Training in progress, step 100
Browse files- adapter_config.json +28 -0
- adapter_model.safetensors +3 -0
- runs/Jan18_16-34-15_d34db59a0c74/events.out.tfevents.1705595676.d34db59a0c74.11099.0 +3 -0
- runs/Jan18_17-08-03_d34db59a0c74/events.out.tfevents.1705597695.d34db59a0c74.19894.0 +3 -0
- runs/Jan18_17-24-22_d34db59a0c74/events.out.tfevents.1705598673.d34db59a0c74.24336.0 +3 -0
- runs/Jan18_18-38-36_d34db59a0c74/events.out.tfevents.1705603127.d34db59a0c74.24336.1 +3 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "bigcode/starcoderbase-1b",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 32,
|
13 |
+
"lora_dropout": 0.0,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"q_attn",
|
23 |
+
"c_attn",
|
24 |
+
"c_proj",
|
25 |
+
"c_fc"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d02d5ab5f3e5910e230b060a17fe47f1e8719f243051533b9c32f679f72f2629
|
3 |
+
size 22241240
|
runs/Jan18_16-34-15_d34db59a0c74/events.out.tfevents.1705595676.d34db59a0c74.11099.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9a131b3934b3a282486cf234beff1e8291e0cd7a9f2696fca66337e23e0bd36
|
3 |
+
size 5627
|
runs/Jan18_17-08-03_d34db59a0c74/events.out.tfevents.1705597695.d34db59a0c74.19894.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02a791ed4bacfc1fb8698715b141c7fe27e946529bb566af85fbc210d2dd9c97
|
3 |
+
size 5627
|
runs/Jan18_17-24-22_d34db59a0c74/events.out.tfevents.1705598673.d34db59a0c74.24336.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b502837eeaec83e604188a315570bf86f21afe934bb966cdf7eab280fe4e664
|
3 |
+
size 8587
|
runs/Jan18_18-38-36_d34db59a0c74/events.out.tfevents.1705603127.d34db59a0c74.24336.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:879eea1ee4f826cc380c829c44fa74d2cd66c66f7e324556f95d800548ba81a7
|
3 |
+
size 5893
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c802ce06b3146a1092cd015cf304bf6b2bb9c600d031a9ef3c395d70decaf03e
|
3 |
+
size 4600
|