|
| 2930 |
+
"step": 365
|
| 2931 |
+
},
|
| 2932 |
+
{
|
| 2933 |
+
"epoch": 2.3624595469255665,
|
| 2934 |
+
"grad_norm": 0.1669609695672989,
|
| 2935 |
+
"learning_rate": 5e-05,
|
| 2936 |
+
"loss": 0.2656,
|
| 2937 |
+
"num_tokens": 354512411.0,
|
| 2938 |
+
"step": 366
|
| 2939 |
+
},
|
| 2940 |
+
{
|
| 2941 |
+
"epoch": 2.3689320388349513,
|
| 2942 |
+
"grad_norm": 0.19705989956855774,
|
| 2943 |
+
"learning_rate": 5e-05,
|
| 2944 |
+
"loss": 0.2638,
|
| 2945 |
+
"num_tokens": 355502656.0,
|
| 2946 |
+
"step": 367
|
| 2947 |
+
},
|
| 2948 |
+
{
|
| 2949 |
+
"epoch": 2.3754045307443366,
|
| 2950 |
+
"grad_norm": 0.19132933020591736,
|
| 2951 |
+
"learning_rate": 5e-05,
|
| 2952 |
+
"loss": 0.2605,
|
| 2953 |
+
"num_tokens": 356484097.0,
|
| 2954 |
+
"step": 368
|
| 2955 |
+
},
|
| 2956 |
+
{
|
| 2957 |
+
"epoch": 2.381877022653722,
|
| 2958 |
+
"grad_norm": 0.19469107687473297,
|
| 2959 |
+
"learning_rate": 5e-05,
|
| 2960 |
+
"loss": 0.2689,
|
| 2961 |
+
"num_tokens": 357461867.0,
|
| 2962 |
+
"step": 369
|
| 2963 |
+
},
|
| 2964 |
+
{
|
| 2965 |
+
"epoch": 2.3883495145631066,
|
| 2966 |
+
"grad_norm": 0.19512927532196045,
|
| 2967 |
+
"learning_rate": 5e-05,
|
| 2968 |
+
"loss": 0.2672,
|
| 2969 |
+
"num_tokens": 358424717.0,
|
| 2970 |
+
"step": 370
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 2.394822006472492,
|
| 2974 |
+
"grad_norm": 0.17178840935230255,
|
| 2975 |
+
"learning_rate": 5e-05,
|
| 2976 |
+
"loss": 0.2669,
|
| 2977 |
+
"num_tokens": 359395193.0,
|
| 2978 |
+
"step": 371
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 2.401294498381877,
|
| 2982 |
+
"grad_norm": 0.204504132270813,
|
| 2983 |
+
"learning_rate": 5e-05,
|
| 2984 |
+
"loss": 0.2642,
|
| 2985 |
+
"num_tokens": 360370130.0,
|
| 2986 |
+
"step": 372
|
| 2987 |
+
},
|
| 2988 |
+
{
|
| 2989 |
+
"epoch": 2.407766990291262,
|
| 2990 |
+
"grad_norm": 0.19293123483657837,
|
| 2991 |
+
"learning_rate": 5e-05,
|
| 2992 |
+
"loss": 0.2651,
|
| 2993 |
+
"num_tokens": 361338296.0,
|
| 2994 |
+
"step": 373
|
| 2995 |
+
},
|
| 2996 |
+
{
|
| 2997 |
+
"epoch": 2.414239482200647,
|
| 2998 |
+
"grad_norm": 0.19161544740200043,
|
| 2999 |
+
"learning_rate": 5e-05,
|
| 3000 |
+
"loss": 0.2599,
|
| 3001 |
+
"num_tokens": 362303269.0,
|
| 3002 |
+
"step": 374
|
| 3003 |
+
},
|
| 3004 |
+
{
|
| 3005 |
+
"epoch": 2.4207119741100325,
|
| 3006 |
+
"grad_norm": 0.17606233060359955,
|
| 3007 |
+
"learning_rate": 5e-05,
|
| 3008 |
+
"loss": 0.2663,
|
| 3009 |
+
"num_tokens": 363269672.0,
|
| 3010 |
+
"step": 375
|
| 3011 |
+
},
|
| 3012 |
+
{
|
| 3013 |
+
"epoch": 2.4271844660194173,
|
| 3014 |
+
"grad_norm": 0.1838853657245636,
|
| 3015 |
+
"learning_rate": 5e-05,
|
| 3016 |
+
"loss": 0.2634,
|
| 3017 |
+
"num_tokens": 364215172.0,
|
| 3018 |
+
"step": 376
|
| 3019 |
+
},
|
| 3020 |
+
{
|
| 3021 |
+
"epoch": 2.4336569579288025,
|
| 3022 |
+
"grad_norm": 0.20035015046596527,
|
| 3023 |
+
"learning_rate": 5e-05,
|
| 3024 |
+
"loss": 0.2683,
|
| 3025 |
+
"num_tokens": 365199593.0,
|
| 3026 |
+
"step": 377
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 2.440129449838188,
|
| 3030 |
+
"grad_norm": 0.19053298234939575,
|
| 3031 |
+
