Model save
Browse files- README.md +58 -0
- all_results.json +8 -0
- generation_config.json +12 -0
- train_results.json +8 -0
- trainer_state.json +455 -0
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/Llama-3.1-8B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: Llama3.1-8B-WebArena-Lite-SFT-CoT-QwQ-32B-epoch-1-no-sys
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Llama3.1-8B-WebArena-Lite-SFT-CoT-QwQ-32B-epoch-1-no-sys
|
| 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="weizhepei/Llama3.1-8B-WebArena-Lite-SFT-CoT-QwQ-32B-epoch-1-no-sys", 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/uva-llm/huggingface/runs/xkvy6ido)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
This model was trained with SFT.
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.16.0.dev0
|
| 38 |
+
- Transformers: 4.49.0
|
| 39 |
+
- Pytorch: 2.5.1
|
| 40 |
+
- Datasets: 3.4.1
|
| 41 |
+
- Tokenizers: 0.21.1
|
| 42 |
+
|
| 43 |
+
## Citations
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
Cite TRL as:
|
| 48 |
+
|
| 49 |
+
```bibtex
|
| 50 |
+
@misc{vonwerra2022trl,
|
| 51 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 52 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
|
| 53 |
+
year = 2020,
|
| 54 |
+
journal = {GitHub repository},
|
| 55 |
+
publisher = {GitHub},
|
| 56 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 57 |
+
}
|
| 58 |
+
```
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 120899332866048.0,
|
| 3 |
+
"train_loss": 0.8681221529841423,
|
| 4 |
+
"train_runtime": 4929.6945,
|
| 5 |
+
"train_samples": 9460,
|
| 6 |
+
"train_samples_per_second": 1.919,
|
| 7 |
+
"train_steps_per_second": 0.06
|
| 8 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 128000,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
128001,
|
| 6 |
+
128008,
|
| 7 |
+
128009
|
| 8 |
+
],
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_p": 0.9,
|
| 11 |
+
"transformers_version": "4.49.0"
|
| 12 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 120899332866048.0,
|
| 3 |
+
"train_loss": 0.8681221529841423,
|
| 4 |
+
"train_runtime": 4929.6945,
|
| 5 |
+
"train_samples": 9460,
|
| 6 |
+
"train_samples_per_second": 1.919,
|
| 7 |
+
"train_steps_per_second": 0.06
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,455 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 296,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.016891891891891893,
|
| 13 |
+
"grad_norm": 8.13028513496866,
|
| 14 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 15 |
+
"loss": 1.2798,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.033783783783783786,
|
| 20 |
+
"grad_norm": 3.5620083115927548,
|
| 21 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 22 |
+
"loss": 1.0801,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.05067567567567568,
|
| 27 |
+
"grad_norm": 3.3093983044774724,
|
| 28 |
+
"learning_rate": 5e-05,
|
| 29 |
+
"loss": 1.0286,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06756756756756757,
|
| 34 |
+
"grad_norm": 2.9259388634182364,
|
| 35 |
+
"learning_rate": 4.9964854757667645e-05,
|
| 36 |
+
"loss": 1.0634,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08445945945945946,
|
| 41 |
+
"grad_norm": 2.8065338500049846,
|
| 42 |
+
"learning_rate": 4.985952882516468e-05,
|
| 43 |
+
"loss": 1.0742,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.10135135135135136,
|
| 48 |
+
"grad_norm": 2.562306586379742,
|
| 49 |
+
"learning_rate": 4.9684351242973035e-05,
|
| 50 |
+
"loss": 1.0474,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.11824324324324324,
|
| 55 |
+
"grad_norm": 2.650398108922061,
|
| 56 |
+
"learning_rate": 4.943986926963291e-05,
|
| 57 |
+
"loss": 1.0506,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.13513513513513514,
|
| 62 |
+
"grad_norm": 2.292721416732774,
|
| 63 |
+
"learning_rate": 4.9126846672095325e-05,
|
| 64 |
+
"loss": 1.0221,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.15202702702702703,
