See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: fxmarty/tiny-random-GemmaForCausalLM
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 5e984ef82926d51e_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/5e984ef82926d51e_train_data.json
  type:
    field_instruction: text
    field_output: title
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 5
eval_max_new_tokens: 128
eval_steps: 50
eval_table_size: null
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 16
gradient_checkpointing: true
group_by_length: false
hub_model_id: Romain-XV/1e148d94-bb45-4d1d-b4ca-0c063dcc0c2a
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_best_model_at_end: true
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: true
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
lr_scheduler: cosine
max_steps: 518
micro_batch_size: 4
mlflow_experiment_name: /tmp/5e984ef82926d51e_train_data.json
model_type: AutoModelForCausalLM
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: 100
sequence_len: 1024
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: 1da19020-a378-4376-9353-43694df558e9
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 1da19020-a378-4376-9353-43694df558e9
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

1e148d94-bb45-4d1d-b4ca-0c063dcc0c2a

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

• Loss: nan

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: 4
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 64
• 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: 518

Training results

Training Loss	Epoch	Step	Validation Loss
0.0	0.0008	1	nan
0.0	0.0375	50	nan
0.0	0.0750	100	nan
0.0	0.1125	150	nan
0.0	0.1500	200	nan
0.0	0.1875	250	nan
0.0	0.2251	300	nan
0.0	0.2626	350	nan

Framework versions

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