"learning_rate": 5e-05,
|
| 3032 |
+
"loss": 0.2639,
|
| 3033 |
+
"num_tokens": 366173715.0,
|
| 3034 |
+
"step": 378
|
| 3035 |
+
},
|
| 3036 |
+
{
|
| 3037 |
+
"epoch": 2.4466019417475726,
|
| 3038 |
+
"grad_norm": 0.18631167709827423,
|
| 3039 |
+
"learning_rate": 5e-05,
|
| 3040 |
+
"loss": 0.2656,
|
| 3041 |
+
"num_tokens": 367134817.0,
|
| 3042 |
+
"step": 379
|
| 3043 |
+
},
|
| 3044 |
+
{
|
| 3045 |
+
"epoch": 2.453074433656958,
|
| 3046 |
+
"grad_norm": 0.17177614569664001,
|
| 3047 |
+
"learning_rate": 5e-05,
|
| 3048 |
+
"loss": 0.2708,
|
| 3049 |
+
"num_tokens": 368117521.0,
|
| 3050 |
+
"step": 380
|
| 3051 |
+
},
|
| 3052 |
+
{
|
| 3053 |
+
"epoch": 2.459546925566343,
|
| 3054 |
+
"grad_norm": 0.15696385502815247,
|
| 3055 |
+
"learning_rate": 5e-05,
|
| 3056 |
+
"loss": 0.2682,
|
| 3057 |
+
"num_tokens": 369068188.0,
|
| 3058 |
+
"step": 381
|
| 3059 |
+
},
|
| 3060 |
+
{
|
| 3061 |
+
"epoch": 2.466019417475728,
|
| 3062 |
+
"grad_norm": 0.1704537272453308,
|
| 3063 |
+
"learning_rate": 5e-05,
|
| 3064 |
+
"loss": 0.2628,
|
| 3065 |
+
"num_tokens": 370072565.0,
|
| 3066 |
+
"step": 382
|
| 3067 |
+
},
|
| 3068 |
+
{
|
| 3069 |
+
"epoch": 2.472491909385113,
|
| 3070 |
+
"grad_norm": 0.16712012887001038,
|
| 3071 |
+
"learning_rate": 5e-05,
|
| 3072 |
+
"loss": 0.2625,
|
| 3073 |
+
"num_tokens": 371036282.0,
|
| 3074 |
+
"step": 383
|
| 3075 |
+
},
|
| 3076 |
+
{
|
| 3077 |
+
"epoch": 2.4789644012944985,
|
| 3078 |
+
"grad_norm": 0.1807146966457367,
|
| 3079 |
+
"learning_rate": 5e-05,
|
| 3080 |
+
"loss": 0.2665,
|
| 3081 |
+
"num_tokens": 372022740.0,
|
| 3082 |
+
"step": 384
|
| 3083 |
+
},
|
| 3084 |
+
{
|
| 3085 |
+
"epoch": 2.4854368932038833,
|
| 3086 |
+
"grad_norm": 0.18959781527519226,
|
| 3087 |
+
"learning_rate": 5e-05,
|
| 3088 |
+
"loss": 0.2661,
|
| 3089 |
+
"num_tokens": 373000607.0,
|
| 3090 |
+
"step": 385
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 2.4919093851132685,
|
| 3094 |
+
"grad_norm": 0.1914069503545761,
|
| 3095 |
+
"learning_rate": 5e-05,
|
| 3096 |
+
"loss": 0.2674,
|
| 3097 |
+
"num_tokens": 373986218.0,
|
| 3098 |
+
"step": 386
|
| 3099 |
+
},
|
| 3100 |
+
{
|
| 3101 |
+
"epoch": 2.498381877022654,
|
| 3102 |
+
"grad_norm": 0.19182051718235016,
|
| 3103 |
+
"learning_rate": 5e-05,
|
| 3104 |
+
"loss": 0.2726,
|
| 3105 |
+
"num_tokens": 374968373.0,
|
| 3106 |
+
"step": 387
|
| 3107 |
+
},
|
| 3108 |
+
{
|
| 3109 |
+
"epoch": 2.5048543689320386,
|
| 3110 |
+
"grad_norm": 0.19095860421657562,
|
| 3111 |
+
"learning_rate": 5e-05,
|
| 3112 |
+
"loss": 0.2731,
|
| 3113 |
+
"num_tokens": 375953242.0,
|
| 3114 |
+
"step": 388
|
| 3115 |
+
},
|
| 3116 |
+
{
|
| 3117 |
+
"epoch": 2.511326860841424,
|
| 3118 |
+
"grad_norm": 0.16908369958400726,
|
| 3119 |
+
"learning_rate": 5e-05,
|
| 3120 |
+
"loss": 0.2667,
|
| 3121 |
+
"num_tokens": 376930298.0,
|
| 3122 |
+
"step": 389
|
| 3123 |
+
},
|
| 3124 |
+
{
|
| 3125 |
+
"epoch": 2.517799352750809,
|
| 3126 |
+
"grad_norm": 0.1663651317358017,
|
| 3127 |
+
"learning_rate": 5e-05,
|
| 3128 |
+
"loss": 0.2611,
|
| 3129 |
+
"num_tokens": 377892697.0,
|
| 3130 |
+
"step": 390
|
| 3131 |
+
},
|
| 3132 |
+
{
|
| 3133 |
+