|
| 69 |
+
"grad_norm": 2.147422350521184,
|
| 70 |
+
"learning_rate": 4.87462613396977e-05,
|
| 71 |
+
"loss": 1.0509,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.16891891891891891,
|
| 76 |
+
"grad_norm": 2.160055777676169,
|
| 77 |
+
"learning_rate": 4.8299302229216506e-05,
|
| 78 |
+
"loss": 1.0222,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1858108108108108,
|
| 83 |
+
"grad_norm": 2.127693396380588,
|
| 84 |
+
"learning_rate": 4.7787365650540663e-05,
|
| 85 |
+
"loss": 0.9793,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.20270270270270271,
|
| 90 |
+
"grad_norm": 2.07524575548144,
|
| 91 |
+
"learning_rate": 4.721205090456941e-05,
|
| 92 |
+
"loss": 0.9856,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.2195945945945946,
|
| 97 |
+
"grad_norm": 1.876482179181115,
|
| 98 |
+
"learning_rate": 4.657515528696183e-05,
|
| 99 |
+
"loss": 0.9715,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.23648648648648649,
|
| 104 |
+
"grad_norm": 2.2104621839173846,
|
| 105 |
+
"learning_rate": 4.5878668473346464e-05,
|
| 106 |
+
"loss": 0.9883,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.2533783783783784,
|
| 111 |
+
"grad_norm": 1.7760907365714962,
|
| 112 |
+
"learning_rate": 4.512476630353183e-05,
|
| 113 |
+
"loss": 0.9657,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2702702702702703,
|
| 118 |
+
"grad_norm": 1.8221427632245704,
|
| 119 |
+
"learning_rate": 4.4315803984135965e-05,
|
| 120 |
+
"loss": 0.9592,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.28716216216216217,
|
| 125 |
+
"grad_norm": 1.9046050199248852,
|
| 126 |
+
"learning_rate": 4.345430873087026e-05,
|
| 127 |
+
"loss": 0.9513,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.30405405405405406,
|
| 132 |
+
"grad_norm": 1.7830292324773953,
|
| 133 |
+
"learning_rate": 4.2542971873463075e-05,
|
| 134 |
+
"loss": 0.9195,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.32094594594594594,
|
| 139 |
+
"grad_norm": 1.841247803426208,
|
| 140 |
+
"learning_rate": 4.158464044788774e-05,
|
| 141 |
+
"loss": 0.9224,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.33783783783783783,
|
| 146 |
+
"grad_norm": 1.8694269639200451,
|
| 147 |
+
"learning_rate": 4.058230830216084e-05,
|
| 148 |
+
"loss": 0.9314,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.3547297297297297,
|
| 153 |
+
"grad_norm": 1.8736222919460577,
|
| 154 |
+
"learning_rate": 3.953910674349652e-05,
|
| 155 |
+
"loss": 0.9304,
|
| 156 |
+
"step": 105
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.3716216216216216,
|
| 160 |
+
"grad_norm": 1.6350257989779668,
|
| 161 |
+
"learning_rate": 3.8458294756035284e-05,
|
| 162 |
+
"loss": 0.9279,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.3885135135135135,
|
| 167 |
+
"grad_norm": 1.803012265683364,
|
| 168 |
+
"learning_rate": 3.734324881970736e-05,
|
| 169 |
+
"loss": 0.9349,
|
| 170 |
+
"step": 115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.40540540540540543,
|
| 174 |
+
"grad_norm": 1.8064493652132048,
|
| 175 |
+
"learning_rate": 3.619745236203666e-05,
|
| 176 |
+
"loss": 0.8794,
|
| 177 |
+
"step": 120
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.4222972972972973,
|
| 181 |
+
"grad_norm": 1.7963697461824464,
|
| 182 |
+
"learning_rate": 3.5024484875838145e-05,
|
| 183 |
+
"loss": 0.8911,
|
| 184 |
+
"step": 125
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.4391891891891892,
|
| 188 |
+
"grad_norm": 1.776261712635235,
|
| 189 |
+
"learning_rate": 3.3828010736805185e-05,
|
| 190 |
+
"loss": 0.9079,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.4560810810810811,
|
| 195 |
+
"grad_norm": 1.6092978364007704,
|
| 196 |
+
"learning_rate": 3.261176775592097e-05,
|
| 197 |
+
"loss": 0.8745,
|
| 198 |
+
"step": 135
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.47297297297297297,
|
| 202 |
+
"grad_norm": 1.5079004831852607,
|
| 203 |
+
"learning_rate": 3.137955550245643e-05,
