See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/Hermes-2-Pro-Mistral-7B
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 117de36e402a7d94_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/117de36e402a7d94_train_data.json
  type:
    field_instruction: prompt
    field_output: prompt_orig
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 3
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 300
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: true
hub_model_id: great0001/5f09db92-5ca5-49cb-84ae-02b50c1c2286
hub_strategy: end
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 50
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: constant
max_grad_norm: 1.0
max_memory:
  0: 75GB
max_steps: 7081
micro_batch_size: 4
mlflow_experiment_name: /tmp/117de36e402a7d94_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1e-5
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 300
saves_per_epoch: null
sequence_len: 512
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 3b9ff96b-31e0-46b0-8d32-6fc3cc74ffb8
wandb_project: SN56-33
wandb_run: your_name
wandb_runid: 3b9ff96b-31e0-46b0-8d32-6fc3cc74ffb8
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

5f09db92-5ca5-49cb-84ae-02b50c1c2286

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

• Loss: 0.5550

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• 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-5
• lr_scheduler_type: constant
• lr_scheduler_warmup_steps: 50
• training_steps: 7081

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0004	1	1.3902
1.9554	0.1199	300	0.5057
1.8121	0.2398	600	0.5014
1.7977	0.3597	900	0.4906
1.8518	0.4796	1200	0.5002
1.9762	0.5995	1500	0.5275
1.9397	0.7194	1800	0.5550

Framework versions

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