axolotl-ai-cloud--axolotl
wehub-resource-sync
78ec5d9290
ci-cd / build-axolotl-uv (<nil>, 130, 13.0.0, linux/amd64,linux/arm64, 3.12, 2.11.0) (push) Has been cancelled
ci-cd / build-axolotl-uv (<nil>, 130, 13.0.0, true, linux/amd64,linux/arm64, 3.12, 2.12.0) (push) Has been cancelled
ci-cd / build-axolotl-cloud-uv (<nil>, 130, 13.0.0, linux/amd64,linux/arm64, 3.12, 2.11.0) (push) Has been cancelled
ci-cd / build-axolotl-cloud-uv (<nil>, 130, 13.0.0, true, linux/amd64,linux/arm64, 3.12, 2.12.0) (push) Has been cancelled
ci-cd / build-axolotl-cloud-no-tmux-uv (<nil>, 130, 13.0.0, linux/amd64,linux/arm64, 3.12, 2.11.0) (push) Has been cancelled
ci-cd / build-axolotl-cloud-no-tmux-uv (<nil>, 130, 13.0.0, true, linux/amd64,linux/arm64, 3.12, 2.12.0) (push) Has been cancelled
ci-cd-base / build-base-uv (130, 13.0.0, , Dockerfile-uv-base, linux/amd64,linux/arm64, 3.12, 2.12.0, 9.0 10.0 10.3 12.0+PTX) (push) Has been cancelled
ci-cd-base / build-base-uv (130, 13.0.0, , Dockerfile-uv-base, linux/amd64,linux/arm64, 3.12, 2.12.1, 9.0 10.0 10.3 12.0+PTX) (push) Has been cancelled
ci-cd-base / build-base-uv (130, 13.0.0, , Dockerfile-uv-base, linux/amd64,linux/arm64, 3.12, 2.13.0, 9.0 10.0 10.3 12.0+PTX) (push) Has been cancelled
ci-cd-base / build-base-uv (132, 13.2.1, , Dockerfile-uv-base, linux/amd64,linux/arm64, 3.12, 2.13.0, 9.0 10.0 10.3 12.0+PTX, https://download.pytorch.org/whl/cu132) (push) Has been cancelled
ci-cd-base / build-base-uv (130, 13.0.0, , Dockerfile-uv-base, linux/amd64,linux/arm64, 3.12, 2.11.0, 9.0 10.0 10.3 12.0+PTX) (push) Has been cancelled
Tests / PyTest (3.12, 2.12.1) (push) Has been cancelled
Tests / PyTest (3.12, 2.13.0) (push) Has been cancelled
docker-e2e-tests / gate-skip-e2e (push) Has been cancelled
docker-e2e-tests / docker-e2e-tests-1st (<nil>, 130, 13.0.0, 1, 3.12, 2.12.1) (push) Has been cancelled
docker-e2e-tests / docker-e2e-tests (<nil>, 130, 13.0.0, 1, 3.12, 2.11.0) (push) Has been cancelled
docker-e2e-tests / docker-e2e-kernel-tests (<nil>, 130, 13.0.0, 1, 3.12, 2.11.0) (push) Has been cancelled
docker-e2e-tests / docker-e2e-kernel-tests (<nil>, 130, 13.0.0, 1, 3.12, 2.12.1) (push) Has been cancelled
docker-e2e-tests / docker-e2e-cleanup (<nil>, 130, 13.0.0, 1, 3.12, 2.12.1) (push) Has been cancelled
Publish Docs / build-deploy (push) Has been cancelled
Tests / PyTest from Source Dist (3.12, 2.11.0) (push) Has been cancelled
Tests / PyTest from Source Dist (3.12, 2.12.1) (push) Has been cancelled
Tests / PyTest from Source Dist (3.12, 2.13.0) (push) Has been cancelled
Tests / pre-commit (push) Has been cancelled
Tests / Prefetch S3 once to prime the CDN cache (push) Has been cancelled
Tests / PyTest (3.12, 2.11.0) (push) Has been cancelled
56 行
1.0 KiB
YAML
56 行
1.0 KiB
YAML
base_model: HuggingFaceTB/SmolLM2-135M
|
|
|
|
# Dataset configuration
|
|
datasets:
|
|
- path: tatsu-lab/alpaca
|
|
type: alpaca
|
|
split: train
|
|
|
|
# Streaming-specific settings
|
|
streaming: true
|
|
streaming_multipack_buffer_size: 10000
|
|
shuffle_merged_datasets: true
|
|
|
|
# Training configuration
|
|
max_steps: 1000
|
|
output_dir: ./outputs/smollm2-135m-sft-streaming
|
|
|
|
# Sequence and packing settings
|
|
sequence_len: 1024
|
|
sample_packing: true
|
|
attn_implementation: flash_attention_2
|
|
|
|
# Batch size settings
|
|
gradient_accumulation_steps: 4
|
|
micro_batch_size: 1
|
|
|
|
# Optimizer and scheduler
|
|
optimizer: adamw_torch
|
|
lr_scheduler: cosine
|
|
learning_rate: 2e-4
|
|
warmup_ratio: 0.1
|
|
weight_decay: 0.0
|
|
|
|
# Precision and performance
|
|
bf16: auto
|
|
tf32: true
|
|
|
|
# Logging and checkpointing
|
|
logging_steps: 10
|
|
save_strategy: steps
|
|
save_steps: 100
|
|
save_total_limit: 3
|
|
|
|
# Weights & Biases (optional)
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
# Special tokens
|
|
special_tokens:
|
|
pad_token: "<|endoftext|>"
|
|
|
|
# save_first_step: true # uncomment this to validate checkpoint saving works with your config
|