See axolotl config

axolotl version: 0.4.0

base_model: meta-llama/Llama-2-7b-hf
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: vicgalle/alpaca-gpt4
    type: alpaca
    conversations: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.001
output_dir: ./outputs/out_llama2_alpaca
hub_model_id: flydust/Llama-2-7b-Alpaca52k-GPT4

sequence_len: 4096
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 2e-5

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

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
flash_attn_cross_entropy: false
flash_attn_rms_norm: true
flash_attn_fuse_qkv: false
flash_attn_fuse_mlp: true

warmup_ratio: 0.03
evals_per_epoch: 3
eval_table_size:
saves_per_epoch: 1
debug:
weight_decay: 0.
fsdp:
fsdp_config:
special_tokens:

Llama-2-7b-Alpaca52k-GPT4

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7849

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: 2e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• 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: 10
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss
1.0592	0.0111	1	1.1104
0.8995	0.3343	30	0.8043
0.8809	0.6685	60	0.7920
0.8642	1.0028	90	0.7868
0.8402	1.3231	120	0.7844
0.8093	1.6574	150	0.7841
0.8071	1.9916	180	0.7804
0.7532	2.3120	210	0.7853
0.7667	2.6462	240	0.7844
0.7555	2.9805	270	0.7836
0.7569	3.3008	300	0.7851
0.7634	3.6351	330	0.7849

Framework versions

• Transformers 4.40.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1