Model save
Browse files- README.md +57 -0
- adapter_model.safetensors +1 -1
- all_results.json +10 -0
- train_results.json +10 -0
- trainer_state.json +3447 -0
README.md
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/Llama-3.1-8B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: legis-llama3-1-8b-valid-arandu
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for legis-llama3-1-8b-valid-arandu
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-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="felipeoes/legis-llama3-1-8b-valid-arandu", 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/felipealumni-usp/huggingface/runs/bm7zcvk0)
|
| 31 |
+
|
| 32 |
+
This model was trained with SFT.
|
| 33 |
+
|
| 34 |
+
### Framework versions
|
| 35 |
+
|
| 36 |
+
- TRL: 0.12.1
|
| 37 |
+
- Transformers: 4.46.3
|
| 38 |
+
- Pytorch: 2.4.1
|
| 39 |
+
- Datasets: 3.1.0
|
| 40 |
+
- Tokenizers: 0.20.3
|
| 41 |
+
|
| 42 |
+
## Citations
|
| 43 |
+
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
Cite TRL as:
|
| 47 |
+
|
| 48 |
+
```bibtex
|
| 49 |
+
@misc{vonwerra2022trl,
|
| 50 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 51 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
|
| 52 |
+
year = 2020,
|
| 53 |
+
journal = {GitHub repository},
|
| 54 |
+
publisher = {GitHub},
|
| 55 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 56 |
+
}
|
| 57 |
+
```
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2269178776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9568b9eff59730f694dac3f3bf24bcc7dc5e810d21f35eadeb2d3aa7c7150d4a
|
| 3 |
size 2269178776
|
all_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9995600527936648,
|
| 3 |
+
"eval_samples": 117,
|
| 4 |
+
"total_flos": 7.211600370336793e+18,
|
| 5 |
+
"train_loss": 0.039691918463984004,
|
| 6 |
+
"train_runtime": 9596.3839,
|
| 7 |
+
"train_samples": 116076,
|
| 8 |
+
"train_samples_per_second": 1.895,
|
| 9 |
+
"train_steps_per_second": 0.118
|
| 10 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9995600527936648,
|
| 3 |
+
"eval_samples": 117,
|
| 4 |
+
"total_flos": 7.211600370336793e+18,
|
| 5 |
+
"train_loss": 0.039691918463984004,
|
| 6 |
+
"train_runtime": 9596.3839,
|
| 7 |
+
"train_samples": 116076,
|
| 8 |
+
"train_samples_per_second": 1.895,
|
| 9 |
+
"train_steps_per_second": 0.118
|
| 10 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3447 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.439,
|
| 3 |
+
"best_model_checkpoint": "runs/legis-llama3-1-8b-valid-arandu/checkpoint-1120",
|
| 4 |
+
"epoch": 0.9995600527936648,
|
| 5 |
+
"eval_steps": 5,
|
| 6 |
+
"global_step": 1136,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.004399472063352398,
|
| 13 |
+
"grad_norm": 25.937191009521484,
|
| 14 |
+
"learning_rate": 8.771929824561403e-06,
|
| 15 |
+
"loss": 1.0992,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.004399472063352398,
|
| 20 |
+
"eval_loss": 1.1428982019424438,
|
| 21 |
+
"eval_runtime": 29.8805,
|
| 22 |
+
"eval_samples_per_second": 0.569,
|
| 23 |
+
"eval_steps_per_second": 0.301,
|
| 24 |
+
"step": 5
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.008798944126704795,
|
| 28 |
+
"grad_norm": 32.52676773071289,
|
| 29 |
+
"learning_rate": 1.7543859649122806e-05,
|
| 30 |
+
"loss": 1.067,
|
| 31 |
+
"step": 10
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.008798944126704795,
|
| 35 |
+
"eval_loss": 1.0669578313827515,
|
| 36 |
+
"eval_runtime": 28.5282,
|
| 37 |
+
"eval_samples_per_second": 0.596,
|
| 38 |
+
"eval_steps_per_second": 0.315,
|
| 39 |
+
"step": 10
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.013198416190057193,
|
| 43 |
+
"grad_norm": 78.51001739501953,
|
| 44 |
+
"learning_rate": 2.6315789473684212e-05,
|
| 45 |
+
"loss": 1.0057,
|
| 46 |
+
"step": 15
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.013198416190057193,
|
| 50 |
+
"eval_loss": 1.0462743043899536,
|
| 51 |
+
"eval_runtime": 28.5697,
|
| 52 |
+
"eval_samples_per_second": 0.595,
|
| 53 |
+
"eval_steps_per_second": 0.315,
|
| 54 |
+
"step": 15
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.01759788825340959,
|
| 58 |
+
"grad_norm": 21.255964279174805,
|
| 59 |
+
"learning_rate": 3.508771929824561e-05,
|
| 60 |
+
"loss": 0.9236,
|
| 61 |
+
"step": 20
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.01759788825340959,
|
| 65 |
+
"eval_loss": 0.9604344367980957,
|
| 66 |
+
"eval_runtime": 28.6152,
|
| 67 |
+
"eval_samples_per_second": 0.594,
|
| 68 |
+
"eval_steps_per_second": 0.315,
|
| 69 |
+
"step": 20
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.02199736031676199,
|
| 73 |
+
"grad_norm": 1.3699233531951904,
|
| 74 |
+
"learning_rate": 4.3859649122807014e-05,
|
| 75 |
+
"loss": 0.8823,
|
| 76 |
+
"step": 25
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.02199736031676199,
|
| 80 |
+
"eval_loss": 0.9002779126167297,
|
| 81 |
+
"eval_runtime": 28.579,
|
| 82 |
+
"eval_samples_per_second": 0.595,
|
| 83 |
+
"eval_steps_per_second": 0.315,
|
| 84 |
+
"step": 25
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.026396832380114386,
|
| 88 |
+
"grad_norm": 2.50810170173645,
|
| 89 |
+
"learning_rate": 5.2631578947368424e-05,
|
| 90 |
+
"loss": 0.8144,
|
| 91 |
+
"step": 30
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.026396832380114386,
|
| 95 |
+
"eval_loss": 0.8441588878631592,
|
| 96 |
+
"eval_runtime": 28.4936,
|
| 97 |
+
"eval_samples_per_second": 0.597,
|
| 98 |
+
"eval_steps_per_second": 0.316,
|
| 99 |
+
"step": 30
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.030796304443466784,
|
| 103 |
+
"grad_norm": 1.6816316843032837,
|
| 104 |
+
"learning_rate": 6.140350877192983e-05,
|
| 105 |
+
"loss": 0.7829,
|
| 106 |
+
"step": 35
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.030796304443466784,
|
| 110 |
+
"eval_loss": 0.7928382754325867,
|
| 111 |
+
"eval_runtime": 28.5908,
|
| 112 |
+
"eval_samples_per_second": 0.595,
|
| 113 |
+
"eval_steps_per_second": 0.315,
|
| 114 |
+
"step": 35
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.03519577650681918,
|
| 118 |
+
"grad_norm": 0.5125584006309509,
|
| 119 |
+
"learning_rate": 7.017543859649122e-05,
|
| 120 |
+
"loss": 0.7075,
|
| 121 |
+
"step": 40
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.03519577650681918,
|
| 125 |
+
"eval_loss": 0.7538504600524902,
|
| 126 |
+
"eval_runtime": 28.5816,
|
| 127 |
+
"eval_samples_per_second": 0.595,
|
| 128 |
+
"eval_steps_per_second": 0.315,
|
| 129 |
+
"step": 40
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.039595248570171576,
|
| 133 |
+
"grad_norm": 0.36081045866012573,
|
| 134 |
+
"learning_rate": 7.894736842105263e-05,
|
| 135 |
+
"loss": 0.6776,
|
| 136 |
+
"step": 45
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.039595248570171576,
|
| 140 |
+
"eval_loss": 0.7313268184661865,
|
| 141 |
+
"eval_runtime": 28.6141,
|
| 142 |
+
"eval_samples_per_second": 0.594,
|
| 143 |
+
"eval_steps_per_second": 0.315,
|
| 144 |
+
"step": 45
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.04399472063352398,
|
| 148 |
+
"grad_norm": 0.32318177819252014,
|
| 149 |
+
"learning_rate": 8.771929824561403e-05,
|
| 150 |
+
"loss": 0.6499,
|
| 151 |
+
"step": 50
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.04399472063352398,
|
| 155 |
+
"eval_loss": 0.71351158618927,
|
| 156 |
+
"eval_runtime": 28.5766,
|
| 157 |
+
"eval_samples_per_second": 0.595,
|
| 158 |
+
"eval_steps_per_second": 0.315,
|
| 159 |
+
"step": 50
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.04839419269687637,
|
| 163 |
+
"grad_norm": 0.34377261996269226,
|
| 164 |
+
"learning_rate": 9.649122807017544e-05,
|
| 165 |
+
"loss": 0.6487,
|
| 166 |
+
"step": 55
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.04839419269687637,
|
| 170 |
+
"eval_loss": 0.7006722092628479,
|
| 171 |
+
"eval_runtime": 28.6048,
|
| 172 |
+
"eval_samples_per_second": 0.594,
|
| 173 |
+
"eval_steps_per_second": 0.315,
|
| 174 |
+
"step": 55
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.05279366476022877,
|
| 178 |
+
"grad_norm": 0.4360629618167877,
|
| 179 |
+
"learning_rate": 0.00010526315789473685,
|
| 180 |
+
"loss": 0.6405,
|
| 181 |
+
"step": 60
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.05279366476022877,
|
| 185 |
+
"eval_loss": 0.6905343532562256,
|
| 186 |
+
"eval_runtime": 28.5257,
|
| 187 |
+
"eval_samples_per_second": 0.596,
|
| 188 |
+
"eval_steps_per_second": 0.316,
|
| 189 |
+
"step": 60
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.05719313682358117,
|
| 193 |
+
"grad_norm": 0.28764936327934265,
|
| 194 |
+
"learning_rate": 0.00011403508771929824,
|
| 195 |
+
"loss": 0.6352,
|
| 196 |
+
"step": 65
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.05719313682358117,
|
| 200 |
+
"eval_loss": 0.68143630027771,
|
| 201 |
+
"eval_runtime": 28.6362,
|
| 202 |
+
"eval_samples_per_second": 0.594,
|
| 203 |
+
"eval_steps_per_second": 0.314,
|
| 204 |
+
"step": 65
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.06159260888693357,
|
| 208 |
+
"grad_norm": 0.34088754653930664,
|
| 209 |
+
"learning_rate": 0.00012280701754385965,
|
| 210 |
+
"loss": 0.6064,
|
| 211 |
+
"step": 70
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.06159260888693357,
|
| 215 |
+
"eval_loss": 0.6742813587188721,
|
| 216 |
+
"eval_runtime": 28.5667,
|
| 217 |
+
"eval_samples_per_second": 0.595,
|
| 218 |
+
"eval_steps_per_second": 0.315,
|
| 219 |
+
"step": 70
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.06599208095028597,
|
| 223 |
+
"grad_norm": 0.31284183263778687,
|
| 224 |
+
"learning_rate": 0.00013157894736842108,
|
| 225 |
+
"loss": 0.5924,
|
| 226 |
+
"step": 75
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.06599208095028597,
|
| 230 |
+
"eval_loss": 0.6679767966270447,
|
| 231 |
+
"eval_runtime": 28.461,
|
| 232 |
+
"eval_samples_per_second": 0.597,
|
| 233 |
+
"eval_steps_per_second": 0.316,
|
| 234 |
+
"step": 75
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.07039155301363836,
|
| 238 |
+
"grad_norm": 0.30470508337020874,
|
| 239 |
+
"learning_rate": 0.00014035087719298245,
|
| 240 |
+
"loss": 0.5992,
|
| 241 |
+
"step": 80
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.07039155301363836,
|
| 245 |
+
"eval_loss": 0.6631008386611938,
|
| 246 |
+
"eval_runtime": 28.6891,
|
| 247 |
+
"eval_samples_per_second": 0.593,
|
| 248 |
+
"eval_steps_per_second": 0.314,
|
| 249 |
+
"step": 80
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.07479102507699076,
|
| 253 |
+
"grad_norm": 0.3255262076854706,
|
| 254 |
+
"learning_rate": 0.00014912280701754387,
|
| 255 |
+
"loss": 0.5704,
|
| 256 |
+
"step": 85
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.07479102507699076,
|
| 260 |
+
"eval_loss": 0.658618688583374,
|
| 261 |
+
"eval_runtime": 28.6094,
|
| 262 |
+
"eval_samples_per_second": 0.594,
|
| 263 |
+
"eval_steps_per_second": 0.315,
|
| 264 |
+
"step": 85
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.07919049714034315,
|
| 268 |
+
"grad_norm": 0.31922295689582825,
|
| 269 |
+
"learning_rate": 0.00015789473684210527,
|
| 270 |
+
"loss": 0.6048,
|
| 271 |
+
"step": 90
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.07919049714034315,
|
| 275 |
+
"eval_loss": 0.6537344455718994,
|
| 276 |
+
"eval_runtime": 28.532,
|
| 277 |
+
"eval_samples_per_second": 0.596,
|
| 278 |
+
"eval_steps_per_second": 0.315,
|
| 279 |
+
"step": 90
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.08358996920369556,
|
| 283 |
+
"grad_norm": 0.45636337995529175,
|
| 284 |
+
"learning_rate": 0.0001666666666666667,
|
| 285 |
+
"loss": 0.613,
|
| 286 |
+
"step": 95
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.08358996920369556,
|
| 290 |
+
"eval_loss": 0.6501972079277039,
|
| 291 |
+
"eval_runtime": 28.6568,
|
| 292 |
+
"eval_samples_per_second": 0.593,
|
| 293 |
+
"eval_steps_per_second": 0.314,
|
| 294 |
+
"step": 95
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.08798944126704795,
|
| 298 |
+
"grad_norm": 0.29334941506385803,
|
| 299 |
+
"learning_rate": 0.00017543859649122806,
|
| 300 |
+
"loss": 0.5799,
|
| 301 |
+
"step": 100
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.08798944126704795,
|
| 305 |
+
"eval_loss": 0.6471393704414368,
|
| 306 |
+
"eval_runtime": 28.5997,
|
| 307 |
+
"eval_samples_per_second": 0.594,
|
| 308 |
+
"eval_steps_per_second": 0.315,
|
| 309 |
+
"step": 100
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.09238891333040035,
|
| 313 |
+
"grad_norm": 0.31318825483322144,
|
| 314 |
+
"learning_rate": 0.00018421052631578948,
|
| 315 |
+
"loss": 0.5887,
|
| 316 |
+
"step": 105
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.09238891333040035,
|
| 320 |
+
"eval_loss": 0.6440868377685547,
|
| 321 |
+
"eval_runtime": 28.6275,
|
| 322 |
+
"eval_samples_per_second": 0.594,
|
| 323 |
+
"eval_steps_per_second": 0.314,
|
| 324 |
+
"step": 105
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.09678838539375274,
|
| 328 |
+
"grad_norm": 0.27908894419670105,
|
| 329 |
+
"learning_rate": 0.00019298245614035088,
|
| 330 |
+
"loss": 0.5905,
|
| 331 |
+
"step": 110
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.09678838539375274,
|
| 335 |
+
"eval_loss": 0.6423875689506531,
|
| 336 |
+
"eval_runtime": 28.5491,
|
| 337 |
+
"eval_samples_per_second": 0.595,
|
| 338 |
+
"eval_steps_per_second": 0.315,
|
| 339 |
+
"step": 110
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.10118785745710515,
|
| 343 |
+
"grad_norm": 0.2715133726596832,
|
| 344 |
+
"learning_rate": 0.00019999952753720356,
|
| 345 |
+
"loss": 0.5902,
|
| 346 |
+
"step": 115
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.10118785745710515,
|
| 350 |
+
"eval_loss": 0.6415910720825195,
|
| 351 |
+
"eval_runtime": 28.5086,
|
| 352 |
+
"eval_samples_per_second": 0.596,
|
| 353 |
+
"eval_steps_per_second": 0.316,
|
| 354 |
+
"step": 115
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.10558732952045755,
|
| 358 |
+
"grad_norm": 0.3028790056705475,
|
| 359 |
+
"learning_rate": 0.000199982991808088,
|
| 360 |
+
"loss": 0.5773,
|
| 361 |
+
"step": 120
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.10558732952045755,
|
| 365 |
+
"eval_loss": 0.6377425789833069,
|
| 366 |
+
"eval_runtime": 28.6438,
|
| 367 |
+
"eval_samples_per_second": 0.593,
|
| 368 |
+
"eval_steps_per_second": 0.314,
|
| 369 |
+
"step": 120
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.10998680158380994,
|
| 373 |
+
"grad_norm": 0.3071883022785187,
|
| 374 |
+
"learning_rate": 0.00019994283740338306,
|
| 375 |
+
"loss": 0.5598,
|
| 376 |
+
"step": 125
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.10998680158380994,
