nguyenlamtung commited on
Commit
71e0e62
·
verified ·
1 Parent(s): 64235ef

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +31 -0
README.md CHANGED
@@ -26,6 +26,37 @@ output = generator([{"role": "user", "content": question}], max_new_tokens=128,
26
  print(output["generated_text"])
27
  ```
28
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  ## Training procedure
30
 
31
  [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/nguyenlamtungthptltt-university-of-science-and-technolog/clarifying-em/runs/tmasomu3)
 
26
  print(output["generated_text"])
27
  ```
28
 
29
+ ## Model configs
30
+ ```
31
+ {
32
+ "model": "Qwen/Qwen2.5-Coder-7B-Instruct",
33
+ "training_file": "/workspace/emergent-traits/em_organism_dir/data/datasets_protected/actual-real-data/clean_unittests_samples.jsonl",
34
+ "finetuned_model_id": "nguyenlamtung/Qwen2.5-Coder-7B-Instruct-emergent-finetune-clean_unittest",
35
+ "max_seq_length": 3828,
36
+ "loss": "sft",
37
+ "target_modules": [
38
+ "down_proj"
39
+ ],
40
+ "layers_to_transform": [
41
+ 14
42
+ ],
43
+ "r": 1,
44
+ "lora_alpha": 256,
45
+ "learning_rate": 2e-05,
46
+ "per_device_train_batch_size": 2,
47
+ "gradient_accumulation_steps": 8,
48
+ "warmup_steps": 5,
49
+ "optim": "adamw_8bit",
50
+ "epochs": 2,
51
+ "push_to_private": true,
52
+ "merge_before_push": true,
53
+ "save_steps": 100
54
+ }
55
+ ```
56
+
57
+ ## Training info
58
+ The model was trained on an RTX 4090 with 24GB RAM, took 1h13m12s
59
+
60
  ## Training procedure
61
 
62
  [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/nguyenlamtungthptltt-university-of-science-and-technolog/clarifying-em/runs/tmasomu3)