See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: teknium/OpenHermes-2.5-Mistral-7B
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - de85f215f8150b43_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/de85f215f8150b43_train_data.json
  type:
    field_instruction: problem
    field_output: solution
    format: '{instruction}'
    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: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 6
gradient_checkpointing: true
group_by_length: false
hub_model_id: dimasik87/60e4a7a3-3717-4c5f-bb39-a019df8e7235
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: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 70GiB
max_steps: 50
micro_batch_size: 4
mlflow_experiment_name: /tmp/de85f215f8150b43_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: 2048
special_tokens:
  pad_token: <|im_end|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
torch_dtype: bfloat16
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 60e4a7a3-3717-4c5f-bb39-a019df8e7235
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 60e4a7a3-3717-4c5f-bb39-a019df8e7235
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

60e4a7a3-3717-4c5f-bb39-a019df8e7235

This model is a fine-tuned version of teknium/OpenHermes-2.5-Mistral-7B 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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 6
• total_train_batch_size: 24
• 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	0.0032	1	nan
0.0	0.0161	5	nan
0.0	0.0321	10	nan
0.0	0.0482	15	nan
0.0	0.0642	20	nan
0.0	0.0803	25	nan
0.0	0.0964	30	nan
0.0	0.1124	35	nan
0.0	0.1285	40	nan
0.0	0.1445	45	nan
0.0	0.1606	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