Hugging Face's logo

bitext
/
Mistral-7B-Customer-Support

Text Generation
Transformers
PyTorch
Safetensors
mistral
axolotl
Generated from Trainer
text-generation-inference
conversational
Model card Files Community
1
Mistral-7B-Customer-Support / README.md
malmarjeh's picture
malmarjeh
Update README.md
57a0f95 verified
preview code
|
raw
history blame
3.81 kB
metadata
license: apache-2.0
library_name: peft
inference: true
pipeline_tag: text-generation
tags:
  - axolotl
  - generated_from_trainer
  - text-generation-inference
base_model: mistralai/Mistral-7B-Instruct-v0.2

Built with Axolotl

See axolotl config

axolotl version: 0.4.0

base_model: mistralai/Mistral-7B-Instruct-v0.2
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true

hub_model_id: malmarjeh/Mistral-7B-instruct-v0.2

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: bitext/Bitext-customer-support-llm-chatbot-training-dataset
    type:
      system_prompt: "You are an expert in customer support."
      field_instruction: instruction
      field_output: response
      format: "[INST] {instruction} [/INST]"
      no_input_format: "[INST] {instruction} [/INST]"
      
#datasets:
#  - path: json
#    type: alpaca_w_system.load_open_orca
#data_files: file.zip

dataset_prepared_path:

val_set_size: 0.05
output_dir: ./qlora-out

adapter: qlora
lora_model_dir:

sequence_len: 1024
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
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: axolotl
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 8
num_epochs: 1
optimizer: adamw_bnb_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

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:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"

Mistral-7B-instruct-v0.2

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7667

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • 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
1.6865 0.01 1 2.0557
0.6351 0.25 32 0.8355
0.5724 0.5 64 0.7859
0.5249 0.75 96 0.7711
0.516 1.0 128 0.7667

Framework versions

  • PEFT 0.10.1.dev0
  • Transformers 4.40.0.dev0
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.0