RyanYr/pm

See axolotl config

axolotl version: 0.4.1

adapter: null
base_model: /var/lib/condor/execute/slot1/dir_873933/llama_model
bf16: auto
dataset_prepared_path: /var/lib/condor/execute/slot1/dir_873933/prepare
dataset_processes: 48
datasets:
- conversation: llama-3
  path: RLHFlow/pair-preference-dataset-mix1
  split: train
  train_on_split: train
  type: sharegpt.load_ultrachat
ddp: null
debug: null
deepspeed: null
early_stopping_patience: null
eval_steps: null
eval_table_max_new_tokens: null
eval_table_size: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
learning_rate: 5.0e-06
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 2
lora_model_dir: null
lr_scheduler: cosine
max_grad_norm: 1.0
micro_batch_size: 2
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_torch_fused
output_dir: /var/lib/condor/execute/slot1/dir_873933/output
pad_to_sequence_len: true
sample_packing: true
save_safetensors: true
save_strategy: epoch
save_total_limit: 1
sequence_len: 3072
special_tokens: null
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.0
wandb_log_model: null
wandb_name: llama-8b-it_data-preference_mix3_bs128_lr5e-6
wandb_watch: null
warmup_steps: 40
weight_decay: 0.0
xformers_attention: null

var/lib/condor/execute/slot1/dir_873933/output

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: 5e-06
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 40
• num_epochs: 1

Training results

Framework versions

• Transformers 4.42.4
• Pytorch 2.1.2+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1