You can deploy this model and start earning money today!

sniperfix/
83c2acf8-f255-4c90-ac05-9d082dc20fe6

Name: 83c2acf8-f255-4c90-ac05-9d082dc20fe6
Availability: InStock

generated_from_trainer

elyza/Llama-3-ELYZA-JP-8B

adapter

llama3

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
base_model: elyza/Llama-3-ELYZA-JP-8B
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 8a34c82f4fcec0a6_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/8a34c82f4fcec0a6_train_data.json
  type:
    field_instruction: question
    field_output: answer
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 256
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 32
gradient_checkpointing: true
group_by_length: false
hub_model_id: sniperfix/83c2acf8-f255-4c90-ac05-9d082dc20fe6
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 3
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- gate_proj
- down_proj
- up_proj
lr_scheduler: cosine
max_grad_norm: 2
max_steps: 90
micro_batch_size: 2
mlflow_experiment_name: /tmp/8a34c82f4fcec0a6_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1.0e-05
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 4
sequence_len: 2048
special_tokens:
  pad_token: <|eot_id|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: indexjupri-sniper-country
wandb_mode: online
wandb_name: 17b9b016-89d5-45c6-b81d-c0c6e8acb440
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 17b9b016-89d5-45c6-b81d-c0c6e8acb440
warmup_steps: 20
weight_decay: 0.02
xformers_attention: false

83c2acf8-f255-4c90-ac05-9d082dc20fe6

This model is a fine-tuned version of elyza/Llama-3-ELYZA-JP-8B on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3653

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: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 32
total_train_batch_size: 64
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-05
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 20
training_steps: 90

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0014	1	0.6262
0.5672	0.0108	8	0.5123
0.4491	0.0216	16	0.4523
0.4339	0.0325	24	0.4225
0.4056	0.0433	32	0.4043
0.39	0.0541	40	0.3920
0.3748	0.0649	48	0.3831
0.3694	0.0758	56	0.3761
0.3612	0.0866	64	0.3714
0.3548	0.0974	72	0.3679
0.3634	0.1082	80	0.3658
0.3592	0.1190	88	0.3653

Framework versions

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