tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

Built site for gh-pages

Browse Source
This commit is contained in:
Quarto GHA Workflow Runner
2025-04-04 17:50:00 +00:00
parent 595c2b4288
commit cc5cf77f6b
173 changed files with 509 additions and 520 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/colab-notebooks/colab-axolotl-example.html
View File

@@ -2,7 +2,7 @@
<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en"><head>
<meta charset="utf-8">
<meta name="generator" content="quarto-1.6.42">
<meta name="generator" content="quarto-1.6.43">
<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes">
@@ -69,7 +69,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
<script src="../../site_libs/quarto-html/tippy.umd.min.js"></script>
<script src="../../site_libs/quarto-html/anchor.min.js"></script>
<link href="../../site_libs/quarto-html/tippy.css" rel="stylesheet">
<link href="../../site_libs/quarto-html/quarto-syntax-highlighting-dark-b53751a350365c71b6c909e95f209ed1.css" rel="stylesheet" id="quarto-text-highlighting-styles">
<link href="../../site_libs/quarto-html/quarto-syntax-highlighting-dark-4379b0ccadffce622b03caf4c46266b3.css" rel="stylesheet" id="quarto-text-highlighting-styles">
<script src="../../site_libs/bootstrap/bootstrap.min.js"></script>
<link href="../../site_libs/bootstrap/bootstrap-icons.css" rel="stylesheet">
<link href="../../site_libs/bootstrap/bootstrap-71f806479865a0e7fd52beea5cc266f1.min.css" rel="stylesheet" append-hash="true" id="quarto-bootstrap" data-mode="dark">

11
examples/llama-2/qlora-fsdp.yml
View File

@@ -26,9 +26,7 @@ pad_to_sequence_len: true
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:
wandb_project:
wandb_entity:
@@ -43,28 +41,19 @@ optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 0.00001
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
- full_shard