|
--- |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: llama3-8B |
|
model-index: |
|
- name: qlora_decrease_lr_promptfix |
|
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: llama3-8B |
|
model_type: LlamaForCausalLM |
|
tokenizer_type: AutoTokenizer |
|
|
|
load_in_8bit: false |
|
load_in_4bit: true |
|
strict: false |
|
|
|
datasets: |
|
- path: llama-3-8b-self-align-data-generation-results/sanitized.jsonl |
|
ds_type: json |
|
type: |
|
system_prompt: "You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions." |
|
field_system: system |
|
field_instruction: instruction |
|
field_output: response |
|
format: "### Instruction:\n{instruction}\n\n### Response:\n" |
|
no_input_format: "### Instruction:\n{instruction}\n\n### Response:\n" |
|
dataset_prepared_path: |
|
val_set_size: 0.05 |
|
|
|
sequence_len: 2048 |
|
sample_packing: true |
|
pad_to_sequence_len: true |
|
|
|
adapter: qlora |
|
save_safetensors: true |
|
lora_model_dir: |
|
lora_r: 64 |
|
lora_alpha: 32 |
|
lora_dropout: 0.05 |
|
lora_target_linear: true |
|
lora_fan_in_fan_out: |
|
|
|
log_with: None |
|
wandb_project: llama-3-8b-self-align-axolotl |
|
wandb_entity: |
|
wandb_watch: |
|
wandb_name: qlora-prince-hps-promptfix |
|
|
|
output_dir: qlora_decrease_lr_promptfix |
|
wandb_log_model: |
|
|
|
gradient_accumulation_steps: 8 |
|
micro_batch_size: 2 |
|
num_epochs: 4 |
|
optimizer: paged_adamw_32bit |
|
lr_scheduler: cosine |
|
learning_rate: 2e-5 |
|
|
|
train_on_inputs: false |
|
group_by_length: false |
|
bf16: auto |
|
fp16: |
|
tf32: false |
|
chat_template: alpaca |
|
|
|
gradient_checkpointing: true |
|
gradient_checkpointing_kwargs: |
|
use_reentrant: false |
|
early_stopping_patience: |
|
resume_from_checkpoint: |
|
local_rank: |
|
logging_steps: 1 |
|
xformers_attention: |
|
flash_attention: true |
|
|
|
warmup_steps: 100 |
|
evals_per_epoch: 8 |
|
eval_table_size: |
|
eval_max_new_tokens: 128 |
|
saves_per_epoch: 2 |
|
debug: |
|
deepspeed: |
|
weight_decay: 0.0 |
|
fsdp: |
|
- full_shard |
|
- auto_wrap |
|
fsdp_config: |
|
fsdp_limit_all_gathers: true |
|
fsdp_sync_module_states: false |
|
fsdp_offload_params: false |
|
fsdp_use_orig_params: false |
|
fsdp_cpu_ram_efficient_loading: false |
|
fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP |
|
fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer |
|
fsdp_state_dict_type: FULL_STATE_DICT |
|
fsdp_sharding_strategy: FULL_SHARD |
|
special_tokens: |
|
eos_token: "<|im_end|>" |
|
pad_token: "<|end_of_text|>" |
|
tokens: |
|
- "<|im_start|>" |
|
- "<|im_end|>" |
|
lora_modules_to_save: |
|
- embed_tokens |
|
- lm_head |
|
``` |
|
|
|
</details><br> |
|
|
|
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/muellerzr/llama-3-8b-self-align-axolotl/runs/2q8jhm3e) |
|
|
|
|
|
This model was trained from scratch on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4121 |
|
|
|
|
|
|
|
More information needed |
|
|
|
|
|
|
|
More information needed |
|
|
|
|
|
|
|
More information needed |
|
|
|
|
|
|
|
|
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 2e-05 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 32 |
|
- total_eval_batch_size: 4 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 100 |
|
- num_epochs: 4 |
|
|
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.6903 | 0.0061 | 1 | 0.6706 | |
|
| 0.6463 | 0.1285 | 21 | 0.6392 | |
|
| 0.4944 | 0.2571 | 42 | 0.4806 | |
|
| 0.4495 | 0.3856 | 63 | 0.4532 | |
|
| 0.4444 | 0.5142 | 84 | 0.4406 | |
|
| 0.4185 | 0.6427 | 105 | 0.4334 | |
|
| 0.4336 | 0.7712 | 126 | 0.4286 | |
|
| 0.4061 | 0.8998 | 147 | 0.4252 | |
|
| 0.4002 | 1.0145 | 168 | 0.4221 | |
|
| 0.4013 | 1.1431 | 189 | 0.4205 | |
|
| 0.3674 | 1.2716 | 210 | 0.4189 | |
|
| 0.3942 | 1.4002 | 231 | 0.4175 | |
|
| 0.3984 | 1.5287 | 252 | 0.4165 | |
|
| 0.3867 | 1.6572 | 273 | 0.4150 | |
|
| 0.3872 | 1.7858 | 294 | 0.4137 | |
|
| 0.401 | 1.9143 | 315 | 0.4130 | |
|
| 0.3602 | 2.0275 | 336 | 0.4126 | |
|
| 0.3817 | 2.1561 | 357 | 0.4131 | |
|
| 0.3592 | 2.2846 | 378 | 0.4129 | |
|
| 0.3729 | 2.4132 | 399 | 0.4127 | |
|
| 0.372 | 2.5417 | 420 | 0.4121 | |
|
| 0.3685 | 2.6702 | 441 | 0.4120 | |
|
| 0.3732 | 2.7988 | 462 | 0.4115 | |
|
| 0.38 | 2.9273 | 483 | 0.4112 | |
|
| 0.3637 | 3.0413 | 504 | 0.4114 | |
|
| 0.3628 | 3.1699 | 525 | 0.4118 | |
|
| 0.355 | 3.2984 | 546 | 0.4122 | |
|
| 0.3646 | 3.4269 | 567 | 0.4121 | |
|
| 0.3496 | 3.5555 | 588 | 0.4121 | |
|
| 0.3573 | 3.6840 | 609 | 0.4121 | |
|
| 0.3598 | 3.8125 | 630 | 0.4121 | |
|
| 0.3669 | 3.9411 | 651 | 0.4121 | |
|
|
|
|
|
|
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.42.0.dev0 |
|
- Pytorch 2.3.0+cu118 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
