See axolotl config

axolotl version: 0.5.2

adapter: lora
auto_find_batch_size: true
base_model: dltjdgh0928/test_instruction
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 7bfc1f73c89d9947_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/7bfc1f73c89d9947_train_data.json
  type:
    field_instruction: instruction
    field_output: output
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: /workspace/axolotl/configs/deepspeed_stage2.json
eval_max_new_tokens: 128
eval_sample_packing: false
eval_steps: 10
eval_table_size: null
flash_attention: true
fp16: false
gpu_memory_limit: 80GiB
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: PhoenixB/b7ee4dc8-f35c-4be4-9cb5-381ff2d64c3c
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 2e-4
liger_fused_linear_cross_entropy: true
liger_glu_activation: true
liger_layer_norm: true
liger_rms_norm: true
liger_rope: true
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 5
lora_alpha: 16
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: 100
micro_batch_size: 2
mlflow_experiment_name: /tmp/7bfc1f73c89d9947_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch_fused
output_dir: miner_id_24
pad_to_sequence_len: true
plugins:
- axolotl.integrations.liger.LigerPlugin
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 10
sequence_len: 32768
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: fd16c759-8369-461a-8cdb-f22aa44f5a17
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: fd16c759-8369-461a-8cdb-f22aa44f5a17
warmup_steps: 10
weight_decay: 0.0

b7ee4dc8-f35c-4be4-9cb5-381ff2d64c3c

This model is a fine-tuned version of dltjdgh0928/test_instruction on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1392

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
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• total_eval_batch_size: 4
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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
No log	0.0001	1	0.8925
0.4113	0.0013	10	0.2989
0.1745	0.0026	20	0.1929
0.2395	0.0039	30	0.1848
0.1694	0.0051	40	0.1609
0.122	0.0064	50	0.1606
0.1695	0.0077	60	0.1522
0.131	0.0090	70	0.1440
0.1814	0.0103	80	0.1424
0.1302	0.0116	90	0.1394
0.1024	0.0129	100	0.1392

Framework versions

• PEFT 0.13.2
• Transformers 4.46.3
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3