See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: echarlaix/tiny-random-mistral
bf16: true
chat_template: llama3
dataloader_num_workers: 24
dataset_prepared_path: null
datasets:
- data_files:
  - 757dd5c118de8497_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/757dd5c118de8497_train_data.json
  type:
    field_instruction: Question
    field_output: Response
    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: 4
gradient_checkpointing: false
group_by_length: true
hub_model_id: abaddon182/9db6cbba-2a7f-4aa3-98b7-fa898ca8f99a
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: 50
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_grad_norm: 1.0
max_steps: 5000
micro_batch_size: 2
mlflow_experiment_name: /tmp/757dd5c118de8497_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.999
  adam_epsilon: 1e-8
optimizer: adamw_torch_fused
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
special_tokens:
  pad_token: </s>
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: 98636a02-2a9f-4056-ad93-8df106611163
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 98636a02-2a9f-4056-ad93-8df106611163
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

9db6cbba-2a7f-4aa3-98b7-fa898ca8f99a

This model is a fine-tuned version of echarlaix/tiny-random-mistral on the None dataset. It achieves the following results on the evaluation set:

• Loss: 10.2680

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: 4
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 50
• training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0003	1	10.3793
41.1971	0.1679	500	10.2975
41.1498	0.3359	1000	10.2845
41.1189	0.5038	1500	10.2774
41.1108	0.6718	2000	10.2739
41.0997	0.8397	2500	10.2709
41.0859	1.0076	3000	10.2694
41.0844	1.1756	3500	10.2687
41.0804	1.3435	4000	10.2683
41.09	1.5115	4500	10.2681
41.0899	1.6794	5000	10.2680

Framework versions

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