|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: mistralai/Mistral-7B-v0.1 |
|
model-index: |
|
- name: qlora-out |
|
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: `0.3.0` |
|
```yaml |
|
base_model: mistralai/Mistral-7B-v0.1 |
|
model_type: MistralForCausalLM |
|
tokenizer_type: LlamaTokenizer |
|
is_mistral_derived_model: true |
|
|
|
load_in_8bit: false |
|
load_in_4bit: true |
|
strict: false |
|
|
|
datasets: |
|
- path: FriezaForce/unranked_theory_of_mind_roleplay |
|
type: alpaca |
|
dataset_prepared_path: last_run_prepared |
|
val_set_size: 0.1 |
|
output_dir: ./qlora-out |
|
|
|
adapter: qlora |
|
lora_model_dir: |
|
|
|
sequence_len: 2048 |
|
sample_packing: false |
|
pad_to_sequence_len: true |
|
|
|
lora_r: 128 |
|
lora_alpha: 256 |
|
lora_dropout: 0.05 |
|
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 |
|
|
|
wandb_project: |
|
wandb_entity: |
|
wandb_watch: |
|
wandb_name: |
|
wandb_log_model: |
|
|
|
gradient_accumulation_steps: 4 |
|
micro_batch_size: 4 |
|
num_epochs: 5 |
|
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 |
|
|
|
loss_watchdog_threshold: 5.0 |
|
loss_watchdog_patience: 3 |
|
|
|
warmup_steps: 10 |
|
evals_per_epoch: 4 |
|
eval_table_size: |
|
eval_table_max_new_tokens: 128 |
|
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> |
|
|
|
# qlora-out |
|
|
|
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. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.5515 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
|
|
The following `bitsandbytes` quantization config was used during training: |
|
- quant_method: bitsandbytes |
|
- load_in_8bit: False |
|
- load_in_4bit: True |
|
- llm_int8_threshold: 6.0 |
|
- llm_int8_skip_modules: None |
|
- llm_int8_enable_fp32_cpu_offload: False |
|
- llm_int8_has_fp16_weight: False |
|
- bnb_4bit_quant_type: nf4 |
|
- bnb_4bit_use_double_quant: True |
|
- bnb_4bit_compute_dtype: bfloat16 |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 0.0002 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 10 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.8421 | 0.06 | 1 | 1.8878 | |
|
| 1.637 | 0.24 | 4 | 1.6567 | |
|
| 1.7706 | 0.48 | 8 | 1.6450 | |
|
| 1.7509 | 0.73 | 12 | 1.6757 | |
|
| 1.4881 | 0.97 | 16 | 1.6913 | |
|
| 0.6743 | 1.21 | 20 | 1.8874 | |
|
| 0.6289 | 1.45 | 24 | 1.9861 | |
|
| 0.582 | 1.7 | 28 | 1.9449 | |
|
| 0.8624 | 1.94 | 32 | 1.8614 | |
|
| 0.2466 | 2.18 | 36 | 2.3687 | |
|
| 0.3151 | 2.42 | 40 | 2.3640 | |
|
| 0.2263 | 2.67 | 44 | 2.1331 | |
|
| 0.3841 | 2.91 | 48 | 2.2528 | |
|
| 0.1032 | 3.15 | 52 | 2.3878 | |
|
| 0.1015 | 3.39 | 56 | 2.5021 | |
|
| 0.1185 | 3.64 | 60 | 2.3578 | |
|
| 0.1111 | 3.88 | 64 | 2.3467 | |
|
| 0.042 | 4.12 | 68 | 2.4165 | |
|
| 0.0466 | 4.36 | 72 | 2.5006 | |
|
| 0.0509 | 4.61 | 76 | 2.5430 | |
|
| 0.0529 | 4.85 | 80 | 2.5515 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.0 |
|
- Transformers 4.37.0.dev0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
