See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
bf16: true
chat_template: llama3
datasets:
- data_files:
  - 78199c73a30c0a17_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/78199c73a30c0a17_train_data.json
  type:
    field_input: table
    field_instruction: question
    field_output: answer
    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/a1955f1f-5767-4c5e-8b2a-66856834d480
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/78199c73a30c0a17_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: a1955f1f-5767-4c5e-8b2a-66856834d480
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: a1955f1f-5767-4c5e-8b2a-66856834d480
warmup_steps: 10
weight_decay: 0.01
xformers_attention: false

a1955f1f-5767-4c5e-8b2a-66856834d480

This model is a fine-tuned version of NousResearch/Nous-Hermes-2-Mistral-7B-DPO 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: 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
0.0	0.0050	1	nan
0.0	0.0252	5	nan
0.0	0.0504	10	nan
0.0	0.0756	15	nan
0.0	0.1008	20	nan
0.0	0.1259	25	nan
0.0	0.1511	30	nan
0.0	0.1763	35	nan
0.0	0.2015	40	nan
0.0	0.2267	45	nan
0.0	0.2519	50	nan

Framework versions

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