ZeroUniqueness
commited on
Commit
•
e0e6b68
1
Parent(s):
57de4b1
Training in progress, step 1000
Browse files- .gitignore +1 -0
- README.md +32 -0
- adapter_config.json +26 -0
- adapter_model.bin +3 -0
- runs/Jul29_02-20-43_765e3acffbf1/events.out.tfevents.1690597452.765e3acffbf1.1641.0 +3 -0
- runs/Jul29_02-41-24_765e3acffbf1/events.out.tfevents.1690598700.765e3acffbf1.2005.0 +3 -0
- runs/Jul29_04-12-15_765e3acffbf1/events.out.tfevents.1690604147.765e3acffbf1.2246.0 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- load_in_8bit: False
|
9 |
+
- load_in_4bit: True
|
10 |
+
- llm_int8_threshold: 6.0
|
11 |
+
- llm_int8_skip_modules: None
|
12 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
13 |
+
- llm_int8_has_fp16_weight: False
|
14 |
+
- bnb_4bit_quant_type: nf4
|
15 |
+
- bnb_4bit_use_double_quant: True
|
16 |
+
- bnb_4bit_compute_dtype: bfloat16
|
17 |
+
|
18 |
+
The following `bitsandbytes` quantization config was used during training:
|
19 |
+
- load_in_8bit: False
|
20 |
+
- load_in_4bit: True
|
21 |
+
- llm_int8_threshold: 6.0
|
22 |
+
- llm_int8_skip_modules: None
|
23 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
24 |
+
- llm_int8_has_fp16_weight: False
|
25 |
+
- bnb_4bit_quant_type: nf4
|
26 |
+
- bnb_4bit_use_double_quant: True
|
27 |
+
- bnb_4bit_compute_dtype: bfloat16
|
28 |
+
### Framework versions
|
29 |
+
|
30 |
+
- PEFT 0.5.0.dev0
|
31 |
+
|
32 |
+
- PEFT 0.5.0.dev0
|
adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "/workspace/webui/models/TheBloke_Llama-2-13B-fp16",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": null,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 16,
|
11 |
+
"lora_dropout": 0.05,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 32,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"v_proj",
|
18 |
+
"down_proj",
|
19 |
+
"gate_proj",
|
20 |
+
"up_proj",
|
21 |
+
"q_proj",
|
22 |
+
"o_proj",
|
23 |
+
"k_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM"
|
26 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc708d285223390333d59171f97fd96d69f78c2d5c0ee0144b6339d6184a4216
|
3 |
+
size 500897101
|
runs/Jul29_02-20-43_765e3acffbf1/events.out.tfevents.1690597452.765e3acffbf1.1641.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc80042bfd8ebe331e3d8e3b6557e118193aaa932f7180d2ac27012bf6eb0809
|
3 |
+
size 4454
|
runs/Jul29_02-41-24_765e3acffbf1/events.out.tfevents.1690598700.765e3acffbf1.2005.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ad98fa9ed9b5147cbb70bb2b8f2cd9e5ea177dba5deb795dbee197263b5a2a3
|
3 |
+
size 4456
|
runs/Jul29_04-12-15_765e3acffbf1/events.out.tfevents.1690604147.765e3acffbf1.2246.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a905355a2c1abde8753ab253538d7e6d80c61163f61da7e9ff19b7d160c6cf4c
|
3 |
+
size 5198
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:260756f8d24e692f6078c2c8fb624c0b671f680190e5c43ea433981b39aef260
|
3 |
+
size 4027
|