See axolotl config
axolotl version: 0.4.0
base_model: mistralai/Mixtral-8x7B-v0.1
model_type: AutoModelForCausalLM
tokenizer_type: LlamaTokenizer
trust_remote_code: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: YoungPanda/chatlaw
type: sharegpt
conversation: chatml # default: vicuna_v1.1
- path: jondurbin/airoboros-3.2
type: sharegpt
conversation: chatml # default: vicuna_v1.1
- path: new_data.jsonl
ds_type: json
type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./qlora-out
## You can optionally freeze the entire model and unfreeze a subset of parameters
unfrozen_parameters:
# - ^lm_head.weight$
# - ^model.embed_tokens.weight$[:32000]
# - model.layers.2[0-9]+.block_sparse_moe.gate
# - model.layers.2[0-9]+.block_sparse_moe.experts
# - model.layers.3[0-9]+.block_sparse_moe.gate
# - model.layers.3[0-9]+.block_sparse_moe.experts
model_config:
output_router_logits: true
adapter: #qlora
lora_model_dir:
sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true
lora_r: #32
lora_alpha: #16
lora_dropout: #0.05
lora_target_linear:
lora_fan_in_fan_out:
#lora_target_modules:
# - gate
# - q_proj
# - k_proj
# - v_proj
# - o_proj
# - w1
# - w2
# - w3
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 3
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002
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
save_safetensors: true
loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3
warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed: deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp_config:
special_tokens:
bos_token: "<s>"
eos_token: "</s>"
unk_token: "<unk>"
tokens: # these are delimiters
- "<|im_start|>"
- "<|im_end|>"
qlora-out
This model is a fine-tuned version of mistralai/Mixtral-8x7B-v0.1 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: 0.0002
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 16
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 3
Training results
Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.1.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.0
- Downloads last month
- 8