See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/Mistral-Nemo-Base-2407
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - a1d6ef83d41c1a1f_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/a1d6ef83d41c1a1f_train_data.json
  type:
    field_input: masked_reference_solution
    field_instruction: question
    field_output: expected_answer
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device: cuda
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: true
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: dzanbek/1e243f6f-2b05-443b-bc61-db54cb213aac
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: 0.1
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: 2
mlflow_experiment_name: /tmp/a1d6ef83d41c1a1f_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: 2028
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 1e243f6f-2b05-443b-bc61-db54cb213aac
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 1e243f6f-2b05-443b-bc61-db54cb213aac
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

1e243f6f-2b05-443b-bc61-db54cb213aac

This model is a fine-tuned version of unsloth/Mistral-Nemo-Base-2407 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: 0.0002
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• 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	0.0023	1	nan
0.0	0.0114	5	nan
0.0	0.0228	10	nan
0.0	0.0343	15	nan
0.0	0.0457	20	nan
0.0	0.0571	25	nan
0.0	0.0685	30	nan
0.0	0.0800	35	nan
0.0	0.0914	40	nan
0.0	0.1028	45	nan
0.0	0.1142	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