adapter: qlora
auto_find_batch_size: true
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - ede7429851ef5df2_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/ede7429851ef5df2_train_data.json
  type:
    field_input: input
    field_instruction: instruction
    field_output: output
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
eval_max_new_tokens: 128
eval_sample_packing: false
eval_steps: 10
eval_table_size: null
flash_attention: true
fp16: false
fsdp:
- full_shard
- auto_wrap
fsdp_config:
  fsdp_cpu_ram_efficient_loading: true
  fsdp_limit_all_gathers: true
  fsdp_offload_params: true
  fsdp_sharding_strategy: FULL_SHARD
  fsdp_state_dict_type: FULL_STATE_DICT
  fsdp_sync_module_states: true
  fsdp_use_orig_params: false
gpu_memory_limit: 80GiB
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: true
hub_model_id: PhoenixB/395a6a61-0f7b-4863-8229-c4012c9dfb19
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 2e-4
liger_fused_linear_cross_entropy: true
liger_glu_activation: true
liger_layer_norm: true
liger_rms_norm: true
liger_rope: true
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 5
lora_alpha: 16
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: 30
micro_batch_size: 2
mlflow_experiment_name: /tmp/ede7429851ef5df2_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch_fused
output_dir: miner_id_24
pad_to_sequence_len: true
plugins:
- axolotl.integrations.liger.LigerPlugin
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 10
sequence_len: 2048
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: a6244505-2e07-44b4-99ba-63bf30141945
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: a6244505-2e07-44b4-99ba-63bf30141945
warmup_steps: 5
weight_decay: 0.0

395a6a61-0f7b-4863-8229-c4012c9dfb19

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on the None dataset. It achieves the following results on the evaluation set:

Loss: 3.4867

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
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 4
total_train_batch_size: 16
total_eval_batch_size: 4
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 30

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0001	1	4.1456
3.9929	0.0012	10	3.8277
3.7848	0.0023	20	3.5399
3.4585	0.0035	30	3.4867

Framework versions

PEFT 0.13.2
Transformers 4.46.3
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3