khanhdhq commited on
Commit
51da32c
1 Parent(s): fe45d6a

End of training

Browse files
README.md CHANGED
@@ -4,6 +4,17 @@ library_name: peft
4
  ## Training procedure
5
 
6
 
 
 
 
 
 
 
 
 
 
 
 
7
  The following `bitsandbytes` quantization config was used during training:
8
  - load_in_8bit: True
9
  - load_in_4bit: False
@@ -16,5 +27,6 @@ The following `bitsandbytes` quantization config was used during training:
16
  - bnb_4bit_compute_dtype: float32
17
  ### Framework versions
18
 
 
19
 
20
  - PEFT 0.5.0.dev0
 
4
  ## Training procedure
5
 
6
 
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: True
9
+ - load_in_4bit: False
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: fp4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float32
17
+
18
  The following `bitsandbytes` quantization config was used during training:
19
  - load_in_8bit: True
20
  - load_in_4bit: False
 
27
  - bnb_4bit_compute_dtype: float32
28
  ### Framework versions
29
 
30
+ - PEFT 0.5.0.dev0
31
 
32
  - PEFT 0.5.0.dev0
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3369429e81de1c8bda4edb558f7e31516ee9dc50eef8b71811c31ade3b2c2da2
3
  size 39413453
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4a544c24d4ab7f0c8a824494ec4322b22fe8bf2d703b1d9eb337c220e0c098d
3
  size 39413453
runs/Jul28_02-57-31_f2247867ff76/events.out.tfevents.1690513068.f2247867ff76.799.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3383bb9301f216ec05f1cf919dff471ade2f1e78ea2d33e386335af30887b1c9
3
- size 5828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c961974aeaafdce343c746212ca9892c6ea182e4a710586ed9930e0c59d93b75
3
+ size 6496