Hugging Face's logo

lesso01
/
ac18793f-13e2-4312-b1a0-d2957d9b1349

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
ac18793f-13e2-4312-b1a0-d2957d9b1349 / README.md
lesso01's picture
lesso01
End of training
058cf61 verified
preview code
|
raw
history blame contribute delete
4.27 kB
metadata
library_name: peft
license: apache-2.0
base_model: JackFram/llama-68m
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: ac18793f-13e2-4312-b1a0-d2957d9b1349
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: JackFram/llama-68m
bf16: true
chat_template: llama3
datasets:
- data_files:
  - 931beb360369d6c0_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/931beb360369d6c0_train_data.json
  type:
    field_input: document_name
    field_instruction: text
    field_output: file_url
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: true
group_by_length: false
hub_model_id: lesso01/ac18793f-13e2-4312-b1a0-d2957d9b1349
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 80GiB
max_steps: 100
micro_batch_size: 8
mlflow_experiment_name: /tmp/931beb360369d6c0_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 25
save_strategy: steps
sequence_len: 1024
special_tokens:
  pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: ac18793f-13e2-4312-b1a0-d2957d9b1349
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: ac18793f-13e2-4312-b1a0-d2957d9b1349
warmup_steps: 10
weight_decay: 0.01
xformers_attention: false

ac18793f-13e2-4312-b1a0-d2957d9b1349

This model is a fine-tuned version of JackFram/llama-68m on the None dataset. It achieves the following results on the evaluation set:

  • Loss: nan

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: 0.0001
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Use OptimizerNames.ADAMW_TORCH 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: 10
  • training_steps: 100

Training results

Training Loss Epoch Step Validation Loss
0.0 0.0028 1 nan
0.0 0.0249 9 nan
0.0 0.0498 18 nan
0.0 0.0747 27 nan
0.0 0.0996 36 nan
0.0 0.1245 45 nan
0.0 0.1494 54 nan
0.0 0.1743 63 nan
0.0 0.1992 72 nan
0.0 0.2241 81 nan
0.0 0.2490 90 nan
0.0 0.2739 99 nan

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.0
  • Pytorch 2.5.0+cu124
  • Datasets 3.0.1
  • Tokenizers 0.20.1