See axolotl config
axolotl version: 0.4.0
base_model: meta-llama/Meta-Llama-3-8B
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: true
load_in_4bit: false
strict: false
datasets:
- path: kloodia/raw_bio
type: oasst
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./lora-out
sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true
adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 3
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002
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
s2_attention:
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:
pad_token: <|end_of_text|>
lora-out
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7317
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: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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: 10
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.795 | 0.0 | 1 | 1.8088 |
| 1.7519 | 0.25 | 137 | 1.7284 |
| 1.7442 | 0.5 | 274 | 1.7260 |
| 1.7182 | 0.75 | 411 | 1.7249 |
| 1.743 | 1.0 | 548 | 1.7237 |
| 1.7075 | 1.24 | 685 | 1.7265 |
| 1.7264 | 1.49 | 822 | 1.7267 |
| 1.6604 | 1.74 | 959 | 1.7260 |
| 1.6562 | 1.99 | 1096 | 1.7255 |
| 1.6455 | 2.22 | 1233 | 1.7308 |
| 1.6258 | 2.47 | 1370 | 1.7315 |
| 1.6792 | 2.72 | 1507 | 1.7317 |
| 1.6364 | 2.97 | 1644 | 1.7317 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0.dev0
- Pytorch 2.1.2+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 39