"epoch": 2.524271844660194,
|
| 3134 |
+
"grad_norm": 0.15641413629055023,
|
| 3135 |
+
"learning_rate": 5e-05,
|
| 3136 |
+
"loss": 0.2668,
|
| 3137 |
+
"num_tokens": 378851468.0,
|
| 3138 |
+
"step": 391
|
| 3139 |
+
},
|
| 3140 |
+
{
|
| 3141 |
+
"epoch": 2.530744336569579,
|
| 3142 |
+
"grad_norm": 0.16256482899188995,
|
| 3143 |
+
"learning_rate": 5e-05,
|
| 3144 |
+
"loss": 0.2633,
|
| 3145 |
+
"num_tokens": 379796295.0,
|
| 3146 |
+
"step": 392
|
| 3147 |
+
},
|
| 3148 |
+
{
|
| 3149 |
+
"epoch": 2.5372168284789645,
|
| 3150 |
+
"grad_norm": 0.1653296798467636,
|
| 3151 |
+
"learning_rate": 5e-05,
|
| 3152 |
+
"loss": 0.2626,
|
| 3153 |
+
"num_tokens": 380749026.0,
|
| 3154 |
+
"step": 393
|
| 3155 |
+
},
|
| 3156 |
+
{
|
| 3157 |
+
"epoch": 2.5436893203883493,
|
| 3158 |
+
"grad_norm": 0.1858127862215042,
|
| 3159 |
+
"learning_rate": 5e-05,
|
| 3160 |
+
"loss": 0.2703,
|
| 3161 |
+
"num_tokens": 381732552.0,
|
| 3162 |
+
"step": 394
|
| 3163 |
+
},
|
| 3164 |
+
{
|
| 3165 |
+
"epoch": 2.5501618122977345,
|
| 3166 |
+
"grad_norm": 0.19651375710964203,
|
| 3167 |
+
"learning_rate": 5e-05,
|
| 3168 |
+
"loss": 0.2675,
|
| 3169 |
+
"num_tokens": 382685936.0,
|
| 3170 |
+
"step": 395
|
| 3171 |
+
},
|
| 3172 |
+
{
|
| 3173 |
+
"epoch": 2.55663430420712,
|
| 3174 |
+
"grad_norm": 0.19574522972106934,
|
| 3175 |
+
"learning_rate": 5e-05,
|
| 3176 |
+
"loss": 0.2681,
|
| 3177 |
+
"num_tokens": 383650180.0,
|
| 3178 |
+
"step": 396
|
| 3179 |
+
},
|
| 3180 |
+
{
|
| 3181 |
+
"epoch": 2.5631067961165046,
|
| 3182 |
+
"grad_norm": 0.1711733341217041,
|
| 3183 |
+
"learning_rate": 5e-05,
|
| 3184 |
+
"loss": 0.2697,
|
| 3185 |
+
"num_tokens": 384648157.0,
|
| 3186 |
+
"step": 397
|
| 3187 |
+
},
|
| 3188 |
+
{
|
| 3189 |
+
"epoch": 2.56957928802589,
|
| 3190 |
+
"grad_norm": 0.1619148850440979,
|
| 3191 |
+
"learning_rate": 5e-05,
|
| 3192 |
+
"loss": 0.2615,
|
| 3193 |
+
"num_tokens": 385633057.0,
|
| 3194 |
+
"step": 398
|
| 3195 |
+
},
|
| 3196 |
+
{
|
| 3197 |
+
"epoch": 2.576051779935275,
|
| 3198 |
+
"grad_norm": 0.1999882608652115,
|
| 3199 |
+
"learning_rate": 5e-05,
|
| 3200 |
+
"loss": 0.2695,
|
| 3201 |
+
"num_tokens": 386630696.0,
|
| 3202 |
+
"step": 399
|
| 3203 |
+
},
|
| 3204 |
+
{
|
| 3205 |
+
"epoch": 2.58252427184466,
|
| 3206 |
+
"grad_norm": 0.20654380321502686,
|
| 3207 |
+
"learning_rate": 5e-05,
|
| 3208 |
+
"loss": 0.2638,
|
| 3209 |
+
"num_tokens": 387613957.0,
|
| 3210 |
+
"step": 400
|
| 3211 |
+
},
|
| 3212 |
+
{
|
| 3213 |
+
"epoch": 2.588996763754045,
|
| 3214 |
+
"grad_norm": 0.16749776899814606,
|
| 3215 |
+
"learning_rate": 5e-05,
|
| 3216 |
+
"loss": 0.2688,
|
| 3217 |
+
"num_tokens": 388558267.0,
|
| 3218 |
+
"step": 401
|
| 3219 |
+
},
|
| 3220 |
+
{
|
| 3221 |
+
"epoch": 2.5954692556634305,
|
| 3222 |
+
"grad_norm": 0.19911642372608185,
|
| 3223 |
+
"learning_rate": 5e-05,
|
| 3224 |
+
"loss": 0.2647,
|
| 3225 |
+
"num_tokens": 389538588.0,
|
| 3226 |
+
"step": 402
|
| 3227 |
+
},
|
| 3228 |
+
{
|
| 3229 |
+
"epoch": 2.6019417475728153,
|
| 3230 |
+
"grad_norm": 0.2113586664199829,
|
| 3231 |
+
"learning_rate": 5e-05,
|
| 3232 |
+
"loss": 0.2674,
|
| 3233 |
+
"num_tokens": 390511972.0,
|
