|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- axolotl |
|
- dpo |
|
- trl |
|
- dpo |
|
- generated_from_trainer |
|
base_model: mistralai/Mistral-7B-v0.1 |
|
model-index: |
|
- name: mistral-7b-base-dpo-run |
|
results: [] |
|
--- |
|
|
|
<!-- 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"/>](https://github.com/OpenAccess-AI-Collective/axolotl) |
|
<details><summary>See axolotl config</summary> |
|
|
|
axolotl version: `0.4.0` |
|
```yaml |
|
base_model: mistralai/Mistral-7B-v0.1 |
|
base_model_ignore_patterns: [] |
|
base_model_config: mistralai/Mistral-7B-v0.1 |
|
model_revision: |
|
tokenizer_config: |
|
model_type: AutoModelForCausalLM |
|
tokenizer_type: AutoTokenizer |
|
trust_remote_code: true |
|
tokenizer_use_fast: true |
|
tokenizer_legacy: true |
|
resize_token_embeddings_to_32x: false |
|
|
|
is_falcon_derived_model: false |
|
is_llama_derived_model: false |
|
is_mistral_derived_model: true |
|
is_qwen_derived_model: false |
|
|
|
model_config: |
|
rope_scaling: |
|
|
|
bnb_config_kwargs: |
|
|
|
gptq: false |
|
gptq_groupsize: |
|
gptq_model_v1: false |
|
|
|
load_in_8bit: false |
|
load_in_4bit: true |
|
|
|
fp16: true |
|
|
|
lora_on_cpu: false |
|
|
|
rl: dpo |
|
datasets: |
|
- path: NobodyExistsOnTheInternet/Fixed-gutenberg-dpo-v0.1 |
|
split: train |
|
type: chatml.intel |
|
- path: NobodyExistsOnTheInternet/Fixed-Distilabel-intel-orca-dpo-pairs |
|
split: train |
|
type: chatml.intel |
|
- path: NobodyExistsOnTheInternet/ToxicDPOqa |
|
split: train |
|
type: chatml.intel |
|
- path: NobodyExistsOnTheInternet/system-message-DPO |
|
split: train |
|
type: chatml.intel |
|
- path: NobodyExistsOnTheInternet/alpaca-intel-data-dpo |
|
split: train |
|
type: chatml.intel |
|
- path: NobodyExistsOnTheInternet/ToxicDPOqa |
|
split: train |
|
type: chatml.intel |
|
|
|
|
|
chat_template: chatml |
|
default_system_message: Generate a preferable answer. |
|
dataset_prepared_path: data/last_run_prepared |
|
push_dataset_to_hub: |
|
dataset_processes: |
|
dataset_keep_in_memory: |
|
hub_model_id: NobodyExistsOnTheInternet/mistral-7b-base-dpo-run |
|
hub_strategy: every_save |
|
hf_use_auth_token: true |
|
val_set_size: 0 |
|
dataset_shard_num: |
|
dataset_shard_idx: |
|
|
|
sequence_len: 1024 |
|
sample_packing: false |
|
eval_sample_packing: |
|
sample_packing_eff_est: |
|
total_num_tokens: |
|
|
|
device_map: |
|
max_memory: |
|
|
|
adapter: qlora |
|
lora_model_dir: |
|
|
|
lora_r: 32 |
|
lora_alpha: 64 |
|
lora_dropout: 0.05 |
|
lora_target_linear: true |
|
lora_target_module: |
|
|
|
lora_modules_to_save: |
|
- embed_tokens |
|
- lm_head |
|
lora_fan_in_fan_out: |
|
|
|
wandb_project: dpo-hermes-2.5 |
|
wandb_entity: |
|
wandb_watch: |
|
wandb_name: |
|
wandb_run_id: |
|
wandb_log_model: |
|
|
|
mlflow_tracking_uri: |
|
mlflow_experiment_name: |
|
|
|
output_dir: ./completed-model |
|
|
|
torch_compile: true |
|
gradient_accumulation_steps: 4 |
|
micro_batch_size: 1 |
|
eval_batch_size: |
|
num_epochs: 2 |
|
warmup_steps: 100 |
|
warmup_ratio: |
|
learning_rate: 0.000001 |
|
lr_quadratic_warmup: |
|
logging_steps: |
|
eval_steps: |
|
evals_per_epoch: |
|
save_strategy: steps |
|
save_steps: 1000 |
|
saves_per_epoch: |
|
save_total_limit: |
|
eval_table_size: |
|
eval_max_new_tokens: |
|
eval_causal_lm_metrics: |
|
|
|
loss_watchdog_threshold: |
|
loss_watchwatchdog_patience: |
|
|
|
train_on_inputs: false |
|
group_by_length: false |
|
|
|
gradient_checkpointing: true |
|
gradient_checkpointing_kwargs: |
|
use_reentrant: false |
|
|
|
lr_scheduler: |
|
|
|
optimizer: paged_adamw_8bit |
|
weight_decay: 0.01 |
|
adam_beta1: 0.95 |
|
adam_beta2: 0.999 |
|
adam_epsilon: 0.0000001 |
|
|
|
neftune_noise_alpha: 5 |
|
|
|
flash_optimum: |
|
xformers_attention: |
|
flash_attention: true |
|
flash_attn_cross_entropy: |
|
flash_attn_rms_norm: |
|
flash_attn_fuse_qkv: |
|
flash_attn_fuse_mlp: |
|
sdp_attention: |
|
s2_attention: |
|
resume_from_checkpoint: |
|
auto_resume_from_checkpoints: false |
|
|
|
local_rank: |
|
|
|
tokens: |
|
|
|
fsdp: |
|
fsdp_config: |
|
|
|
deepspeed: |
|
|
|
ddp_timeout: |
|
ddp_bucket_cap_mb: |
|
ddp_broadcast_buffers: |
|
|
|
torchdistx_path: |
|
|
|
pretraining_dataset: |
|
|
|
debug: |
|
|
|
seed: |
|
|
|
``` |
|
|
|
</details><br> |
|
|
|
# mistral-7b-base-dpo-run |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset. |
|
|
|
## 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-06 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 4 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 16 |
|
- total_eval_batch_size: 32 |
|
- optimizer: Adam with betas=(0.95,0.999) and epsilon=1e-07 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 100 |
|
- training_steps: 15031 |
|
|
|
### Training results |
|
|
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.8.2 |
|
- Transformers 4.38.0 |
|
- Pytorch 2.2.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
