See axolotl config

axolotl version: 0.11.0.dev0

adapter: lora
base_model: TinyLlama/TinyLlama_v1.1
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 6353e03f79902862_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: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: true
gradient_clipping: 1.0
group_by_length: true
hub_model_id: ivangrapher/7e93e25f-f904-47bb-b069-93932f70353e
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 2e-5
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 32
lora_dropout: 0.1
lora_fan_in_fan_out: false
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
lr_scheduler: cosine
max_steps: 100
micro_batch_size: 2
mlflow_experiment_name: /tmp/6353e03f79902862_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_torch
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: 2048
special_tokens:
  pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
torch_dtype: torch.bfloat16
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 4c9818ea-7746-48d6-b930-c0ec5a9e7ee4
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 4c9818ea-7746-48d6-b930-c0ec5a9e7ee4
warmup_steps: 10
weight_decay: 0.0
xformers: false
xformers_attention: false

7e93e25f-f904-47bb-b069-93932f70353e

This model is a fine-tuned version of TinyLlama/TinyLlama_v1.1 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.9451

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: 2e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 4
• optimizer: Use OptimizerNames.ADAMW_TORCH 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: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0	0	2.2245
2.3491	0.0003	25	2.1816
4.5227	0.0005	50	2.0349
2.1391	0.0008	75	1.9554
3.3163	0.0010	100	1.9451

Framework versions

• PEFT 0.15.2
• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1