| 3234 |
+
"step": 403
|
| 3235 |
+
},
|
| 3236 |
+
{
|
| 3237 |
+
"epoch": 2.6084142394822005,
|
| 3238 |
+
"grad_norm": 0.18251682817935944,
|
| 3239 |
+
"learning_rate": 5e-05,
|
| 3240 |
+
"loss": 0.2722,
|
| 3241 |
+
"num_tokens": 391448045.0,
|
| 3242 |
+
"step": 404
|
| 3243 |
+
},
|
| 3244 |
+
{
|
| 3245 |
+
"epoch": 2.614886731391586,
|
| 3246 |
+
"grad_norm": 0.18107876181602478,
|
| 3247 |
+
"learning_rate": 5e-05,
|
| 3248 |
+
"loss": 0.2681,
|
| 3249 |
+
"num_tokens": 392472093.0,
|
| 3250 |
+
"step": 405
|
| 3251 |
+
},
|
| 3252 |
+
{
|
| 3253 |
+
"epoch": 2.6213592233009706,
|
| 3254 |
+
"grad_norm": 0.15655288100242615,
|
| 3255 |
+
"learning_rate": 5e-05,
|
| 3256 |
+
"loss": 0.2674,
|
| 3257 |
+
"num_tokens": 393430332.0,
|
| 3258 |
+
"step": 406
|
| 3259 |
+
},
|
| 3260 |
+
{
|
| 3261 |
+
"epoch": 2.627831715210356,
|
| 3262 |
+
"grad_norm": 0.17552509903907776,
|
| 3263 |
+
"learning_rate": 5e-05,
|
| 3264 |
+
"loss": 0.2752,
|
| 3265 |
+
"num_tokens": 394429159.0,
|
| 3266 |
+
"step": 407
|
| 3267 |
+
},
|
| 3268 |
+
{
|
| 3269 |
+
"epoch": 2.634304207119741,
|
| 3270 |
+
"grad_norm": 0.1833338737487793,
|
| 3271 |
+
"learning_rate": 5e-05,
|
| 3272 |
+
"loss": 0.2689,
|
| 3273 |
+
"num_tokens": 395426297.0,
|
| 3274 |
+
"step": 408
|
| 3275 |
+
},
|
| 3276 |
+
{
|
| 3277 |
+
"epoch": 2.6407766990291264,
|
| 3278 |
+
"grad_norm": 0.1764242798089981,
|
| 3279 |
+
"learning_rate": 5e-05,
|
| 3280 |
+
"loss": 0.27,
|
| 3281 |
+
"num_tokens": 396358492.0,
|
| 3282 |
+
"step": 409
|
| 3283 |
+
},
|
| 3284 |
+
{
|
| 3285 |
+
"epoch": 2.647249190938511,
|
| 3286 |
+
"grad_norm": 0.1662444919347763,
|
| 3287 |
+
"learning_rate": 5e-05,
|
| 3288 |
+
"loss": 0.2632,
|
| 3289 |
+
"num_tokens": 397312727.0,
|
| 3290 |
+
"step": 410
|
| 3291 |
+
},
|
| 3292 |
+
{
|
| 3293 |
+
"epoch": 2.6537216828478964,
|
| 3294 |
+
"grad_norm": 0.1601162552833557,
|
| 3295 |
+
"learning_rate": 5e-05,
|
| 3296 |
+
"loss": 0.2636,
|
| 3297 |
+
"num_tokens": 398277677.0,
|
| 3298 |
+
"step": 411
|
| 3299 |
+
},
|
| 3300 |
+
{
|
| 3301 |
+
"epoch": 2.6601941747572817,
|
| 3302 |
+
"grad_norm": 0.16820690035820007,
|
| 3303 |
+
"learning_rate": 5e-05,
|
| 3304 |
+
"loss": 0.2692,
|
| 3305 |
+
"num_tokens": 399270732.0,
|
| 3306 |
+
"step": 412
|
| 3307 |
+
},
|
| 3308 |
+
{
|
| 3309 |
+
"epoch": 2.6666666666666665,
|
| 3310 |
+
"grad_norm": 0.17408967018127441,
|
| 3311 |
+
"learning_rate": 5e-05,
|
| 3312 |
+
"loss": 0.2674,
|
| 3313 |
+
"num_tokens": 400214224.0,
|
| 3314 |
+
"step": 413
|
| 3315 |
+
},
|
| 3316 |
+
{
|
| 3317 |
+
"epoch": 2.6731391585760518,
|
| 3318 |
+
"grad_norm": 0.1643182784318924,
|
| 3319 |
+
"learning_rate": 5e-05,
|
| 3320 |
+
"loss": 0.2725,
|
| 3321 |
+
"num_tokens": 401197793.0,
|
| 3322 |
+
"step": 414
|
| 3323 |
+
},
|
| 3324 |
+
{
|
| 3325 |
+
"epoch": 2.679611650485437,
|
| 3326 |
+
"grad_norm": 0.1726103127002716,
|
| 3327 |
+
"learning_rate": 5e-05,
|
| 3328 |
+
"loss": 0.2717,
|
| 3329 |
+
"num_tokens": 402201191.0,
|
| 3330 |
+
"step": 415
|
| 3331 |
+
},
|
| 3332 |
+
{
|
| 3333 |
+
"epoch": 2.686084142394822,
|
| 3334 |
+
"grad_norm": 0.17164799571037292,
|
| 3335 |
+
"learning_rate": 5e-05,
