See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: fxmarty/tiny-dummy-qwen2
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 0dede6371eb018a8_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/0dede6371eb018a8_train_data.json
  type:
    field_instruction: label_name
    field_output: text
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 30
eval_max_new_tokens: 128
eval_steps: 50
eval_table_size: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 16
gradient_checkpointing: true
group_by_length: false
hub_model_id: Romain-XV/4f86287a-8d7f-482c-a3c5-f5469d9d434f
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: true
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
lr_scheduler: cosine
micro_batch_size: 4
mlflow_experiment_name: /tmp/0dede6371eb018a8_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
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: 04808d17-ba6e-4c71-9301-c50f7f6725a3
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 04808d17-ba6e-4c71-9301-c50f7f6725a3
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

4f86287a-8d7f-482c-a3c5-f5469d9d434f

This model is a fine-tuned version of fxmarty/tiny-dummy-qwen2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 11.9094

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
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
11.9329	0.0024	1	11.9330
11.9279	0.1184	50	11.9270
11.9171	0.2369	100	11.9180
11.911	0.3553	150	11.9126
11.9083	0.4738	200	11.9107
11.9095	0.5922	250	11.9100
11.9112	0.7107	300	11.9096
11.9072	0.8291	350	11.9094
11.91	0.9476	400	11.9094

Framework versions

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