See axolotl config

axolotl version: 0.4.1

base_model: meta-llama/Meta-Llama-3-8B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
max_steps: 
bnb_config_kwargs:
  llm_int8_has_fp16_weight: false
  bnb_4bit_quant_type: nf4
  bnb_4bit_use_double_quant: true

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: VinitT/Sanskrit-Llama_Base-Dataset
    type: alpaca
dataset_prepared_path:
val_set_size: 0
output_dir: ./outputs/qlora-out
chat_template: chatml
hub_model_id: VinitT/Sanskrit-llama
hf_use_auth_token: true
adapter: qlora
lora_model_dir:

sequence_len: 512
sample_packing: true
eval_sample_packing: false
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: 

gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
cosine_min_lr_ratio: 0.2
learning_rate: 1e-5

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

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: false

warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
#fsdp:
#  - full_shard
#  - auto_wrap
#fsdp_config:
#  fsdp_limit_all_gathers: true
#  fsdp_sync_module_states: true
#  fsdp_offload_params: true
#  fsdp_use_orig_params: false
#  fsdp_cpu_ram_efficient_loading: true
#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#  fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer
#  fsdp_state_dict_type: FULL_STATE_DICT
special_tokens:
  pad_token: "<|end_of_text|>"

Sanskrit-llama

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B 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: 4
• total_train_batch_size: 8
• 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: 10
• num_epochs: 1

Training results

Framework versions

• PEFT 0.11.1
• Transformers 4.42.4
• Pytorch 2.1.2
• Datasets 2.19.1
• Tokenizers 0.19.1