See axolotl config

axolotl version: 0.12.1

adapter: lora
base_model: samoline/2ef5d586-50e6-4f2e-a6eb-ad6b1d4c4b69
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 875bc234fee76007_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/
  type:
    field_input: input
    field_instruction: instruct
    field_output: output
    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: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: false
hub_model_id: eason668/6fa535e6-25e7-4009-b06c-f6dc400fc5d2
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_steps: 10
micro_batch_size: 2
mlflow_experiment_name: /tmp/875bc234fee76007_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
saves_per_epoch: 4
sequence_len: 512
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: offline
wandb_name: bebb9e3d-5b46-4742-91e1-ba81a90b3337
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: bebb9e3d-5b46-4742-91e1-ba81a90b3337
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

6fa535e6-25e7-4009-b06c-f6dc400fc5d2

This model is a fine-tuned version of samoline/2ef5d586-50e6-4f2e-a6eb-ad6b1d4c4b69 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6267
• Memory/max Mem Active(gib): 26.66
• Memory/max Mem Allocated(gib): 26.66
• Memory/device Mem Reserved(gib): 27.11

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_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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Mem Active(gib)	Mem Allocated(gib)	Mem Reserved(gib)
No log	0	0	0.6268	16.87	16.87	17.23
0.695	0.0002	3	0.6268	26.66	26.66	27.08
0.6261	0.0004	6	0.6267	26.66	26.66	27.11
0.4308	0.0006	9	0.6267	26.66	26.66	27.11

Framework versions

• PEFT 0.17.0
• Transformers 4.55.0
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.4