f2155eaf79
* feat: add trackio as experiment tracking integration - Add TrackioConfig to integrations schema with project_name, run_name, and space_id - Create trackio_.py module for environment setup - Add is_trackio_available() utility function - Integrate trackio with report_to in trainer builder - Add trackio callback for experiment tracking - Add trackio config keys to gpt-oss example YAMLs - Trackio runs locally by default, syncs to HF Space if space_id provided * changes * changes * changes * changes * changes * changes * changes * Update requirements.txt * don't allow pydantic 2.12 for now --------- Co-authored-by: Abubakar Abid <aaabid93@gmail.com> Co-authored-by: Wing Lian <wing@axolotl.ai>
63 lines
1.3 KiB
YAML
63 lines
1.3 KiB
YAML
base_model: openai/gpt-oss-20b
|
|
use_kernels: false
|
|
model_quantization_config: Mxfp4Config
|
|
model_quantization_config_kwargs:
|
|
dequantize: true
|
|
|
|
plugins:
|
|
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
|
|
|
|
experimental_skip_move_to_device: true # prevent OOM by NOT putting model to GPU before sharding
|
|
|
|
datasets:
|
|
- path: HuggingFaceH4/Multilingual-Thinking
|
|
type: chat_template
|
|
field_thinking: thinking
|
|
template_thinking_key: thinking
|
|
|
|
dataset_prepared_path: last_run_prepared
|
|
val_set_size: 0
|
|
output_dir: ./outputs/gpt-oss-out/
|
|
|
|
sequence_len: 4096
|
|
sample_packing: true
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
trackio_project_name:
|
|
trackio_run_name:
|
|
trackio_space_id:
|
|
|
|
gradient_accumulation_steps: 2
|
|
micro_batch_size: 1
|
|
num_epochs: 1
|
|
|
|
optimizer: adamw_torch_8bit
|
|
lr_scheduler: constant_with_warmup
|
|
learning_rate: 2e-5
|
|
|
|
bf16: true
|
|
tf32: true
|
|
|
|
flash_attention: true
|
|
attn_implementation: kernels-community/vllm-flash-attn3 # this is not needed if using flash_attn >= 2.8.3
|
|
|
|
gradient_checkpointing: true
|
|
activation_offloading: true
|
|
|
|
logging_steps: 1
|
|
saves_per_epoch: 1
|
|
|
|
warmup_ratio: 0.03
|
|
|
|
special_tokens:
|
|
eot_tokens:
|
|
- "<|end|>"
|
|
|
|
# choose the zero3 configuration that best fits your system capabilities
|
|
deepspeed: deepspeed_configs/zero3_bf16.json
|