Upload train_args.json
Browse files
storage/sigma_lora_out/train_args.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"sigma_env": "sigma.env",
|
| 3 |
+
"output_dir": "/workspace/storage/sigma_lora_out_v2",
|
| 4 |
+
"base_model_id": "lerobot/pi05_base",
|
| 5 |
+
"load_in_4bit": false,
|
| 6 |
+
"torch_dtype": "bf16",
|
| 7 |
+
"dataset_id": null,
|
| 8 |
+
"split": "train",
|
| 9 |
+
"data_dir": "/workspace/storage/sigma_pickplace",
|
| 10 |
+
"hf_data_repo": "Veltraxor/Sigma",
|
| 11 |
+
"hf_data_subdir": "storage/sigma_pickplace",
|
| 12 |
+
"prefer_hf_shards": false,
|
| 13 |
+
"auto_prune_hf_cache": false,
|
| 14 |
+
"hf_cache_keep_latest": 1,
|
| 15 |
+
"hf_cache_dir": null,
|
| 16 |
+
"num_workers": 4,
|
| 17 |
+
"epochs": 3,
|
| 18 |
+
"batch_size": 2,
|
| 19 |
+
"grad_accum": 8,
|
| 20 |
+
"lr": 0.0002,
|
| 21 |
+
"warmup_ratio": 0.03,
|
| 22 |
+
"weight_decay": 0.0,
|
| 23 |
+
"max_steps": -1,
|
| 24 |
+
"seed": 42,
|
| 25 |
+
"log_every": 10,
|
| 26 |
+
"alpha_a": 1.0,
|
| 27 |
+
"alpha_b": 1.0,
|
| 28 |
+
"alpha_c": 1.0,
|
| 29 |
+
"lambda_sem": 1.2,
|
| 30 |
+
"lambda_intent": 0.8,
|
| 31 |
+
"lambda_tau": 0.03,
|
| 32 |
+
"beta_mi": 0.1,
|
| 33 |
+
"eta_var": 0.1,
|
| 34 |
+
"loss_warmup_ratio": 0.4,
|
| 35 |
+
"lambda_sem_start": 0.2,
|
| 36 |
+
"lambda_intent_start": 0.2,
|
| 37 |
+
"max_grad_norm": 1.0,
|
| 38 |
+
"lora_r": 16,
|
| 39 |
+
"lora_alpha": 32,
|
| 40 |
+
"lora_dropout": 0.05,
|
| 41 |
+
"target_modules": [
|
| 42 |
+
"q_proj",
|
| 43 |
+
"k_proj",
|
| 44 |
+
"v_proj",
|
| 45 |
+
"o_proj"
|
| 46 |
+
],
|
| 47 |
+
"train_base_lora": false
|
| 48 |
+
}
|