Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/Nous-Hermes-llama-2-7b
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 9514728ea10d4b5e_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/9514728ea10d4b5e_train_data.json
  type:
    field_input: answer_prompt
    field_instruction: instructions
    field_output: gen_target
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 32
gradient_checkpointing: false
group_by_length: false
hub_model_id: kooff11/3efd3e47-99ad-4552-9b9d-57b7625b793c
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
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
- v_proj
lr_scheduler: cosine
max_memory:
  0: 130GiB
  1: 130GiB
max_steps: 20
micro_batch_size: 2
mlflow_experiment_name: /tmp/9514728ea10d4b5e_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
quantization_config:
  llm_int8_enable_fp32_cpu_offload: false
  load_in_8bit: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 4
sequence_len: 4056
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 3efd3e47-99ad-4552-9b9d-57b7625b793c
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 3efd3e47-99ad-4552-9b9d-57b7625b793c
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

3efd3e47-99ad-4552-9b9d-57b7625b793c

This model is a fine-tuned version of NousResearch/Nous-Hermes-llama-2-7b on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1396

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: 2
  • eval_batch_size: 2
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 32
  • total_train_batch_size: 128
  • total_eval_batch_size: 4
  • 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: 20

Training results

Training Loss Epoch Step Validation Loss
2.9208 0.0027 1 2.9215
2.2015 0.0136 5 1.4313
0.1487 0.0273 10 0.2616
0.1375 0.0409 15 0.2123
0.1314 0.0545 20 0.1396

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
16
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for kooff11/3efd3e47-99ad-4552-9b9d-57b7625b793c

Adapter
(29)
this model