underwoods/medius-erebus-magnum-14b

See axolotl config

axolotl version: 0.4.1

base_model: /workspace/medius-erebus
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

hub_model_id: magnum-erebus-14b-v1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-core/c2_logs_32k_llama3_qwen2_v1.2
    type: sharegpt
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: sharegpt
  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
    type: sharegpt
  - path: anthracite-org/nopm_claude_writing_fixed
    type: sharegpt
  - path: anthracite-org/kalo_opus_misc_240827
    type: sharegpt
  - path: anthracite-org/kalo_misc_part2
    type: sharegpt
chat_template: chatml
shuffle_merged_datasets: true
default_system_message: "You are an assistant that responds to the user."
dataset_prepared_path: /workspace/data/magnum-14b-data
val_set_size: 0.0
output_dir: /workspace/data/magnum-erebus-14b-fft

sequence_len: 32768
sample_packing: true
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
lora_fan_in_fan_out:

wandb_project: 14b-magnum-fft
wandb_entity:
wandb_watch:
wandb_name: v4-r2-erebus-attempt-1
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.000008

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: deepspeed_configs/zero3_bf16.json
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:

medius-erebus-magnum

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 8e-06
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 16
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 40
• num_epochs: 2

Training results

Framework versions

• Transformers 4.45.1
• Pytorch 2.3.1+cu121
• Datasets 2.21.0
• Tokenizers 0.20.0