bts_mistral_7b_v3_32k_LoRA

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

<details><summary>See axolotl config</summary>

axolotl version: 0.4.0

base_model: mistralai/Mistral-7B-v0.1
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer

load_in_8bit: true
load_in_4bit: false
strict: false

datasets:
  - path: jspr/bts-long-gpt-4-32k-0314-prompt
    type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./out

# using lora for lower cost
adapter: lora
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
  - q_proj
  - v_proj

sequence_len: 4096
sample_packing: false # makes it faster but uses more memory
pad_to_sequence_len: false

model_config:
  rope_scaling:
    type: linear
    factor: 8.0

hub_model_id: jspr/bts_mistral_7b_v3_32k
hub_strategy: end
hub_private_repo: true

wandb_project: bts
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

# only 2 epochs because of small dataset
gradient_accumulation_steps: 3
micro_batch_size: 2
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
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: 4
eval_table_size:
eval_max_new_tokens: 16
eval_sample_packing: false
saves_per_epoch: 1
debug:

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

</details><br>

bts_mistral_7b_v3_32k

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.8543

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
• gradient_accumulation_steps: 3
• total_train_batch_size: 6
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• num_epochs: 2

Training results

Framework versions

• PEFT 0.9.0
• Transformers 4.39.0.dev0
• Pytorch 2.1.2+cu118
• Datasets 2.17.1
• Tokenizers 0.15.0