See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: Qwen/Qwen2.5-7B-Instruct
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - e3cffd1d6d2bc346_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/e3cffd1d6d2bc346_train_data.json
  type:
    field_input: endings
    field_instruction: ctx_a
    field_output: ctx_b
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: false
group_by_length: false
hub_model_id: leixa/34cc3756-3fd4-46e7-87b5-ba9e57d6cb24
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: 0
logging_steps: 3
lora_alpha: 128
lora_dropout: 0.1
lora_fan_in_fan_out: true
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_steps: 500
micro_batch_size: 4
mlflow_experiment_name: /tmp/e3cffd1d6d2bc346_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: false
sample_packing: false
saves_per_epoch: 4
sequence_len: 512
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: leixa-personal
wandb_mode: online
wandb_name: 34cc3756-3fd4-46e7-87b5-ba9e57d6cb24
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 34cc3756-3fd4-46e7-87b5-ba9e57d6cb24
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

34cc3756-3fd4-46e7-87b5-ba9e57d6cb24

This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: nan

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: 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: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0006	1	nan
1.4067	0.0238	42	nan
1.4301	0.0477	84	nan
1.2709	0.0715	126	nan
1.1093	0.0953	168	nan
1.4336	0.1192	210	nan
1.0939	0.1430	252	nan
0.5194	0.1669	294	nan
1.1726	0.1907	336	nan
0.6855	0.2145	378	nan
0.9775	0.2384	420	nan
0.6243	0.2622	462	nan

Framework versions

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