See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 4b9f7432feb5e651_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/4b9f7432feb5e651_train_data.json
  type:
    field_instruction: instruction
    field_output: response
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 5
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 50
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: ardaspear/3035acbb-208c-45e8-b45a-42740f4e387f
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
lora_alpha: 128
lora_dropout: 0.3
lora_fan_in_fan_out: null
lora_model_dir: null
lora_modules_to_save:
- lm_head
lora_r: 64
lora_target_linear: true
loraplus_lr_ratio: 8
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
  0: 75GB
max_steps: 600
micro_batch_size: 8
mlflow_experiment_name: /tmp/4b9f7432feb5e651_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1.0e-05
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
peft_use_rslora: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 150
saves_per_epoch: null
sequence_len: 1024
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: techspear-hub
wandb_mode: online
wandb_name: 11001b84-0290-4dbe-ace2-7cce8778af71
wandb_project: Gradients-On-Five
wandb_run: your_name
wandb_runid: 11001b84-0290-4dbe-ace2-7cce8778af71
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

3035acbb-208c-45e8-b45a-42740f4e387f

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: 7.2856

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: 8
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-05
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• training_steps: 600

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0006	1	1.4292
83.1917	0.0307	50	31.8326
55.4798	0.0613	100	18.1148
34.554	0.0920	150	9.6674
31.387	0.1226	200	8.8578
30.4714	0.1533	250	8.1497
30.6027	0.1839	300	7.7460
32.9979	0.2146	350	8.0175
32.1933	0.2452	400	7.4365
30.9719	0.2759	450	7.3362
30.6896	0.3065	500	7.3630
30.1351	0.3372	550	7.2547
31.064	0.3678	600	7.2856

Framework versions

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