cf0c79d52e
* fix: update chat_template * fix: handle gemma3 showing a lot of no content for turn 0 * fix: remove unknown config from examples * fix: test * fix: temporary disable gemma2 test * fix: stop overwriting config.text_config unnecessarily * fix: handling of set cache to the text_config section * feat: add liger gemma support and bump liger to 0.5.5 * fix: add double use_cache setting * fix: add support for final_logit_softcap in CCE for gemma2/3 * fix: set use_cache before model load * feat: add missing layernorm override * fix: handle gemma3 rmsnorm * fix: use wrapper to pass dim as hidden_size * fix: change dim to positional * fix: patch with wrong mlp * chore: refactor use_cache handling * fix import issues * fix tests.e2e.utils import --------- Co-authored-by: Wing Lian <wing@axolotl.ai>
75 lines
1.3 KiB
YAML
75 lines
1.3 KiB
YAML
base_model: google/gemma-3-1b-it
|
|
# optionally might have model_type or tokenizer_type
|
|
model_type: AutoModelForCausalLM
|
|
tokenizer_type: AutoTokenizer
|
|
# Automatically upload checkpoint and final model to HF
|
|
# hub_model_id: username/custom_model_name
|
|
|
|
load_in_8bit: false
|
|
load_in_4bit: true
|
|
strict: false
|
|
|
|
# huggingface repo
|
|
chat_template: gemma3
|
|
datasets:
|
|
- path: cgato/SlimOrcaDedupCleaned
|
|
type: chat_template
|
|
field_messages: conversations
|
|
message_property_mappings:
|
|
role: from
|
|
content: value
|
|
|
|
val_set_size: 0.0
|
|
output_dir: ./outputs/out
|
|
|
|
adapter: qlora
|
|
lora_r: 32
|
|
lora_alpha: 16
|
|
lora_dropout: 0.05
|
|
lora_target_linear: true
|
|
|
|
sequence_len: 2048
|
|
sample_packing: true
|
|
eval_sample_packing: false
|
|
pad_to_sequence_len: true
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
|
|
gradient_accumulation_steps: 4
|
|
micro_batch_size: 1
|
|
num_epochs: 4
|
|
optimizer: adamw_bnb_8bit
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0002
|
|
|
|
train_on_inputs: false
|
|
group_by_length: false
|
|
bf16: auto
|
|
fp16:
|
|
tf32: true
|
|
|
|
gradient_checkpointing: true
|
|
early_stopping_patience:
|
|
resume_from_checkpoint:
|
|
local_rank:
|
|
logging_steps: 1
|
|
xformers_attention:
|
|
flash_attention: true
|
|
|
|
warmup_ratio: 0.1
|
|
evals_per_epoch:
|
|
eval_table_size:
|
|
eval_max_new_tokens: 128
|
|
saves_per_epoch: 1
|
|
debug:
|
|
deepspeed:
|
|
weight_decay: 0.0
|
|
fsdp:
|
|
fsdp_config:
|
|
special_tokens:
|