See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/Hermes-2-Pro-Llama-3-8B
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 823d37b8588de3b9_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/823d37b8588de3b9_train_data.json
  type:
    field_input: question
    field_instruction: problem
    field_output: solution
    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: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: false
hub_model_id: dimasik87/de33f694-50e1-4884-8566-140c2e9ee8b8
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: 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: 70GiB
max_steps: 50
micro_batch_size: 1
mlflow_experiment_name: /tmp/823d37b8588de3b9_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 4
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 4
sequence_len: 2028
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: de33f694-50e1-4884-8566-140c2e9ee8b8
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: de33f694-50e1-4884-8566-140c2e9ee8b8
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

de33f694-50e1-4884-8566-140c2e9ee8b8

This model is a fine-tuned version of NousResearch/Hermes-2-Pro-Llama-3-8B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2001

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• 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
0.9466	0.0001	1	1.1514
0.886	0.0004	4	1.0636
0.6905	0.0007	8	0.6157
0.3233	0.0011	12	0.2960
0.1823	0.0015	16	0.2611
0.1479	0.0018	20	0.2346
0.2695	0.0022	24	0.2255
0.1645	0.0025	28	0.2141
0.1804	0.0029	32	0.2088
0.2318	0.0033	36	0.2063
0.1563	0.0036	40	0.2020
0.1512	0.0040	44	0.2004
0.1529	0.0044	48	0.2001

Framework versions

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