metadata
license: llama3
library_name: peft
tags:
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B
model-index:
- name: outputs/lora-out
results: []
See axolotl config
axolotl version: 0.4.1
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: Peaky8linders/euro-summary-alpaca
type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/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:
lora_modules_to_save:
- embed_tokens
- lm_head
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4
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|>
outputs/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: 0.0000
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- 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
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4887 | 0.0202 | 1 | 0.4672 |
| 0.0 | 0.2626 | 13 | 0.0001 |
| 0.0 | 0.5253 | 26 | 0.0000 |
| 0.0 | 0.7879 | 39 | 0.0000 |
| 0.0 | 1.0303 | 52 | 0.0000 |
| 0.0 | 1.2929 | 65 | 0.0000 |
| 0.0 | 1.5556 | 78 | 0.0000 |
| 0.0 | 1.8182 | 91 | 0.0000 |
| 0.0 | 2.0606 | 104 | 0.0000 |
| 0.0 | 2.3232 | 117 | 0.0000 |
| 0.0 | 2.5859 | 130 | 0.0000 |
| 0.0 | 2.8485 | 143 | 0.0000 |
| 0.0 | 3.0909 | 156 | 0.0000 |
| 0.0 | 3.3535 | 169 | 0.0000 |
| 0.0 | 3.6162 | 182 | 0.0000 |
| 0.0 | 3.8788 | 195 | 0.0000 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.1.2+cu118
- Datasets 2.19.1
- Tokenizers 0.19.1