Update README.md
Browse files
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)
|