metadata
library_name: peft
license: apache-2.0
base_model: unsloth/tinyllama-chat
tags:
- axolotl
- generated_from_trainer
model-index:
- name: cdf861c6-72a4-41b4-ac3f-a9bb00013b19
results: []
See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: unsloth/tinyllama-chat
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 11bfdd43471b04af_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/11bfdd43471b04af_train_data.json
type:
field_instruction: question
field_output: response
format: '{instruction}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 1
eval_max_new_tokens: 128
eval_steps: 25
eval_table_size: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 16
gradient_checkpointing: true
group_by_length: true
hub_model_id: jssky/cdf861c6-72a4-41b4-ac3f-a9bb00013b19
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: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_steps: 50
micro_batch_size: 2
mlflow_experiment_name: /tmp/11bfdd43471b04af_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
sequence_len: 2048
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: cdf861c6-72a4-41b4-ac3f-a9bb00013b19
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: cdf861c6-72a4-41b4-ac3f-a9bb00013b19
warmup_ratio: 0.05
weight_decay: 0.01
xformers_attention: null
cdf861c6-72a4-41b4-ac3f-a9bb00013b19
This model is a fine-tuned version of unsloth/tinyllama-chat on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6460
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: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- total_eval_batch_size: 8
- 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: 2
- training_steps: 50
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.9528 | 0.0012 | 1 | 0.8671 |
0.3753 | 0.0310 | 25 | 0.6584 |
0.3556 | 0.0621 | 50 | 0.6460 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1