cheater-7b

<!-- 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: cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer

load_in_8bit: true
load_in_4bit: false
strict: false

datasets:
  - path: ./julia/data.jsonl
    type: sharegpt
    conversation: chatml
dataset_prepared_path: ./julia/prepared_data
chat_template: chatml
val_set_size: 0.05
output_dir: ./julia/lora-out
hub_model_id: animmina/cheater-7b
hub_strategy: every_save
hf_use_auth_token: true

sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false

adapter: lora
lora_model_dir:
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: cheater-7b
wandb_entity:
wandb_watch:
wandb_name: v02
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 4
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00003

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: 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: "<|im_end|>"
  unk_token: "<unk>"

</details><br>

cheater-7b

This model is a fine-tuned version of cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser on 11 test cases from the Julia LLM Leaderboard. It achieves the following results on the evaluation set:

• Loss: 0.5741

Model description

Simple LORA adapter (rank: 8).

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: 3e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• num_epochs: 4

Training results

Framework versions

• PEFT 0.9.0
• Transformers 4.38.2
• Pytorch 2.1.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.0