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

Merge branch 'main' of github.com:axolotl-ai-cloud/axolotl into 775-option-to-drop-vs-truncate-on-rows-longer-than-context-length

Browse Source
This commit is contained in:
mhenrhcsen
2025-05-14 13:36:43 +02:00
parent 9c5b8da22f c0a0c7534c
commit 5ecf22b54e
50 changed files with 2366 additions and 678 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docs/config.qmd
View File

@@ -507,6 +507,7 @@ save_strategy: # Set to `"no"` to skip checkpoint saves, `"epoch"` at end of eac
save_steps: # Leave empty to save at each epoch, integer for every N steps. float for fraction of total steps
saves_per_epoch: # number of times per epoch to save a checkpoint, mutually exclusive with save_steps
save_total_limit: # Checkpoints saved at a time
save_only_model: # Save only the model weights, skipping the optimizer. Using this means you can't resume from checkpoints.
# Maximum number of iterations to train for. It precedes num_epochs which means that
# if both are set, num_epochs will not be guaranteed.
# e.g., when 1 epoch is 1000 steps => `num_epochs: 2` and `max_steps: 100` will train for 100 steps
@@ -540,7 +541,7 @@ train_on_inputs: false
# Note that training loss may have an oscillating pattern with this enabled.
group_by_length: false
# Whether to use gradient checkpointing. Available options are: true, false, "offload".
# Whether to use gradient checkpointing. Available options are: true, false, "offload", "offload_disk".
# https://huggingface.co/docs/transformers/v4.18.0/en/performance#gradient-checkpointing
gradient_checkpointing: false
# additional kwargs to pass to the trainer for gradient checkpointing