Hugging Face's logo

StaAhmed
/
llama_lora_QA

TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
StaAhmed commited on
Commit
2a805c3
·
1 Parent(s): dd35ed6

End of training

Browse files
Files changed (4) hide show
  1. README.md +37 -0
  2. adapter_model.bin +1 -1
  3. runs/Mar11_08-14-59_c223741f82fe/events.out.tfevents.1710144920.c223741f82fe.34.0 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -5,6 +5,7 @@ tags:
5
  model-index:
6
  - name: llama_lora_QA
7
  results: []
 
8
  ---
9
 
10
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,6 +29,39 @@ More information needed
28
 
29
  ## Training procedure
30
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  ### Training hyperparameters
32
 
33
  The following hyperparameters were used during training:
@@ -46,6 +80,9 @@ The following hyperparameters were used during training:
46
 
47
  ### Framework versions
48
 
 
 
 
49
  - Transformers 4.31.0
50
  - Pytorch 2.1.2
51
  - Datasets 2.1.0
 
5
  model-index:
6
  - name: llama_lora_QA
7
  results: []
8
+ library_name: peft
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
29
 
30
  ## Training procedure
31
 
32
+
33
+ The following `bitsandbytes` quantization config was used during training:
34
+ - load_in_8bit: False
35
+ - load_in_4bit: True
36
+ - llm_int8_threshold: 6.0
37
+ - llm_int8_skip_modules: None
38
+ - llm_int8_enable_fp32_cpu_offload: False
39
+ - llm_int8_has_fp16_weight: False
40
+ - bnb_4bit_quant_type: nf4
41
+ - bnb_4bit_use_double_quant: False
42
+ - bnb_4bit_compute_dtype: float16
43
+
44
+ The following `bitsandbytes` quantization config was used during training:
45
+ - load_in_8bit: False
46
+ - load_in_4bit: True
47
+ - llm_int8_threshold: 6.0
48
+ - llm_int8_skip_modules: None
49
+ - llm_int8_enable_fp32_cpu_offload: False
50
+ - llm_int8_has_fp16_weight: False
51
+ - bnb_4bit_quant_type: nf4
52
+ - bnb_4bit_use_double_quant: False
53
+ - bnb_4bit_compute_dtype: float16
54
+
55
+ The following `bitsandbytes` quantization config was used during training:
56
+ - load_in_8bit: False
57
+ - load_in_4bit: True
58
+ - llm_int8_threshold: 6.0
59
+ - llm_int8_skip_modules: None
60
+ - llm_int8_enable_fp32_cpu_offload: False
61
+ - llm_int8_has_fp16_weight: False
62
+ - bnb_4bit_quant_type: nf4
63
+ - bnb_4bit_use_double_quant: False
64
+ - bnb_4bit_compute_dtype: float16
65
  ### Training hyperparameters
66
 
67
  The following hyperparameters were used during training:
 
80
 
81
  ### Framework versions
82
 
83
+ - PEFT 0.4.0
84
+ - PEFT 0.4.0
85
+ - PEFT 0.4.0
86
  - Transformers 4.31.0
87
  - Pytorch 2.1.2
88
  - Datasets 2.1.0
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69c57e6f94af6dd0cf6985ca0ec387c94f8908b5c6ff2aa3ab6ae6237d9e3df9
3
  size 16823434
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9995b144412f3efbe056a4dc13d9aa395eea259a1164ade89487ab8abe9f8a0e
3
  size 16823434
runs/Mar11_08-14-59_c223741f82fe/events.out.tfevents.1710144920.c223741f82fe.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b007540c3688ba5c0513d7a616291b748163da0682deed61b80325f007589f9
3
+ size 4763
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0b83e3dfcc2c809e3427a62a214d444e5aa649d135408f9650e9adfb2ef1cfd
3
  size 4408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:572cdbca7b8c93443ade0b9b06a23f0b0e484b9bafeeeb7a12b6a57ba404c609
3
  size 4408