|
| 3336 |
+
"loss": 0.2727,
|
| 3337 |
+
"num_tokens": 403166232.0,
|
| 3338 |
+
"step": 416
|
| 3339 |
+
},
|
| 3340 |
+
{
|
| 3341 |
+
"epoch": 2.692556634304207,
|
| 3342 |
+
"grad_norm": 0.18190601468086243,
|
| 3343 |
+
"learning_rate": 5e-05,
|
| 3344 |
+
"loss": 0.2741,
|
| 3345 |
+
"num_tokens": 404128378.0,
|
| 3346 |
+
"step": 417
|
| 3347 |
+
},
|
| 3348 |
+
{
|
| 3349 |
+
"epoch": 2.6990291262135924,
|
| 3350 |
+
"grad_norm": 0.1727588027715683,
|
| 3351 |
+
"learning_rate": 5e-05,
|
| 3352 |
+
"loss": 0.2647,
|
| 3353 |
+
"num_tokens": 405053317.0,
|
| 3354 |
+
"step": 418
|
| 3355 |
+
},
|
| 3356 |
+
{
|
| 3357 |
+
"epoch": 2.705501618122977,
|
| 3358 |
+
"grad_norm": 0.16334885358810425,
|
| 3359 |
+
"learning_rate": 5e-05,
|
| 3360 |
+
"loss": 0.2723,
|
| 3361 |
+
"num_tokens": 406034988.0,
|
| 3362 |
+
"step": 419
|
| 3363 |
+
},
|
| 3364 |
+
{
|
| 3365 |
+
"epoch": 2.7119741100323624,
|
| 3366 |
+
"grad_norm": 0.17315317690372467,
|
| 3367 |
+
"learning_rate": 5e-05,
|
| 3368 |
+
"loss": 0.2698,
|
| 3369 |
+
"num_tokens": 406979391.0,
|
| 3370 |
+
"step": 420
|
| 3371 |
+
},
|
| 3372 |
+
{
|
| 3373 |
+
"epoch": 2.7184466019417477,
|
| 3374 |
+
"grad_norm": 0.17514127492904663,
|
| 3375 |
+
"learning_rate": 5e-05,
|
| 3376 |
+
"loss": 0.2643,
|
| 3377 |
+
"num_tokens": 407949200.0,
|
| 3378 |
+
"step": 421
|
| 3379 |
+
},
|
| 3380 |
+
{
|
| 3381 |
+
"epoch": 2.724919093851133,
|
| 3382 |
+
"grad_norm": 0.17451779544353485,
|
| 3383 |
+
"learning_rate": 5e-05,
|
| 3384 |
+
"loss": 0.2746,
|
| 3385 |
+
"num_tokens": 408927182.0,
|
| 3386 |
+
"step": 422
|
| 3387 |
+
},
|
| 3388 |
+
{
|
| 3389 |
+
"epoch": 2.7313915857605178,
|
| 3390 |
+
"grad_norm": 0.1621076911687851,
|
| 3391 |
+
"learning_rate": 5e-05,
|
| 3392 |
+
"loss": 0.2701,
|
| 3393 |
+
"num_tokens": 409918480.0,
|
| 3394 |
+
"step": 423
|
| 3395 |
+
},
|
| 3396 |
+
{
|
| 3397 |
+
"epoch": 2.737864077669903,
|
| 3398 |
+
"grad_norm": 0.16276338696479797,
|
| 3399 |
+
"learning_rate": 5e-05,
|
| 3400 |
+
"loss": 0.2657,
|
| 3401 |
+
"num_tokens": 410898982.0,
|
| 3402 |
+
"step": 424
|
| 3403 |
+
},
|
| 3404 |
+
{
|
| 3405 |
+
"epoch": 2.7443365695792883,
|
| 3406 |
+
"grad_norm": 0.1621464043855667,
|
| 3407 |
+
"learning_rate": 5e-05,
|
| 3408 |
+
"loss": 0.266,
|
| 3409 |
+
"num_tokens": 411875141.0,
|
| 3410 |
+
"step": 425
|
| 3411 |
+
},
|
| 3412 |
+
{
|
| 3413 |
+
"epoch": 2.750809061488673,
|
| 3414 |
+
"grad_norm": 0.16960802674293518,
|
| 3415 |
+
"learning_rate": 5e-05,
|
| 3416 |
+
"loss": 0.2702,
|
| 3417 |
+
"num_tokens": 412824562.0,
|
| 3418 |
+
"step": 426
|
| 3419 |
+
},
|
| 3420 |
+
{
|
| 3421 |
+
"epoch": 2.7572815533980584,
|
| 3422 |
+
"grad_norm": 0.15773984789848328,
|
| 3423 |
+
"learning_rate": 5e-05,
|
| 3424 |
+
"loss": 0.2677,
|
| 3425 |
+
"num_tokens": 413825079.0,
|
| 3426 |
+
"step": 427
|
| 3427 |
+
},
|
| 3428 |
+
{
|
| 3429 |
+
"epoch": 2.7637540453074436,
|
| 3430 |
+
"grad_norm": 0.1705068200826645,
|
| 3431 |
+
"learning_rate": 5e-05,
|
| 3432 |
+
"loss": 0.2711,
|
| 3433 |
+
"num_tokens": 414777217.0,
|
| 3434 |
+
"step": 428
|
| 3435 |
+
},
|
| 3436 |
+
{
|
| 3437 |
+
"epoch": 2.7702265372168284,
