See axolotl config

axolotl version: 0.4.1

adapter: qlora
auto_resume_from_checkpoints: true
base_model: tiiuae/falcon-rw-1b
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 65dbaacc563afe36_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/65dbaacc563afe36_train_data.json
  type:
    field_input: input
    field_instruction: instruction
    field_output: output
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 4
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
flash_attention: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: error577/7681a1f8-bdf2-420a-8e2e-f666ce81f192
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 128
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: null
micro_batch_size: 2
mlflow_experiment_name: /tmp/65dbaacc563afe36_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch_4bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 100
sequence_len: 512
special_tokens:
  pad_token: <|endoftext|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.005
wandb_entity: null
wandb_mode: online
wandb_name: f654025e-8528-4441-9291-7085a15cfc33
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: f654025e-8528-4441-9291-7085a15cfc33
warmup_steps: 30
weight_decay: 0.0
xformers_attention: null

7681a1f8-bdf2-420a-8e2e-f666ce81f192

This model is a fine-tuned version of tiiuae/falcon-rw-1b on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3504

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_4BIT 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: 30
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
10.8178	0.0002	1	2.7038
1.2847	0.0249	100	0.4833
2.2278	0.0498	200	0.4151
1.3564	0.0747	300	0.4230
2.2454	0.0997	400	0.4007
1.2143	0.1246	500	0.3940
1.566	0.1495	600	0.3742
1.562	0.1744	700	0.3894
1.657	0.1993	800	0.3653
1.919	0.2242	900	0.3571
1.3022	0.2492	1000	0.3635
2.5185	0.2741	1100	0.3635
2.0116	0.2990	1200	0.3493
1.5989	0.3239	1300	0.3701
1.0495	0.3488	1400	0.3492
2.2359	0.3737	1500	0.3684
1.0462	0.3987	1600	0.3437
1.6378	0.4236	1700	0.3567
1.3856	0.4485	1800	0.3470
1.1789	0.4734	1900	0.3491
1.4038	0.4983	2000	0.3504

Framework versions

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