You can deploy this model and start earning money today!

romainnn/
535414a4-66d5-4d2b-ab1e-d6490f61a922

Name: 535414a4-66d5-4d2b-ab1e-d6490f61a922
Availability: InStock

generated_from_trainer

oopsung/llama2-7b-koNqa-test-v1

adapter

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
base_model: oopsung/llama2-7b-koNqa-test-v1
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 2aa15a3681945449_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/2aa15a3681945449_train_data.json
  type:
    field_instruction: prompt
    field_output: gold_standard_solution
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: romainnn/535414a4-66d5-4d2b-ab1e-d6490f61a922
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_best_model_at_end: true
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
lora_target_modules:
- q_proj
- k_proj
- v_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 1344
micro_batch_size: 4
mlflow_experiment_name: /tmp/2aa15a3681945449_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
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: 100
sequence_len: 2048
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.006433706445415791
wandb_entity: null
wandb_mode: online
wandb_name: 747b4d7f-063f-4aa9-9aba-12c76c3697a5
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 747b4d7f-063f-4aa9-9aba-12c76c3697a5
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

535414a4-66d5-4d2b-ab1e-d6490f61a922

This model is a fine-tuned version of oopsung/llama2-7b-koNqa-test-v1 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.6226

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: 8
total_train_batch_size: 32
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: 10
training_steps: 1344

Training results

Training Loss	Epoch	Step	Validation Loss
1.7469	0.0000	1	1.8583
0.8163	0.0041	100	0.7862
0.7514	0.0083	200	0.7376
0.6684	0.0124	300	0.7114
0.7101	0.0166	400	0.6887
0.5704	0.0207	500	0.6746
0.5891	0.0249	600	0.6617
0.6217	0.0290	700	0.6511
0.6322	0.0332	800	0.6414
0.552	0.0373	900	0.6346
0.6941	0.0414	1000	0.6291
0.6391	0.0456	1100	0.6253
0.6176	0.0497	1200	0.6232
0.5881	0.0539	1300	0.6226

Framework versions

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