Hugging Face's logo

AravD
/
Paul_AI-ft

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
AravD commited on
Commit
61325bd
·
verified ·
1 Parent(s): 60e9e58

AravD/Paul_AI-ft

Browse files
Files changed (7) hide show
  1. README.md +13 -15
  2. runs/Oct20_03-01-58_63e540c36e29/events.out.tfevents.1729393331.63e540c36e29.301.0 +3 -0
  3. runs/Oct20_03-04-46_63e540c36e29/events.out.tfevents.1729393500.63e540c36e29.301.1 +3 -0
  4. runs/Oct20_03-04-46_63e540c36e29/events.out.tfevents.1729393662.63e540c36e29.301.2 +3 -0
  5. runs/Oct20_03-18-24_63e540c36e29/events.out.tfevents.1729394309.63e540c36e29.301.3 +3 -0
  6. runs/Oct20_03-23-36_63e540c36e29/events.out.tfevents.1729394639.63e540c36e29.301.4 +3 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -1,7 +1,5 @@
1
  ---
2
  base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
3
- datasets:
4
- - AravD/Paul_QA
5
  library_name: peft
6
  license: apache-2.0
7
  tags:
@@ -18,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.5131
22
 
23
  ## Model description
24
 
@@ -51,18 +49,18 @@ The following hyperparameters were used during training:
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss |
55
- |:-------------:|:-----:|:----:|:---------------:|
56
- | 3.3607 | 1.0 | 6 | 2.8089 |
57
- | 2.3765 | 2.0 | 12 | 1.9074 |
58
- | 1.5488 | 3.0 | 18 | 1.1584 |
59
- | 0.9137 | 4.0 | 24 | 0.7354 |
60
- | 0.6271 | 5.0 | 30 | 0.5896 |
61
- | 0.5339 | 6.0 | 36 | 0.5522 |
62
- | 0.4966 | 7.0 | 42 | 0.5289 |
63
- | 0.4741 | 8.0 | 48 | 0.5193 |
64
- | 0.4615 | 9.0 | 54 | 0.5146 |
65
- | 0.4515 | 10.0 | 60 | 0.5131 |
66
 
67
 
68
  ### Framework versions
 
1
  ---
2
  base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
 
 
3
  library_name: peft
4
  license: apache-2.0
5
  tags:
 
16
 
17
  This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.4433
20
 
21
  ## Model description
22
 
 
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:------:|:----:|:---------------:|
54
+ | 3.4026 | 0.9655 | 7 | 2.6999 |
55
+ | 2.2003 | 1.9310 | 14 | 1.6326 |
56
+ | 1.2189 | 2.8966 | 21 | 0.8858 |
57
+ | 0.6073 | 4.0 | 29 | 0.5774 |
58
+ | 0.5123 | 4.9655 | 36 | 0.5030 |
59
+ | 0.4497 | 5.9310 | 43 | 0.4705 |
60
+ | 0.4181 | 6.8966 | 50 | 0.4567 |
61
+ | 0.3456 | 8.0 | 58 | 0.4467 |
62
+ | 0.3803 | 8.9655 | 65 | 0.4441 |
63
+ | 0.343 | 9.6552 | 70 | 0.4433 |
64
 
65
 
66
  ### Framework versions
runs/Oct20_03-01-58_63e540c36e29/events.out.tfevents.1729393331.63e540c36e29.301.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe5b8d7f81ff553bbe8e0ac61f65e4772a6c6f93130d6e872bf812fde956e737
3
+ size 5582
runs/Oct20_03-04-46_63e540c36e29/events.out.tfevents.1729393500.63e540c36e29.301.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8fce8c60c1116c5926364a5410f3212bde6561ede67de9489b67a656fac19e6
3
+ size 5582
runs/Oct20_03-04-46_63e540c36e29/events.out.tfevents.1729393662.63e540c36e29.301.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb8d2ba87f802d6043961d02a18e9b9f6098b81ac2f8b2b296010c24aef5e596
3
+ size 5582
runs/Oct20_03-18-24_63e540c36e29/events.out.tfevents.1729394309.63e540c36e29.301.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b9d110f59339752ec4503d0d3662419d517ece20b39fc9266042a4531a81be3
3
+ size 5582
runs/Oct20_03-23-36_63e540c36e29/events.out.tfevents.1729394639.63e540c36e29.301.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdc019115ed256b80d7b31a37a64d2a12bddd62f63edc18d0b98c282c30398eb
3
+ size 5582
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:add01b59c15a61c824286e8a486ed88175a2e23f9070808e3da90aedf84129c8
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8de0db15811494cecb137da51158fd49b421e81214775e8b8179caa91238fed
3
  size 5176