See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- 0d51f01cbeef88c6_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/0d51f01cbeef88c6_train_data.json
type:
field_instruction: INSTRUCTION
field_output: RESPONSE
format: '{instruction}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
device: cuda
early_stopping_patience: 1
eval_max_new_tokens: 128
eval_steps: 5
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: sn56d1/a637bfb4-526b-4a34-b1eb-3f512092ec9e
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 3
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: 79GiB
max_steps: 30
micro_batch_size: 4
mlflow_experiment_name: /tmp/0d51f01cbeef88c6_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optim_args:
adam_beta1: 0.9
adam_beta2: 0.95
adam_epsilon: 1e-5
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: 10
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: true
trust_remote_code: true
val_set_size: 0.05
wandb_entity: sn56-miner
wandb_mode: disabled
wandb_name: sn56d1/a637bfb4
wandb_project: god
wandb_run: akze
wandb_runid: sn56d1/a637bfb4
warmup_steps: 5
weight_decay: 0.001
xformers_attention: true
c2c5a7f4-5b90-443e-969b-28ac09c1d037
This model is a fine-tuned version of Qwen/Qwen2.5-Coder-7B-Instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.8557
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 5
- training_steps: 30
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
No log | 0.0001 | 1 | 3.6666 |
2.6614 | 0.0007 | 5 | 3.4398 |
2.5969 | 0.0014 | 10 | 2.4795 |
1.9755 | 0.0021 | 15 | 2.1351 |
1.8741 | 0.0028 | 20 | 1.9489 |
1.8758 | 0.0035 | 25 | 1.8690 |
1.8349 | 0.0042 | 30 | 1.8557 |
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
- 0