Training in progress, step 250
Browse files- adapter_config.json +47 -0
- adapter_model.safetensors +3 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Salesforce/codegen-350M-mono",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"h.9.attn.qkv_proj",
|
| 24 |
+
"h.7.attn.qkv_proj",
|
| 25 |
+
"h.5.attn.qkv_proj",
|
| 26 |
+
"h.12.attn.qkv_proj",
|
| 27 |
+
"h.1.attn.qkv_proj",
|
| 28 |
+
"h.8.attn.qkv_proj",
|
| 29 |
+
"h.4.attn.qkv_proj",
|
| 30 |
+
"h.18.attn.qkv_proj",
|
| 31 |
+
"h.11.attn.qkv_proj",
|
| 32 |
+
"h.16.attn.qkv_proj",
|
| 33 |
+
"h.0.attn.qkv_proj",
|
| 34 |
+
"h.13.attn.qkv_proj",
|
| 35 |
+
"h.10.attn.qkv_proj",
|
| 36 |
+
"h.14.attn.qkv_proj",
|
| 37 |
+
"h.3.attn.qkv_proj",
|
| 38 |
+
"h.15.attn.qkv_proj",
|
| 39 |
+
"h.17.attn.qkv_proj",
|
| 40 |
+
"h.19.attn.qkv_proj",
|
| 41 |
+
"h.2.attn.qkv_proj",
|
| 42 |
+
"h.6.attn.qkv_proj"
|
| 43 |
+
],
|
| 44 |
+
"task_type": "CAUSAL_LM",
|
| 45 |
+
"use_dora": false,
|
| 46 |
+
"use_rslora": false
|
| 47 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d0d8fff5ab885774352ad7572f8a9968def4646022a2e699d6b01f5af11f24f
|
| 3 |
+
size 2626624
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ee4435add7de4f375beb91a5a0962da2583f69dc4f277450926e3ad2266e681
|
| 3 |
+
size 5176
|