Dans-DiscountModels/Dans-Instruct-Mix-8b-ChatML-V0.2.0

See axolotl config

axolotl version: 0.4.1

base_model: Dans-DiscountModels/Meta-Llama-3.1-8B-ChatML
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code:

# wandb configuration
wandb_project: l3.1-8b-dans-instruct
wandb_watch:
wandb_run_id: attempt-03
wandb_log_model:

# push checkpoints to hub
hub_model_id: anthracite-core/Dans-L3.1-Test
# how to push checkpoints to hub
# https://huggingface.co/docs/transformers/v4.31.0/en/main_classes/trainer#transformers.TrainingArguments.hub_strategy
hub_strategy: "all_checkpoints"
# Whether to use hf `use_auth_token` for loading datasets. Useful for fetching private datasets
# Required to be true when used in combination with `push_dataset_to_hub`
hf_use_auth_token: true

# where to save the finished model to
output_dir: ./l3.1-8b-dans-instruct

# dataset settings (local or huggingface repo)
datasets:
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: dan-chat
  - path: AquaV/Energetic-Materials-Sharegpt
    type: dan-chat
  - path: AquaV/Chemical-Biological-Safety-Applications-Sharegpt
    type: dan-chat
  - path: AquaV/US-Army-Survival-Sharegpt
    type: dan-chat
  - path: AquaV/Resistance-Sharegpt
    type: dan-chat
  - path: AquaV/Interrogation-Sharegpt
    type: dan-chat
  - path: AquaV/Multi-Environment-Operations-Sharegpt
    type: dan-chat
  - path: PocketDoc/Dans-Mathmaxx
    type: dan-chat
  - path: PJMixers/Math-Multiturn-1K-ShareGPT
    type: dan-chat
  - path: PocketDoc/Dans-Benchmaxx
    type: dan-chat
  - path: PocketDoc/Dans-Codemaxx-LeetCode
    type: dan-chat
  - path: PocketDoc/Dans-Codemaxx-CodeFeedback-Conversations
    type: dan-chat
  - path: PocketDoc/Dans-Codemaxx-CodeFeedback-SingleTurn
    type: dan-chat
  - path: PocketDoc/Dans-Taskmaxx
    type: dan-chat
  - path: PocketDoc/Dans-Taskmaxx-DataPrepper
    type: dan-chat
  - path: PocketDoc/Dans-Taskmaxx-ConcurrentQA-Reworked
    type: dan-chat
  - path: PocketDoc/Dans-Toolmaxx-Agent
    type: dan-chat
  - path: PocketDoc/Dans-Toolmaxx-ShellCommands
    type: dan-chat
  - path: PocketDoc/Dans-ASCIIMaxx-Wordart
    type: dan-chat
  - path: PocketDoc/Dans-Prosemaxx-Gutenberg
    type: dan-chat
  - path: PocketDoc/Dans-Prosemaxx-Cowriter-XS
    type: dan-chat
  - path: PocketDoc/Dans-Prosemaxx-Adventure
    type: dan-chat
  - path: PocketDoc/Dans-Prosemaxx-Opus-Writing
    type: dan-chat
  - path: PocketDoc/Dans-Assistantmaxx-Sharegpt
    type: dan-chat
  - path: PocketDoc/Dans-Assistantmaxx-OpenAssistant2
    type: dan-chat
  - path: PocketDoc/Dans-Assistantmaxx-Opus-instruct-1
    type: dan-chat
  - path: PocketDoc/Dans-Assistantmaxx-Opus-instruct-2
    type: dan-chat
  - path: PocketDoc/Dans-Assistantmaxx-Opus-instruct-3
    type: dan-chat
  - path: PocketDoc/Dans-Assistantmaxx-NoRobots
    type: dan-chat
  - path: PocketDoc/Dans-Personamaxx
    type: dan-chat
  - path: PocketDoc/DansTestYard
    type: completion
    
chat_template: chatml

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

dataset_prepared_path: ./l3.1-8b-dans-instruct-data
val_set_size: 0.0

sequence_len: 8192

sample_packing: true
eval_sample_packing: false

pad_to_sequence_len: true

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false

gradient_accumulation_steps: 2
micro_batch_size: 2

num_epochs: 3

optimizer: adamw_torch

lr_scheduler: cosine
learning_rate: 0.0000015
cosine_min_lr_ratio: 

adam_beta1: 0.9
adam_beta2: 0.95
adam_epsilon: 0.00000001

weight_decay: 0.01

max_grad_norm: 20

train_on_inputs: false
group_by_length: true

bf16: true
fp16: false
tf32: false

early_stopping_patience:

resume_from_checkpoint:
auto_resume_from_checkpoints:

local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_ratio: 0.1
saves_per_epoch: 2

debug: false

deepspeed: deepspeed_configs/zero2.json

fsdp:
fsdp_config:

special_tokens:
  pad_token: <|finetune_right_pad_id|>
  eos_token: <|im_end|>

Dans-L3.1-Test

This model is a fine-tuned version of Dans-DiscountModels/Meta-Llama-3.1-8B-ChatML 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: 1.5e-06
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 230
• num_epochs: 3

Training results

Framework versions

• Transformers 4.45.0.dev0
• Pytorch 2.3.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1