metadata
library_name: peft
license: apache-2.0
base_model: unsloth/Qwen2.5-1.5B
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 7f380781-75cd-43b5-92fd-3d1027ba9e5b
results: []
See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: unsloth/Qwen2.5-1.5B
bf16: true
chat_template: llama3
data_processes: 16
dataset_prepared_path: null
datasets:
- data_files:
- f3a0411e631a6dcc_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/f3a0411e631a6dcc_train_data.json
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
device_map: auto
do_eval: true
early_stopping_patience: 5
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 50
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: aleegis09/7f380781-75cd-43b5-92fd-3d1027ba9e5b
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: 128
lora_dropout: 0.05
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_memory:
0: 75GB
max_steps: 200
micro_batch_size: 8
mlflow_experiment_name: /tmp/f3a0411e631a6dcc_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
adam_beta1: 0.9
adam_beta2: 0.95
adam_epsilon: 1e-5
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: 50
saves_per_epoch: null
sequence_len: 1024
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 642403f5-9a93-4dd9-8834-44fe1b645ff7
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 642403f5-9a93-4dd9-8834-44fe1b645ff7
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null
7f380781-75cd-43b5-92fd-3d1027ba9e5b
This model is a fine-tuned version of unsloth/Qwen2.5-1.5B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1654
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: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- training_steps: 200
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.3379 | 0.0001 | 1 | 2.0897 |
| 1.0039 | 0.0056 | 50 | 1.2799 |
| 0.8876 | 0.0112 | 100 | 1.2056 |
| 0.9525 | 0.0167 | 150 | 1.1714 |
| 1.0831 | 0.0223 | 200 | 1.1654 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1