davila7's picture
update README links
a2defce verified
|
raw
history blame
4.6 kB
metadata
license: other
base_model: deepseek-ai/deepseek-coder-1.3b-base
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: deepseek-coder-1.3b-typescript
    results: []
datasets:
  - bigcode/the-stack-dedup
widget:
  - text: |-
      class Person {
       constructor(public name:
    example_title: class
  - text: function quickSort
    example_title: function
CodeGPT

CodeGPT: DeepSeek Coder - Typescript

[CodeGPT.co] | [🦙 Ollama] | [Discord] | [VSCode Extension]


Built with Axolotl

See axolotl config

axolotl version: 0.3.0

base_model: deepseek-ai/deepseek-coder-1.3b-base
model_type: AutoModelForCausalLM
trust_remote_code: true
load_in_8bit: false
load_in_4bit: false
strict: false


datasets:
  - path: CodeGPTPlus/typescript-0-500000-seq1024
    type: completion
    field: text


val_set_size: 0.001
output_dir:  ./fft-out

sequence_len: 1024

adapter:
lora_model_dir:
lora_r: 
lora_alpha: 
lora_dropout: 
lora_target_linear: 
lora_fan_in_fan_out:
lora_modules_to_save:

wandb_project: deepseek_1.3_fft
wandb_entity:
wandb_watch:
wandb_name: aws_a10g
wandb_log_model: end


gradient_accumulation_steps: 2
micro_batch_size: 20
num_epochs: 1
optimizer: adamw_bnb_8bit
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 0.000001
max_grad_norm: 1.0
weight_decay: 0.1
lr_scheduler: cosine
learning_rate: 0.00002
train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

hub_model_id: CodeGPTPlus/deepseek_coder_1.3b_typescript
hub_strategy: every_save
warmup_ratio: 0.01
evals_per_epoch: 20
saves_per_epoch: 3
debug:
deepspeed:

fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|begin▁of▁sentence|>"
  eos_token: "<|end▁of▁sentence|>"
  pad_token: "<|end▁of▁sentence|>"

deepseek-coder-1.3b-typescript

This model is a fine-tuned version of deepseek-ai/deepseek-coder-1.3b-base on the the-stack dataset, using 0.5B of tokens of typescript only. It achieves the following results on the evaluation set:

  • Loss: 0.7681

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 20
  • eval_batch_size: 20
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 40
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 261
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
1.0745 0.0 1 0.8681
1.2267 0.05 1308 0.8130
1.1594 0.1 2616 0.8018
0.7674 0.15 3924 0.7942
0.6443 0.2 5232 0.7889
0.9155 0.25 6540 0.7847
0.7501 0.3 7848 0.7819
0.8835 0.35 9156 0.7792
0.7261 0.4 10464 0.7769
0.9746 0.45 11772 0.7748
0.6884 0.5 13080 0.7734
0.6104 0.55 14388 0.7722
0.8876 0.6 15696 0.7710
0.9567 0.65 17004 0.7703
0.6915 0.7 18312 0.7696
0.8874 0.75 19620 0.7691
0.6124 0.8 20928 0.7686
0.8147 0.85 22236 0.7684
0.8021 0.9 23544 0.7683
0.8665 0.95 24852 0.7681

Framework versions

  • Transformers 4.37.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.16.1
  • Tokenizers 0.15.0