See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/mistral-7b-v0.3
bf16: true
chat_template: llama3
dataloader_num_workers: 24
dataset_prepared_path: null
datasets:
- data_files:
  - e6a79d4047b4de0a_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/e6a79d4047b4de0a_train_data.json
  type:
    field_instruction: user
    field_output: chip2
    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: 2
eval_max_new_tokens: 128
eval_steps: 500
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: false
group_by_length: true
hub_model_id: arcwarden46/d3b96371-1fe9-476d-967e-d640b85481ff
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: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 5000
micro_batch_size: 4
mlflow_experiment_name: /tmp/e6a79d4047b4de0a_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1000
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.999
  adam_epsilon: 1e-8
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: 500
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: 0334cf54-2e76-4e9b-ac0f-c48d8c7532a1
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 0334cf54-2e76-4e9b-ac0f-c48d8c7532a1
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

d3b96371-1fe9-476d-967e-d640b85481ff

This model is a fine-tuned version of unsloth/mistral-7b-v0.3 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8963

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: 2
• seed: 42
• gradient_accumulation_steps: 8
• 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=0.999,adam_epsilon=1e-8
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss
8.1935	0.0002	1	1.6503
5.163	0.0802	500	1.1166
6.5552	0.1604	1000	1.0699
6.6385	0.2406	1500	1.0042
4.668	0.3208	2000	0.9929
4.778	0.4010	2500	0.9526
5.1346	0.4812	3000	0.9267
4.0962	0.5614	3500	0.9098
4.1541	0.6417	4000	0.9013
4.6333	0.7219	4500	0.8972
4.5676	0.8021	5000	0.8963

Framework versions

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