Downloads · 30 days
2
13% of all-time downloads
ahmedelgebaly/llama-3.1-8b-squadv2_SciQ_e1_v2
llama-3.1-8b-squadv2_SciQ_e1_v2 is a machine learning model from ahmedelgebaly. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as llama3.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
2
13% of all-time downloads
All-time downloads
15
Public
Repo size
2 GB
Likes
0
Public
Click a slice to open those files.
.bin671 MB · 49%
From the Hugging Face model README
axolotl version: 0.4.1
base_model: meta-llama/Meta-Llama-3.1-8B # same model you originally used
peft_model: ahmedelgebaly/llama-3.1-8b-squadv2
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
- path: ahmedelgebaly/SciQ_Alpaca
type: alpaca
split: train
test_datasets:
- path: ahmedelgebaly/SciQ_Alpaca
type: alpaca
split: validation
dataset_prepared_path:
output_dir: ./outputs/qlora-out
adapter: qlora
lora_model_dir:
sequence_len: 2048 # Halves memory usage decreasing from 4096
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true
lora_r: 64 # Increased from 32
lora_alpha: 32 # Increased from 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:
wandb_project: llama-3.1-8b-squadv2_SciQ_e1_v2
wandb_entity:
wandb_watch:
wandb_name: llama-3.1-8b-squadv2-v0_SciQ_e1_v2
wandb_log_model:
hub_model_id: ahmedelgebaly/llama-3.1-8b-squadv2_SciQ_e1_v2
gradient_accumulation_steps: 32 # Keeps effective batch size=64 (2x32)
micro_batch_size: 2 # Decrreses from 4
num_epochs: 1
optimizer: paged_adamw_32bit
lr_scheduler: cosine_with_restarts # Updated
learning_rate: 0.0001 # Reduced from 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
warmup_steps: 100 # Increased from 10
evals_per_epoch: 4
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
pad_token: "<|end_of_text|>"
</details><br>
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B on the None dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8006 | 0.0598 | 1 | 1.8330 |
| 1.7825 | 0.2393 | 4 | 1.8315 |
| 1.7629 | 0.4785 | 8 | 1.8140 |
| 1.6663 | 0.7178 | 12 | 1.7312 |
| 1.5168 | 0.9570 | 16 | 1.5100 |