metadata
license: other
- wand (still internal, needs to be moved to public-sft)
- checkpoint: 3319 steps
Note
In order to load this model you need to install a pre-release version of the Huggingface transformers library.
Model Configuration
llama2_13b_orca_8k:
rng_seed: 0xe1291f1a
use_custom_sampler: true
sort_by_length: false
dtype: fp16
log_dir: "llama2_log_13b_orca_8k"
learning_rate: 1e-5
model_name: /mnt/data/llama2/Llama-2-13b-hf/
output_dir: llama2_13b_orca_8k
deepspeed_config: configs/zero_config_pretrain.json
weight_decay: 0.0
max_length: 8192
warmup_steps: 100
use_flash_attention: true
gradient_checkpointing: true
gradient_accumulation_steps: 8
per_device_train_batch_size: 2
per_device_eval_batch_size: 1
residual_dropout: 0.0
eval_steps: 200
save_steps: 1000 # (total steps: 3319)
num_train_epochs: 1
save_total_limit: 4
superhot: true
superhot_config:
type: linear
scale: 2
datasets:
# Dataset Composition:
# Tain (sampled):
# orca-chat: 100.00% (188842)
# fanfics: 100.00% (47760)
# red_pajama: 25.00% (188262)
# Valid:
# orca-chat: 5000 (71.43%)
# fanfics: 1000 (14.29%)
# red_pajama: 1000 (14.29%)
- orca-chat:
max_val_set: 5000
- fanfics:
max_chunk_size: 65535
max_val_set: 1000
- red_pajama:
fraction: 0.25
max_val_set: 1000
max_chunk_size: 65535
peft_model: false