axolotl version: 0.5.0
#base_model: unsloth/Llama-3.2-3B
#base_model: anthracite-core/llama3.2-3b-chatml-v2
base_model: NewEden/L3.2-Erebus-Base
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: NewEden/Claude-Instruct-5K
type: chat_template
chat_template: chatml
roles_to_train: ["gpt"]
field_messages: conversations
message_field_role: from
message_field_content: value
train_on_eos: turn
- path: NewEden/Claude-Instruct-2.7K
type: chat_template
chat_template: chatml
roles_to_train: ["gpt"]
field_messages: conversations
message_field_role: from
message_field_content: value
train_on_eos: turn
- path: anthracite-org/kalo-opus-instruct-22k-no-refusal
type: chat_template
chat_template: chatml
roles_to_train: ["gpt"]
field_messages: conversations
message_field_role: from
message_field_content: value
train_on_eos: turn
chat_template: chatml
shuffle_merged_datasets: true
default_system_message: "Currently, your role is {{char}}, described in detail below. As {{char}}, continue the narrative exchange with {{user}}.\n\n<Guidelines>\n• Maintain the character persona but allow it to evolve with the story.\n• Be creative and proactive. Drive the story forward, introducing plotlines and events when relevant.\n• All types of outputs are encouraged; respond accordingly to the narrative.\n• Include dialogues, actions, and thoughts in each response.\n• Utilize all five senses to describe scenarios within {{char}}'s dialogue.\n• Use emotional symbols such as \"!\" and \"~\" in appropriate contexts.\n• Incorporate onomatopoeia when suitable.\n• Allow time for {{user}} to respond with their own input, respecting their agency.\n• Act as secondary characters and NPCs as needed, and remove them when appropriate.\n• When prompted for an Out of Character [OOC:] reply, answer neutrally and in plaintext, not as {{char}}.\n</Guidelines>\n\n<Forbidden>\n• Using excessive literary embellishments and purple prose unless dictated by {{char}}'s persona.\n• Writing for, speaking, thinking, acting, or replying as {{user}} in your response.\n• Repetitive and monotonous outputs.\n• Positivity bias in your replies.\n• Being overly extreme or NSFW when the narrative context is inappropriate.\n</Forbidden>\n\nFollow the instructions in <Guidelines></Guidelines>, avoiding the items listed in <Forbidden></Forbidden>."
dataset_prepared_path: 4b-erebus-lora
val_set_size: 0.0
output_dir: 4b-erebus-rslora-out
plugins:
- axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: true
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
wandb_project: 4b-erebus
wandb_entity:
wandb_watch:
wandb_name: base-attempt-01
wandb_log_model:
gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0001
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: /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <|finetune_right_pad_id|>
eos_token: <|eot_id|>
4b-erebus-rslora-out
This model is a fine-tuned version of NewEden/L3.2-Erebus-Base 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: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 40
- num_epochs: 2
Training results
Framework versions
- Transformers 4.46.1
- Pytorch 2.3.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.3