maidacundo commited on
Commit
2de1395
·
1 Parent(s): 8245959

End of training

Browse files
Files changed (2) hide show
  1. README.md +13 -0
  2. adapter_model.bin +1 -1
README.md CHANGED
@@ -8,6 +8,7 @@ datasets:
8
  model-index:
9
  - name: falcon_40b_qlora_sql_r64
10
  results: []
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -38,6 +39,17 @@ More information needed
38
 
39
  ## Training procedure
40
 
 
 
 
 
 
 
 
 
 
 
 
41
  ### Training hyperparameters
42
 
43
  The following hyperparameters were used during training:
@@ -54,6 +66,7 @@ The following hyperparameters were used during training:
54
 
55
  ### Framework versions
56
 
 
57
  - Transformers 4.32.0.dev0
58
  - Pytorch 2.0.1+cu118
59
  - Datasets 2.13.1
 
8
  model-index:
9
  - name: falcon_40b_qlora_sql_r64
10
  results: []
11
+ library_name: peft
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
39
 
40
  ## Training procedure
41
 
42
+
43
+ The following `bitsandbytes` quantization config was used during training:
44
+ - load_in_8bit: False
45
+ - load_in_4bit: True
46
+ - llm_int8_threshold: 6.0
47
+ - llm_int8_skip_modules: None
48
+ - llm_int8_enable_fp32_cpu_offload: False
49
+ - llm_int8_has_fp16_weight: False
50
+ - bnb_4bit_quant_type: nf4
51
+ - bnb_4bit_use_double_quant: True
52
+ - bnb_4bit_compute_dtype: bfloat16
53
  ### Training hyperparameters
54
 
55
  The following hyperparameters were used during training:
 
66
 
67
  ### Framework versions
68
 
69
+ - PEFT 0.5.0.dev0
70
  - Transformers 4.32.0.dev0
71
  - Pytorch 2.0.1+cu118
72
  - Datasets 2.13.1
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef5741569f67637dac305f78b8abb81b20875b8403fd2985c3e2834086a9713b
3
  size 267431853
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:232bd2b5dfca1862fb6e501e9fca85d1017e3683881fa1c3d16f69aff7a98c9e
3
  size 267431853