metadata
library_name: peft
base_model: oopsung/llama2-7b-n-ox-test-v1
tags:
- axolotl
- generated_from_trainer
model-index:
- name: a3da2374-35fa-4202-9d7c-76441bafae87
results: []
See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: oopsung/llama2-7b-n-ox-test-v1
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 4d79fb1fb8c5e535_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/4d79fb1fb8c5e535_train_data.json
type:
field_instruction: prompt
field_output: text
format: '{instruction}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 3
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 300
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: true
hub_model_id: great0001/a3da2374-35fa-4202-9d7c-76441bafae87
hub_strategy: end
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 50
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: constant
max_grad_norm: 1.0
max_memory:
0: 75GB
max_steps: 6115
micro_batch_size: 4
mlflow_experiment_name: /tmp/4d79fb1fb8c5e535_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optim_args:
adam_beta1: 0.9
adam_beta2: 0.95
adam_epsilon: 1e-5
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 300
saves_per_epoch: null
sequence_len: 512
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 8a8a88d9-a691-4f54-9486-9182caa88758
wandb_project: SN56-33
wandb_run: your_name
wandb_runid: 8a8a88d9-a691-4f54-9486-9182caa88758
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null
a3da2374-35fa-4202-9d7c-76441bafae87
This model is a fine-tuned version of oopsung/llama2-7b-n-ox-test-v1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1485
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 50
- training_steps: 6115
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0002 | 1 | 1.9852 |
| 1.3236 | 0.0507 | 300 | 1.3126 |
| 1.2706 | 0.1014 | 600 | 1.2655 |
| 1.2347 | 0.1520 | 900 | 1.2386 |
| 1.2262 | 0.2027 | 1200 | 1.2222 |
| 1.1851 | 0.2534 | 1500 | 1.2076 |
| 1.2077 | 0.3041 | 1800 | 1.1966 |
| 1.1848 | 0.3547 | 2100 | 1.1903 |
| 1.1881 | 0.4054 | 2400 | 1.1822 |
| 1.1857 | 0.4561 | 2700 | 1.1781 |
| 1.1703 | 0.5068 | 3000 | 1.1698 |
| 1.1637 | 0.5575 | 3300 | 1.1645 |
| 1.165 | 0.6081 | 3600 | 1.1589 |
| 1.152 | 0.6588 | 3900 | 1.1553 |
| 1.1557 | 0.7095 | 4200 | 1.1511 |
| 1.1591 | 0.7602 | 4500 | 1.1488 |
| 1.1438 | 0.8108 | 4800 | 1.1451 |
| 1.1348 | 0.8615 | 5100 | 1.1438 |
| 1.1426 | 0.9122 | 5400 | 1.1393 |
| 1.1468 | 0.9629 | 5700 | 1.1358 |
| 0.9472 | 1.0136 | 6000 | 1.1485 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1