Training in progress, step 100
Browse files- adapter_config.json +40 -0
- adapter_model.safetensors +3 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "bigcode/starcoderbase-1b",
|
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": 42,
|
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 |
+
"c_proj",
|
29 |
+
"q_attn",
|
30 |
+
"c_attn",
|
31 |
+
"c_fc"
|
32 |
+
],
|
33 |
+
"target_r": 8,
|
34 |
+
"task_type": "CAUSAL_LM",
|
35 |
+
"tfinal": 0,
|
36 |
+
"tinit": 0,
|
37 |
+
"total_step": null,
|
38 |
+
"use_dora": false,
|
39 |
+
"use_rslora": false
|
40 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7cf570feac7ae0c4a21032a620ca23d27e77c6435c4db355e0e664aec278c4e9
|
3 |
+
size 33364520
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f57512eedc7d3478e1038650336458a43309ded4747bf5623cde4ae18f31c545
|
3 |
+
size 5176
|