NewEden/Erebus-3B-attempt1

See axolotl config

axolotl version: 0.4.1

#base_model: unsloth/Llama-3.2-3B
#base_model: anthracite-core/llama3.2-3b-chatml-v2
base_model: ./models/anthracite-core_llama3.2-3b-chatml-v2
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: Mielikki/Erebus-87k
    type: completion
    field: body
  # - path: anthracite-core/c2_logs_32k_llama3_qwen2_v1.2
  #   type: sharegpt
  #   conversation: mistral
  # - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
  #   type: sharegpt
  #   conversation: mistral
  # - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
  #   type: sharegpt
  #   conversation: mistral
  # - path: anthracite-org/nopm_claude_writing_fixed
  #   type: sharegpt
  #   conversation: mistral
  # - path: anthracite-org/kalo_opus_misc_240827
  #   type: sharegpt
  #   conversation: mistral
  # - path: anthracite-org/kalo_misc_part2
  #   type: sharegpt
  #   conversation: mistral
#chat_template: chatml
shuffle_merged_datasets: true
#default_system_message: "You are an assistant that responds to the user."
dataset_prepared_path: 4b-erebus-data
val_set_size: 0.0
output_dir: 4b-erebus-fft-out

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

sequence_len: 8192
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: 4b-erebus
wandb_entity:
wandb_watch:
wandb_name: base-attempt-01
wandb_log_model:

hub_model_id: NewEden/Erebus-4B-attempt1
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00001

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

gradient_checkpointing: true
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: /workspace/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>
  eos_token: <|eot_id|>

Erebus-4B-attempt1

This model was trained from scratch on the None dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 16
• total_train_batch_size: 32
• total_eval_batch_size: 2
• 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