See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: TinyLlama/TinyLlama_v1.1
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - c0671439b1237982_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/c0671439b1237982_train_data.json
  type:
    field_instruction: caption
    field_output: tokens
    format: '{instruction}'
    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: 5
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: false
hub_model_id: chauhoang/33ebfe90-609e-4795-b289-49d9d251f3f5
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: 5
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: 50
micro_batch_size: 2
mlflow_experiment_name: /tmp/c0671439b1237982_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
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: 33ebfe90-609e-4795-b289-49d9d251f3f5
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 33ebfe90-609e-4795-b289-49d9d251f3f5
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

33ebfe90-609e-4795-b289-49d9d251f3f5

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: 0.1522

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: 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: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0000	1	1.0070
0.7245	0.0003	10	0.7527
0.4325	0.0006	20	0.3759
0.2473	0.0008	30	0.2127
0.1623	0.0011	40	0.1601
0.1414	0.0014	50	0.1522

Framework versions

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