You can deploy this model and start earning money today!

0x1202/
388af280-06a7-45fa-ac84-aa62113888d9

Name: 388af280-06a7-45fa-ac84-aa62113888d9
Availability: InStock

generated_from_trainer

NousResearch/Hermes-2-Pro-Llama-3-8B

adapter

llama3

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
base_model: NousResearch/Hermes-2-Pro-Llama-3-8B
bf16: auto
chat_template: llama3
data_processes: 16
dataset_prepared_path: null
datasets:
- data_files:
  - 6d6407602e45a4f3_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/6d6407602e45a4f3_train_data.json
  type:
    field_input: pythoncode
    field_instruction: prompt
    field_output: answer
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 1
eval_batch_size: 1
eval_max_new_tokens: 128
eval_steps: 25
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 32
gradient_checkpointing: true
group_by_length: true
hub_model_id: 0x1202/388af280-06a7-45fa-ac84-aa62113888d9
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0003
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_grad_norm: 1.0
max_memory:
  0: 70GB
max_steps: 200
micro_batch_size: 1
mlflow_experiment_name: /tmp/6d6407602e45a4f3_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
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: 50
saves_per_epoch: null
sequence_len: 1028
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 50
wandb_entity: null
wandb_mode: online
wandb_name: 388af280-06a7-45fa-ac84-aa62113888d9
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 388af280-06a7-45fa-ac84-aa62113888d9
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

388af280-06a7-45fa-ac84-aa62113888d9

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: 0.0398

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: 0.0003
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 32
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-5
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss
11.1334	0.0096	1	10.3080
0.0002	0.2388	25	0.5137
0.0001	0.4776	50	0.2329
0.0	0.7164	75	0.0725
0.0	0.9552	100	0.0931
0.0001	1.1940	125	0.0821
0.0	1.4328	150	0.0616
0.0	1.6716	175	0.0435
0.0	1.9104	200	0.0398

Framework versions

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