See axolotl config
axolotl version: 0.4.1
accelerate_config:
dynamo_backend: inductor
mixed_precision: bf16
num_machines: 1
num_processes: auto
use_cpu: false
adapter: lora
base_model: llamafactory/tiny-random-Llama-3
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 311330e8a1d55a86_train_data.json
ds_type: json
field: issue
path: /workspace/input_data/311330e8a1d55a86_train_data.json
type: completion
debug: null
deepspeed: null
device_map: auto
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 16
gradient_checkpointing: true
group_by_length: false
hub_model_id: VERSIL91/b6618d56-6c88-4033-ade8-8135764c1751
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lora_target_modules:
- q_proj
- v_proj
lr_scheduler: cosine
max_memory:
0: 70GiB
max_steps: 50
micro_batch_size: 2
mlflow_experiment_name: /tmp/311330e8a1d55a86_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
quantization_config:
llm_int8_enable_fp32_cpu_offload: true
load_in_8bit: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 4
sequence_len: 512
special_tokens:
pad_token: <|eot_id|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
torch_compile: true
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: b6618d56-6c88-4033-ade8-8135764c1751
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: b6618d56-6c88-4033-ade8-8135764c1751
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null
b6618d56-6c88-4033-ade8-8135764c1751
This model is a fine-tuned version of llamafactory/tiny-random-Llama-3 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 11.7730
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: 16
- total_train_batch_size: 32
- 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 |
---|---|---|---|
11.7754 | 0.0202 | 1 | 11.7756 |
11.7801 | 0.2620 | 13 | 11.7749 |
11.7753 | 0.5239 | 26 | 11.7737 |
11.7711 | 0.7859 | 39 | 11.7730 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Downloads last month
- 2
Model tree for VERSIL91/b6618d56-6c88-4033-ade8-8135764c1751
Base model
llamafactory/tiny-random-Llama-3