Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: Qwen/Qwen2.5-7B
bf16: true
chat_template: llama3
datasets:
- data_files:
  - 81a9c55afb29101d_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/81a9c55afb29101d_train_data.json
  type:
    field_input: question_body
    field_instruction: question_title
    field_output: tags
    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: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: true
group_by_length: false
hub_model_id: lesso11/ffbe4db1-c70b-4da9-bf75-f3a913391a9c
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
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
lr_scheduler: cosine
max_memory:
  0: 77GiB
max_steps: 50
micro_batch_size: 8
mlflow_experiment_name: /tmp/81a9c55afb29101d_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 25
save_strategy: steps
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: true
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: ffbe4db1-c70b-4da9-bf75-f3a913391a9c
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: ffbe4db1-c70b-4da9-bf75-f3a913391a9c
warmup_steps: 10
weight_decay: 0.01
xformers_attention: false

ffbe4db1-c70b-4da9-bf75-f3a913391a9c

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

  • Loss: 1.8966

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Use OptimizerNames.ADAMW_TORCH 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: 50

Training results

Training Loss Epoch Step Validation Loss
2.057 0.0035 1 2.1368
1.903 0.0176 5 2.1261
2.1421 0.0353 10 2.0246
1.8361 0.0529 15 1.9552
1.9907 0.0705 20 1.9234
1.9136 0.0882 25 1.9131
1.9985 0.1058 30 1.9048
1.9873 0.1235 35 1.9004
1.9818 0.1411 40 1.8975
1.8772 0.1587 45 1.8970
1.7014 0.1764 50 1.8966

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.0
  • Pytorch 2.5.0+cu124
  • Datasets 3.0.1
  • Tokenizers 0.20.1
Downloads last month
0
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for lesso11/ffbe4db1-c70b-4da9-bf75-f3a913391a9c

Base model

Qwen/Qwen2.5-7B
Adapter
(95)
this model