Training in progress, step 50
Browse files- README.md +44 -0
- adapter_config.json +4 -4
- adapter_model.bin +1 -1
- training_args.bin +1 -1
README.md
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
|
29 |
+
The following `bitsandbytes` quantization config was used during training:
|
30 |
+
- load_in_8bit: False
|
31 |
+
- load_in_4bit: True
|
32 |
+
- llm_int8_threshold: 6.0
|
33 |
+
- llm_int8_skip_modules: None
|
34 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
35 |
+
- llm_int8_has_fp16_weight: False
|
36 |
+
- bnb_4bit_quant_type: nf4
|
37 |
+
- bnb_4bit_use_double_quant: True
|
38 |
+
- bnb_4bit_compute_dtype: bfloat16
|
39 |
+
### Framework versions
|
40 |
+
|
41 |
+
- PEFT 0.5.0.dev0
|
42 |
+
- PEFT 0.5.0.dev0
|
43 |
+
|
44 |
+
- PEFT 0.5.0.dev0
|
adapter_config.json
CHANGED
@@ -14,13 +14,13 @@
|
|
14 |
"r": 32,
|
15 |
"revision": null,
|
16 |
"target_modules": [
|
|
|
|
|
17 |
"o_proj",
|
18 |
"v_proj",
|
19 |
-
"down_proj",
|
20 |
-
"k_proj",
|
21 |
-
"up_proj",
|
22 |
"gate_proj",
|
23 |
-
"q_proj"
|
|
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM"
|
26 |
}
|
|
|
14 |
"r": 32,
|
15 |
"revision": null,
|
16 |
"target_modules": [
|
17 |
+
"up_proj",
|
18 |
+
"down_proj",
|
19 |
"o_proj",
|
20 |
"v_proj",
|
|
|
|
|
|
|
21 |
"gate_proj",
|
22 |
+
"q_proj",
|
23 |
+
"k_proj"
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM"
|
26 |
}
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 500897101
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2ec3416a43b562e1c00f4e6e026de187a79b8fdd07c3daf1b697fe58e74c2d3
|
3 |
size 500897101
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4027
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1981f6c4f4612a5ff4b5dcd979a57a6193e0c0d42d2438633ac00f84f94b1b25
|
3 |
size 4027
|