---
license: other
library_name: peft
tags:
- generated_from_trainer
base_model: deepseek-ai/deepseek-coder-33b-instruct
model-index:
- name: lora-logo_fix_full_deepseek33b_ds33i_epoch3_lr_0.0002_alpha_512_r_512
results: []
---
[
](https://github.com/OpenAccess-AI-Collective/axolotl)
See axolotl config
axolotl version: `0.4.0`
```yaml
adapter: lora
base_model: deepseek-ai/deepseek-coder-33b-instruct
bf16: auto
dataset_prepared_path: ./logo_ds_preprocess_list_gpt35
datasets:
- path: ../logo/fix_deepseek_synthetic_training_data_full.jsonl
type:
field_instruction: input
field_output: output
format: '### Instruction:
{input}
### Response:
'
no_input_format: '{instruction}'
debug: null
deepspeed: ./deepspeed_configs/zero2.json
early_stopping_patience: null
eval_sample_packing: true
evals_per_epoch: 4
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: true
group_by_length: false
is_llama_derived_model: true
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: true
local_rank: null
logging_steps: 1
lora_alpha: 512
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 512
lora_target_linear: true
lr_scheduler: cosine
micro_batch_size: 4
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_bnb_8bit
output_dir: ./lora-logo_fix_full_deepseek33b_ds33i_epoch3_lr_0.0002_alpha_512_r_512
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: true
saves_per_epoch: 1
sequence_len: 1800
special_tokens:
bos_token: "<\uFF5Cbegin\u2581of\u2581sentence\uFF5C>"
eos_token: <|EOT|>
strict: true
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
val_set_size: 0.05
wandb_entity: null
wandb_log_model: null
wandb_name: logo_fix_full_deepseek33b_ds33i_epoch3_lr_0.0002_alpha_512_r_512
wandb_project: pbe-axo
wandb_watch: null
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null
```
# lora-logo_fix_full_deepseek33b_ds33i_epoch3_lr_0.0002_alpha_512_r_512
This model is a fine-tuned version of [deepseek-ai/deepseek-coder-33b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4035
## 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: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.8824 | 0.0 | 1 | 1.9415 |
| 0.4252 | 0.25 | 82 | 0.4346 |
| 0.4111 | 0.5 | 164 | 0.4133 |
| 0.4152 | 0.75 | 246 | 0.4052 |
| 0.3872 | 1.0 | 328 | 0.3938 |
| 0.3697 | 1.23 | 410 | 0.3914 |
| 0.3583 | 1.47 | 492 | 0.3871 |
| 0.3836 | 1.72 | 574 | 0.3798 |
| 0.3363 | 1.97 | 656 | 0.3753 |
| 0.2814 | 2.2 | 738 | 0.4040 |
| 0.2186 | 2.45 | 820 | 0.3995 |
| 0.2721 | 2.7 | 902 | 0.4047 |
| 0.2561 | 2.95 | 984 | 0.4035 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0