|
| 380 |
+
"eval_loss": 0.6367806196212769,
|
| 381 |
+
"eval_runtime": 28.4852,
|
| 382 |
+
"eval_samples_per_second": 0.597,
|
| 383 |
+
"eval_steps_per_second": 0.316,
|
| 384 |
+
"step": 125
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.11438627364716233,
|
| 388 |
+
"grad_norm": 0.34842655062675476,
|
| 389 |
+
"learning_rate": 0.00019987907380864062,
|
| 390 |
+
"loss": 0.596,
|
| 391 |
+
"step": 130
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.11438627364716233,
|
| 395 |
+
"eval_loss": 0.6347749829292297,
|
| 396 |
+
"eval_runtime": 28.5908,
|
| 397 |
+
"eval_samples_per_second": 0.595,
|
| 398 |
+
"eval_steps_per_second": 0.315,
|
| 399 |
+
"step": 130
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.11878574571051474,
|
| 403 |
+
"grad_norm": 0.2854275107383728,
|
| 404 |
+
"learning_rate": 0.00019979171608653924,
|
| 405 |
+
"loss": 0.5733,
|
| 406 |
+
"step": 135
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.11878574571051474,
|
| 410 |
+
"eval_loss": 0.6301032900810242,
|
| 411 |
+
"eval_runtime": 28.5482,
|
| 412 |
+
"eval_samples_per_second": 0.595,
|
| 413 |
+
"eval_steps_per_second": 0.315,
|
| 414 |
+
"step": 135
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.12318521777386714,
|
| 418 |
+
"grad_norm": 0.27615901827812195,
|
| 419 |
+
"learning_rate": 0.00019968078487332566,
|
| 420 |
+
"loss": 0.5875,
|
| 421 |
+
"step": 140
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.12318521777386714,
|
| 425 |
+
"eval_loss": 0.6269793510437012,
|
| 426 |
+
"eval_runtime": 28.4974,
|
| 427 |
+
"eval_samples_per_second": 0.597,
|
| 428 |
+
"eval_steps_per_second": 0.316,
|
| 429 |
+
"step": 140
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.12758468983721954,
|
| 433 |
+
"grad_norm": 0.2709368169307709,
|
| 434 |
+
"learning_rate": 0.00019954630637394029,
|
| 435 |
+
"loss": 0.5711,
|
| 436 |
+
"step": 145
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.12758468983721954,
|
| 440 |
+
"eval_loss": 0.6240233182907104,
|
| 441 |
+
"eval_runtime": 28.5264,
|
| 442 |
+
"eval_samples_per_second": 0.596,
|
| 443 |
+
"eval_steps_per_second": 0.315,
|
| 444 |
+
"step": 145
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.13198416190057194,
|
| 448 |
+
"grad_norm": 0.2877412736415863,
|
| 449 |
+
"learning_rate": 0.00019938831235582672,
|
| 450 |
+
"loss": 0.5885,
|
| 451 |
+
"step": 150
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.13198416190057194,
|
| 455 |
+
"eval_loss": 0.6206945776939392,
|
| 456 |
+
"eval_runtime": 28.5668,
|
| 457 |
+
"eval_samples_per_second": 0.595,
|
| 458 |
+
"eval_steps_per_second": 0.315,
|
| 459 |
+
"step": 150
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.13638363396392433,
|
| 463 |
+
"grad_norm": 0.2922605574131012,
|
| 464 |
+
"learning_rate": 0.00019920684014142738,
|
| 465 |
+
"loss": 0.5485,
|
| 466 |
+
"step": 155
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.13638363396392433,
|
| 470 |
+
"eval_loss": 0.6200662851333618,
|
| 471 |
+
"eval_runtime": 28.5452,
|
| 472 |
+
"eval_samples_per_second": 0.596,
|
| 473 |
+
"eval_steps_per_second": 0.315,
|
| 474 |
+
"step": 155
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.14078310602727673,
|
| 478 |
+
"grad_norm": 0.28340834379196167,
|
| 479 |
+
"learning_rate": 0.00019900193259936704,
|
| 480 |
+
"loss": 0.5754,
|
| 481 |
+
"step": 160
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.14078310602727673,
|
| 485 |
+
"eval_loss": 0.6187402606010437,
|
| 486 |
+
"eval_runtime": 28.5939,
|
| 487 |
+
"eval_samples_per_second": 0.595,
|
| 488 |
+
"eval_steps_per_second": 0.315,
|
| 489 |
+
"step": 160
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.14518257809062912,
|
| 493 |
+
"grad_norm": 0.2796618938446045,
|
| 494 |
+
"learning_rate": 0.0001987736381343261,
|
| 495 |
+
"loss": 0.5535,
|
| 496 |
+
"step": 165
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.14518257809062912,
|
| 500 |
+
"eval_loss": 0.6156266331672668,
|
| 501 |
+
"eval_runtime": 28.5378,
|
| 502 |
+
"eval_samples_per_second": 0.596,
|
| 503 |
+
"eval_steps_per_second": 0.315,
|
| 504 |
+
"step": 165
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.14958205015398152,
|
| 508 |
+
"grad_norm": 0.25343528389930725,
|
| 509 |
+
"learning_rate": 0.00019852201067560606,
|
| 510 |
+
"loss": 0.5697,
|
| 511 |
+
"step": 170
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.14958205015398152,
|
| 515 |
+
"eval_loss": 0.6125033497810364,
|
| 516 |
+
"eval_runtime": 28.5565,
|
| 517 |
+
"eval_samples_per_second": 0.595,
|
| 518 |
+
"eval_steps_per_second": 0.315,
|
| 519 |
+
"step": 170
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.1539815222173339,
|
| 523 |
+
"grad_norm": 0.23438464105129242,
|
| 524 |
+
"learning_rate": 0.00019824710966438996,
|
| 525 |
+
"loss": 0.5335,
|
| 526 |
+
"step": 175
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.1539815222173339,
|
| 530 |
+
"eval_loss": 0.6096713542938232,
|
| 531 |
+
"eval_runtime": 28.6017,
|
| 532 |
+
"eval_samples_per_second": 0.594,
|
| 533 |
+
"eval_steps_per_second": 0.315,
|
| 534 |
+
"step": 175
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.1583809942806863,
|
| 538 |
+
"grad_norm": 0.24729043245315552,
|
| 539 |
+
"learning_rate": 0.00019794900003970077,
|
| 540 |
+
"loss": 0.5702,
|
| 541 |
+
"step": 180
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.1583809942806863,
|
| 545 |
+
"eval_loss": 0.6071114540100098,
|
| 546 |
+
"eval_runtime": 28.5677,
|
| 547 |
+
"eval_samples_per_second": 0.595,
|
| 548 |
+
"eval_steps_per_second": 0.315,
|
| 549 |
+
"step": 180
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.16278046634403873,
|
| 553 |
+
"grad_norm": 0.257964551448822,
|
| 554 |
+
"learning_rate": 0.00019762775222306107,
|
| 555 |
+
"loss": 0.5494,
|
| 556 |
+
"step": 185
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.16278046634403873,
|
| 560 |
+
"eval_loss": 0.6062531471252441,
|
| 561 |
+
"eval_runtime": 28.5933,
|
| 562 |
+
"eval_samples_per_second": 0.595,
|
| 563 |
+
"eval_steps_per_second": 0.315,
|
| 564 |
+
"step": 185
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.16717993840739112,
|
| 568 |
+
"grad_norm": 0.2648680806159973,
|
| 569 |
+
"learning_rate": 0.0001972834421018576,
|
| 570 |
+
"loss": 0.5379,
|
| 571 |
+
"step": 190
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.16717993840739112,
|
| 575 |
+
"eval_loss": 0.6054437756538391,
|
| 576 |
+
"eval_runtime": 28.5575,
|
| 577 |
+
"eval_samples_per_second": 0.595,
|
| 578 |
+
"eval_steps_per_second": 0.315,
|
| 579 |
+
"step": 190
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.17157941047074352,
|
| 583 |
+
"grad_norm": 0.2540712356567383,
|
| 584 |
+
"learning_rate": 0.00019691615101141455,
|
| 585 |
+
"loss": 0.5415,
|
| 586 |
+
"step": 195
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.17157941047074352,
|
| 590 |
+
"eval_loss": 0.6023730039596558,
|
| 591 |
+
"eval_runtime": 28.5419,
|
| 592 |
+
"eval_samples_per_second": 0.596,
|
| 593 |
+
"eval_steps_per_second": 0.315,
|
| 594 |
+
"step": 195
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.1759788825340959,
|
| 598 |
+
"grad_norm": 0.2424851357936859,
|
| 599 |
+
"learning_rate": 0.00019652596571578004,
|
| 600 |
+
"loss": 0.5504,
|
| 601 |
+
"step": 200
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.1759788825340959,
|
| 605 |
+
"eval_loss": 0.5997632145881653,
|
| 606 |
+
"eval_runtime": 28.6422,
|
| 607 |
+
"eval_samples_per_second": 0.594,
|
| 608 |
+
"eval_steps_per_second": 0.314,
|
| 609 |
+
"step": 200
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.1803783545974483,
|
| 613 |
+
"grad_norm": 0.2573873698711395,
|
| 614 |
+
"learning_rate": 0.0001961129783872301,
|
| 615 |
+
"loss": 0.5418,
|
| 616 |
+
"step": 205
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.1803783545974483,
|
| 620 |
+
"eval_loss": 0.5976300239562988,
|
| 621 |
+
"eval_runtime": 28.5752,
|
| 622 |
+
"eval_samples_per_second": 0.595,
|
| 623 |
+
"eval_steps_per_second": 0.315,
|
| 624 |
+
"step": 205
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.1847778266608007,
|
| 628 |
+
"grad_norm": 0.22338183224201202,
|
| 629 |
+
"learning_rate": 0.00019567728658449504,
|
| 630 |
+
"loss": 0.54,
|
| 631 |
+
"step": 210
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.1847778266608007,
|
| 635 |
+
"eval_loss": 0.5960862040519714,
|
| 636 |
+
"eval_runtime": 28.4685,
|
| 637 |
+
"eval_samples_per_second": 0.597,
|
| 638 |
+
"eval_steps_per_second": 0.316,
|
| 639 |
+
"step": 210
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.1891772987241531,
|
| 643 |
+
"grad_norm": 0.2706097960472107,
|
| 644 |
+
"learning_rate": 0.00019521899322971352,
|
| 645 |
+
"loss": 0.5522,
|
| 646 |
+
"step": 215
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.1891772987241531,
|
| 650 |
+
"eval_loss": 0.5958646535873413,
|
| 651 |
+
"eval_runtime": 28.5678,
|
| 652 |
+
"eval_samples_per_second": 0.595,
|
| 653 |
+
"eval_steps_per_second": 0.315,
|
| 654 |
+
"step": 215
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.1935767707875055,
|
| 658 |
+
"grad_norm": 0.23476411402225494,
|
| 659 |
+
"learning_rate": 0.00019473820658411957,
|
| 660 |
+
"loss": 0.5262,
|
| 661 |
+
"step": 220
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.1935767707875055,
|
| 665 |
+
"eval_loss": 0.5945417284965515,
|
| 666 |
+
"eval_runtime": 28.5611,
|
| 667 |
+
"eval_samples_per_second": 0.595,
|
| 668 |
+
"eval_steps_per_second": 0.315,
|
| 669 |
+
"step": 220
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.1979762428508579,
|
| 673 |
+
"grad_norm": 0.23705659806728363,
|
| 674 |
+
"learning_rate": 0.00019423504022246825,
|
| 675 |
+
"loss": 0.5439,
|
| 676 |
+
"step": 225
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.1979762428508579,
|
| 680 |
+
"eval_loss": 0.5934200286865234,
|
| 681 |
+
"eval_runtime": 28.5955,
|
| 682 |
+
"eval_samples_per_second": 0.594,
|
| 683 |
+
"eval_steps_per_second": 0.315,
|
| 684 |
+
"step": 225
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.2023757149142103,
|
| 688 |
+
"grad_norm": 0.22662319242954254,
|
| 689 |
+
"learning_rate": 0.00019370961300620637,
|
| 690 |
+
"loss": 0.5262,
|
| 691 |
+
"step": 230
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.2023757149142103,
|
| 695 |
+
"eval_loss": 0.5928044319152832,
|
| 696 |
+
"eval_runtime": 28.514,
|
| 697 |
+
"eval_samples_per_second": 0.596,
|
| 698 |
+
"eval_steps_per_second": 0.316,
|
| 699 |
+
"step": 230
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.2067751869775627,
|
| 703 |
+
"grad_norm": 0.24046145379543304,
|
| 704 |
+
"learning_rate": 0.00019316204905539425,
|
| 705 |
+
"loss": 0.5462,
|
| 706 |
+
"step": 235
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.2067751869775627,
|
| 710 |
+
"eval_loss": 0.5904839038848877,
|
| 711 |
+
"eval_runtime": 28.5557,
|
| 712 |
+
"eval_samples_per_second": 0.595,
|
| 713 |
+
"eval_steps_per_second": 0.315,
|
| 714 |
+
"step": 235
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.2111746590409151,
|
| 718 |
+
"grad_norm": 0.23923470079898834,
|
| 719 |
+
"learning_rate": 0.000192592477719385,
|
| 720 |
+
"loss": 0.5345,
|
| 721 |
+
"step": 240
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 0.2111746590409151,
|
| 725 |
+
"eval_loss": 0.590508759021759,
|
| 726 |
+
"eval_runtime": 28.5204,
|
| 727 |
+
"eval_samples_per_second": 0.596,
|
| 728 |
+
"eval_steps_per_second": 0.316,
|
| 729 |
+
"step": 240
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.21557413110426749,
|
| 733 |
+
"grad_norm": 0.24345721304416656,
|
| 734 |
+
"learning_rate": 0.00019200103354626892,
|
| 735 |
+
"loss": 0.5478,
|
| 736 |
+
"step": 245
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.21557413110426749,
|
| 740 |
+
"eval_loss": 0.5882726907730103,
|
| 741 |
+
"eval_runtime": 28.5722,
|
| 742 |
+
"eval_samples_per_second": 0.595,
|
| 743 |
+
"eval_steps_per_second": 0.315,
|
| 744 |
+
"step": 245
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.21997360316761988,
|
| 748 |
+
"grad_norm": 0.27501732110977173,
|
| 749 |
+
"learning_rate": 0.00019138785625108957,
|
| 750 |
+
"loss": 0.5607,
|
| 751 |
+
"step": 250
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.21997360316761988,
|
| 755 |
+
"eval_loss": 0.5860432982444763,
|
| 756 |
+
"eval_runtime": 28.503,
|
| 757 |
+
"eval_samples_per_second": 0.596,
|
| 758 |
+
"eval_steps_per_second": 0.316,
|
| 759 |
+
"step": 250
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.22437307523097227,
|
| 763 |
+
"grad_norm": 0.3151032328605652,
|
| 764 |
+
"learning_rate": 0.0001907530906828393,
|
| 765 |
+
"loss": 0.5479,
|
| 766 |
+
"step": 255
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.22437307523097227,
|
| 770 |
+
"eval_loss": 0.5846895575523376,
|
| 771 |
+
"eval_runtime": 28.6081,
|
| 772 |
+
"eval_samples_per_second": 0.594,
|
| 773 |
+
"eval_steps_per_second": 0.315,
|
| 774 |
+
"step": 255
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.22877254729432467,
|
| 778 |
+
"grad_norm": 0.2758755385875702,
|
| 779 |
+
"learning_rate": 0.0001900968867902419,
|
| 780 |
+
"loss": 0.5767,
|
| 781 |
+
"step": 260
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.22877254729432467,
|
| 785 |
+
"eval_loss": 0.5815722942352295,
|
| 786 |
+
"eval_runtime": 28.5574,
|
| 787 |
+
"eval_samples_per_second": 0.595,
|
| 788 |
+
"eval_steps_per_second": 0.315,
|
| 789 |
+
"step": 260
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.2331720193576771,
|
| 793 |
+
"grad_norm": 0.25241315364837646,
|
| 794 |
+
"learning_rate": 0.000189419399586331,
|
| 795 |
+
"loss": 0.5568,
|
| 796 |
+
"step": 265
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.2331720193576771,
|
| 800 |
+
"eval_loss": 0.5822274684906006,
|
| 801 |
+
"eval_runtime": 28.573,
|
| 802 |
+
"eval_samples_per_second": 0.595,
|
| 803 |
+
"eval_steps_per_second": 0.315,
|
| 804 |
+
"step": 265
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.23757149142102948,
|
| 808 |
+
"grad_norm": 0.316436767578125,
|
| 809 |
+
"learning_rate": 0.00018872078911183146,
|
| 810 |
+
"loss": 0.5385,
|
| 811 |
+
"step": 270
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.23757149142102948,
|
| 815 |
+
"eval_loss": 0.5809066891670227,
|
| 816 |
+
"eval_runtime": 28.5598,
|
| 817 |
+
"eval_samples_per_second": 0.595,
|
| 818 |
+
"eval_steps_per_second": 0.315,
|
| 819 |
+
"step": 270
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.24197096348438188,
|
| 823 |
+
"grad_norm": 0.27813801169395447,
|
| 824 |