|
| 204 |
+
"loss": 0.8652,
|
| 205 |
+
"step": 140
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.48986486486486486,
|
| 209 |
+
"grad_norm": 1.6792811022830822,
|
| 210 |
+
"learning_rate": 3.0135223434034053e-05,
|
| 211 |
+
"loss": 0.8882,
|
| 212 |
+
"step": 145
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.5067567567567568,
|
| 216 |
+
"grad_norm": 1.6638882399627897,
|
| 217 |
+
"learning_rate": 2.8882658870839326e-05,
|
| 218 |
+
"loss": 0.8961,
|
| 219 |
+
"step": 150
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5236486486486487,
|
| 223 |
+
"grad_norm": 1.6445982084590969,
|
| 224 |
+
"learning_rate": 2.7625774851548708e-05,
|
| 225 |
+
"loss": 0.8333,
|
| 226 |
+
"step": 155
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5405405405405406,
|
| 230 |
+
"grad_norm": 1.3995403314995896,
|
| 231 |
+
"learning_rate": 2.6368497908912592e-05,
|
| 232 |
+
"loss": 0.8184,
|
| 233 |
+
"step": 160
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.5574324324324325,
|
| 237 |
+
"grad_norm": 1.4804077164539369,
|
| 238 |
+
"learning_rate": 2.511475580318233e-05,
|
| 239 |
+
"loss": 0.84,
|
| 240 |
+
"step": 165
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.5743243243243243,
|
| 244 |
+
"grad_norm": 1.5022073909572482,
|
| 245 |
+
"learning_rate": 2.386846525170263e-05,
|
| 246 |
+
"loss": 0.8374,
|
| 247 |
+
"step": 170
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.5912162162162162,
|
| 251 |
+
"grad_norm": 1.7168462642599709,
|
| 252 |
+
"learning_rate": 2.2633519693002247e-05,
|
| 253 |
+
"loss": 0.8018,
|
| 254 |
+
"step": 175
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.6081081081081081,
|
| 258 |
+
"grad_norm": 1.6168306870973288,
|
| 259 |
+
"learning_rate": 2.1413777123608103e-05,
|
| 260 |
+
"loss": 0.8316,
|
| 261 |
+
"step": 180
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.625,
|
| 265 |
+
"grad_norm": 1.594518741356322,
|
| 266 |
+
"learning_rate": 2.0213048045581014e-05,
|
| 267 |
+
"loss": 0.8005,
|
| 268 |
+
"step": 185
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.6418918918918919,
|
| 272 |
+
"grad_norm": 1.6309292174197987,
|
| 273 |
+
"learning_rate": 1.903508356242525e-05,
|
| 274 |
+
"loss": 0.7838,
|
| 275 |
+
"step": 190
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.6587837837837838,
|
| 279 |
+
"grad_norm": 1.5472838462411251,
|
| 280 |
+
"learning_rate": 1.78835636605603e-05,
|
| 281 |
+
"loss": 0.7833,
|
| 282 |
+
"step": 195
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.6756756756756757,
|
| 286 |
+
"grad_norm": 1.4645171972887558,
|
| 287 |
+
"learning_rate": 1.676208571296408e-05,
|
| 288 |
+
"loss": 0.7703,
|
| 289 |
+
"step": 200
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.6925675675675675,
|
| 293 |
+
"grad_norm": 1.544406833425164,
|
| 294 |
+
"learning_rate": 1.5674153240902257e-05,
|
| 295 |
+
"loss": 0.7837,
|
| 296 |
+
"step": 205
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.7094594594594594,
|
| 300 |
+
"grad_norm": 1.5227639810165863,
|
| 301 |
+
"learning_rate": 1.4623164968852327e-05,
|
| 302 |
+
"loss": 0.7935,
|
| 303 |
+
"step": 210
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.7263513513513513,
|
| 307 |
+
"grad_norm": 1.466593262947162,
|
| 308 |
+
"learning_rate": 1.3612404206815144e-05,
|
| 309 |
+
"loss": 0.7625,
|
| 310 |
+
"step": 215
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.7432432432432432,
|
| 314 |
+
"grad_norm": 1.5122312078520845,
|
| 315 |
+
"learning_rate": 1.2645028593183763e-05,
|
| 316 |
+
"loss": 0.7523,
|
| 317 |
+
"step": 220
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.7601351351351351,
|
| 321 |
+
"grad_norm": 1.4925416635497781,
|
| 322 |
+
"learning_rate": 1.1724060230213075e-05,
|
| 323 |
+
"loss": 0.7408,
|
| 324 |
+
"step": 225
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.777027027027027,
|
| 328 |
+
"grad_norm": 1.486253191645707,
|
| 329 |
+
