See axolotl config

axolotl version: 0.4.0

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

load_in_8bit: false
load_in_4bit: true
strict: false

chat_template: chatml
datasets:
  - path: winglian/financial_phrasebank_augmented
    type: sharegpt
    split: train
    strict: false
test_datasets:
  - path: winglian/financial_phrasebank_augmented-validation
    type: sharegpt
    split: train
    strict: false
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./finetuned-out
hub_model_id: winglian/financial-phrasebank-sentiment-reasoning

adapter: lora
lora_model_dir:

sequence_len: 768 
sample_packing: false
pad_to_sequence_len: false

lora_r: 32
lora_alpha: 16
lora_dropout: 0.1
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: financial-phrasebank-reasoning
wandb_entity: oaaic
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00001

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

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:
  eos_token: "<|im_end|>"
tokens:
  - "<|im_start|>"

financial-phrasebank-sentiment-reasoning

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: 0.6457

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: 1e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_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: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.1125	0.0	1	1.3634
0.4981	0.25	71	0.7488
0.3236	0.5	142	0.6989
0.2667	0.76	213	0.6727
0.2922	1.01	284	0.6553
0.2897	1.26	355	0.6526
0.3039	1.51	426	0.6491
0.2948	1.77	497	0.6462
0.2858	2.02	568	0.6440
0.2795	2.27	639	0.6448
0.1904	2.52	710	0.6463
0.2829	2.77	781	0.6457

Framework versions

• PEFT 0.9.1.dev0
• Transformers 4.39.0.dev0
• Pytorch 2.1.2+cu118
• Datasets 2.18.0
• Tokenizers 0.15.0