+
"learning_rate": 0.00018800122039735358,
|
| 825 |
+
"loss": 0.5348,
|
| 826 |
+
"step": 275
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.24197096348438188,
|
| 830 |
+
"eval_loss": 0.5786107778549194,
|
| 831 |
+
"eval_runtime": 28.546,
|
| 832 |
+
"eval_samples_per_second": 0.596,
|
| 833 |
+
"eval_steps_per_second": 0.315,
|
| 834 |
+
"step": 275
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.24637043554773427,
|
| 838 |
+
"grad_norm": 0.2552705407142639,
|
| 839 |
+
"learning_rate": 0.00018726086342440846,
|
| 840 |
+
"loss": 0.5207,
|
| 841 |
+
"step": 280
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.24637043554773427,
|
| 845 |
+
"eval_loss": 0.5768923759460449,
|
| 846 |
+
"eval_runtime": 28.5995,
|
| 847 |
+
"eval_samples_per_second": 0.594,
|
| 848 |
+
"eval_steps_per_second": 0.315,
|
| 849 |
+
"step": 280
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.2507699076110867,
|
| 853 |
+
"grad_norm": 0.21993091702461243,
|
| 854 |
+
"learning_rate": 0.00018649989308525372,
|
| 855 |
+
"loss": 0.5292,
|
| 856 |
+
"step": 285
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.2507699076110867,
|
| 860 |
+
"eval_loss": 0.5762263536453247,
|
| 861 |
+
"eval_runtime": 28.4816,
|
| 862 |
+
"eval_samples_per_second": 0.597,
|
| 863 |
+
"eval_steps_per_second": 0.316,
|
| 864 |
+
"step": 285
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.2551693796744391,
|
| 868 |
+
"grad_norm": 0.27086153626441956,
|
| 869 |
+
"learning_rate": 0.0001857184891415794,
|
| 870 |
+
"loss": 0.5312,
|
| 871 |
+
"step": 290
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.2551693796744391,
|
| 875 |
+
"eval_loss": 0.5758266448974609,
|
| 876 |
+
"eval_runtime": 28.5295,
|
| 877 |
+
"eval_samples_per_second": 0.596,
|
| 878 |
+
"eval_steps_per_second": 0.315,
|
| 879 |
+
"step": 290
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.2595688517377915,
|
| 883 |
+
"grad_norm": 0.21816319227218628,
|
| 884 |
+
"learning_rate": 0.0001849168361820431,
|
| 885 |
+
"loss": 0.5223,
|
| 886 |
+
"step": 295
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 0.2595688517377915,
|
| 890 |
+
"eval_loss": 0.574447751045227,
|
| 891 |
+
"eval_runtime": 28.5859,
|
| 892 |
+
"eval_samples_per_second": 0.595,
|
| 893 |
+
"eval_steps_per_second": 0.315,
|
| 894 |
+
"step": 295
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.2639683238011439,
|
| 898 |
+
"grad_norm": 0.24796700477600098,
|
| 899 |
+
"learning_rate": 0.00018409512357866548,
|
| 900 |
+
"loss": 0.5485,
|
| 901 |
+
"step": 300
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.2639683238011439,
|
| 905 |
+
"eval_loss": 0.573371410369873,
|
| 906 |
+
"eval_runtime": 28.6178,
|
| 907 |
+
"eval_samples_per_second": 0.594,
|
| 908 |
+
"eval_steps_per_second": 0.314,
|
| 909 |
+
"step": 300
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.2683677958644963,
|
| 913 |
+
"grad_norm": 0.2425287663936615,
|
| 914 |
+
"learning_rate": 0.00018325354544209535,
|
| 915 |
+
"loss": 0.5217,
|
| 916 |
+
"step": 305
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 0.2683677958644963,
|
| 920 |
+
"eval_loss": 0.5723298788070679,
|
| 921 |
+
"eval_runtime": 28.5916,
|
| 922 |
+
"eval_samples_per_second": 0.595,
|
| 923 |
+
"eval_steps_per_second": 0.315,
|
| 924 |
+
"step": 305
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.27276726792784867,
|
| 928 |
+
"grad_norm": 0.21630050241947174,
|
| 929 |
+
"learning_rate": 0.00018239230057575542,
|
| 930 |
+
"loss": 0.5074,
|
| 931 |
+
"step": 310
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 0.27276726792784867,
|
| 935 |
+
"eval_loss": 0.5725327134132385,
|
| 936 |
+
"eval_runtime": 28.536,
|
| 937 |
+
"eval_samples_per_second": 0.596,
|
| 938 |
+
"eval_steps_per_second": 0.315,
|
| 939 |
+
"step": 310
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.27716673999120106,
|
| 943 |
+
"grad_norm": 0.21529468894004822,
|
| 944 |
+
"learning_rate": 0.0001815115924288798,
|
| 945 |
+
"loss": 0.5487,
|
| 946 |
+
"step": 315
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.27716673999120106,
|
| 950 |
+
"eval_loss": 0.5721793174743652,
|
| 951 |
+
"eval_runtime": 28.6852,
|
| 952 |
+
"eval_samples_per_second": 0.593,
|
| 953 |
+
"eval_steps_per_second": 0.314,
|
| 954 |
+
"step": 315
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.28156621205455346,
|
| 958 |
+
"grad_norm": 0.21623414754867554,
|
| 959 |
+
"learning_rate": 0.00018061162904845358,
|
| 960 |
+
"loss": 0.5106,
|
| 961 |
+
"step": 320
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.28156621205455346,
|
| 965 |
+
"eval_loss": 0.5709577202796936,
|
| 966 |
+
"eval_runtime": 28.4592,
|
| 967 |
+
"eval_samples_per_second": 0.597,
|
| 968 |
+
"eval_steps_per_second": 0.316,
|
| 969 |
+
"step": 320
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.28596568411790585,
|
| 973 |
+
"grad_norm": 0.2219308316707611,
|
| 974 |
+
"learning_rate": 0.0001796926230300667,
|
| 975 |
+
"loss": 0.5218,
|
| 976 |
+
"step": 325
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.28596568411790585,
|
| 980 |
+
"eval_loss": 0.5698617100715637,
|
| 981 |
+
"eval_runtime": 28.5588,
|
| 982 |
+
"eval_samples_per_second": 0.595,
|
| 983 |
+
"eval_steps_per_second": 0.315,
|
| 984 |
+
"step": 325
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.29036515618125824,
|
| 988 |
+
"grad_norm": 0.2264701873064041,
|
| 989 |
+
"learning_rate": 0.00017875479146769305,
|
| 990 |
+
"loss": 0.5162,
|
| 991 |
+
"step": 330
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.29036515618125824,
|
| 995 |
+
"eval_loss": 0.5689781308174133,
|
| 996 |
+
"eval_runtime": 28.6221,
|
| 997 |
+
"eval_samples_per_second": 0.594,
|
| 998 |
+
"eval_steps_per_second": 0.314,
|
| 999 |
+
"step": 330
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.29476462824461064,
|
| 1003 |
+
"grad_norm": 0.24004362523555756,
|
| 1004 |
+
"learning_rate": 0.000177798355902407,
|
| 1005 |
+
"loss": 0.539,
|
| 1006 |
+
"step": 335
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.29476462824461064,
|
| 1010 |
+
"eval_loss": 0.5678241848945618,
|
| 1011 |
+
"eval_runtime": 28.5677,
|
| 1012 |
+
"eval_samples_per_second": 0.595,
|
| 1013 |
+
"eval_steps_per_second": 0.315,
|
| 1014 |
+
"step": 335
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 0.29916410030796303,
|
| 1018 |
+
"grad_norm": 0.22996000945568085,
|
| 1019 |
+
"learning_rate": 0.00017682354227004963,
|
| 1020 |
+
"loss": 0.5002,
|
| 1021 |
+
"step": 340
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 0.29916410030796303,
|
| 1025 |
+
"eval_loss": 0.5670127272605896,
|
| 1026 |
+
"eval_runtime": 28.6425,
|
| 1027 |
+
"eval_samples_per_second": 0.594,
|
| 1028 |
+
"eval_steps_per_second": 0.314,
|
| 1029 |
+
"step": 340
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.3035635723713154,
|
| 1033 |
+
"grad_norm": 0.23163671791553497,
|
| 1034 |
+
"learning_rate": 0.00017583058084785625,
|
| 1035 |
+
"loss": 0.5175,
|
| 1036 |
+
"step": 345
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 0.3035635723713154,
|
| 1040 |
+
"eval_loss": 0.5650352239608765,
|
| 1041 |
+
"eval_runtime": 28.5994,
|
| 1042 |
+
"eval_samples_per_second": 0.594,
|
| 1043 |
+
"eval_steps_per_second": 0.315,
|
| 1044 |
+
"step": 345
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 0.3079630444346678,
|
| 1048 |
+
"grad_norm": 0.20120489597320557,
|
| 1049 |
+
"learning_rate": 0.00017481970620005912,
|
| 1050 |
+
"loss": 0.5269,
|
| 1051 |
+
"step": 350
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 0.3079630444346678,
|
| 1055 |
+
"eval_loss": 0.5640237927436829,
|
| 1056 |
+
"eval_runtime": 28.5009,
|
| 1057 |
+
"eval_samples_per_second": 0.596,
|
| 1058 |
+
"eval_steps_per_second": 0.316,
|
| 1059 |
+
"step": 350
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.3123625164980202,
|
| 1063 |
+
"grad_norm": 0.22231583297252655,
|
| 1064 |
+
"learning_rate": 0.00017379115712247675,
|
| 1065 |
+
"loss": 0.5444,
|
| 1066 |
+
"step": 355
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.3123625164980202,
|
| 1070 |
+
"eval_loss": 0.5634257197380066,
|
| 1071 |
+
"eval_runtime": 28.5722,
|
| 1072 |
+
"eval_samples_per_second": 0.595,
|
| 1073 |
+
"eval_steps_per_second": 0.315,
|
| 1074 |
+
"step": 355
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.3167619885613726,
|
| 1078 |
+
"grad_norm": 0.216331347823143,
|
| 1079 |
+
"learning_rate": 0.00017274517658610398,
|
| 1080 |
+
"loss": 0.5074,
|
| 1081 |
+
"step": 360
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.3167619885613726,
|
| 1085 |
+
"eval_loss": 0.5618783831596375,
|
| 1086 |
+
"eval_runtime": 28.6759,
|
| 1087 |
+
"eval_samples_per_second": 0.593,
|
| 1088 |
+
"eval_steps_per_second": 0.314,
|
| 1089 |
+
"step": 360
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.32116146062472506,
|
| 1093 |
+
"grad_norm": 0.21976010501384735,
|
| 1094 |
+
"learning_rate": 0.0001716820116797158,
|
| 1095 |
+
"loss": 0.5259,
|
| 1096 |
+
"step": 365
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 0.32116146062472506,
|
| 1100 |
+
"eval_loss": 0.5602042078971863,
|
| 1101 |
+
"eval_runtime": 28.6019,
|
| 1102 |
+
"eval_samples_per_second": 0.594,
|
| 1103 |
+
"eval_steps_per_second": 0.315,
|
| 1104 |
+
"step": 365
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.32556093268807745,
|
| 1108 |
+
"grad_norm": 0.22740119695663452,
|
| 1109 |
+
"learning_rate": 0.0001706019135514982,
|
| 1110 |
+
"loss": 0.5158,
|
| 1111 |
+
"step": 370
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.32556093268807745,
|
| 1115 |
+
"eval_loss": 0.5599080920219421,
|
| 1116 |
+
"eval_runtime": 28.5177,
|
| 1117 |
+
"eval_samples_per_second": 0.596,
|
| 1118 |
+
"eval_steps_per_second": 0.316,
|
| 1119 |
+
"step": 370
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.32996040475142985,
|
| 1123 |
+
"grad_norm": 0.21888501942157745,
|
| 1124 |
+
"learning_rate": 0.0001695051373497202,
|
| 1125 |
+
"loss": 0.527,
|
| 1126 |
+
"step": 375
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.32996040475142985,
|
| 1130 |
+
"eval_loss": 0.558814525604248,
|
| 1131 |
+
"eval_runtime": 28.661,
|
| 1132 |
+
"eval_samples_per_second": 0.593,
|
| 1133 |
+
"eval_steps_per_second": 0.314,
|
| 1134 |
+
"step": 375
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 0.33435987681478224,
|
| 1138 |
+
"grad_norm": 0.20402850210666656,
|
| 1139 |
+
"learning_rate": 0.00016839194216246108,
|
| 1140 |
+
"loss": 0.5027,
|
| 1141 |
+
"step": 380
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 0.33435987681478224,
|
| 1145 |
+
"eval_loss": 0.5578404664993286,
|
| 1146 |
+
"eval_runtime": 28.5421,
|
| 1147 |
+
"eval_samples_per_second": 0.596,
|
| 1148 |
+
"eval_steps_per_second": 0.315,
|
| 1149 |
+
"step": 380
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.33875934887813464,
|
| 1153 |
+
"grad_norm": 0.20368748903274536,
|
| 1154 |
+
"learning_rate": 0.00016726259095640664,
|
| 1155 |
+
"loss": 0.505,
|
| 1156 |
+
"step": 385
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 0.33875934887813464,
|
| 1160 |
+
"eval_loss": 0.5567160844802856,
|
| 1161 |
+
"eval_runtime": 28.6126,
|
| 1162 |
+
"eval_samples_per_second": 0.594,
|
| 1163 |
+
"eval_steps_per_second": 0.315,
|
| 1164 |
+
"step": 385
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.34315882094148703,
|
| 1168 |
+
"grad_norm": 0.2069130390882492,
|
| 1169 |
+
"learning_rate": 0.0001661173505147295,
|
| 1170 |
+
"loss": 0.5086,
|
| 1171 |
+
"step": 390
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.34315882094148703,
|
| 1175 |
+
"eval_loss": 0.55617755651474,
|
| 1176 |
+
"eval_runtime": 28.4879,
|
| 1177 |
+
"eval_samples_per_second": 0.597,
|
| 1178 |
+
"eval_steps_per_second": 0.316,
|
| 1179 |
+
"step": 390
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.3475582930048394,
|
| 1183 |
+
"grad_norm": 0.23644201457500458,
|
| 1184 |
+
"learning_rate": 0.00016495649137406772,
|
| 1185 |
+
"loss": 0.5412,
|
| 1186 |
+
"step": 395
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.3475582930048394,
|
| 1190 |
+
"eval_loss": 0.5556927919387817,
|
| 1191 |
+
"eval_runtime": 28.6713,
|
| 1192 |
+
"eval_samples_per_second": 0.593,
|
| 1193 |
+
"eval_steps_per_second": 0.314,
|
| 1194 |
+
"step": 395
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.3519577650681918,
|
| 1198 |
+
"grad_norm": 0.21997737884521484,
|
| 1199 |
+
"learning_rate": 0.00016378028776061667,
|
| 1200 |
+
"loss": 0.4908,
|
| 1201 |
+
"step": 400
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 0.3519577650681918,
|
| 1205 |
+
"eval_loss": 0.5555915832519531,
|
| 1206 |
+
"eval_runtime": 28.596,
|
| 1207 |
+
"eval_samples_per_second": 0.594,
|
| 1208 |
+
"eval_steps_per_second": 0.315,
|
| 1209 |
+
"step": 400
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.3563572371315442,
|
| 1213 |
+
"grad_norm": 0.22075805068016052,
|
| 1214 |
+
"learning_rate": 0.00016258901752534948,
|
| 1215 |
+
"loss": 0.5155,
|
| 1216 |
+
"step": 405
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 0.3563572371315442,
|
| 1220 |
+
"eval_loss": 0.5552019476890564,
|
| 1221 |
+
"eval_runtime": 28.595,
|
| 1222 |
+
"eval_samples_per_second": 0.595,
|
| 1223 |
+
"eval_steps_per_second": 0.315,
|
| 1224 |
+
"step": 405
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.3607567091948966,
|
| 1228 |
+
"grad_norm": 0.5917304158210754,
|
| 1229 |
+
"learning_rate": 0.00016138296207838127,
|
| 1230 |
+
"loss": 0.4991,
|
| 1231 |
+
"step": 410
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.3607567091948966,
|
| 1235 |
+
"eval_loss": 0.5550567507743835,
|
| 1236 |
+
"eval_runtime": 28.6222,
|
| 1237 |
+
"eval_samples_per_second": 0.594,
|
| 1238 |
+
"eval_steps_per_second": 0.314,
|
| 1239 |
+
"step": 410
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 0.365156181258249,
|
| 1243 |
+
"grad_norm": 0.21421152353286743,
|
| 1244 |
+
"learning_rate": 0.00016016240632249224,
|
| 1245 |
+
"loss": 0.4769,
|
| 1246 |
+
"step": 415
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 0.365156181258249,
|
| 1250 |
+
"eval_loss": 0.5548796653747559,
|
| 1251 |
+
"eval_runtime": 28.5933,
|
| 1252 |
+
"eval_samples_per_second": 0.595,
|
| 1253 |
+
"eval_steps_per_second": 0.315,
|
| 1254 |
+
"step": 415
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 0.3695556533216014,
|
| 1258 |
+
"grad_norm": 0.201774463057518,
|
| 1259 |
+
"learning_rate": 0.0001589276385858262,
|
| 1260 |
+
"loss": 0.4914,
|
| 1261 |
+
"step": 420
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 0.3695556533216014,
