See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: fxmarty/really-tiny-falcon-testing
bf16: true
chat_template: llama3
datasets:
- data_files:
  - 2d75da559a891ff1_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/2d75da559a891ff1_train_data.json
  type:
    field_input: legal_term
    field_instruction: judgment_chunk
    field_output: summary
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 5
eval_table_size: null
flash_attention: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: false
hub_model_id: lesso10/a7c57234-fde2-414f-bd26-b954804d5948
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: true
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: 50
micro_batch_size: 4
mlflow_experiment_name: /tmp/2d75da559a891ff1_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
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: 10
sequence_len: 1024
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: 1b97ca28-5569-4f21-bf43-913c71accac7
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 1b97ca28-5569-4f21-bf43-913c71accac7
warmup_steps: 5
weight_decay: 0.0
xformers_attention: null

a7c57234-fde2-414f-bd26-b954804d5948

This model is a fine-tuned version of fxmarty/really-tiny-falcon-testing on the None dataset. It achieves the following results on the evaluation set:

• Loss: 11.0337

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• 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: 5
• training_steps: 50

Training results

Training Loss	Epoch	Step	Validation Loss
44.3435	0.0000	1	11.0855
44.321	0.0002	5	11.0825
44.278	0.0003	10	11.0690
44.2487	0.0005	15	11.0619
44.2342	0.0007	20	11.0534
44.1804	0.0008	25	11.0463
44.159	0.0010	30	11.0416
44.1507	0.0012	35	11.0378
44.1369	0.0013	40	11.0350
44.1435	0.0015	45	11.0339
44.1407	0.0017	50	11.0337

Framework versions

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