See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: fxmarty/tiny-random-GemmaForCausalLM
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 1e8160f019383753_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/1e8160f019383753_train_data.json
  type:
    field_input: wrong_code
    field_instruction: description
    field_output: correct_code
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_clipping: 1.0
group_by_length: false
hub_model_id: dixedus/8f4afc96-d841-4c0a-ba51-143c8993abdd
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: 0
logging_steps: 3
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: 200
micro_batch_size: 8
mlflow_experiment_name: /tmp/1e8160f019383753_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
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: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: techspear-hub
wandb_mode: online
wandb_name: 8a435482-b6aa-45bf-8c77-6d77e14a0f91
wandb_project: Gradients-On-Eight
wandb_run: your_name
wandb_runid: 8a435482-b6aa-45bf-8c77-6d77e14a0f91
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

8f4afc96-d841-4c0a-ba51-143c8993abdd

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: 12.4424

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• 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: 200

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0008	1	12.4506
12.4487	0.0128	17	12.4504
12.4509	0.0257	34	12.4501
12.4478	0.0385	51	12.4495
12.4508	0.0514	68	12.4486
12.4457	0.0642	85	12.4475
12.4479	0.0771	102	12.4461
12.4446	0.0899	119	12.4448
12.4432	0.1028	136	12.4436
12.4425	0.1156	153	12.4429
12.4421	0.1284	170	12.4425
12.4442	0.1413	187	12.4424

Framework versions

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