|
| 1265 |
+
"eval_loss": 0.5546624064445496,
|
| 1266 |
+
"eval_runtime": 28.5213,
|
| 1267 |
+
"eval_samples_per_second": 0.596,
|
| 1268 |
+
"eval_steps_per_second": 0.316,
|
| 1269 |
+
"step": 420
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.3739551253849538,
|
| 1273 |
+
"grad_norm": 0.22172759473323822,
|
| 1274 |
+
"learning_rate": 0.0001576789505537795,
|
| 1275 |
+
"loss": 0.4726,
|
| 1276 |
+
"step": 425
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.3739551253849538,
|
| 1280 |
+
"eval_loss": 0.5535080432891846,
|
| 1281 |
+
"eval_runtime": 28.6645,
|
| 1282 |
+
"eval_samples_per_second": 0.593,
|
| 1283 |
+
"eval_steps_per_second": 0.314,
|
| 1284 |
+
"step": 425
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.3783545974483062,
|
| 1288 |
+
"grad_norm": 0.23269815742969513,
|
| 1289 |
+
"learning_rate": 0.00015641663720009733,
|
| 1290 |
+
"loss": 0.5076,
|
| 1291 |
+
"step": 430
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.3783545974483062,
|
| 1295 |
+
"eval_loss": 0.5522862076759338,
|
| 1296 |
+
"eval_runtime": 28.5697,
|
| 1297 |
+
"eval_samples_per_second": 0.595,
|
| 1298 |
+
"eval_steps_per_second": 0.315,
|
| 1299 |
+
"step": 430
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.3827540695116586,
|
| 1303 |
+
"grad_norm": 0.23303498327732086,
|
| 1304 |
+
"learning_rate": 0.00015514099671719268,
|
| 1305 |
+
"loss": 0.5064,
|
| 1306 |
+
"step": 435
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.3827540695116586,
|
| 1310 |
+
"eval_loss": 0.5502522587776184,
|
| 1311 |
+
"eval_runtime": 28.5369,
|
| 1312 |
+
"eval_samples_per_second": 0.596,
|
| 1313 |
+
"eval_steps_per_second": 0.315,
|
| 1314 |
+
"step": 435
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.387153541575011,
|
| 1318 |
+
"grad_norm": 0.24087387323379517,
|
| 1319 |
+
"learning_rate": 0.00015385233044570555,
|
| 1320 |
+
"loss": 0.5361,
|
| 1321 |
+
"step": 440
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.387153541575011,
|
| 1325 |
+
"eval_loss": 0.5471201539039612,
|
| 1326 |
+
"eval_runtime": 28.5791,
|
| 1327 |
+
"eval_samples_per_second": 0.595,
|
| 1328 |
+
"eval_steps_per_second": 0.315,
|
| 1329 |
+
"step": 440
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.3915530136383634,
|
| 1333 |
+
"grad_norm": 0.20800553262233734,
|
| 1334 |
+
"learning_rate": 0.00015255094280331797,
|
| 1335 |
+
"loss": 0.5169,
|
| 1336 |
+
"step": 445
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.3915530136383634,
|
| 1340 |
+
"eval_loss": 0.5466722846031189,
|
| 1341 |
+
"eval_runtime": 28.6339,
|
| 1342 |
+
"eval_samples_per_second": 0.594,
|
| 1343 |
+
"eval_steps_per_second": 0.314,
|
| 1344 |
+
"step": 445
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 0.3959524857017158,
|
| 1348 |
+
"grad_norm": 0.37092360854148865,
|
| 1349 |
+
"learning_rate": 0.0001512371412128424,
|
| 1350 |
+
"loss": 0.5362,
|
| 1351 |
+
"step": 450
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 0.3959524857017158,
|
| 1355 |
+
"eval_loss": 0.5455148220062256,
|
| 1356 |
+
"eval_runtime": 28.637,
|
| 1357 |
+
"eval_samples_per_second": 0.594,
|
| 1358 |
+
"eval_steps_per_second": 0.314,
|
| 1359 |
+
"step": 450
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.4003519577650682,
|
| 1363 |
+
"grad_norm": 0.20706337690353394,
|
| 1364 |
+
"learning_rate": 0.00014991123602960018,
|
| 1365 |
+
"loss": 0.4994,
|
| 1366 |
+
"step": 455
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 0.4003519577650682,
|
| 1370 |
+
"eval_loss": 0.5440109968185425,
|
| 1371 |
+
"eval_runtime": 28.5672,
|
| 1372 |
+
"eval_samples_per_second": 0.595,
|
| 1373 |
+
"eval_steps_per_second": 0.315,
|
| 1374 |
+
"step": 455
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.4047514298284206,
|
| 1378 |
+
"grad_norm": 0.2135256677865982,
|
| 1379 |
+
"learning_rate": 0.00014857354046810732,
|
| 1380 |
+
"loss": 0.5005,
|
| 1381 |
+
"step": 460
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.4047514298284206,
|
| 1385 |
+
"eval_loss": 0.5431147813796997,
|
| 1386 |
+
"eval_runtime": 28.4835,
|
| 1387 |
+
"eval_samples_per_second": 0.597,
|
| 1388 |
+
"eval_steps_per_second": 0.316,
|
| 1389 |
+
"step": 460
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.409150901891773,
|
| 1393 |
+
"grad_norm": 0.5737074613571167,
|
| 1394 |
+
"learning_rate": 0.00014722437052808472,
|
| 1395 |
+
"loss": 0.5208,
|
| 1396 |
+
"step": 465
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.409150901891773,
|
| 1400 |
+
"eval_loss": 0.541969358921051,
|
| 1401 |
+
"eval_runtime": 28.6004,
|
| 1402 |
+
"eval_samples_per_second": 0.594,
|
| 1403 |
+
"eval_steps_per_second": 0.315,
|
| 1404 |
+
"step": 465
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 0.4135503739551254,
|
| 1408 |
+
"grad_norm": 0.24099959433078766,
|
| 1409 |
+
"learning_rate": 0.00014586404491981052,
|
| 1410 |
+
"loss": 0.5074,
|
| 1411 |
+
"step": 470
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 0.4135503739551254,
|
| 1415 |
+
"eval_loss": 0.5449388027191162,
|
| 1416 |
+
"eval_runtime": 28.658,
|
| 1417 |
+
"eval_samples_per_second": 0.593,
|
| 1418 |
+
"eval_steps_per_second": 0.314,
|
| 1419 |
+
"step": 470
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 0.4179498460184778,
|
| 1423 |
+
"grad_norm": 0.2046642154455185,
|
| 1424 |
+
"learning_rate": 0.0001444928849888321,
|
| 1425 |
+
"loss": 0.5052,
|
| 1426 |
+
"step": 475
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 0.4179498460184778,
|
| 1430 |
+
"eval_loss": 0.5407991409301758,
|
| 1431 |
+
"eval_runtime": 28.5688,
|
| 1432 |
+
"eval_samples_per_second": 0.595,
|
| 1433 |
+
"eval_steps_per_second": 0.315,
|
| 1434 |
+
"step": 475
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.4223493180818302,
|
| 1438 |
+
"grad_norm": 0.2824171185493469,
|
| 1439 |
+
"learning_rate": 0.00014311121464005583,
|
| 1440 |
+
"loss": 0.5179,
|
| 1441 |
+
"step": 480
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.4223493180818302,
|
| 1445 |
+
"eval_loss": 0.54000324010849,
|
| 1446 |
+
"eval_runtime": 28.7144,
|
| 1447 |
+
"eval_samples_per_second": 0.592,
|
| 1448 |
+
"eval_steps_per_second": 0.313,
|
| 1449 |
+
"step": 480
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.4267487901451826,
|
| 1453 |
+
"grad_norm": 0.2045980840921402,
|
| 1454 |
+
"learning_rate": 0.00014171936026123168,
|
| 1455 |
+
"loss": 0.4634,
|
| 1456 |
+
"step": 485
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.4267487901451826,
|
| 1460 |
+
"eval_loss": 0.5398800373077393,
|
| 1461 |
+
"eval_runtime": 28.5209,
|
| 1462 |
+
"eval_samples_per_second": 0.596,
|
| 1463 |
+
"eval_steps_per_second": 0.316,
|
| 1464 |
+
"step": 485
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 0.43114826220853497,
|
| 1468 |
+
"grad_norm": 0.2092169225215912,
|
| 1469 |
+
"learning_rate": 0.00014031765064585197,
|
| 1470 |
+
"loss": 0.4802,
|
| 1471 |
+
"step": 490
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 0.43114826220853497,
|
| 1475 |
+
"eval_loss": 0.5395181179046631,
|
| 1476 |
+
"eval_runtime": 28.5086,
|
| 1477 |
+
"eval_samples_per_second": 0.596,
|
| 1478 |
+
"eval_steps_per_second": 0.316,
|
| 1479 |
+
"step": 490
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.43554773427188737,
|
| 1483 |
+
"grad_norm": 0.20700140297412872,
|
| 1484 |
+
"learning_rate": 0.00013890641691548114,
|
| 1485 |
+
"loss": 0.4962,
|
| 1486 |
+
"step": 495
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.43554773427188737,
|
| 1490 |
+
"eval_loss": 0.5390854477882385,
|
| 1491 |
+
"eval_runtime": 28.5682,
|
| 1492 |
+
"eval_samples_per_second": 0.595,
|
| 1493 |
+
"eval_steps_per_second": 0.315,
|
| 1494 |
+
"step": 495
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.43994720633523976,
|
| 1498 |
+
"grad_norm": 0.19903522729873657,
|
| 1499 |
+
"learning_rate": 0.00013748599244153633,
|
| 1500 |
+
"loss": 0.4841,
|
| 1501 |
+
"step": 500
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.43994720633523976,
|
| 1505 |
+
"eval_loss": 0.5381758213043213,
|
| 1506 |
+
"eval_runtime": 29.4274,
|
| 1507 |
+
"eval_samples_per_second": 0.578,
|
| 1508 |
+
"eval_steps_per_second": 0.306,
|
| 1509 |
+
"step": 500
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 0.44434667839859215,
|
| 1513 |
+
"grad_norm": 0.4766729474067688,
|
| 1514 |
+
"learning_rate": 0.00013605671276653567,
|
| 1515 |
+
"loss": 0.5252,
|
| 1516 |
+
"step": 505
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 0.44434667839859215,
|
| 1520 |
+
"eval_loss": 0.5368968844413757,
|
| 1521 |
+
"eval_runtime": 28.6474,
|
| 1522 |
+
"eval_samples_per_second": 0.593,
|
| 1523 |
+
"eval_steps_per_second": 0.314,
|
| 1524 |
+
"step": 505
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 0.44874615046194455,
|
| 1528 |
+
"grad_norm": 0.21688155829906464,
|
| 1529 |
+
"learning_rate": 0.00013461891552483444,
|
| 1530 |
+
"loss": 0.515,
|
| 1531 |
+
"step": 510
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 0.44874615046194455,
|
| 1535 |
+
"eval_loss": 0.5366407036781311,
|
| 1536 |
+
"eval_runtime": 28.5352,
|
| 1537 |
+
"eval_samples_per_second": 0.596,
|
| 1538 |
+
"eval_steps_per_second": 0.315,
|
| 1539 |
+
"step": 510
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 0.45314562252529694,
|
| 1543 |
+
"grad_norm": 0.20375116169452667,
|
| 1544 |
+
"learning_rate": 0.00013317294036286644,
|
| 1545 |
+
"loss": 0.4887,
|
| 1546 |
+
"step": 515
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 0.45314562252529694,
|
| 1550 |
+
"eval_loss": 0.5360764861106873,
|
| 1551 |
+
"eval_runtime": 28.6533,
|
| 1552 |
+
"eval_samples_per_second": 0.593,
|
| 1553 |
+
"eval_steps_per_second": 0.314,
|
| 1554 |
+
"step": 515
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 0.45754509458864934,
|
| 1558 |
+
"grad_norm": 0.1958196461200714,
|
| 1559 |
+
"learning_rate": 0.00013171912885891063,
|
| 1560 |
+
"loss": 0.4868,
|
| 1561 |
+
"step": 520
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 0.45754509458864934,
|
| 1565 |
+
"eval_loss": 0.5356424450874329,
|
| 1566 |
+
"eval_runtime": 28.5027,
|
| 1567 |
+
"eval_samples_per_second": 0.596,
|
| 1568 |
+
"eval_steps_per_second": 0.316,
|
| 1569 |
+
"step": 520
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 0.4619445666520018,
|
| 1573 |
+
"grad_norm": 0.22040507197380066,
|
| 1574 |
+
"learning_rate": 0.00013025782444240087,
|
| 1575 |
+
"loss": 0.5086,
|
| 1576 |
+
"step": 525
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 0.4619445666520018,
|
| 1580 |
+
"eval_loss": 0.5351347327232361,
|
| 1581 |
+
"eval_runtime": 28.6428,
|
| 1582 |
+
"eval_samples_per_second": 0.594,
|
| 1583 |
+
"eval_steps_per_second": 0.314,
|
| 1584 |
+
"step": 525
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.4663440387153542,
|
| 1588 |
+
"grad_norm": 0.19495758414268494,
|
| 1589 |
+
"learning_rate": 0.00012878937231279892,
|
| 1590 |
+
"loss": 0.5113,
|
| 1591 |
+
"step": 530
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.4663440387153542,
|
| 1595 |
+
"eval_loss": 0.5347647070884705,
|
| 1596 |
+
"eval_runtime": 28.6252,
|
| 1597 |
+
"eval_samples_per_second": 0.594,
|
| 1598 |
+
"eval_steps_per_second": 0.314,
|
| 1599 |
+
"step": 530
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.4707435107787066,
|
| 1603 |
+
"grad_norm": 0.21149738132953644,
|
| 1604 |
+
"learning_rate": 0.0001273141193580488,
|
| 1605 |
+
"loss": 0.483,
|
| 1606 |
+
"step": 535
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.4707435107787066,
|
| 1610 |
+
"eval_loss": 0.5339221954345703,
|
| 1611 |
+
"eval_runtime": 28.6055,
|
| 1612 |
+
"eval_samples_per_second": 0.594,
|
| 1613 |
+
"eval_steps_per_second": 0.315,
|
| 1614 |
+
"step": 535
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 0.47514298284205897,
|
| 1618 |
+
"grad_norm": 0.20391018688678741,
|
| 1619 |
+
"learning_rate": 0.0001258324140726326,
|
| 1620 |
+
"loss": 0.4728,
|
| 1621 |
+
"step": 540
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 0.47514298284205897,
|
| 1625 |
+
"eval_loss": 0.5337977409362793,
|
| 1626 |
+
"eval_runtime": 28.5842,
|
| 1627 |
+
"eval_samples_per_second": 0.595,
|
| 1628 |
+
"eval_steps_per_second": 0.315,
|
| 1629 |
+
"step": 540
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 0.47954245490541136,
|
| 1633 |
+
"grad_norm": 0.20913545787334442,
|
| 1634 |
+
"learning_rate": 0.00012434460647524676,
|
| 1635 |
+
"loss": 0.5016,
|
| 1636 |
+
"step": 545
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 0.47954245490541136,
|
| 1640 |
+
"eval_loss": 0.532899022102356,
|
| 1641 |
+
"eval_runtime": 28.4759,
|
| 1642 |
+
"eval_samples_per_second": 0.597,
|
| 1643 |
+
"eval_steps_per_second": 0.316,
|
| 1644 |
+
"step": 545
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 0.48394192696876376,
|
| 1648 |
+
"grad_norm": 0.19410260021686554,
|
| 1649 |
+
"learning_rate": 0.00012285104802611812,
|
| 1650 |
+
"loss": 0.5103,
|
| 1651 |
+
"step": 550
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 0.48394192696876376,
|
| 1655 |
+
"eval_loss": 0.5321294665336609,
|
| 1656 |
+
"eval_runtime": 28.5662,
|
| 1657 |
+
"eval_samples_per_second": 0.595,
|
| 1658 |
+
"eval_steps_per_second": 0.315,
|
| 1659 |
+
"step": 550
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 0.48834139903211615,
|
| 1663 |
+
"grad_norm": 0.2097245752811432,
|
| 1664 |
+
"learning_rate": 0.00012135209154397962,
|
| 1665 |
+
"loss": 0.4954,
|
| 1666 |
+
"step": 555
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 0.48834139903211615,
|
| 1670 |
+
"eval_loss": 0.532034695148468,
|
| 1671 |
+
"eval_runtime": 28.652,
|
| 1672 |
+
"eval_samples_per_second": 0.593,
|
| 1673 |
+
"eval_steps_per_second": 0.314,
|
| 1674 |
+
"step": 555
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 0.49274087109546855,
|
| 1678 |
+
"grad_norm": 0.21518121659755707,
|
| 1679 |
+
"learning_rate": 0.00011984809112272495,
|
| 1680 |
+
"loss": 0.4999,
|
| 1681 |
+
"step": 560
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 0.49274087109546855,
|
| 1685 |
+
"eval_loss": 0.5313233733177185,
|
| 1686 |
+
"eval_runtime": 28.5662,
|
| 1687 |
+
"eval_samples_per_second": 0.595,
|
| 1688 |
+
"eval_steps_per_second": 0.315,
|
| 1689 |
+
"step": 560
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.49714034315882094,
|
| 1693 |
+
"grad_norm": 0.19571034610271454,
|
| 1694 |
+
"learning_rate": 0.00011833940204776209,
|
| 1695 |
+
"loss": 0.4931,
|
| 1696 |
+
"step": 565
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.49714034315882094,
|
| 1700 |
+
"eval_loss": 0.5311394333839417,