|
| 3438 |
+
"grad_norm": 0.17718885838985443,
|
| 3439 |
+
"learning_rate": 5e-05,
|
| 3440 |
+
"loss": 0.273,
|
| 3441 |
+
"num_tokens": 415746492.0,
|
| 3442 |
+
"step": 429
|
| 3443 |
+
},
|
| 3444 |
+
{
|
| 3445 |
+
"epoch": 2.7766990291262137,
|
| 3446 |
+
"grad_norm": 0.1792534738779068,
|
| 3447 |
+
"learning_rate": 5e-05,
|
| 3448 |
+
"loss": 0.2682,
|
| 3449 |
+
"num_tokens": 416686095.0,
|
| 3450 |
+
"step": 430
|
| 3451 |
+
},
|
| 3452 |
+
{
|
| 3453 |
+
"epoch": 2.783171521035599,
|
| 3454 |
+
"grad_norm": 0.18403004109859467,
|
| 3455 |
+
"learning_rate": 5e-05,
|
| 3456 |
+
"loss": 0.2666,
|
| 3457 |
+
"num_tokens": 417634189.0,
|
| 3458 |
+
"step": 431
|
| 3459 |
+
},
|
| 3460 |
+
{
|
| 3461 |
+
"epoch": 2.7896440129449838,
|
| 3462 |
+
"grad_norm": 0.18006184697151184,
|
| 3463 |
+
"learning_rate": 5e-05,
|
| 3464 |
+
"loss": 0.2723,
|
| 3465 |
+
"num_tokens": 418602339.0,
|
| 3466 |
+
"step": 432
|
| 3467 |
+
},
|
| 3468 |
+
{
|
| 3469 |
+
"epoch": 2.796116504854369,
|
| 3470 |
+
"grad_norm": 0.16311366856098175,
|
| 3471 |
+
"learning_rate": 5e-05,
|
| 3472 |
+
"loss": 0.2682,
|
| 3473 |
+
"num_tokens": 419563873.0,
|
| 3474 |
+
"step": 433
|
| 3475 |
+
},
|
| 3476 |
+
{
|
| 3477 |
+
"epoch": 2.8025889967637543,
|
| 3478 |
+
"grad_norm": 0.1562502086162567,
|
| 3479 |
+
"learning_rate": 5e-05,
|
| 3480 |
+
"loss": 0.2704,
|
| 3481 |
+
"num_tokens": 420562393.0,
|
| 3482 |
+
"step": 434
|
| 3483 |
+
},
|
| 3484 |
+
{
|
| 3485 |
+
"epoch": 2.809061488673139,
|
| 3486 |
+
"grad_norm": 0.19003362953662872,
|
| 3487 |
+
"learning_rate": 5e-05,
|
| 3488 |
+
"loss": 0.2722,
|
| 3489 |
+
"num_tokens": 421523768.0,
|
| 3490 |
+
"step": 435
|
| 3491 |
+
},
|
| 3492 |
+
{
|
| 3493 |
+
"epoch": 2.8155339805825244,
|
| 3494 |
+
"grad_norm": 0.18127073347568512,
|
| 3495 |
+
"learning_rate": 5e-05,
|
| 3496 |
+
"loss": 0.2707,
|
| 3497 |
+
"num_tokens": 422472099.0,
|
| 3498 |
+
"step": 436
|
| 3499 |
+
},
|
| 3500 |
+
{
|
| 3501 |
+
"epoch": 2.8220064724919096,
|
| 3502 |
+
"grad_norm": 0.16787101328372955,
|
| 3503 |
+
"learning_rate": 5e-05,
|
| 3504 |
+
"loss": 0.2738,
|
| 3505 |
+
"num_tokens": 423413417.0,
|
| 3506 |
+
"step": 437
|
| 3507 |
+
},
|
| 3508 |
+
{
|
| 3509 |
+
"epoch": 2.8284789644012944,
|
| 3510 |
+
"grad_norm": 0.16646350920200348,
|
| 3511 |
+
"learning_rate": 5e-05,
|
| 3512 |
+
"loss": 0.2679,
|
| 3513 |
+
"num_tokens": 424390973.0,
|
| 3514 |
+
"step": 438
|
| 3515 |
+
},
|
| 3516 |
+
{
|
| 3517 |
+
"epoch": 2.8349514563106797,
|
| 3518 |
+
"grad_norm": 0.17200861871242523,
|
| 3519 |
+
"learning_rate": 5e-05,
|
| 3520 |
+
"loss": 0.2794,
|
| 3521 |
+
"num_tokens": 425350702.0,
|
| 3522 |
+
"step": 439
|
| 3523 |
+
},
|
| 3524 |
+
{
|
| 3525 |
+
"epoch": 2.841423948220065,
|
| 3526 |
+
"grad_norm": 0.18369479477405548,
|
| 3527 |
+
"learning_rate": 5e-05,
|
| 3528 |
+
"loss": 0.2704,
|
| 3529 |
+
"num_tokens": 426331291.0,
|
| 3530 |
+
"step": 440
|
| 3531 |
+
},
|
| 3532 |
+
{
|
| 3533 |
+
"epoch": 2.8478964401294498,
|
| 3534 |
+
"grad_norm": 0.16849413514137268,
|
| 3535 |
+
"learning_rate": 5e-05,
|
| 3536 |
+
"loss": 0.2692,
|
| 3537 |
+
"num_tokens": 427296200.0,
|
| 3538 |
