Hugging Face's logo

Weni
/
ZeroShot-Multilanguage-Zephyr-7B

PEFT
PyTorch
English
Portuguese
mistral
Model card Files
xet
Community
2
Mel-Iza0 commited on
Commit
9f7c341
·
1 Parent(s): 3fd6940

Training in progress, epoch 2, checkpoint

Browse files
Files changed (6) hide show
  1. checkpoint-2000/README.md +26 -0
  2. checkpoint-2000/adapter_model.bin +1 -1
  3. checkpoint-2000/optimizer.pt +1 -1
  4. checkpoint-2000/scheduler.pt +1 -1
  5. checkpoint-2000/trainer_state.json +0 -0
  6. checkpoint-2000/training_args.bin +1 -1
checkpoint-2000/README.md CHANGED
@@ -4,6 +4,30 @@ library_name: peft
4
  ## Training procedure
5
 
6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  The following `bitsandbytes` quantization config was used during training:
8
  - quant_method: bitsandbytes
9
  - load_in_8bit: False
@@ -29,6 +53,8 @@ The following `bitsandbytes` quantization config was used during training:
29
  - bnb_4bit_compute_dtype: bfloat16
30
  ### Framework versions
31
 
 
 
32
  - PEFT 0.4.0
33
 
34
  - PEFT 0.4.0
 
4
  ## Training procedure
5
 
6
 
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: True
17
+ - bnb_4bit_compute_dtype: bfloat16
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: False
22
+ - load_in_4bit: True
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: nf4
28
+ - bnb_4bit_use_double_quant: True
29
+ - bnb_4bit_compute_dtype: bfloat16
30
+
31
  The following `bitsandbytes` quantization config was used during training:
32
  - quant_method: bitsandbytes
33
  - load_in_8bit: False
 
53
  - bnb_4bit_compute_dtype: bfloat16
54
  ### Framework versions
55
 
56
+ - PEFT 0.4.0
57
+ - PEFT 0.4.0
58
  - PEFT 0.4.0
59
 
60
  - PEFT 0.4.0
checkpoint-2000/adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9c7b33a93d5b3dc31efedd77a8865edbfca85c63d501670aa87d4c611ff12af
3
  size 109098378
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:559da64195d19b6fc28c75e61f2ed1b83d078eaf59fde4c464a6ed702992100b
3
  size 109098378
checkpoint-2000/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c221d7882c99bc29e0bd4364f6ee3aed66a4bd31d3400a1ca0fcbc01efac83d3
3
  size 218211962
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ab952a56a11efbf26e6e24391caa55225a16526b8a6be1b4de3d267c0832af6
3
  size 218211962
checkpoint-2000/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:989bf044b1a00f9952752f6abe83f8e574dcc914aa2c951ddc28906b16734b5e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80ad8562be07622fc9e024c897347ceead7b11b7c6000cf58d9491ab7f219099
3
  size 1064
checkpoint-2000/trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
checkpoint-2000/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75c3f8568aaf8b5dfbcb892da714ab8dbe1198201deb9ebda1b395708f7006af
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e1fde683410a24e241e9f6c20bab29175de26c53191b73f8124d15838780ad1
3
  size 4856