|
| 1701 |
+
"eval_runtime": 28.5352,
|
| 1702 |
+
"eval_samples_per_second": 0.596,
|
| 1703 |
+
"eval_steps_per_second": 0.315,
|
| 1704 |
+
"step": 565
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.5015398152221734,
|
| 1708 |
+
"grad_norm": 0.20554794371128082,
|
| 1709 |
+
"learning_rate": 0.00011682638071208533,
|
| 1710 |
+
"loss": 0.4833,
|
| 1711 |
+
"step": 570
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.5015398152221734,
|
| 1715 |
+
"eval_loss": 0.5300410389900208,
|
| 1716 |
+
"eval_runtime": 28.5679,
|
| 1717 |
+
"eval_samples_per_second": 0.595,
|
| 1718 |
+
"eval_steps_per_second": 0.315,
|
| 1719 |
+
"step": 570
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 0.5059392872855257,
|
| 1723 |
+
"grad_norm": 0.20373423397541046,
|
| 1724 |
+
"learning_rate": 0.00011530938453208559,
|
| 1725 |
+
"loss": 0.5057,
|
| 1726 |
+
"step": 575
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 0.5059392872855257,
|
| 1730 |
+
"eval_loss": 0.5300309658050537,
|
| 1731 |
+
"eval_runtime": 28.5821,
|
| 1732 |
+
"eval_samples_per_second": 0.595,
|
| 1733 |
+
"eval_steps_per_second": 0.315,
|
| 1734 |
+
"step": 575
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 0.5103387593488782,
|
| 1738 |
+
"grad_norm": 0.1982477903366089,
|
| 1739 |
+
"learning_rate": 0.00011378877186311912,
|
| 1740 |
+
"loss": 0.4754,
|
| 1741 |
+
"step": 580
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 0.5103387593488782,
|
| 1745 |
+
"eval_loss": 0.5292160511016846,
|
| 1746 |
+
"eval_runtime": 28.5256,
|
| 1747 |
+
"eval_samples_per_second": 0.596,
|
| 1748 |
+
"eval_steps_per_second": 0.316,
|
| 1749 |
+
"step": 580
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 0.5147382314122305,
|
| 1753 |
+
"grad_norm": 0.20576219260692596,
|
| 1754 |
+
"learning_rate": 0.00011226490191485421,
|
| 1755 |
+
"loss": 0.4991,
|
| 1756 |
+
"step": 585
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 0.5147382314122305,
|
| 1760 |
+
"eval_loss": 0.5280917882919312,
|
| 1761 |
+
"eval_runtime": 28.6835,
|
| 1762 |
+
"eval_samples_per_second": 0.593,
|
| 1763 |
+
"eval_steps_per_second": 0.314,
|
| 1764 |
+
"step": 585
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 0.519137703475583,
|
| 1768 |
+
"grad_norm": 0.2154638022184372,
|
| 1769 |
+
"learning_rate": 0.00011073813466641632,
|
| 1770 |
+
"loss": 0.4811,
|
| 1771 |
+
"step": 590
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 0.519137703475583,
|
| 1775 |
+
"eval_loss": 0.5274674296379089,
|
| 1776 |
+
"eval_runtime": 28.4766,
|
| 1777 |
+
"eval_samples_per_second": 0.597,
|
| 1778 |
+
"eval_steps_per_second": 0.316,
|
| 1779 |
+
"step": 590
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 0.5235371755389353,
|
| 1783 |
+
"grad_norm": 0.2037007063627243,
|
| 1784 |
+
"learning_rate": 0.00010920883078135117,
|
| 1785 |
+
"loss": 0.4717,
|
| 1786 |
+
"step": 595
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 0.5235371755389353,
|
| 1790 |
+
"eval_loss": 0.5270927548408508,
|
| 1791 |
+
"eval_runtime": 28.5377,
|
| 1792 |
+
"eval_samples_per_second": 0.596,
|
| 1793 |
+
"eval_steps_per_second": 0.315,
|
| 1794 |
+
"step": 595
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.5279366476022878,
|
| 1798 |
+
"grad_norm": 0.21386198699474335,
|
| 1799 |
+
"learning_rate": 0.00010767735152242649,
|
| 1800 |
+
"loss": 0.4776,
|
| 1801 |
+
"step": 600
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.5279366476022878,
|
| 1805 |
+
"eval_loss": 0.526791512966156,
|
| 1806 |
+
"eval_runtime": 28.596,
|
| 1807 |
+
"eval_samples_per_second": 0.594,
|
| 1808 |
+
"eval_steps_per_second": 0.315,
|
| 1809 |
+
"step": 600
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.5323361196656401,
|
| 1813 |
+
"grad_norm": 0.1984720528125763,
|
| 1814 |
+
"learning_rate": 0.0001061440586662917,
|
| 1815 |
+
"loss": 0.4708,
|
| 1816 |
+
"step": 605
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.5323361196656401,
|
| 1820 |
+
"eval_loss": 0.5266034007072449,
|
| 1821 |
+
"eval_runtime": 28.6491,
|
| 1822 |
+
"eval_samples_per_second": 0.593,
|
| 1823 |
+
"eval_steps_per_second": 0.314,
|
| 1824 |
+
"step": 605
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 0.5367355917289925,
|
| 1828 |
+
"grad_norm": 0.19453096389770508,
|
| 1829 |
+
"learning_rate": 0.000104609314418017,
|
| 1830 |
+
"loss": 0.4659,
|
| 1831 |
+
"step": 610
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 0.5367355917289925,
|
| 1835 |
+
"eval_loss": 0.5267328023910522,
|
| 1836 |
+
"eval_runtime": 28.6358,
|
| 1837 |
+
"eval_samples_per_second": 0.594,
|
| 1838 |
+
"eval_steps_per_second": 0.314,
|
| 1839 |
+
"step": 610
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 0.5411350637923449,
|
| 1843 |
+
"grad_norm": 0.2048104703426361,
|
| 1844 |
+
"learning_rate": 0.00010307348132553025,
|
| 1845 |
+
"loss": 0.5138,
|
| 1846 |
+
"step": 615
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 0.5411350637923449,
|
| 1850 |
+
"eval_loss": 0.5270944833755493,
|
| 1851 |
+
"eval_runtime": 28.5902,
|
| 1852 |
+
"eval_samples_per_second": 0.595,
|
| 1853 |
+
"eval_steps_per_second": 0.315,
|
| 1854 |
+
"step": 615
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 0.5455345358556973,
|
| 1858 |
+
"grad_norm": 0.1899915337562561,
|
| 1859 |
+
"learning_rate": 0.00010153692219397387,
|
| 1860 |
+
"loss": 0.4797,
|
| 1861 |
+
"step": 620
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 0.5455345358556973,
|
| 1865 |
+
"eval_loss": 0.5260502099990845,
|
| 1866 |
+
"eval_runtime": 28.5533,
|
| 1867 |
+
"eval_samples_per_second": 0.595,
|
| 1868 |
+
"eval_steps_per_second": 0.315,
|
| 1869 |
+
"step": 620
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 0.5499340079190497,
|
| 1873 |
+
"grad_norm": 0.18520919978618622,
|
| 1874 |
+
"learning_rate": 0.0001,
|
| 1875 |
+
"loss": 0.5068,
|
| 1876 |
+
"step": 625
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 0.5499340079190497,
|
| 1880 |
+
"eval_loss": 0.5251287817955017,
|
| 1881 |
+
"eval_runtime": 28.4846,
|
| 1882 |
+
"eval_samples_per_second": 0.597,
|
| 1883 |
+
"eval_steps_per_second": 0.316,
|
| 1884 |
+
"step": 625
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 0.5543334799824021,
|
| 1888 |
+
"grad_norm": 0.21325986087322235,
|
| 1889 |
+
"learning_rate": 9.84630778060262e-05,
|
| 1890 |
+
"loss": 0.4799,
|
| 1891 |
+
"step": 630
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 0.5543334799824021,
|
| 1895 |
+
"eval_loss": 0.524385929107666,
|
| 1896 |
+
"eval_runtime": 28.5917,
|
| 1897 |
+
"eval_samples_per_second": 0.595,
|
| 1898 |
+
"eval_steps_per_second": 0.315,
|
| 1899 |
+
"step": 630
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.5587329520457545,
|
| 1903 |
+
"grad_norm": 0.20572926104068756,
|
| 1904 |
+
"learning_rate": 9.692651867446973e-05,
|
| 1905 |
+
"loss": 0.49,
|
| 1906 |
+
"step": 635
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.5587329520457545,
|
| 1910 |
+
"eval_loss": 0.523975133895874,
|
| 1911 |
+
"eval_runtime": 28.6052,
|
| 1912 |
+
"eval_samples_per_second": 0.594,
|
| 1913 |
+
"eval_steps_per_second": 0.315,
|
| 1914 |
+
"step": 635
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.5631324241091069,
|
| 1918 |
+
"grad_norm": 0.20347937941551208,
|
| 1919 |
+
"learning_rate": 9.539068558198304e-05,
|
| 1920 |
+
"loss": 0.4702,
|
| 1921 |
+
"step": 640
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.5631324241091069,
|
| 1925 |
+
"eval_loss": 0.5229539275169373,
|
| 1926 |
+
"eval_runtime": 28.6223,
|
| 1927 |
+
"eval_samples_per_second": 0.594,
|
| 1928 |
+
"eval_steps_per_second": 0.314,
|
| 1929 |
+
"step": 640
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 0.5675318961724594,
|
| 1933 |
+
"grad_norm": 0.21256154775619507,
|
| 1934 |
+
"learning_rate": 9.38559413337083e-05,
|
| 1935 |
+
"loss": 0.4736,
|
| 1936 |
+
"step": 645
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 0.5675318961724594,
|
| 1940 |
+
"eval_loss": 0.5221072435379028,
|
| 1941 |
+
"eval_runtime": 28.6189,
|
| 1942 |
+
"eval_samples_per_second": 0.594,
|
| 1943 |
+
"eval_steps_per_second": 0.314,
|
| 1944 |
+
"step": 645
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 0.5719313682358117,
|
| 1948 |
+
"grad_norm": 0.2260565459728241,
|
| 1949 |
+
"learning_rate": 9.232264847757357e-05,
|
| 1950 |
+
"loss": 0.5065,
|
| 1951 |
+
"step": 650
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 0.5719313682358117,
|
| 1955 |
+
"eval_loss": 0.5213314890861511,
|
| 1956 |
+
"eval_runtime": 28.6771,
|
| 1957 |
+
"eval_samples_per_second": 0.593,
|
| 1958 |
+
"eval_steps_per_second": 0.314,
|
| 1959 |
+
"step": 650
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 0.5763308402991641,
|
| 1963 |
+
"grad_norm": 0.21002529561519623,
|
| 1964 |
+
"learning_rate": 9.079116921864884e-05,
|
| 1965 |
+
"loss": 0.4796,
|
| 1966 |
+
"step": 655
|
| 1967 |
+
},
|
| 1968 |
+
{
|
| 1969 |
+
"epoch": 0.5763308402991641,
|
| 1970 |
+
"eval_loss": 0.5214037299156189,
|
| 1971 |
+
"eval_runtime": 28.6202,
|
| 1972 |
+
"eval_samples_per_second": 0.594,
|
| 1973 |
+
"eval_steps_per_second": 0.314,
|
| 1974 |
+
"step": 655
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 0.5807303123625165,
|
| 1978 |
+
"grad_norm": 0.19340470433235168,
|
| 1979 |
+
"learning_rate": 8.92618653335837e-05,
|
| 1980 |
+
"loss": 0.4788,
|
| 1981 |
+
"step": 660
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 0.5807303123625165,
|
| 1985 |
+
"eval_loss": 0.5211138725280762,
|
| 1986 |
+
"eval_runtime": 28.6313,
|
| 1987 |
+
"eval_samples_per_second": 0.594,
|
| 1988 |
+
"eval_steps_per_second": 0.314,
|
| 1989 |
+
"step": 660
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 0.5851297844258689,
|
| 1993 |
+
"grad_norm": 0.19035720825195312,
|
| 1994 |
+
"learning_rate": 8.773509808514581e-05,
|
| 1995 |
+
"loss": 0.468,
|
| 1996 |
+
"step": 665
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 0.5851297844258689,
|
| 2000 |
+
"eval_loss": 0.5191999077796936,
|
| 2001 |
+
"eval_runtime": 28.0607,
|
| 2002 |
+
"eval_samples_per_second": 0.606,
|
| 2003 |
+
"eval_steps_per_second": 0.321,
|
| 2004 |
+
"step": 665
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.5895292564892213,
|
| 2008 |
+
"grad_norm": 0.19168096780776978,
|
| 2009 |
+
"learning_rate": 8.62112281368809e-05,
|
| 2010 |
+
"loss": 0.5066,
|
| 2011 |
+
"step": 670
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.5895292564892213,
|
| 2015 |
+
"eval_loss": 0.5176913142204285,
|
| 2016 |
+
"eval_runtime": 28.5375,
|
| 2017 |
+
"eval_samples_per_second": 0.596,
|
| 2018 |
+
"eval_steps_per_second": 0.315,
|
| 2019 |
+
"step": 670
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.5939287285525737,
|
| 2023 |
+
"grad_norm": 0.19758321344852448,
|
| 2024 |
+
"learning_rate": 8.469061546791442e-05,
|
| 2025 |
+
"loss": 0.51,
|
| 2026 |
+
"step": 675
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.5939287285525737,
|
| 2030 |
+
"eval_loss": 0.517296314239502,
|
| 2031 |
+
"eval_runtime": 28.5712,
|
| 2032 |
+
"eval_samples_per_second": 0.595,
|
| 2033 |
+
"eval_steps_per_second": 0.315,
|
| 2034 |
+
"step": 675
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 0.5983282006159261,
|
| 2038 |
+
"grad_norm": 0.19562241435050964,
|
| 2039 |
+
"learning_rate": 8.317361928791469e-05,
|
| 2040 |
+
"loss": 0.4932,
|
| 2041 |
+
"step": 680
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 0.5983282006159261,
|
| 2045 |
+
"eval_loss": 0.5170657634735107,
|
| 2046 |
+
"eval_runtime": 28.4877,
|
| 2047 |
+
"eval_samples_per_second": 0.597,
|
| 2048 |
+
"eval_steps_per_second": 0.316,
|
| 2049 |
+
"step": 680
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 0.6027276726792785,
|
| 2053 |
+
"grad_norm": 0.18590031564235687,
|
| 2054 |
+
"learning_rate": 8.166059795223794e-05,
|
| 2055 |
+
"loss": 0.5055,
|
| 2056 |
+
"step": 685
|
| 2057 |
+
},
|
| 2058 |
+
{
|
| 2059 |
+
"epoch": 0.6027276726792785,
|
| 2060 |
+
"eval_loss": 0.5166193842887878,
|
| 2061 |
+
"eval_runtime": 28.625,
|
| 2062 |
+
"eval_samples_per_second": 0.594,
|
| 2063 |
+
"eval_steps_per_second": 0.314,
|
| 2064 |
+
"step": 685
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 0.6071271447426309,
|
| 2068 |
+
"grad_norm": 0.2049984484910965,
|
| 2069 |
+
"learning_rate": 8.015190887727509e-05,
|
| 2070 |
+
"loss": 0.4846,
|
| 2071 |
+
"step": 690
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"epoch": 0.6071271447426309,
|
| 2075 |
+
"eval_loss": 0.5160765647888184,
|
| 2076 |
+
"eval_runtime": 28.5582,
|
| 2077 |
+
"eval_samples_per_second": 0.595,
|
| 2078 |
+
"eval_steps_per_second": 0.315,
|
| 2079 |
+
"step": 690
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 0.6115266168059833,
|
| 2083 |
+
"grad_norm": 0.19373777508735657,
|
| 2084 |
+
"learning_rate": 7.864790845602039e-05,
|
| 2085 |
+
"loss": 0.4862,
|
| 2086 |
+
"step": 695
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 0.6115266168059833,
|
| 2090 |
+
"eval_loss": 0.5157306790351868,
|
| 2091 |
+
"eval_runtime": 28.6078,
|
| 2092 |
+
"eval_samples_per_second": 0.594,
|
| 2093 |
+
"eval_steps_per_second": 0.315,
|
| 2094 |
+
"step": 695
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 0.6159260888693356,
|
| 2098 |
+
"grad_norm": 0.20326727628707886,
|
| 2099 |
+
"learning_rate": 7.714895197388189e-05,
|
| 2100 |
+
"loss": 0.5064,
|
| 2101 |
+
"step": 700
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 0.6159260888693356,
|
| 2105 |
+
"eval_loss": 0.5153770446777344,
|
| 2106 |
+
"eval_runtime": 28.6597,
|
| 2107 |
+
"eval_samples_per_second": 0.593,
|
| 2108 |
+
"eval_steps_per_second": 0.314,
|
| 2109 |
+
"step": 700
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.6203255609326881,
|
| 2113 |
+
"grad_norm": 0.19425565004348755,
|
| 2114 |
+
"learning_rate": 7.565539352475326e-05,
|
| 2115 |
+
"loss": 0.5018,
|
| 2116 |
+
"step": 705
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.6203255609326881,
|
| 2120 |
+
"eval_loss": 0.5147074460983276,
|
| 2121 |
+
"eval_runtime": 28.5261,
|
| 2122 |
+
"eval_samples_per_second": 0.596,
|
| 2123 |
+
"eval_steps_per_second": 0.316,
|
| 2124 |
+
"step": 705
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 0.6247250329960404,
|
| 2128 |
+
"grad_norm": 0.19491039216518402,
|
| 2129 |
+
"learning_rate": 7.416758592736744e-05,
|
| 2130 |
+
"loss": 0.482,
|
| 2131 |
+
"step": 710
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 0.6247250329960404,
|
| 2135 |
+
"eval_loss": 0.5144516229629517,
|
| 2136 |
+
"eval_runtime": 28.533,
|
| 2137 |
+
