Hugging Face's logo

SystemAdmin123
/
llama-68m

Text Generation
Transformers
Safetensors
llama
axolotl
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
llama-68m / README.md
SystemAdmin123's picture
SystemAdmin123
End of training
f0c17a7 verified
preview code
|
raw
history blame
3.88 kB
metadata
library_name: transformers
license: apache-2.0
base_model: JackFram/llama-68m
tags:
  - axolotl
  - generated_from_trainer
datasets:
  - argilla/databricks-dolly-15k-curated-en
model-index:
  - name: llama-68m
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.6.0

base_model: JackFram/llama-68m
batch_size: 64
bf16: true
chat_template: tokenizer_default_fallback_alpaca
datasets:
- format: custom
  path: argilla/databricks-dolly-15k-curated-en
  type:
    field_input: original-instruction
    field_instruction: original-instruction
    field_output: original-response
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
device_map: auto
eval_sample_packing: false
eval_steps: 50
flash_attention: true
gradient_checkpointing: true
group_by_length: true
hub_model_id: SystemAdmin123/llama-68m
hub_strategy: checkpoint
learning_rate: 0.0002
logging_steps: 10
lr_scheduler: cosine
max_steps: 5000
micro_batch_size: 32
model_type: AutoModelForCausalLM
num_epochs: 100
optimizer: adamw_bnb_8bit
output_dir: /root/.sn56/axolotl/tmp/llama-68m
pad_to_sequence_len: true
resize_token_embeddings_to_32x: false
sample_packing: true
save_steps: 50
save_total_limit: 2
sequence_len: 2048
special_tokens:
  pad_token: </s>
tokenizer_type: LlamaTokenizerFast
torch_dtype: bf16
trust_remote_code: true
val_set_size: 0.1
wandb_entity: ''
wandb_mode: online
wandb_name: JackFram/llama-68m-argilla/databricks-dolly-15k-curated-en
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: default
warmup_ratio: 0.05

llama-68m

This model is a fine-tuned version of JackFram/llama-68m on the argilla/databricks-dolly-15k-curated-en dataset. It achieves the following results on the evaluation set:

  • Loss: 4.0103

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: 32
  • eval_batch_size: 32
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • total_train_batch_size: 64
  • total_eval_batch_size: 64
  • optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 30
  • training_steps: 600

Training results

Training Loss Epoch Step Validation Loss
No log 0.0769 1 3.9168
2.5978 3.8462 50 2.8149
2.0808 7.6923 100 2.9664
1.6294 11.5385 150 3.2337
1.2699 15.3846 200 3.5217
1.0092 19.2308 250 3.7262
0.8392 23.0769 300 3.8683
0.7428 26.9231 350 3.9435
0.6952 30.7692 400 3.9860
0.6762 34.6154 450 3.9990
0.6739 38.4615 500 4.0167
0.6691 42.3077 550 4.0208
0.6667 46.1538 600 4.0103

Framework versions

  • Transformers 4.48.1
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.21.0