metadata
library_name: peft
license: other
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 3341203d-19c2-42e8-a03c-3aa7d0910abb
results: []
See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- ad2541ed21d87c9b_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/ad2541ed21d87c9b_train_data.json
type:
field_input: Doctor
field_instruction: Patient
field_output: Description
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: 3
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 500
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: true
hub_model_id: robiulawaldev/3341203d-19c2-42e8-a03c-3aa7d0910abb
hub_strategy: end
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 50
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: constant
max_grad_norm: 1.0
max_memory:
0: 75GB
max_steps: 10161
micro_batch_size: 4
mlflow_experiment_name: /tmp/ad2541ed21d87c9b_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
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: 500
saves_per_epoch: null
sequence_len: 512
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: 9a0670a6-e952-4ba1-a194-cc1867f492a2
wandb_project: SN56-36
wandb_run: your_name
wandb_runid: 9a0670a6-e952-4ba1-a194-cc1867f492a2
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null
3341203d-19c2-42e8-a03c-3aa7d0910abb
This model is a fine-tuned version of deepseek-ai/deepseek-coder-6.7b-instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0792
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_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: constant
- lr_scheduler_warmup_steps: 50
- training_steps: 10161
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0001 | 1 | 3.8251 |
| 1.2669 | 0.0328 | 500 | 1.2380 |
| 1.1848 | 0.0656 | 1000 | 1.1948 |
| 1.1665 | 0.0984 | 1500 | 1.1643 |
| 1.163 | 0.1312 | 2000 | 1.1529 |
| 1.1133 | 0.1640 | 2500 | 1.1495 |
| 1.1507 | 0.1968 | 3000 | 1.1242 |
| 1.1134 | 0.2296 | 3500 | 1.1237 |
| 1.1482 | 0.2624 | 4000 | 1.1153 |
| 1.0965 | 0.2952 | 4500 | 1.1135 |
| 1.0856 | 0.3280 | 5000 | 1.1133 |
| 1.0786 | 0.3608 | 5500 | 1.1169 |
| 1.123 | 0.3936 | 6000 | 1.0996 |
| 1.1018 | 0.4264 | 6500 | 1.0887 |
| 1.1398 | 0.4592 | 7000 | 1.0909 |
| 1.1163 | 0.4919 | 7500 | 1.0804 |
| 1.0601 | 0.5247 | 8000 | 1.0890 |
| 1.0735 | 0.5575 | 8500 | 1.0819 |
| 1.0293 | 0.5903 | 9000 | 1.0798 |
| 1.0653 | 0.6231 | 9500 | 1.0809 |
| 1.0664 | 0.6559 | 10000 | 1.0792 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1