"learning_rate": 1.085237624290726e-05,
|
| 330 |
+
"loss": 0.7423,
|
| 331 |
+
"step": 230
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.793918918918919,
|
| 335 |
+
"grad_norm": 1.385533463280539,
|
| 336 |
+
"learning_rate": 1.0032699790819288e-05,
|
| 337 |
+
"loss": 0.7508,
|
| 338 |
+
"step": 235
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.8108108108108109,
|
| 342 |
+
"grad_norm": 1.4094819946848187,
|
| 343 |
+
"learning_rate": 9.267591560841876e-06,
|
| 344 |
+
"loss": 0.7251,
|
| 345 |
+
"step": 240
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.8277027027027027,
|
| 349 |
+
"grad_norm": 1.5065956940993193,
|
| 350 |
+
"learning_rate": 8.559441767566378e-06,
|
| 351 |
+
"loss": 0.7249,
|
| 352 |
+
"step": 245
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.8445945945945946,
|
| 356 |
+
"grad_norm": 1.5597571594417456,
|
| 357 |
+
"learning_rate": 7.91046268620102e-06,
|
| 358 |
+
"loss": 0.7681,
|
| 359 |
+
"step": 250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.8614864864864865,
|
| 363 |
+
"grad_norm": 1.4344047894033067,
|
| 364 |
+
"learning_rate": 7.322681741375405e-06,
|
| 365 |
+
"loss": 0.729,
|
| 366 |
+
"step": 255
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.8783783783783784,
|
| 370 |
+
"grad_norm": 1.406848470364391,
|
| 371 |
+
"learning_rate": 6.797935173422361e-06,
|
| 372 |
+
"loss": 0.707,
|
| 373 |
+
"step": 260
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.8952702702702703,
|
| 377 |
+
"grad_norm": 1.473371363524701,
|
| 378 |
+
"learning_rate": 6.337862301923552e-06,
|
| 379 |
+
"loss": 0.7237,
|
| 380 |
+
"step": 265
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.9121621621621622,
|
| 384 |
+
"grad_norm": 1.4053578084417369,
|
| 385 |
+
"learning_rate": 5.943900404439816e-06,
|
| 386 |
+
"loss": 0.7005,
|
| 387 |
+
"step": 270
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.9290540540540541,
|
| 391 |
+
"grad_norm": 1.4260858889219359,
|
| 392 |
+
"learning_rate": 5.617280226425088e-06,
|
| 393 |
+
"loss": 0.6978,
|
| 394 |
+
"step": 275
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.9459459459459459,
|
| 398 |
+
"grad_norm": 1.458565550822819,
|
| 399 |
+
"learning_rate": 5.3590221363510965e-06,
|
| 400 |
+
"loss": 0.6992,
|
| 401 |
+
"step": 280
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.9628378378378378,
|
| 405 |
+
"grad_norm": 1.3712460796459922,
|
| 406 |
+
"learning_rate": 5.169932938054281e-06,
|
| 407 |
+
"loss": 0.6935,
|
| 408 |
+
"step": 285
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.9797297297297297,
|
| 412 |
+
"grad_norm": 1.4140757719345507,
|
| 413 |
+
"learning_rate": 5.050603350263229e-06,
|
| 414 |
+
"loss": 0.6866,
|
| 415 |
+
"step": 290
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.9966216216216216,
|
| 419 |
+
"grad_norm": 1.56665314387651,
|
| 420 |
+
"learning_rate": 5.001406161180633e-06,
|
| 421 |
+
"loss": 0.687,
|
| 422 |
+
"step": 295
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.0,
|
| 426 |
+
"step": 296,
|
| 427 |
+
"total_flos": 120899332866048.0,
|
| 428 |
+
"train_loss": 0.8681221529841423,
|
| 429 |
+
"train_runtime": 4929.6945,
|
| 430 |
+
"train_samples_per_second": 1.919,
|
| 431 |
+
"train_steps_per_second": 0.06
|
| 432 |
+
}
|
| 433 |
+
],
|
| 434 |
+
"logging_steps": 5,
|
| 435 |
+
"max_steps": 296,
|
| 436 |
+
"num_input_tokens_seen": 0,
|
| 437 |
+
"num_train_epochs": 1,
|
| 438 |
+
"save_steps": 500,
|
| 439 |
+
"stateful_callbacks": {
|
| 440 |
+
"TrainerControl": {
|
| 441 |
+
"args": {
|
| 442 |
+
"should_epoch_stop": false,
|
| 443 |
+
"should_evaluate": false,
|
| 444 |
+
"should_log": false,
|
| 445 |
+
"should_save": true,
|
| 446 |
+
"should_training_stop": true
|
| 447 |
+
},
|
| 448 |
+
"attributes": {}
|
| 449 |
+
}
|
| 450 |
+
},
|
| 451 |
+
"total_flos": 120899332866048.0,
|
| 452 |
+
"train_batch_size": 4,
|
| 453 |
+
"trial_name": null,
|
| 454 |
+
"trial_params": null
|
| 455 |
+
}
|