OnlyThings/OnlyChats-v1.7.7-L3.1-lora

See axolotl config

axolotl version: 0.6.0

base_model: meta-llama/Meta-Llama-3.1-70B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: true
strict: false
chat_template: llama3

datasets:
  - path: Undi95/OGOF_Conv_Filtered
    type: chat_template
    chat_template: llama3
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user:
        - human
      assistant:
        - gpt
      system:
        - system
  - path: Undi95/LLM_OFDUMP_WITHMASSDM
    type: chat_template
    chat_template: llama3
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    roles:
      user:
        - human
      assistant:
        - gpt
      system:
        - system
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./lora-out

adapter: lora
lora_model_dir:

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: OnlyChats-v1.7.6-L3.1-70B-dupes-lora
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 6
optimizer: paged_adamw_32bit
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: 10
evals_per_epoch: 4
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: "<|end_of_text|>"
save_safetensors: true

lora-out

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-70B-Instruct on the Undi95/OGOF_Conv_Filtered and the Undi95/LLM_OFDUMP_WITHMASSDM datasets.

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: 8e-06
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 4
• total_eval_batch_size: 4
• optimizer: Use OptimizerNames.PAGED_ADAMW 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: 10
• num_epochs: 6.0

Training results

Framework versions

• PEFT 0.14.0
• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0