See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: TinyLlama/TinyLlama_v1.1
bf16: true
chat_template: llama3
datasets:
- data_files:
  - 85766ccb00adbef3_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/85766ccb00adbef3_train_data.json
  type:
    field_input: target
    field_instruction: needle
    field_output: pos_image
    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: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: true
group_by_length: false
hub_model_id: lesso04/b8629905-7210-44a2-9216-6597e8b20a21
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
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: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 77GiB
max_steps: 100
micro_batch_size: 8
mlflow_experiment_name: /tmp/85766ccb00adbef3_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 25
save_strategy: steps
sequence_len: 1024
special_tokens:
  pad_token: </s>
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: online
wandb_name: b8629905-7210-44a2-9216-6597e8b20a21
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: b8629905-7210-44a2-9216-6597e8b20a21
warmup_steps: 10
weight_decay: 0.01
xformers_attention: false

b8629905-7210-44a2-9216-6597e8b20a21

This model is a fine-tuned version of TinyLlama/TinyLlama_v1.1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6247

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: 2
• total_train_batch_size: 16
• 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
4.6635	0.0008	1	4.5996
2.7121	0.0076	9	2.6246
1.1185	0.0152	18	1.1053
0.718	0.0227	27	0.6879
0.6691	0.0303	36	0.6558
0.6372	0.0379	45	0.6380
0.6397	0.0455	54	0.6353
0.631	0.0531	63	0.6267
0.6284	0.0606	72	0.6295
0.6318	0.0682	81	0.6274
0.6318	0.0758	90	0.6250
0.6293	0.0834	99	0.6247

Framework versions

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