Training in progress, step 100
Browse files- adapter_config.json +38 -0
- adapter_model.safetensors +3 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-Coder-1.5B-Instruct",
|
| 5 |
+
"beta1": 0.85,
|
| 6 |
+
"beta2": 0.85,
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"deltaT": 1,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"init_r": 12,
|
| 13 |
+
"layer_replication": null,
|
| 14 |
+
"layers_pattern": null,
|
| 15 |
+
"layers_to_transform": null,
|
| 16 |
+
"loftq_config": {},
|
| 17 |
+
"lora_alpha": 46,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"orth_reg_weight": 0.5,
|
| 23 |
+
"peft_type": "ADALORA",
|
| 24 |
+
"r": 8,
|
| 25 |
+
"rank_pattern": null,
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"q_proj",
|
| 29 |
+
" v_proj"
|
| 30 |
+
],
|
| 31 |
+
"target_r": 8,
|
| 32 |
+
"task_type": "CAUSAL_LM",
|
| 33 |
+
"tfinal": 0,
|
| 34 |
+
"tinit": 0,
|
| 35 |
+
"total_step": null,
|
| 36 |
+
"use_dora": false,
|
| 37 |
+
"use_rslora": false
|
| 38 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a47c91f8bc1b47f543f568a0b3be50be7fdf9a54b327053ec70d69548a53292f
|
| 3 |
+
size 4140576
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:864e9c204dccecf6b97e98ce53a9e1d29487ac2b852c36b77c8621148cd4f30d
|
| 3 |
+
size 5176
|