+
"step": 441
|
| 3539 |
+
},
|
| 3540 |
+
{
|
| 3541 |
+
"epoch": 2.854368932038835,
|
| 3542 |
+
"grad_norm": 0.18574877083301544,
|
| 3543 |
+
"learning_rate": 5e-05,
|
| 3544 |
+
"loss": 0.2695,
|
| 3545 |
+
"num_tokens": 428296391.0,
|
| 3546 |
+
"step": 442
|
| 3547 |
+
},
|
| 3548 |
+
{
|
| 3549 |
+
"epoch": 2.8608414239482203,
|
| 3550 |
+
"grad_norm": 0.2154499888420105,
|
| 3551 |
+
"learning_rate": 5e-05,
|
| 3552 |
+
"loss": 0.2693,
|
| 3553 |
+
"num_tokens": 429272004.0,
|
| 3554 |
+
"step": 443
|
| 3555 |
+
},
|
| 3556 |
+
{
|
| 3557 |
+
"epoch": 2.867313915857605,
|
| 3558 |
+
"grad_norm": 0.20533370971679688,
|
| 3559 |
+
"learning_rate": 5e-05,
|
| 3560 |
+
"loss": 0.2712,
|
| 3561 |
+
"num_tokens": 430235969.0,
|
| 3562 |
+
"step": 444
|
| 3563 |
+
},
|
| 3564 |
+
{
|
| 3565 |
+
"epoch": 2.8737864077669903,
|
| 3566 |
+
"grad_norm": 0.17873993515968323,
|
| 3567 |
+
"learning_rate": 5e-05,
|
| 3568 |
+
"loss": 0.2695,
|
| 3569 |
+
"num_tokens": 431174501.0,
|
| 3570 |
+
"step": 445
|
| 3571 |
+
},
|
| 3572 |
+
{
|
| 3573 |
+
"epoch": 2.8802588996763756,
|
| 3574 |
+
"grad_norm": 0.17518216371536255,
|
| 3575 |
+
"learning_rate": 5e-05,
|
| 3576 |
+
"loss": 0.2742,
|
| 3577 |
+
"num_tokens": 432123098.0,
|
| 3578 |
+
"step": 446
|
| 3579 |
+
},
|
| 3580 |
+
{
|
| 3581 |
+
"epoch": 2.8867313915857604,
|
| 3582 |
+
"grad_norm": 0.18824835121631622,
|
| 3583 |
+
"learning_rate": 5e-05,
|
| 3584 |
+
"loss": 0.2794,
|
| 3585 |
+
"num_tokens": 433097167.0,
|
| 3586 |
+
"step": 447
|
| 3587 |
+
},
|
| 3588 |
+
{
|
| 3589 |
+
"epoch": 2.8932038834951457,
|
| 3590 |
+
"grad_norm": 0.22121001780033112,
|
| 3591 |
+
"learning_rate": 5e-05,
|
| 3592 |
+
"loss": 0.2774,
|
| 3593 |
+
"num_tokens": 434079373.0,
|
| 3594 |
+
"step": 448
|
| 3595 |
+
},
|
| 3596 |
+
{
|
| 3597 |
+
"epoch": 2.899676375404531,
|
| 3598 |
+
"grad_norm": 0.17103159427642822,
|
| 3599 |
+
"learning_rate": 5e-05,
|
| 3600 |
+
"loss": 0.2702,
|
| 3601 |
+
"num_tokens": 435065151.0,
|
| 3602 |
+
"step": 449
|
| 3603 |
+
},
|
| 3604 |
+
{
|
| 3605 |
+
"epoch": 2.9061488673139158,
|
| 3606 |
+
"grad_norm": 0.19851639866828918,
|
| 3607 |
+
"learning_rate": 5e-05,
|
| 3608 |
+
"loss": 0.2751,
|
| 3609 |
+
"num_tokens": 436063130.0,
|
| 3610 |
+
"step": 450
|
| 3611 |
+
},
|
| 3612 |
+
{
|
| 3613 |
+
"epoch": 2.912621359223301,
|
| 3614 |
+
"grad_norm": 0.17771649360656738,
|
| 3615 |
+
"learning_rate": 5e-05,
|
| 3616 |
+
"loss": 0.2682,
|
| 3617 |
+
"num_tokens": 437032520.0,
|
| 3618 |
+
"step": 451
|
| 3619 |
+
},
|
| 3620 |
+
{
|
| 3621 |
+
"epoch": 2.9190938511326863,
|
| 3622 |
+
"grad_norm": 0.17466633021831512,
|
| 3623 |
+
"learning_rate": 5e-05,
|
| 3624 |
+
"loss": 0.2768,
|
| 3625 |
+
"num_tokens": 437990354.0,
|
| 3626 |
+
"step": 452
|
| 3627 |
+
},
|
| 3628 |
+
{
|
| 3629 |
+
"epoch": 2.925566343042071,
|
| 3630 |
+
"grad_norm": 0.16329172253608704,
|
| 3631 |
+
"learning_rate": 5e-05,
|
| 3632 |
+
"loss": 0.269,
|
| 3633 |
+
"num_tokens": 439009642.0,
|
| 3634 |
+
"step": 453
|
| 3635 |
+
},
|
| 3636 |
+
{
|
| 3637 |
+
"epoch": 2.9320388349514563,
|
| 3638 |
+
"grad_norm": 0.17622993886470795,
|
| 3639 |
+
"learning_rate": 5e-05,
