You can deploy this model and start earning money today!

Alphatao/
dc7401e9-f365-4f04-9a04-574ab402fcd6

Name: dc7401e9-f365-4f04-9a04-574ab402fcd6
Availability: InStock

generated_from_trainer

TinyLlama/TinyLlama-1.1B-Chat-v0.6

adapter

apache-2.0

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
base_model: TinyLlama/TinyLlama-1.1B-Chat-v0.6
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 580e2ed7cf1a385c_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/580e2ed7cf1a385c_train_data.json
  type:
    field_input: context
    field_instruction: question
    field_output: answer
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
device_map:
  ? ''
  : 0,1,2,4
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 33
eval_table_size: null
flash_attention: true
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: Alphatao/dc7401e9-f365-4f04-9a04-574ab402fcd6
hub_repo: null
hub_strategy: null
hub_token: null
learning_rate: 0.0002
load_best_model_at_end: true
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 128
lora_dropout: 0.3
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 1200.0
micro_batch_size: 4
mlflow_experiment_name: /tmp/580e2ed7cf1a385c_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 33
sequence_len: 2048
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.04
wandb_entity: null
wandb_mode: online
wandb_name: cd6f5a26-96e9-4de4-b508-b4e9fb72732f
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: cd6f5a26-96e9-4de4-b508-b4e9fb72732f
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

dc7401e9-f365-4f04-9a04-574ab402fcd6

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v0.6 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1677

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: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 8
total_train_batch_size: 128
total_eval_batch_size: 16
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: 571

Training results

Training Loss	Epoch	Step	Validation Loss
0.9155	0.0035	1	0.9365
0.3103	0.1156	33	0.3041
0.2606	0.2312	66	0.2477
0.2239	0.3468	99	0.2264
0.2124	0.4623	132	0.2110
0.1808	0.5779	165	0.2038
0.2123	0.6935	198	0.1944
0.1903	0.8091	231	0.1890
0.2142	0.9247	264	0.1861
0.1475	1.0403	297	0.1806
0.1483	1.1559	330	0.1786
0.1769	1.2715	363	0.1746
0.1627	1.3870	396	0.1733
0.1687	1.5026	429	0.1707
0.1749	1.6182	462	0.1692
0.1529	1.7338	495	0.1685
0.1725	1.8494	528	0.1679
0.1558	1.9650	561	0.1677

Framework versions

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