"eval_samples_per_second": 0.596,
|
| 2138 |
+
"eval_steps_per_second": 0.315,
|
| 2139 |
+
"step": 710
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 0.6291245050593929,
|
| 2143 |
+
"grad_norm": 0.1957363337278366,
|
| 2144 |
+
"learning_rate": 7.268588064195122e-05,
|
| 2145 |
+
"loss": 0.4883,
|
| 2146 |
+
"step": 715
|
| 2147 |
+
},
|
| 2148 |
+
{
|
| 2149 |
+
"epoch": 0.6291245050593929,
|
| 2150 |
+
"eval_loss": 0.5139791965484619,
|
| 2151 |
+
"eval_runtime": 28.5313,
|
| 2152 |
+
"eval_samples_per_second": 0.596,
|
| 2153 |
+
"eval_steps_per_second": 0.315,
|
| 2154 |
+
"step": 715
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 0.6335239771227452,
|
| 2158 |
+
"grad_norm": 0.21253836154937744,
|
| 2159 |
+
"learning_rate": 7.12106276872011e-05,
|
| 2160 |
+
"loss": 0.4768,
|
| 2161 |
+
"step": 720
|
| 2162 |
+
},
|
| 2163 |
+
{
|
| 2164 |
+
"epoch": 0.6335239771227452,
|
| 2165 |
+
"eval_loss": 0.5137556195259094,
|
| 2166 |
+
"eval_runtime": 28.6307,
|
| 2167 |
+
"eval_samples_per_second": 0.594,
|
| 2168 |
+
"eval_steps_per_second": 0.314,
|
| 2169 |
+
"step": 720
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 0.6379234491860977,
|
| 2173 |
+
"grad_norm": 0.1721029132604599,
|
| 2174 |
+
"learning_rate": 6.974217555759915e-05,
|
| 2175 |
+
"loss": 0.4816,
|
| 2176 |
+
"step": 725
|
| 2177 |
+
},
|
| 2178 |
+
{
|
| 2179 |
+
"epoch": 0.6379234491860977,
|
| 2180 |
+
"eval_loss": 0.5133811831474304,
|
| 2181 |
+
"eval_runtime": 28.5925,
|
| 2182 |
+
"eval_samples_per_second": 0.595,
|
| 2183 |
+
"eval_steps_per_second": 0.315,
|
| 2184 |
+
"step": 725
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 0.6423229212494501,
|
| 2188 |
+
"grad_norm": 0.19211679697036743,
|
| 2189 |
+
"learning_rate": 6.82808711410894e-05,
|
| 2190 |
+
"loss": 0.5035,
|
| 2191 |
+
"step": 730
|
| 2192 |
+
},
|
| 2193 |
+
{
|
| 2194 |
+
"epoch": 0.6423229212494501,
|
| 2195 |
+
"eval_loss": 0.5132091641426086,
|
| 2196 |
+
"eval_runtime": 28.5078,
|
| 2197 |
+
"eval_samples_per_second": 0.596,
|
| 2198 |
+
"eval_steps_per_second": 0.316,
|
| 2199 |
+
"step": 730
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 0.6467223933128025,
|
| 2203 |
+
"grad_norm": 0.19252945482730865,
|
| 2204 |
+
"learning_rate": 6.682705963713356e-05,
|
| 2205 |
+
"loss": 0.4822,
|
| 2206 |
+
"step": 735
|
| 2207 |
+
},
|
| 2208 |
+
{
|
| 2209 |
+
"epoch": 0.6467223933128025,
|
| 2210 |
+
"eval_loss": 0.5131357908248901,
|
| 2211 |
+
"eval_runtime": 28.6326,
|
| 2212 |
+
"eval_samples_per_second": 0.594,
|
| 2213 |
+
"eval_steps_per_second": 0.314,
|
| 2214 |
+
"step": 735
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.6511218653761549,
|
| 2218 |
+
"grad_norm": 0.1986207813024521,
|
| 2219 |
+
"learning_rate": 6.538108447516558e-05,
|
| 2220 |
+
"loss": 0.4612,
|
| 2221 |
+
"step": 740
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.6511218653761549,
|
| 2225 |
+
"eval_loss": 0.5128303170204163,
|
| 2226 |
+
"eval_runtime": 28.6066,
|
| 2227 |
+
"eval_samples_per_second": 0.594,
|
| 2228 |
+
"eval_steps_per_second": 0.315,
|
| 2229 |
+
"step": 740
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 0.6555213374395072,
|
| 2233 |
+
"grad_norm": 0.19202682375907898,
|
| 2234 |
+
"learning_rate": 6.394328723346434e-05,
|
| 2235 |
+
"loss": 0.4578,
|
| 2236 |
+
"step": 745
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 0.6555213374395072,
|
| 2240 |
+
"eval_loss": 0.5124692916870117,
|
| 2241 |
+
"eval_runtime": 28.6064,
|
| 2242 |
+
"eval_samples_per_second": 0.594,
|
| 2243 |
+
"eval_steps_per_second": 0.315,
|
| 2244 |
+
"step": 745
|
| 2245 |
+
},
|
| 2246 |
+
{
|
| 2247 |
+
"epoch": 0.6599208095028597,
|
| 2248 |
+
"grad_norm": 0.198526531457901,
|
| 2249 |
+
"learning_rate": 6.251400755846372e-05,
|
| 2250 |
+
"loss": 0.5176,
|
| 2251 |
+
"step": 750
|
| 2252 |
+
},
|
| 2253 |
+
{
|
| 2254 |
+
"epoch": 0.6599208095028597,
|
| 2255 |
+
"eval_loss": 0.5121349096298218,
|
| 2256 |
+
"eval_runtime": 28.5313,
|
| 2257 |
+
"eval_samples_per_second": 0.596,
|
| 2258 |
+
"eval_steps_per_second": 0.315,
|
| 2259 |
+
"step": 750
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 0.664320281566212,
|
| 2263 |
+
"grad_norm": 0.19058994948863983,
|
| 2264 |
+
"learning_rate": 6.109358308451885e-05,
|
| 2265 |
+
"loss": 0.4877,
|
| 2266 |
+
"step": 755
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 0.664320281566212,
|
| 2270 |
+
"eval_loss": 0.5118634700775146,
|
| 2271 |
+
"eval_runtime": 28.5287,
|
| 2272 |
+
"eval_samples_per_second": 0.596,
|
| 2273 |
+
"eval_steps_per_second": 0.315,
|
| 2274 |
+
"step": 755
|
| 2275 |
+
},
|
| 2276 |
+
{
|
| 2277 |
+
"epoch": 0.6687197536295645,
|
| 2278 |
+
"grad_norm": 0.1798192411661148,
|
| 2279 |
+
"learning_rate": 5.968234935414807e-05,
|
| 2280 |
+
"loss": 0.4805,
|
| 2281 |
+
"step": 760
|
| 2282 |
+
},
|
| 2283 |
+
{
|
| 2284 |
+
"epoch": 0.6687197536295645,
|
| 2285 |
+
"eval_loss": 0.5116167664527893,
|
| 2286 |
+
"eval_runtime": 28.5918,
|
| 2287 |
+
"eval_samples_per_second": 0.595,
|
| 2288 |
+
"eval_steps_per_second": 0.315,
|
| 2289 |
+
"step": 760
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 0.6731192256929168,
|
| 2293 |
+
"grad_norm": 0.18448549509048462,
|
| 2294 |
+
"learning_rate": 5.828063973876834e-05,
|
| 2295 |
+
"loss": 0.4993,
|
| 2296 |
+
"step": 765
|
| 2297 |
+
},
|
| 2298 |
+
{
|
| 2299 |
+
"epoch": 0.6731192256929168,
|
| 2300 |
+
"eval_loss": 0.5111361742019653,
|
| 2301 |
+
"eval_runtime": 28.5586,
|
| 2302 |
+
"eval_samples_per_second": 0.595,
|
| 2303 |
+
"eval_steps_per_second": 0.315,
|
| 2304 |
+
"step": 765
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 0.6775186977562693,
|
| 2308 |
+
"grad_norm": 0.18624383211135864,
|
| 2309 |
+
"learning_rate": 5.688878535994421e-05,
|
| 2310 |
+
"loss": 0.4844,
|
| 2311 |
+
"step": 770
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 0.6775186977562693,
|
| 2315 |
+
"eval_loss": 0.5107051134109497,
|
| 2316 |
+
"eval_runtime": 28.5748,
|
| 2317 |
+
"eval_samples_per_second": 0.595,
|
| 2318 |
+
"eval_steps_per_second": 0.315,
|
| 2319 |
+
"step": 770
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.6819181698196216,
|
| 2323 |
+
"grad_norm": 0.18364666402339935,
|
| 2324 |
+
"learning_rate": 5.550711501116789e-05,
|
| 2325 |
+
"loss": 0.4674,
|
| 2326 |
+
"step": 775
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.6819181698196216,
|
| 2330 |
+
"eval_loss": 0.5101103186607361,
|
| 2331 |
+
"eval_runtime": 28.5159,
|
| 2332 |
+
"eval_samples_per_second": 0.596,
|
| 2333 |
+
"eval_steps_per_second": 0.316,
|
| 2334 |
+
"step": 775
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 0.6863176418829741,
|
| 2338 |
+
"grad_norm": 0.23952247202396393,
|
| 2339 |
+
"learning_rate": 5.413595508018952e-05,
|
| 2340 |
+
"loss": 0.4943,
|
| 2341 |
+
"step": 780
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 0.6863176418829741,
|
| 2345 |
+
"eval_loss": 0.5096238255500793,
|
| 2346 |
+
"eval_runtime": 28.516,
|
| 2347 |
+
"eval_samples_per_second": 0.596,
|
| 2348 |
+
"eval_steps_per_second": 0.316,
|
| 2349 |
+
"step": 780
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 0.6907171139463264,
|
| 2353 |
+
"grad_norm": 0.20105206966400146,
|
| 2354 |
+
"learning_rate": 5.27756294719153e-05,
|
| 2355 |
+
"loss": 0.4924,
|
| 2356 |
+
"step": 785
|
| 2357 |
+
},
|
| 2358 |
+
{
|
| 2359 |
+
"epoch": 0.6907171139463264,
|
| 2360 |
+
"eval_loss": 0.5093135237693787,
|
| 2361 |
+
"eval_runtime": 28.5941,
|
| 2362 |
+
"eval_samples_per_second": 0.595,
|
| 2363 |
+
"eval_steps_per_second": 0.315,
|
| 2364 |
+
"step": 785
|
| 2365 |
+
},
|
| 2366 |
+
{
|
| 2367 |
+
"epoch": 0.6951165860096788,
|
| 2368 |
+
"grad_norm": 0.19826586544513702,
|
| 2369 |
+
"learning_rate": 5.1426459531892714e-05,
|
| 2370 |
+
"loss": 0.4986,
|
| 2371 |
+
"step": 790
|
| 2372 |
+
},
|
| 2373 |
+
{
|
| 2374 |
+
"epoch": 0.6951165860096788,
|
| 2375 |
+
"eval_loss": 0.5086015462875366,
|
| 2376 |
+
"eval_runtime": 28.6207,
|
| 2377 |
+
"eval_samples_per_second": 0.594,
|
| 2378 |
+
"eval_steps_per_second": 0.314,
|
| 2379 |
+
"step": 790
|
| 2380 |
+
},
|
| 2381 |
+
{
|
| 2382 |
+
"epoch": 0.6995160580730312,
|
| 2383 |
+
"grad_norm": 0.17991924285888672,
|
| 2384 |
+
"learning_rate": 5.008876397039983e-05,
|
| 2385 |
+
"loss": 0.4698,
|
| 2386 |
+
"step": 795
|
| 2387 |
+
},
|
| 2388 |
+
{
|
| 2389 |
+
"epoch": 0.6995160580730312,
|
| 2390 |
+
"eval_loss": 0.5082879662513733,
|
| 2391 |
+
"eval_runtime": 28.6587,
|
| 2392 |
+
"eval_samples_per_second": 0.593,
|
| 2393 |
+
"eval_steps_per_second": 0.314,
|
| 2394 |
+
"step": 795
|
| 2395 |
+
},
|
| 2396 |
+
{
|
| 2397 |
+
"epoch": 0.7039155301363836,
|
| 2398 |
+
"grad_norm": 0.19232523441314697,
|
| 2399 |
+
"learning_rate": 4.876285878715764e-05,
|
| 2400 |
+
"loss": 0.4981,
|
| 2401 |
+
"step": 800
|
| 2402 |
+
},
|
| 2403 |
+
{
|
| 2404 |
+
"epoch": 0.7039155301363836,
|
| 2405 |
+
"eval_loss": 0.5078893899917603,
|
| 2406 |
+
"eval_runtime": 28.5038,
|
| 2407 |
+
"eval_samples_per_second": 0.596,
|
| 2408 |
+
"eval_steps_per_second": 0.316,
|
| 2409 |
+
"step": 800
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 0.708315002199736,
|
| 2413 |
+
"grad_norm": 0.19006720185279846,
|
| 2414 |
+
"learning_rate": 4.744905719668207e-05,
|
| 2415 |
+
"loss": 0.4758,
|
| 2416 |
+
"step": 805
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 0.708315002199736,
|
| 2420 |
+
"eval_loss": 0.5076141357421875,
|
| 2421 |
+
"eval_runtime": 28.6324,
|
| 2422 |
+
"eval_samples_per_second": 0.594,
|
| 2423 |
+
"eval_steps_per_second": 0.314,
|
| 2424 |
+
"step": 805
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.7127144742630884,
|
| 2428 |
+
"grad_norm": 0.19002890586853027,
|
| 2429 |
+
"learning_rate": 4.614766955429447e-05,
|
| 2430 |
+
"loss": 0.4642,
|
| 2431 |
+
"step": 810
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.7127144742630884,
|
| 2435 |
+
"eval_loss": 0.507789671421051,
|
| 2436 |
+
"eval_runtime": 28.6356,
|
| 2437 |
+
"eval_samples_per_second": 0.594,
|
| 2438 |
+
"eval_steps_per_second": 0.314,
|
| 2439 |
+
"step": 810
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 0.7171139463264409,
|
| 2443 |
+
"grad_norm": 0.2051495909690857,
|
| 2444 |
+
"learning_rate": 4.485900328280731e-05,
|
| 2445 |
+
"loss": 0.4669,
|
| 2446 |
+
"step": 815
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 0.7171139463264409,
|
| 2450 |
+
"eval_loss": 0.5073484182357788,
|
| 2451 |
+
"eval_runtime": 28.5748,
|
| 2452 |
+
"eval_samples_per_second": 0.595,
|
| 2453 |
+
"eval_steps_per_second": 0.315,
|
| 2454 |
+
"step": 815
|
| 2455 |
+
},
|
| 2456 |
+
{
|
| 2457 |
+
"epoch": 0.7215134183897932,
|
| 2458 |
+
"grad_norm": 0.6378114223480225,
|
| 2459 |
+
"learning_rate": 4.358336279990268e-05,
|
| 2460 |
+
"loss": 0.4711,
|
| 2461 |
+
"step": 820
|
| 2462 |
+
},
|
| 2463 |
+
{
|
| 2464 |
+
"epoch": 0.7215134183897932,
|
| 2465 |
+
"eval_loss": 0.5070581436157227,
|
| 2466 |
+
"eval_runtime": 28.6233,
|
| 2467 |
+
"eval_samples_per_second": 0.594,
|
| 2468 |
+
"eval_steps_per_second": 0.314,
|
| 2469 |
+
"step": 820
|
| 2470 |
+
},
|
| 2471 |
+
{
|
| 2472 |
+
"epoch": 0.7259128904531457,
|
| 2473 |
+
"grad_norm": 0.181978240609169,
|
| 2474 |
+
"learning_rate": 4.2321049446220505e-05,
|
| 2475 |
+
"loss": 0.4704,
|
| 2476 |
+
"step": 825
|
| 2477 |
+
},
|
| 2478 |
+
{
|
| 2479 |
+
"epoch": 0.7259128904531457,
|
| 2480 |
+
"eval_loss": 0.5068845748901367,
|
| 2481 |
+
"eval_runtime": 28.5225,
|
| 2482 |
+
"eval_samples_per_second": 0.596,
|
| 2483 |
+
"eval_steps_per_second": 0.316,
|
| 2484 |
+
"step": 825
|
| 2485 |
+
},
|
| 2486 |
+
{
|
| 2487 |
+
"epoch": 0.730312362516498,
|
| 2488 |
+
"grad_norm": 0.1777966171503067,
|
| 2489 |
+
"learning_rate": 4.107236141417382e-05,
|
| 2490 |
+
"loss": 0.4752,
|
| 2491 |
+
"step": 830
|
| 2492 |
+
},
|
| 2493 |
+
{
|
| 2494 |
+
"epoch": 0.730312362516498,
|
| 2495 |
+
"eval_loss": 0.5066249966621399,
|
| 2496 |
+
"eval_runtime": 28.5423,
|
| 2497 |
+
"eval_samples_per_second": 0.596,
|
| 2498 |
+
"eval_steps_per_second": 0.315,
|
| 2499 |
+
"step": 830
|
| 2500 |
+
},
|
| 2501 |
+
{
|
| 2502 |
+
"epoch": 0.7347118345798505,
|
| 2503 |
+
"grad_norm": 0.18686190247535706,
|
| 2504 |
+
"learning_rate": 3.9837593677507726e-05,
|
| 2505 |
+
"loss": 0.4621,
|
| 2506 |
+
"step": 835
|
| 2507 |
+
},
|
| 2508 |
+
{
|
| 2509 |
+
"epoch": 0.7347118345798505,
|
| 2510 |
+
"eval_loss": 0.5066962242126465,
|
| 2511 |
+
"eval_runtime": 28.428,
|
| 2512 |
+
"eval_samples_per_second": 0.598,
|
| 2513 |
+
"eval_steps_per_second": 0.317,
|
| 2514 |
+
"step": 835
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 0.7391113066432028,
|
| 2518 |
+
"grad_norm": 0.18854567408561707,
|
| 2519 |
+
"learning_rate": 3.8617037921618705e-05,
|
| 2520 |
+
"loss": 0.4748,
|
| 2521 |
+
"step": 840
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 0.7391113066432028,
|
| 2525 |
+
"eval_loss": 0.50632643699646,
|
| 2526 |
+
"eval_runtime": 28.5075,
|
| 2527 |
+
"eval_samples_per_second": 0.596,
|
| 2528 |
+
"eval_steps_per_second": 0.316,
|
| 2529 |
+
"step": 840
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.7435107787065552,
|
| 2533 |
+
"grad_norm": 0.19204109907150269,
|
| 2534 |
+
"learning_rate": 3.741098247465049e-05,
|
| 2535 |
+
"loss": 0.4948,
|
| 2536 |
+
"step": 845
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 0.7435107787065552,
|
| 2540 |
+
"eval_loss": 0.5060507655143738,
|
| 2541 |
+
"eval_runtime": 28.5753,
|
| 2542 |
+
"eval_samples_per_second": 0.595,
|
| 2543 |
+
"eval_steps_per_second": 0.315,
|
| 2544 |
+
"step": 845
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.7479102507699076,
|
| 2548 |
+
"grad_norm": 0.19182614982128143,
|
| 2549 |
+
"learning_rate": 3.621971223938334e-05,
|
| 2550 |
+
"loss": 0.4832,
|
| 2551 |
+
"step": 850
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.7479102507699076,
|
| 2555 |
+
"eval_loss": 0.5058286190032959,
|
| 2556 |
+
"eval_runtime": 28.5184,
|
| 2557 |
+
"eval_samples_per_second": 0.596,
|
| 2558 |
+
"eval_steps_per_second": 0.316,
|
| 2559 |
+
"step": 850
|
| 2560 |
+
},
|
| 2561 |
+
{
|
| 2562 |
+
"epoch": 0.75230972283326,
|
| 2563 |
+
"grad_norm": 0.18205444514751434,
|
| 2564 |
+
"learning_rate": 3.504350862593231e-05,
|
| 2565 |
+
"loss": 0.4642,
|
| 2566 |
+
"step": 855
|
| 2567 |
+
},
|
| 2568 |
+
{
|
| 2569 |
+
"epoch": 0.75230972283326,
|
| 2570 |
+
"eval_loss": 0.505698025226593,
|
| 2571 |
+
"eval_runtime": 28.6382,
|
| 2572 |
+
"eval_samples_per_second": 0.594,
|
| 2573 |
+
"eval_steps_per_second": 0.314,
|
| 2574 |