|
| 3640 |
+
"loss": 0.2691,
|
| 3641 |
+
"num_tokens": 439985459.0,
|
| 3642 |
+
"step": 454
|
| 3643 |
+
},
|
| 3644 |
+
{
|
| 3645 |
+
"epoch": 2.9385113268608416,
|
| 3646 |
+
"grad_norm": 0.17430156469345093,
|
| 3647 |
+
"learning_rate": 5e-05,
|
| 3648 |
+
"loss": 0.2677,
|
| 3649 |
+
"num_tokens": 440955967.0,
|
| 3650 |
+
"step": 455
|
| 3651 |
+
},
|
| 3652 |
+
{
|
| 3653 |
+
"epoch": 2.9449838187702264,
|
| 3654 |
+
"grad_norm": 0.16609232127666473,
|
| 3655 |
+
"learning_rate": 5e-05,
|
| 3656 |
+
"loss": 0.2668,
|
| 3657 |
+
"num_tokens": 441912223.0,
|
| 3658 |
+
"step": 456
|
| 3659 |
+
},
|
| 3660 |
+
{
|
| 3661 |
+
"epoch": 2.9514563106796117,
|
| 3662 |
+
"grad_norm": 0.16747066378593445,
|
| 3663 |
+
"learning_rate": 5e-05,
|
| 3664 |
+
"loss": 0.2761,
|
| 3665 |
+
"num_tokens": 442916739.0,
|
| 3666 |
+
"step": 457
|
| 3667 |
+
},
|
| 3668 |
+
{
|
| 3669 |
+
"epoch": 2.957928802588997,
|
| 3670 |
+
"grad_norm": 0.17249858379364014,
|
| 3671 |
+
"learning_rate": 5e-05,
|
| 3672 |
+
"loss": 0.2669,
|
| 3673 |
+
"num_tokens": 443875303.0,
|
| 3674 |
+
"step": 458
|
| 3675 |
+
},
|
| 3676 |
+
{
|
| 3677 |
+
"epoch": 2.9644012944983817,
|
| 3678 |
+
"grad_norm": 0.16850367188453674,
|
| 3679 |
+
"learning_rate": 5e-05,
|
| 3680 |
+
"loss": 0.2759,
|
| 3681 |
+
"num_tokens": 444853831.0,
|
| 3682 |
+
"step": 459
|
| 3683 |
+
},
|
| 3684 |
+
{
|
| 3685 |
+
"epoch": 2.970873786407767,
|
| 3686 |
+
"grad_norm": 0.15697653591632843,
|
| 3687 |
+
"learning_rate": 5e-05,
|
| 3688 |
+
"loss": 0.2712,
|
| 3689 |
+
"num_tokens": 445812377.0,
|
| 3690 |
+
"step": 460
|
| 3691 |
+
},
|
| 3692 |
+
{
|
| 3693 |
+
"epoch": 2.9773462783171523,
|
| 3694 |
+
"grad_norm": 0.1761552393436432,
|
| 3695 |
+
"learning_rate": 5e-05,
|
| 3696 |
+
"loss": 0.2755,
|
| 3697 |
+
"num_tokens": 446783660.0,
|
| 3698 |
+
"step": 461
|
| 3699 |
+
},
|
| 3700 |
+
{
|
| 3701 |
+
"epoch": 2.983818770226537,
|
| 3702 |
+
"grad_norm": 0.16302275657653809,
|
| 3703 |
+
"learning_rate": 5e-05,
|
| 3704 |
+
"loss": 0.2745,
|
| 3705 |
+
"num_tokens": 447813574.0,
|
| 3706 |
+
"step": 462
|
| 3707 |
+
},
|
| 3708 |
+
{
|
| 3709 |
+
"epoch": 2.983818770226537,
|
| 3710 |
+
"step": 462,
|
| 3711 |
+
"total_flos": 1.8506098969109594e+19,
|
| 3712 |
+
"train_loss": 0.3598332001920386,
|
| 3713 |
+
"train_runtime": 11724.7761,
|
| 3714 |
+
"train_samples_per_second": 17.689,
|
| 3715 |
+
"train_steps_per_second": 0.039
|
| 3716 |
+
}
|
| 3717 |
+
],
|
| 3718 |
+
"logging_steps": 1,
|
| 3719 |
+
"max_steps": 462,
|
| 3720 |
+
"num_input_tokens_seen": 0,
|
| 3721 |
+
"num_train_epochs": 3,
|
| 3722 |
+
"save_steps": 24,
|
| 3723 |
+
"stateful_callbacks": {
|
| 3724 |
+
"TrainerControl": {
|
| 3725 |
+
"args": {
|
| 3726 |
+
"should_epoch_stop": false,
|
| 3727 |
+
"should_evaluate": false,
|
| 3728 |
+
"should_log": false,
|
| 3729 |
+
"should_save": true,
|
| 3730 |
+
"should_training_stop": true
|
| 3731 |
+
},
|
| 3732 |
+
"attributes": {}
|
| 3733 |
+
}
|
| 3734 |
+
},
|
| 3735 |
+
"total_flos": 1.8506098969109594e+19,
|
| 3736 |
+
"train_batch_size": 16,
|
| 3737 |
+
"trial_name": null,
|
| 3738 |
+
"trial_params": null
|
| 3739 |
+
}
|