See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: katuni4ka/tiny-random-falcon-40b
bf16: false
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 93d9886916e01068_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/93d9886916e01068_train_data.json
  type:
    field_instruction: utterance
    field_output: semantic_parse
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
devices:
- 0
- 1
- 2
- 3
- 4
- 5
- 6
- 7
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: 4
gradient_checkpointing: false
group_by_length: false
hub_model_id: jssky/a5daa407-e03b-4c0e-a434-cbfb1f57aff6
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: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_steps: 10
micro_batch_size: 1
mlflow_experiment_name: /tmp/93d9886916e01068_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
num_gpus: 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
saves_per_epoch: 4
sequence_len: 4056
special_tokens:
  pad_token: <|endoftext|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_batch_size: 32
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: a5daa407-e03b-4c0e-a434-cbfb1f57aff6
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: a5daa407-e03b-4c0e-a434-cbfb1f57aff6
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

a5daa407-e03b-4c0e-a434-cbfb1f57aff6

This model is a fine-tuned version of katuni4ka/tiny-random-falcon-40b on the None dataset. It achieves the following results on the evaluation set:

• Loss: 11.0403

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: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• total_eval_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB 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: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
44.4846	0.0001	1	11.1092
44.4614	0.0003	3	11.1038
44.4082	0.0007	6	11.0816
44.2531	0.0010	9	11.0403

Framework versions

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