+
"step": 855
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 0.7567091948966124,
|
| 2578 |
+
"grad_norm": 0.20196740329265594,
|
| 2579 |
+
"learning_rate": 3.388264948527052e-05,
|
| 2580 |
+
"loss": 0.4877,
|
| 2581 |
+
"step": 860
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 0.7567091948966124,
|
| 2585 |
+
"eval_loss": 0.5052359700202942,
|
| 2586 |
+
"eval_runtime": 28.5347,
|
| 2587 |
+
"eval_samples_per_second": 0.596,
|
| 2588 |
+
"eval_steps_per_second": 0.315,
|
| 2589 |
+
"step": 860
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 0.7611086669599648,
|
| 2593 |
+
"grad_norm": 0.18125030398368835,
|
| 2594 |
+
"learning_rate": 3.2737409043593405e-05,
|
| 2595 |
+
"loss": 0.4727,
|
| 2596 |
+
"step": 865
|
| 2597 |
+
},
|
| 2598 |
+
{
|
| 2599 |
+
"epoch": 0.7611086669599648,
|
| 2600 |
+
"eval_loss": 0.504954993724823,
|
| 2601 |
+
"eval_runtime": 28.5976,
|
| 2602 |
+
"eval_samples_per_second": 0.594,
|
| 2603 |
+
"eval_steps_per_second": 0.315,
|
| 2604 |
+
"step": 865
|
| 2605 |
+
},
|
| 2606 |
+
{
|
| 2607 |
+
"epoch": 0.7655081390233172,
|
| 2608 |
+
"grad_norm": 0.18927669525146484,
|
| 2609 |
+
"learning_rate": 3.160805783753897e-05,
|
| 2610 |
+
"loss": 0.4691,
|
| 2611 |
+
"step": 870
|
| 2612 |
+
},
|
| 2613 |
+
{
|
| 2614 |
+
"epoch": 0.7655081390233172,
|
| 2615 |
+
"eval_loss": 0.5047942399978638,
|
| 2616 |
+
"eval_runtime": 28.5051,
|
| 2617 |
+
"eval_samples_per_second": 0.596,
|
| 2618 |
+
"eval_steps_per_second": 0.316,
|
| 2619 |
+
"step": 870
|
| 2620 |
+
},
|
| 2621 |
+
{
|
| 2622 |
+
"epoch": 0.7699076110866696,
|
| 2623 |
+
"grad_norm": 0.18508534133434296,
|
| 2624 |
+
"learning_rate": 3.0494862650279822e-05,
|
| 2625 |
+
"loss": 0.5292,
|
| 2626 |
+
"step": 875
|
| 2627 |
+
},
|
| 2628 |
+
{
|
| 2629 |
+
"epoch": 0.7699076110866696,
|
| 2630 |
+
"eval_loss": 0.5046341419219971,
|
| 2631 |
+
"eval_runtime": 28.5445,
|
| 2632 |
+
"eval_samples_per_second": 0.596,
|
| 2633 |
+
"eval_steps_per_second": 0.315,
|
| 2634 |
+
"step": 875
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 0.774307083150022,
|
| 2638 |
+
"grad_norm": 0.18230414390563965,
|
| 2639 |
+
"learning_rate": 2.939808644850184e-05,
|
| 2640 |
+
"loss": 0.4708,
|
| 2641 |
+
"step": 880
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 0.774307083150022,
|
| 2645 |
+
"eval_loss": 0.5046290755271912,
|
| 2646 |
+
"eval_runtime": 28.6138,
|
| 2647 |
+
"eval_samples_per_second": 0.594,
|
| 2648 |
+
"eval_steps_per_second": 0.315,
|
| 2649 |
+
"step": 880
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 0.7787065552133744,
|
| 2653 |
+
"grad_norm": 0.17352643609046936,
|
| 2654 |
+
"learning_rate": 2.8317988320284228e-05,
|
| 2655 |
+
"loss": 0.4863,
|
| 2656 |
+
"step": 885
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 0.7787065552133744,
|
| 2660 |
+
"eval_loss": 0.5044691562652588,
|
| 2661 |
+
"eval_runtime": 28.6321,
|
| 2662 |
+
"eval_samples_per_second": 0.594,
|
| 2663 |
+
"eval_steps_per_second": 0.314,
|
| 2664 |
+
"step": 885
|
| 2665 |
+
},
|
| 2666 |
+
{
|
| 2667 |
+
"epoch": 0.7831060272767268,
|
| 2668 |
+
"grad_norm": 0.1845002919435501,
|
| 2669 |
+
"learning_rate": 2.7254823413896058e-05,
|
| 2670 |
+
"loss": 0.5006,
|
| 2671 |
+
"step": 890
|
| 2672 |
+
},
|
| 2673 |
+
{
|
| 2674 |
+
"epoch": 0.7831060272767268,
|
| 2675 |
+
"eval_loss": 0.5042091012001038,
|
| 2676 |
+
"eval_runtime": 28.6132,
|
| 2677 |
+
"eval_samples_per_second": 0.594,
|
| 2678 |
+
"eval_steps_per_second": 0.315,
|
| 2679 |
+
"step": 890
|
| 2680 |
+
},
|
| 2681 |
+
{
|
| 2682 |
+
"epoch": 0.7875054993400792,
|
| 2683 |
+
"grad_norm": 0.17883773148059845,
|
| 2684 |
+
"learning_rate": 2.6208842877523278e-05,
|
| 2685 |
+
"loss": 0.4887,
|
| 2686 |
+
"step": 895
|
| 2687 |
+
},
|
| 2688 |
+
{
|
| 2689 |
+
"epoch": 0.7875054993400792,
|
| 2690 |
+
"eval_loss": 0.5039156675338745,
|
| 2691 |
+
"eval_runtime": 28.5693,
|
| 2692 |
+
"eval_samples_per_second": 0.595,
|
| 2693 |
+
"eval_steps_per_second": 0.315,
|
| 2694 |
+
"step": 895
|
| 2695 |
+
},
|
| 2696 |
+
{
|
| 2697 |
+
"epoch": 0.7919049714034316,
|
| 2698 |
+
"grad_norm": 0.19202597439289093,
|
| 2699 |
+
"learning_rate": 2.518029379994089e-05,
|
| 2700 |
+
"loss": 0.4867,
|
| 2701 |
+
"step": 900
|
| 2702 |
+
},
|
| 2703 |
+
{
|
| 2704 |
+
"epoch": 0.7919049714034316,
|
| 2705 |
+
"eval_loss": 0.5037320852279663,
|
| 2706 |
+
"eval_runtime": 28.549,
|
| 2707 |
+
"eval_samples_per_second": 0.595,
|
| 2708 |
+
"eval_steps_per_second": 0.315,
|
| 2709 |
+
"step": 900
|
| 2710 |
+
},
|
| 2711 |
+
{
|
| 2712 |
+
"epoch": 0.796304443466784,
|
| 2713 |
+
"grad_norm": 0.18246056139469147,
|
| 2714 |
+
"learning_rate": 2.4169419152143768e-05,
|
| 2715 |
+
"loss": 0.4662,
|
| 2716 |
+
"step": 905
|
| 2717 |
+
},
|
| 2718 |
+
{
|
| 2719 |
+
"epoch": 0.796304443466784,
|
| 2720 |
+
"eval_loss": 0.5035374164581299,
|
| 2721 |
+
"eval_runtime": 28.6042,
|
| 2722 |
+
"eval_samples_per_second": 0.594,
|
| 2723 |
+
"eval_steps_per_second": 0.315,
|
| 2724 |
+
"step": 905
|
| 2725 |
+
},
|
| 2726 |
+
{
|
| 2727 |
+
"epoch": 0.8007039155301364,
|
| 2728 |
+
"grad_norm": 0.18989378213882446,
|
| 2729 |
+
"learning_rate": 2.317645772995042e-05,
|
| 2730 |
+
"loss": 0.4744,
|
| 2731 |
+
"step": 910
|
| 2732 |
+
},
|
| 2733 |
+
{
|
| 2734 |
+
"epoch": 0.8007039155301364,
|
| 2735 |
+
"eval_loss": 0.5033923387527466,
|
| 2736 |
+
"eval_runtime": 28.4795,
|
| 2737 |
+
"eval_samples_per_second": 0.597,
|
| 2738 |
+
"eval_steps_per_second": 0.316,
|
| 2739 |
+
"step": 910
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 0.8051033875934888,
|
| 2743 |
+
"grad_norm": 0.19525018334388733,
|
| 2744 |
+
"learning_rate": 2.220164409759299e-05,
|
| 2745 |
+
"loss": 0.5159,
|
| 2746 |
+
"step": 915
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 0.8051033875934888,
|
| 2750 |
+
"eval_loss": 0.503151535987854,
|
| 2751 |
+
"eval_runtime": 28.6198,
|
| 2752 |
+
"eval_samples_per_second": 0.594,
|
| 2753 |
+
"eval_steps_per_second": 0.314,
|
| 2754 |
+
"step": 915
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 0.8095028596568412,
|
| 2758 |
+
"grad_norm": 0.18840977549552917,
|
| 2759 |
+
"learning_rate": 2.124520853230697e-05,
|
| 2760 |
+
"loss": 0.4848,
|
| 2761 |
+
"step": 920
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.8095028596568412,
|
| 2765 |
+
"eval_loss": 0.5029481649398804,
|
| 2766 |
+
"eval_runtime": 28.614,
|
| 2767 |
+
"eval_samples_per_second": 0.594,
|
| 2768 |
+
"eval_steps_per_second": 0.315,
|
| 2769 |
+
"step": 920
|
| 2770 |
+
},
|
| 2771 |
+
{
|
| 2772 |
+
"epoch": 0.8139023317201936,
|
| 2773 |
+
"grad_norm": 0.18055056035518646,
|
| 2774 |
+
"learning_rate": 2.03073769699333e-05,
|
| 2775 |
+
"loss": 0.4648,
|
| 2776 |
+
"step": 925
|
| 2777 |
+
},
|
| 2778 |
+
{
|
| 2779 |
+
"epoch": 0.8139023317201936,
|
| 2780 |
+
"eval_loss": 0.5028063654899597,
|
| 2781 |
+
"eval_runtime": 28.5662,
|
| 2782 |
+
"eval_samples_per_second": 0.595,
|
| 2783 |
+
"eval_steps_per_second": 0.315,
|
| 2784 |
+
"step": 925
|
| 2785 |
+
},
|
| 2786 |
+
{
|
| 2787 |
+
"epoch": 0.818301803783546,
|
| 2788 |
+
"grad_norm": 0.18352611362934113,
|
| 2789 |
+
"learning_rate": 1.9388370951546432e-05,
|
| 2790 |
+
"loss": 0.4733,
|
| 2791 |
+
"step": 930
|
| 2792 |
+
},
|
| 2793 |
+
{
|
| 2794 |
+
"epoch": 0.818301803783546,
|
| 2795 |
+
"eval_loss": 0.5027296543121338,
|
| 2796 |
+
"eval_runtime": 28.5532,
|
| 2797 |
+
"eval_samples_per_second": 0.595,
|
| 2798 |
+
"eval_steps_per_second": 0.315,
|
| 2799 |
+
"step": 930
|
| 2800 |
+
},
|
| 2801 |
+
{
|
| 2802 |
+
"epoch": 0.8227012758468983,
|
| 2803 |
+
"grad_norm": 0.18161964416503906,
|
| 2804 |
+
"learning_rate": 1.848840757112019e-05,
|
| 2805 |
+
"loss": 0.4556,
|
| 2806 |
+
"step": 935
|
| 2807 |
+
},
|
| 2808 |
+
{
|
| 2809 |
+
"epoch": 0.8227012758468983,
|
| 2810 |
+
"eval_loss": 0.5025849342346191,
|
| 2811 |
+
"eval_runtime": 28.6672,
|
| 2812 |
+
"eval_samples_per_second": 0.593,
|
| 2813 |
+
"eval_steps_per_second": 0.314,
|
| 2814 |
+
"step": 935
|
| 2815 |
+
},
|
| 2816 |
+
{
|
| 2817 |
+
"epoch": 0.8271007479102508,
|
| 2818 |
+
"grad_norm": 0.19485127925872803,
|
| 2819 |
+
"learning_rate": 1.7607699424244585e-05,
|
| 2820 |
+
"loss": 0.4973,
|
| 2821 |
+
"step": 940
|
| 2822 |
+
},
|
| 2823 |
+
{
|
| 2824 |
+
"epoch": 0.8271007479102508,
|
| 2825 |
+
"eval_loss": 0.5023777484893799,
|
| 2826 |
+
"eval_runtime": 28.5856,
|
| 2827 |
+
"eval_samples_per_second": 0.595,
|
| 2828 |
+
"eval_steps_per_second": 0.315,
|
| 2829 |
+
"step": 940
|
| 2830 |
+
},
|
| 2831 |
+
{
|
| 2832 |
+
"epoch": 0.8315002199736031,
|
| 2833 |
+
"grad_norm": 0.19218072295188904,
|
| 2834 |
+
"learning_rate": 1.674645455790468e-05,
|
| 2835 |
+
"loss": 0.4708,
|
| 2836 |
+
"step": 945
|
| 2837 |
+
},
|
| 2838 |
+
{
|
| 2839 |
+
"epoch": 0.8315002199736031,
|
| 2840 |
+
"eval_loss": 0.5024308562278748,
|
| 2841 |
+
"eval_runtime": 28.6001,
|
| 2842 |
+
"eval_samples_per_second": 0.594,
|
| 2843 |
+
"eval_steps_per_second": 0.315,
|
| 2844 |
+
"step": 945
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 0.8358996920369556,
|
| 2848 |
+
"grad_norm": 0.18270643055438995,
|
| 2849 |
+
"learning_rate": 1.5904876421334536e-05,
|
| 2850 |
+
"loss": 0.4547,
|
| 2851 |
+
"step": 950
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 0.8358996920369556,
|
| 2855 |
+
"eval_loss": 0.5024178624153137,
|
| 2856 |
+
"eval_runtime": 28.5464,
|
| 2857 |
+
"eval_samples_per_second": 0.596,
|
| 2858 |
+
"eval_steps_per_second": 0.315,
|
| 2859 |
+
"step": 950
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 0.8402991641003079,
|
| 2863 |
+
"grad_norm": 0.18350371718406677,
|
| 2864 |
+
"learning_rate": 1.5083163817956914e-05,
|
| 2865 |
+
"loss": 0.4663,
|
| 2866 |
+
"step": 955
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 0.8402991641003079,
|
| 2870 |
+
"eval_loss": 0.5021481513977051,
|
| 2871 |
+
"eval_runtime": 28.5783,
|
| 2872 |
+
"eval_samples_per_second": 0.595,
|
| 2873 |
+
"eval_steps_per_second": 0.315,
|
| 2874 |
+
"step": 955
|
| 2875 |
+
},
|
| 2876 |
+
{
|
| 2877 |
+
"epoch": 0.8446986361636604,
|
| 2878 |
+
"grad_norm": 0.18115630745887756,
|
| 2879 |
+
"learning_rate": 1.4281510858420632e-05,
|
| 2880 |
+
"loss": 0.4857,
|
| 2881 |
+
"step": 960
|
| 2882 |
+
},
|
| 2883 |
+
{
|
| 2884 |
+
"epoch": 0.8446986361636604,
|
| 2885 |
+
"eval_loss": 0.5019457340240479,
|
| 2886 |
+
"eval_runtime": 28.5976,
|
| 2887 |
+
"eval_samples_per_second": 0.594,
|
| 2888 |
+
"eval_steps_per_second": 0.315,
|
| 2889 |
+
"step": 960
|
| 2890 |
+
},
|
| 2891 |
+
{
|
| 2892 |
+
"epoch": 0.8490981082270127,
|
| 2893 |
+
"grad_norm": 0.1744571477174759,
|
| 2894 |
+
"learning_rate": 1.350010691474629e-05,
|
| 2895 |
+
"loss": 0.4633,
|
| 2896 |
+
"step": 965
|
| 2897 |
+
},
|
| 2898 |
+
{
|
| 2899 |
+
"epoch": 0.8490981082270127,
|
| 2900 |
+
"eval_loss": 0.5019629597663879,
|
| 2901 |
+
"eval_runtime": 28.5207,
|
| 2902 |
+
"eval_samples_per_second": 0.596,
|
| 2903 |
+
"eval_steps_per_second": 0.316,
|
| 2904 |
+
"step": 965
|
| 2905 |
+
},
|
| 2906 |
+
{
|
| 2907 |
+
"epoch": 0.8534975802903652,
|
| 2908 |
+
"grad_norm": 0.18827442824840546,
|
| 2909 |
+
"learning_rate": 1.2739136575591581e-05,
|
| 2910 |
+
"loss": 0.4723,
|
| 2911 |
+
"step": 970
|
| 2912 |
+
},
|
| 2913 |
+
{
|
| 2914 |
+
"epoch": 0.8534975802903652,
|
| 2915 |
+
"eval_loss": 0.5018792748451233,
|
| 2916 |
+
"eval_runtime": 28.4515,
|
| 2917 |
+
"eval_samples_per_second": 0.598,
|
| 2918 |
+
"eval_steps_per_second": 0.316,
|
| 2919 |
+
"step": 970
|
| 2920 |
+
},
|
| 2921 |
+
{
|
| 2922 |
+
"epoch": 0.8578970523537176,
|
| 2923 |
+
"grad_norm": 0.18166576325893402,
|
| 2924 |
+
"learning_rate": 1.1998779602646437e-05,
|
| 2925 |
+
"loss": 0.4691,
|
| 2926 |
+
"step": 975
|
| 2927 |
+
},
|
| 2928 |
+
{
|
| 2929 |
+
"epoch": 0.8578970523537176,
|
| 2930 |
+
"eval_loss": 0.5017500519752502,
|
| 2931 |
+
"eval_runtime": 28.5978,
|
| 2932 |
+
"eval_samples_per_second": 0.594,
|
| 2933 |
+
"eval_steps_per_second": 0.315,
|
| 2934 |
+
"step": 975
|
| 2935 |
+
},
|
| 2936 |
+
{
|
| 2937 |
+
"epoch": 0.8622965244170699,
|
| 2938 |
+
"grad_norm": 0.18091408908367157,
|
| 2939 |
+
"learning_rate": 1.1279210888168546e-05,
|
| 2940 |
+
"loss": 0.4874,
|
| 2941 |
+
"step": 980
|
| 2942 |
+
},
|
| 2943 |
+
{
|
| 2944 |
+
"epoch": 0.8622965244170699,
|
| 2945 |
+
"eval_loss": 0.5017052888870239,
|
| 2946 |
+
"eval_runtime": 28.7541,
|
| 2947 |
+
"eval_samples_per_second": 0.591,
|
| 2948 |
+
"eval_steps_per_second": 0.313,
|
| 2949 |
+
"step": 980
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 0.8666959964804224,
|
| 2953 |
+
"grad_norm": 0.182442307472229,
|
| 2954 |
+
"learning_rate": 1.0580600413668984e-05,
|
| 2955 |
+
"loss": 0.4773,
|
| 2956 |
+
"step": 985
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 0.8666959964804224,
|
| 2960 |
+
"eval_loss": 0.5016083121299744,
|
| 2961 |
+
"eval_runtime": 28.5972,
|
| 2962 |
+
"eval_samples_per_second": 0.594,
|
| 2963 |
+
"eval_steps_per_second": 0.315,
|
| 2964 |
+
"step": 985
|
| 2965 |
+
},
|
| 2966 |
+
{
|
| 2967 |
+
"epoch": 0.8710954685437747,
|
| 2968 |
+
"grad_norm": 0.18171900510787964,
|
| 2969 |
+
"learning_rate": 9.903113209758096e-06,
|
| 2970 |
+
"loss": 0.4806,
|
| 2971 |
+
"step": 990
|
| 2972 |
+
},
|
| 2973 |
+
{
|
| 2974 |
+
"epoch": 0.8710954685437747,
|
| 2975 |
+
"eval_loss": 0.5015130043029785,
|
| 2976 |
+
"eval_runtime": 28.5707,
|
| 2977 |
+
"eval_samples_per_second": 0.595,
|
| 2978 |
+
"eval_steps_per_second": 0.315,
|
| 2979 |
+
"step": 990
|
| 2980 |
+
},
|
| 2981 |
+
{
|
| 2982 |
+
"epoch": 0.8754949406071272,
|
| 2983 |
+
"grad_norm": 0.1896371841430664,
|
| 2984 |
+
"learning_rate": 9.246909317160746e-06,
|
| 2985 |
+
"loss": 0.4512,
|
| 2986 |
+
"step": 995
|
| 2987 |
+
},
|
| 2988 |
+
{
|
| 2989 |
+
"epoch": 0.8754949406071272,
|
| 2990 |
+
"eval_loss": 0.5013110637664795,
|
| 2991 |
+
"eval_runtime": 28.6509,
|
| 2992 |
+
"eval_samples_per_second": 0.593,
|
| 2993 |
+
"eval_steps_per_second": 0.314,
|
| 2994 |
+
"step": 995
|
| 2995 |
+
},
|
| 2996 |
+
{
|
| 2997 |
+
"epoch": 0.8798944126704795,
|
| 2998 |
+
"grad_norm": 0.1779976189136505,
|
| 2999 |
+
"learning_rate": 8.612143748910451e-06,
|
| 3000 |
+
"loss": 0.4561,
|
| 3001 |
+
"step": 1000
|
| 3002 |
+
},
|
| 3003 |
+
{
|
| 3004 |
+
"epoch": 0.8798944126704795,
|
| 3005 |
+
"eval_loss": 0.5013135075569153,
|
| 3006 |
+
"eval_runtime": 28.8047,
|
| 3007 |
+
"eval_samples_per_second": 0.59,
|
| 3008 |
+
"eval_steps_per_second": 0.312,
|
| 3009 |
+
"step": 1000
|
| 3010 |
+
},
|
| 3011 |
+
{
|
| 3012 |
