base_model: meta-llama/Meta-Llama-3-8B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: manishiitg/aditi-syn-train-v3
    type: completion
  

# 25 has only sythentic data, and has judge removed data 
# 26 = 25 + caybara + robots
hub_model_id: manishiitg/open-aditi-chat-hi-1.26-llama3
hf_use_auth_token: true

wandb_project: open-aditi-chat-hi-1.26-llama3

dataset_prepared_path: manishiitg
push_dataset_to_hub: manishiitg
val_set_size: .1
output_dir: /sky-notebook/manishiitg/open-aditi-chat-hi-1.26-llama3

adapter: qlora
lora_model_dir:
save_safetensors: true

sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false

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

wandb_entity:
wandb_watch:
wandb_run_id:
wandb_log_model:

gradient_accumulation_steps: 8
micro_batch_size: 6
num_epochs: 1
optimizer: paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 0.0002

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


gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
auto_resume_from_checkpoints: true ## manage check point resume from here
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
evals_per_epoch: 2
eval_table_size:
eval_table_max_new_tokens: 128
save_steps: 20 ## increase based on your dataset
save_strategy: steps
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|end_of_text|>

open-aditi-chat-hi-1.26-llama3

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.1448

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: 0.0002
train_batch_size: 6
eval_batch_size: 6
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 8
total_train_batch_size: 384
total_eval_batch_size: 48
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

Training Loss	Epoch	Step	Validation Loss
1.4205	0.01	1	1.5139
0.7895	0.5	73	1.1448

Framework versions

PEFT 0.9.0
Transformers 4.40.0.dev0
Pytorch 2.1.2+cu121
Datasets 2.18.0
Tokenizers 0.15.0