axolotl version: 0.4.0
base_model: JackFram/llama-68m
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: /data/data/final_set_cleaned/train/
type: sharegpt
conversation: chatml
- path: /data/data/map_coig_cqia.jsonl
type: sharegpt
conversation: chatml
- path: /data/data/ruozhiba.jsonl
type: sharegpt
conversation: chatml
dataset_prepared_path: last_run_prepared
val_set_size: 0
output_dir: ./out
sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 8
micro_batch_size: 4
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 2e-5
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 100
evals_per_epoch: 0
eval_table_size:
saves_per_epoch: 4
debug:
deepspeed: deepspeed/zero2.json
weight_decay: 0.0
fsdp:
fsdp_config:
default_system_message: "You are a helpful assistant."
special_tokens:
eos_token: "<|im_end|>"
pad_token: "<|end_of_text|>"
tokens:
- "<|im_start|>"
- "<|im_end|>"
data/llama-68m-20240502-0037
This model is a fine-tuned version of JackFram/llama-68m 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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 6
- gradient_accumulation_steps: 8
- total_train_batch_size: 192
- total_eval_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 2
Training results
Framework versions
- Transformers 4.40.1
- Pytorch 2.0.1+cu118
- Datasets 2.15.0
- Tokenizers 0.19.1