Hugging Face's logo

venetis
/
llama3-8b-hermes-sandals-sample-10k

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
llama3-8b-hermes-sandals-sample-10k / README.md
venetis's picture
venetis
End of training
b9aa706 verified
preview code
|
raw
history blame
No virus
3.88 kB
metadata
license: llama3
library_name: peft
tags:
  - axolotl
  - generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B
model-index:
  - name: llama3-8b-hermes-sandals-sample-10k
    results: []

Built with Axolotl

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: false
load_in_4bit: false
strict: false

datasets:
  - path: ./data/openhermes2_5_10k.jsonl
    type: sharegpt
    conversation: llama3
dataset_prepared_path: 
val_set_size: 0.15
output_dir: ./outputs_lora-out
hub_model_id: venetis/llama3-8b-hermes-sandals-sample-10k

data_seed: 117
seed: 117

chat_template: llama3
adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:


sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
wandb_project: llama-3-8b-hermes-sandals-sample-10k
wandb_entity: venetispall

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 2e-4

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|>

llama3-8b-hermes-sandals-sample-10k

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: 0.7611

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: 117
  • 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
0.918 0.0102 1 0.9709
0.7146 0.2538 25 0.7678
0.728 0.5076 50 0.7419
0.6843 0.7614 75 0.7328
0.6819 1.0152 100 0.7259
0.6342 1.2487 125 0.7269
0.616 1.5025 150 0.7298
0.7092 1.7563 175 0.7250
0.6453 2.0102 200 0.7224
0.5267 2.2411 225 0.7425
0.5702 2.4949 250 0.7424
0.5459 2.7487 275 0.7421
0.6327 3.0025 300 0.7428
0.5649 3.2335 325 0.7573
0.4318 3.4873 350 0.7617
0.5523 3.7411 375 0.7611

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.2
  • Pytorch 2.1.2+cu118
  • Datasets 2.19.1
  • Tokenizers 0.19.1