Hugging Face's logo

liuylhf
/
special-token-qkvo

PEFT
Safetensors
mixtral
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
special-token-qkvo / README.md
liuylhf's picture
liuylhf
End of training
35f7360 verified
preview code
|
raw
history blame
3.8 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - axolotl
  - generated_from_trainer
base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
model-index:
  - name: special-token-qkvo
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.0

adapter: qlora
base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
bf16: true
chat_template: inst
dataset_prepared_path: last_run_prepared
datasets:
- conversation: mistral
  path: 0f1c33b1bc764a9e88489e7d76eabe72/./data/with_function_response/original_clean/function_used_training.jsonl
  type: sharegpt
- conversation: mistral
  path: 0f1c33b1bc764a9e88489e7d76eabe72/./data/with_function_response/original_clean/function_not_used_training.jsonl
  type: sharegpt
- conversation: mistral
  path: 0f1c33b1bc764a9e88489e7d76eabe72/./data/with_function_response/parallel_call/parallel_data_training.jsonl
  type: sharegpt
debug: null
eval_max_new_tokens: 256
eval_steps: 0.2
eval_table_size: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: liuylhf/special-token-qkvo
learning_rate: 0.0002
load_in_4bit: true
load_in_8bit: false
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.05
lora_model_dir: null
lora_modules_to_save:
- embed_tokens
- lm_head
lora_r: 32
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
loss_watchdog_patience: 3
loss_watchdog_threshold: 5.0
lr_scheduler: cosine
micro_batch_size: 2
model_config:
  output_router_logits: true
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: paged_adamw_8bit
output_dir: 0f1c33b1bc764a9e88489e7d76eabe72/model
pad_to_sequence_len: true
sample_packing: true
save_steps: 0.1
sequence_len: 4096
strict: false
tf32: false
tokenizer_type: AutoTokenizer
tokens:
- '[f]'
- '[c]'
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_log_model: end
wandb_name: more-tools
wandb_project: function-call
warmup_steps: 10
weight_decay: 0.0

special-token-qkvo

This model is a fine-tuned version of mistralai/Mixtral-8x7B-Instruct-v0.1 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0876

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: 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: 1

Training results

Training Loss Epoch Step Validation Loss
2.2744 0.01 1 2.3107
0.1104 0.2 37 0.1094
0.0951 0.41 74 0.0959
0.0928 0.61 111 0.0905
0.0868 0.81 148 0.0876

Framework versions

  • PEFT 0.9.0
  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.0