library_name: peft
tags:
- generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.2
model-index:
- name: emissions-extraction-lora
results: []
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
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: nopperl/sustainability-report-emissions-instruction-style
type:
system_prompt: ""
field_instruction: prompt
field_output: completion
format: "[INST] {instruction} [/INST] I have extracted the Scope 1, 2 and 3 emission values from the document, converted them into metric tons and put them into the following json object:\n```json\n"
no_input_format: "[INST] {instruction} [/INST] I have extracted the Scope 1, 2 and 3 emission values from the document, converted them into metric tons and put them into the following json object:\n```json\n"
dataset_prepared_path:
val_set_size: 0
output_dir: ./emissions-extraction-lora
adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.1
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
sequence_len: 32768
sample_packing: false
pad_to_sequence_len: false
eval_sample_packing: false
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.000005
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
warmup_steps: 10
evals_per_epoch: 0
eval_table_size:
eval_table_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed: train_config/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
bos_token: "<s>"
eos_token: "</s>"
unk_token: "<unk>"
save_safetensors: true
emissions-extraction-lora
This is a LoRA for the mistralai/Mistral-7B-Instruct-v0.2 model finetuned on the nopperl/sustainability-report-emissions-instruction-style dataset.
Model description
Given text extracted from pages of a sustainability report, this model extracts the scope 1, 2 and 3 emissions in JSON format. The JSON object also contains the pages containing this information. For example, the 2022 sustainability report by the Bristol-Myers Squibb Company leads to the following output: {"scope_1":202290,"scope_2":161907,"scope_3":1696100,"sources":[88,89]}. For more information, refer to the GitHub repo.
Intended uses & limitations
The model is intended to be used together with the mistralai/Mistral-7B-Instruct-v0.2 model using the inference.py script from the GitHub repo. The script ensures that the prompt string and token ids exactly match the ones used for training.
Example usage:
python inference.py --model mistral --lora emissions-extraction-lora/ggml-adapter-model.bin https://www.bms.com/assets/bms/us/en-us/pdf/bmy-2022-esg-report.pdf
Compare to base model without LoRA:
python inference.py --model mistral https://www.bms.com/assets/bms/us/en-us/pdf/bmy-2022-esg-report.pdf
Training and evaluation data
Finetuned on the sustainability-report-emissions-instruction-style dataset.
Reaches an emission value extraction accuracy of 57% (up from 46% of the base model) and a source citation accuracy of 68% (base model: 52%) on the corporate-emission-reports dataset.
Training procedure
Trained on two A40 GPUs with ZeRO Stage 3 and FlashAttention 2. ZeRO-3 and FlashAttention 2 are necessary to just barely fit the sequence length of 32768 (without them, the max sequence length was 6144). The bloat16 datatype (and no quantization) was used. One epoch took roughly 3 hours.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- total_eval_batch_size: 2
- 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
Framework versions
- PEFT 0.7.0
- Transformers 4.37.1
- Pytorch 2.0.1
- Datasets 2.16.1
- Tokenizers 0.15.0