+
"epoch": 0.884293884733832,
|
| 3013 |
+
"grad_norm": 0.17416957020759583,
|
| 3014 |
+
"learning_rate": 7.998966453731094e-06,
|
| 3015 |
+
"loss": 0.4637,
|
| 3016 |
+
"step": 1005
|
| 3017 |
+
},
|
| 3018 |
+
{
|
| 3019 |
+
"epoch": 0.884293884733832,
|
| 3020 |
+
"eval_loss": 0.5013565421104431,
|
| 3021 |
+
"eval_runtime": 28.5911,
|
| 3022 |
+
"eval_samples_per_second": 0.595,
|
| 3023 |
+
"eval_steps_per_second": 0.315,
|
| 3024 |
+
"step": 1005
|
| 3025 |
+
},
|
| 3026 |
+
{
|
| 3027 |
+
"epoch": 0.8886933567971843,
|
| 3028 |
+
"grad_norm": 0.1769402176141739,
|
| 3029 |
+
"learning_rate": 7.40752228061502e-06,
|
| 3030 |
+
"loss": 0.4527,
|
| 3031 |
+
"step": 1010
|
| 3032 |
+
},
|
| 3033 |
+
{
|
| 3034 |
+
"epoch": 0.8886933567971843,
|
| 3035 |
+
"eval_loss": 0.5010828375816345,
|
| 3036 |
+
"eval_runtime": 28.5203,
|
| 3037 |
+
"eval_samples_per_second": 0.596,
|
| 3038 |
+
"eval_steps_per_second": 0.316,
|
| 3039 |
+
"step": 1010
|
| 3040 |
+
},
|
| 3041 |
+
{
|
| 3042 |
+
"epoch": 0.8930928288605368,
|
| 3043 |
+
"grad_norm": 0.17784808576107025,
|
| 3044 |
+
"learning_rate": 6.8379509446057644e-06,
|
| 3045 |
+
"loss": 0.4903,
|
| 3046 |
+
"step": 1015
|
| 3047 |
+
},
|
| 3048 |
+
{
|
| 3049 |
+
"epoch": 0.8930928288605368,
|
| 3050 |
+
"eval_loss": 0.5012202262878418,
|
| 3051 |
+
"eval_runtime": 27.8441,
|
| 3052 |
+
"eval_samples_per_second": 0.611,
|
| 3053 |
+
"eval_steps_per_second": 0.323,
|
| 3054 |
+
"step": 1015
|
| 3055 |
+
},
|
| 3056 |
+
{
|
| 3057 |
+
"epoch": 0.8974923009238891,
|
| 3058 |
+
"grad_norm": 0.18067394196987152,
|
| 3059 |
+
"learning_rate": 6.290386993793618e-06,
|
| 3060 |
+
"loss": 0.4689,
|
| 3061 |
+
"step": 1020
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 0.8974923009238891,
|
| 3065 |
+
"eval_loss": 0.5012267231941223,
|
| 3066 |
+
"eval_runtime": 28.517,
|
| 3067 |
+
"eval_samples_per_second": 0.596,
|
| 3068 |
+
"eval_steps_per_second": 0.316,
|
| 3069 |
+
"step": 1020
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 0.9018917729872415,
|
| 3073 |
+
"grad_norm": 0.17478391528129578,
|
| 3074 |
+
"learning_rate": 5.764959777531776e-06,
|
| 3075 |
+
"loss": 0.4589,
|
| 3076 |
+
"step": 1025
|
| 3077 |
+
},
|
| 3078 |
+
{
|
| 3079 |
+
"epoch": 0.9018917729872415,
|
| 3080 |
+
"eval_loss": 0.5011836290359497,
|
| 3081 |
+
"eval_runtime": 28.6023,
|
| 3082 |
+
"eval_samples_per_second": 0.594,
|
| 3083 |
+
"eval_steps_per_second": 0.315,
|
| 3084 |
+
"step": 1025
|
| 3085 |
+
},
|
| 3086 |
+
{
|
| 3087 |
+
"epoch": 0.9062912450505939,
|
| 3088 |
+
"grad_norm": 0.185857892036438,
|
| 3089 |
+
"learning_rate": 5.261793415880456e-06,
|
| 3090 |
+
"loss": 0.4528,
|
| 3091 |
+
"step": 1030
|
| 3092 |
+
},
|
| 3093 |
+
{
|
| 3094 |
+
"epoch": 0.9062912450505939,
|
| 3095 |
+
"eval_loss": 0.501183807849884,
|
| 3096 |
+
"eval_runtime": 28.5159,
|
| 3097 |
+
"eval_samples_per_second": 0.596,
|
| 3098 |
+
"eval_steps_per_second": 0.316,
|
| 3099 |
+
"step": 1030
|
| 3100 |
+
},
|
| 3101 |
+
{
|
| 3102 |
+
"epoch": 0.9106907171139463,
|
| 3103 |
+
"grad_norm": 0.17951223254203796,
|
| 3104 |
+
"learning_rate": 4.781006770286478e-06,
|
| 3105 |
+
"loss": 0.4845,
|
| 3106 |
+
"step": 1035
|
| 3107 |
+
},
|
| 3108 |
+
{
|
| 3109 |
+
"epoch": 0.9106907171139463,
|
| 3110 |
+
"eval_loss": 0.5011433959007263,
|
| 3111 |
+
"eval_runtime": 28.6072,
|
| 3112 |
+
"eval_samples_per_second": 0.594,
|
| 3113 |
+
"eval_steps_per_second": 0.315,
|
| 3114 |
+
"step": 1035
|
| 3115 |
+
},
|
| 3116 |
+
{
|
| 3117 |
+
"epoch": 0.9150901891772987,
|
| 3118 |
+
"grad_norm": 0.18096089363098145,
|
| 3119 |
+
"learning_rate": 4.322713415504975e-06,
|
| 3120 |
+
"loss": 0.4578,
|
| 3121 |
+
"step": 1040
|
| 3122 |
+
},
|
| 3123 |
+
{
|
| 3124 |
+
"epoch": 0.9150901891772987,
|
| 3125 |
+
"eval_loss": 0.5011703968048096,
|
| 3126 |
+
"eval_runtime": 28.6287,
|
| 3127 |
+
"eval_samples_per_second": 0.594,
|
| 3128 |
+
"eval_steps_per_second": 0.314,
|
| 3129 |
+
"step": 1040
|
| 3130 |
+
},
|
| 3131 |
+
{
|
| 3132 |
+
"epoch": 0.9194896612406511,
|
| 3133 |
+
"grad_norm": 0.2069099247455597,
|
| 3134 |
+
"learning_rate": 3.887021612769936e-06,
|
| 3135 |
+
"loss": 0.5027,
|
| 3136 |
+
"step": 1045
|
| 3137 |
+
},
|
| 3138 |
+
{
|
| 3139 |
+
"epoch": 0.9194896612406511,
|
| 3140 |
+
"eval_loss": 0.5011240839958191,
|
| 3141 |
+
"eval_runtime": 29.0514,
|
| 3142 |
+
"eval_samples_per_second": 0.585,
|
| 3143 |
+
"eval_steps_per_second": 0.31,
|
| 3144 |
+
"step": 1045
|
| 3145 |
+
},
|
| 3146 |
+
{
|
| 3147 |
+
"epoch": 0.9238891333040036,
|
| 3148 |
+
"grad_norm": 0.18762987852096558,
|
| 3149 |
+
"learning_rate": 3.4740342842199956e-06,
|
| 3150 |
+
"loss": 0.4695,
|
| 3151 |
+
"step": 1050
|
| 3152 |
+
},
|
| 3153 |
+
{
|
| 3154 |
+
"epoch": 0.9238891333040036,
|
| 3155 |
+
"eval_loss": 0.5010772347450256,
|
| 3156 |
+
"eval_runtime": 28.5655,
|
| 3157 |
+
"eval_samples_per_second": 0.595,
|
| 3158 |
+
"eval_steps_per_second": 0.315,
|
| 3159 |
+
"step": 1050
|
| 3160 |
+
},
|
| 3161 |
+
{
|
| 3162 |
+
"epoch": 0.9282886053673559,
|
| 3163 |
+
"grad_norm": 0.178373321890831,
|
| 3164 |
+
"learning_rate": 3.0838489885854805e-06,
|
| 3165 |
+
"loss": 0.484,
|
| 3166 |
+
"step": 1055
|
| 3167 |
+
},
|
| 3168 |
+
{
|
| 3169 |
+
"epoch": 0.9282886053673559,
|
| 3170 |
+
"eval_loss": 0.5010451674461365,
|
| 3171 |
+
"eval_runtime": 28.6083,
|
| 3172 |
+
"eval_samples_per_second": 0.594,
|
| 3173 |
+
"eval_steps_per_second": 0.315,
|
| 3174 |
+
"step": 1055
|
| 3175 |
+
},
|
| 3176 |
+
{
|
| 3177 |
+
"epoch": 0.9326880774307084,
|
| 3178 |
+
"grad_norm": 0.1794215440750122,
|
| 3179 |
+
"learning_rate": 2.7165578981424357e-06,
|
| 3180 |
+
"loss": 0.4784,
|
| 3181 |
+
"step": 1060
|
| 3182 |
+
},
|
| 3183 |
+
{
|
| 3184 |
+
"epoch": 0.9326880774307084,
|
| 3185 |
+
"eval_loss": 0.5010905265808105,
|
| 3186 |
+
"eval_runtime": 28.5675,
|
| 3187 |
+
"eval_samples_per_second": 0.595,
|
| 3188 |
+
"eval_steps_per_second": 0.315,
|
| 3189 |
+
"step": 1060
|
| 3190 |
+
},
|
| 3191 |
+
{
|
| 3192 |
+
"epoch": 0.9370875494940607,
|
| 3193 |
+
"grad_norm": 0.17699354887008667,
|
| 3194 |
+
"learning_rate": 2.3722477769389517e-06,
|
| 3195 |
+
"loss": 0.4698,
|
| 3196 |
+
"step": 1065
|
| 3197 |
+
},
|
| 3198 |
+
{
|
| 3199 |
+
"epoch": 0.9370875494940607,
|
| 3200 |
+
"eval_loss": 0.5010352730751038,
|
| 3201 |
+
"eval_runtime": 28.6041,
|
| 3202 |
+
"eval_samples_per_second": 0.594,
|
| 3203 |
+
"eval_steps_per_second": 0.315,
|
| 3204 |
+
"step": 1065
|
| 3205 |
+
},
|
| 3206 |
+
{
|
| 3207 |
+
"epoch": 0.9414870215574132,
|
| 3208 |
+
"grad_norm": 0.17208220064640045,
|
| 3209 |
+
"learning_rate": 2.0509999602992493e-06,
|
| 3210 |
+
"loss": 0.4517,
|
| 3211 |
+
"step": 1070
|
| 3212 |
+
},
|
| 3213 |
+
{
|
| 3214 |
+
"epoch": 0.9414870215574132,
|
| 3215 |
+
"eval_loss": 0.5010344982147217,
|
| 3216 |
+
"eval_runtime": 28.5865,
|
| 3217 |
+
"eval_samples_per_second": 0.595,
|
| 3218 |
+
"eval_steps_per_second": 0.315,
|
| 3219 |
+
"step": 1070
|
| 3220 |
+
},
|
| 3221 |
+
{
|
| 3222 |
+
"epoch": 0.9458864936207655,
|
| 3223 |
+
"grad_norm": 0.1774464249610901,
|
| 3224 |
+
"learning_rate": 1.7528903356100469e-06,
|
| 3225 |
+
"loss": 0.4846,
|
| 3226 |
+
"step": 1075
|
| 3227 |
+
},
|
| 3228 |
+
{
|
| 3229 |
+
"epoch": 0.9458864936207655,
|
| 3230 |
+
"eval_loss": 0.5010223388671875,
|
| 3231 |
+
"eval_runtime": 28.5634,
|
| 3232 |
+
"eval_samples_per_second": 0.595,
|
| 3233 |
+
"eval_steps_per_second": 0.315,
|
| 3234 |
+
"step": 1075
|
| 3235 |
+
},
|
| 3236 |
+
{
|
| 3237 |
+
"epoch": 0.9502859656841179,
|
| 3238 |
+
"grad_norm": 0.1773741990327835,
|
| 3239 |
+
"learning_rate": 1.4779893243939359e-06,
|
| 3240 |
+
"loss": 0.4402,
|
| 3241 |
+
"step": 1080
|
| 3242 |
+
},
|
| 3243 |
+
{
|
| 3244 |
+
"epoch": 0.9502859656841179,
|
| 3245 |
+
"eval_loss": 0.5009992718696594,
|
| 3246 |
+
"eval_runtime": 28.5952,
|
| 3247 |
+
"eval_samples_per_second": 0.595,
|
| 3248 |
+
"eval_steps_per_second": 0.315,
|
| 3249 |
+
"step": 1080
|
| 3250 |
+
},
|
| 3251 |
+
{
|
| 3252 |
+
"epoch": 0.9546854377474703,
|
| 3253 |
+
"grad_norm": 0.18979211151599884,
|
| 3254 |
+
"learning_rate": 1.2263618656739084e-06,
|
| 3255 |
+
"loss": 0.5013,
|
| 3256 |
+
"step": 1085
|
| 3257 |
+
},
|
| 3258 |
+
{
|
| 3259 |
+
"epoch": 0.9546854377474703,
|
| 3260 |
+
"eval_loss": 0.501004159450531,
|
| 3261 |
+
"eval_runtime": 28.614,
|
| 3262 |
+
"eval_samples_per_second": 0.594,
|
| 3263 |
+
"eval_steps_per_second": 0.315,
|
| 3264 |
+
"step": 1085
|
| 3265 |
+
},
|
| 3266 |
+
{
|
| 3267 |
+
"epoch": 0.9590849098108227,
|
| 3268 |
+
"grad_norm": 0.1895236372947693,
|
| 3269 |
+
"learning_rate": 9.98067400632985e-07,
|
| 3270 |
+
"loss": 0.4588,
|
| 3271 |
+
"step": 1090
|
| 3272 |
+
},
|
| 3273 |
+
{
|
| 3274 |
+
"epoch": 0.9590849098108227,
|
| 3275 |
+
"eval_loss": 0.5009981393814087,
|
| 3276 |
+
"eval_runtime": 28.5601,
|
| 3277 |
+
"eval_samples_per_second": 0.595,
|
| 3278 |
+
"eval_steps_per_second": 0.315,
|
| 3279 |
+
"step": 1090
|
| 3280 |
+
},
|
| 3281 |
+
{
|
| 3282 |
+
"epoch": 0.9634843818741751,
|
| 3283 |
+
"grad_norm": 0.17328618466854095,
|
| 3284 |
+
"learning_rate": 7.931598585726563e-07,
|
| 3285 |
+
"loss": 0.4712,
|
| 3286 |
+
"step": 1095
|
| 3287 |
+
},
|
| 3288 |
+
{
|
| 3289 |
+
"epoch": 0.9634843818741751,
|
| 3290 |
+
"eval_loss": 0.500961184501648,
|
| 3291 |
+
"eval_runtime": 28.574,
|
| 3292 |
+
"eval_samples_per_second": 0.595,
|
| 3293 |
+
"eval_steps_per_second": 0.315,
|
| 3294 |
+
"step": 1095
|
| 3295 |
+
},
|
| 3296 |
+
{
|
| 3297 |
+
"epoch": 0.9678838539375275,
|
| 3298 |
+
"grad_norm": 0.18122579157352448,
|
| 3299 |
+
"learning_rate": 6.116876441733088e-07,
|
| 3300 |
+
"loss": 0.4534,
|
| 3301 |
+
"step": 1100
|
| 3302 |
+
},
|
| 3303 |
+
{
|
| 3304 |
+
"epoch": 0.9678838539375275,
|
| 3305 |
+
"eval_loss": 0.5009814500808716,
|
| 3306 |
+
"eval_runtime": 28.5934,
|
| 3307 |
+
"eval_samples_per_second": 0.595,
|
| 3308 |
+
"eval_steps_per_second": 0.315,
|
| 3309 |
+
"step": 1100
|
| 3310 |
+
},
|
| 3311 |
+
{
|
| 3312 |
+
"epoch": 0.9722833260008799,
|
| 3313 |
+
"grad_norm": 0.18148748576641083,
|
| 3314 |
+
"learning_rate": 4.536936260597258e-07,
|
| 3315 |
+
"loss": 0.4587,
|
| 3316 |
+
"step": 1105
|
| 3317 |
+
},
|
| 3318 |
+
{
|
| 3319 |
+
"epoch": 0.9722833260008799,
|
| 3320 |
+
"eval_loss": 0.5009997487068176,
|
| 3321 |
+
"eval_runtime": 28.5275,
|
| 3322 |
+
"eval_samples_per_second": 0.596,
|
| 3323 |
+
"eval_steps_per_second": 0.315,
|
| 3324 |
+
"step": 1105
|
| 3325 |
+
},
|
| 3326 |
+
{
|
| 3327 |
+
"epoch": 0.9766827980642323,
|
| 3328 |
+
"grad_norm": 0.18024764955043793,
|
| 3329 |
+
"learning_rate": 3.192151266743548e-07,
|
| 3330 |
+
"loss": 0.4783,
|
| 3331 |
+
"step": 1110
|
| 3332 |
+
},
|
| 3333 |
+
{
|
| 3334 |
+
"epoch": 0.9766827980642323,
|
| 3335 |
+
"eval_loss": 0.5009670853614807,
|
| 3336 |
+
"eval_runtime": 28.5688,
|
| 3337 |
+
"eval_samples_per_second": 0.595,
|
| 3338 |
+
"eval_steps_per_second": 0.315,
|
| 3339 |
+
"step": 1110
|
| 3340 |
+
},
|
| 3341 |
+
{
|
| 3342 |
+
"epoch": 0.9810822701275846,
|
| 3343 |
+
"grad_norm": 0.18152055144309998,
|
| 3344 |
+
"learning_rate": 2.082839134607828e-07,
|
| 3345 |
+
"loss": 0.4623,
|
| 3346 |
+
"step": 1115
|
| 3347 |
+
},
|
| 3348 |
+
{
|
| 3349 |
+
"epoch": 0.9810822701275846,
|
| 3350 |
+
"eval_loss": 0.5009202361106873,
|
| 3351 |
+
"eval_runtime": 28.6066,
|
| 3352 |
+
"eval_samples_per_second": 0.594,
|
| 3353 |
+
"eval_steps_per_second": 0.315,
|
| 3354 |
+
"step": 1115
|
| 3355 |
+
},
|
| 3356 |
+
{
|
| 3357 |
+
"epoch": 0.9854817421909371,
|
| 3358 |
+
"grad_norm": 0.17324087023735046,
|
| 3359 |
+
"learning_rate": 1.2092619135937177e-07,
|
| 3360 |
+
"loss": 0.439,
|
| 3361 |
+
"step": 1120
|
| 3362 |
+
},
|
| 3363 |
+
{
|
| 3364 |
+
"epoch": 0.9854817421909371,
|
| 3365 |
+
"eval_loss": 0.5010377168655396,
|
| 3366 |
+
"eval_runtime": 28.5308,
|
| 3367 |
+
"eval_samples_per_second": 0.596,
|
| 3368 |
+
"eval_steps_per_second": 0.315,
|
| 3369 |
+
"step": 1120
|
| 3370 |
+
},
|
| 3371 |
+
{
|
| 3372 |
+
"epoch": 0.9898812142542894,
|
| 3373 |
+
"grad_norm": 0.17685554921627045,
|
| 3374 |
+
"learning_rate": 5.716259661695533e-08,
|
| 3375 |
+
"loss": 0.4629,
|
| 3376 |
+
"step": 1125
|
| 3377 |
+
},
|
| 3378 |
+
{
|
| 3379 |
+
"epoch": 0.9898812142542894,
|
| 3380 |
+
"eval_loss": 0.5009082555770874,
|
| 3381 |
+
"eval_runtime": 28.6259,
|
| 3382 |
+
"eval_samples_per_second": 0.594,
|
| 3383 |
+
"eval_steps_per_second": 0.314,
|
| 3384 |
+
"step": 1125
|
| 3385 |
+
},
|
| 3386 |
+
{
|
| 3387 |
+
"epoch": 0.9942806863176419,
|
| 3388 |
+
"grad_norm": 0.17675389349460602,
|
| 3389 |
+
"learning_rate": 1.7008191912004646e-08,
|
| 3390 |
+
"loss": 0.4716,
|
| 3391 |
+
"step": 1130
|
| 3392 |
+
},
|
| 3393 |
+
{
|
| 3394 |
+
"epoch": 0.9942806863176419,
|
| 3395 |
+
"eval_loss": 0.5009535551071167,
|
| 3396 |
+
"eval_runtime": 28.626,
|
| 3397 |
+
"eval_samples_per_second": 0.594,
|
| 3398 |
+
"eval_steps_per_second": 0.314,
|
| 3399 |
+
"step": 1130
|
| 3400 |
+
},
|
| 3401 |
+
{
|
| 3402 |
+
"epoch": 0.9986801583809943,
|
| 3403 |
+
"grad_norm": 0.18398317694664001,
|
| 3404 |
+
"learning_rate": 4.724627964303175e-10,
|
| 3405 |
+
"loss": 0.4832,
|
| 3406 |
+
"step": 1135
|
| 3407 |
+
},
|
| 3408 |
+
{
|
| 3409 |
+
"epoch": 0.9986801583809943,
|
| 3410 |
+
"eval_loss": 0.5010104179382324,
|
| 3411 |
+
"eval_runtime": 28.6106,
|
| 3412 |
+
"eval_samples_per_second": 0.594,
|
| 3413 |
+
"eval_steps_per_second": 0.315,
|
| 3414 |
+
"step": 1135
|
| 3415 |
+
},
|
| 3416 |
+
{
|
| 3417 |
+
"epoch": 0.9995600527936648,
|
| 3418 |
+
"step": 1136,
|
| 3419 |
+
"total_flos": 7.211600370336793e+18,
|
| 3420 |
+
"train_loss": 0.039691918463984004,
|
| 3421 |
+
"train_runtime": 9596.3839,
|
| 3422 |
+
"train_samples_per_second": 1.895,
|
| 3423 |
+
"train_steps_per_second": 0.118
|
| 3424 |
+
}
|
| 3425 |
+
],
|
| 3426 |
+
"logging_steps": 5,
|
| 3427 |
+
"max_steps": 1136,
|
| 3428 |
+
"num_input_tokens_seen": 0,
|
| 3429 |
+
"num_train_epochs": 1,
|
| 3430 |
+
"save_steps": 5,
|
| 3431 |
+
"stateful_callbacks": {
|
| 3432 |
+
"TrainerControl": {
|
| 3433 |
+
"args": {
|
| 3434 |
+
"should_epoch_stop": false,
|
| 3435 |
+
"should_evaluate": false,
|
| 3436 |
+
"should_log": false,
|
| 3437 |
+
"should_save": true,
|
| 3438 |
+
"should_training_stop": true
|
| 3439 |
+
},
|
| 3440 |
+
"attributes": {}
|
| 3441 |
+
}
|
| 3442 |
+
},
|
| 3443 |
+
"total_flos": 7.211600370336793e+18,
|
| 3444 |
+
"train_batch_size": 8,
|
| 3445 |
+
"trial_name": null,
|
| 3446 |
+
"trial_params": null
|
| 3447 |
+
}
|