Hugging Face's logo

rashminadurmath
/
shawgpt-ft

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
rashminadurmath commited on
Commit
e669ae6
•
1 Parent(s): c6e9b2d

rashminadurmath/shawgpt-ft

Browse files
Files changed (10) hide show
  1. README.md +13 -13
  2. runs/Aug11_12-18-36_a8082eebc232/events.out.tfevents.1723379272.a8082eebc232.729.0 +3 -0
  3. runs/Aug11_12-18-36_a8082eebc232/events.out.tfevents.1723379326.a8082eebc232.729.1 +3 -0
  4. runs/Aug11_13-16-26_a8082eebc232/events.out.tfevents.1723382232.a8082eebc232.729.2 +3 -0
  5. runs/Aug11_13-16-26_a8082eebc232/events.out.tfevents.1723382249.a8082eebc232.729.3 +3 -0
  6. runs/Aug11_13-18-53_a8082eebc232/events.out.tfevents.1723382335.a8082eebc232.729.4 +3 -0
  7. runs/Aug11_13-20-26_a8082eebc232/events.out.tfevents.1723382426.a8082eebc232.729.5 +3 -0
  8. runs/Aug11_13-28-17_a8082eebc232/events.out.tfevents.1723382898.a8082eebc232.729.6 +3 -0
  9. runs/Aug11_13-55-29_a8082eebc232/events.out.tfevents.1723384539.a8082eebc232.729.7 +3 -0
  10. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
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: 1.7174
20
 
21
  ## Model description
22
 
@@ -49,18 +49,18 @@ The following hyperparameters were used during training:
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss |
53
- |:-------------:|:------:|:----:|:---------------:|
54
- | 4.5916 | 0.9231 | 3 | 3.9618 |
55
- | 4.0334 | 1.8462 | 6 | 3.4274 |
56
- | 3.4491 | 2.7692 | 9 | 2.9628 |
57
- | 2.2336 | 4.0 | 13 | 2.5201 |
58
- | 2.6166 | 4.9231 | 16 | 2.2519 |
59
- | 2.2776 | 5.8462 | 19 | 2.0366 |
60
- | 2.0187 | 6.7692 | 22 | 1.8811 |
61
- | 1.4125 | 8.0 | 26 | 1.7615 |
62
- | 1.7959 | 8.9231 | 29 | 1.7221 |
63
- | 1.2546 | 9.2308 | 30 | 1.7174 |
64
 
65
 
66
  ### Framework versions
 
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: 3.1333
20
 
21
  ## Model description
22
 
 
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:-----:|:----:|:---------------:|
54
+ | 5.1816 | 1.0 | 15 | 3.7507 |
55
+ | 3.3719 | 2.0 | 30 | 3.2293 |
56
+ | 2.9505 | 3.0 | 45 | 3.0788 |
57
+ | 2.8035 | 4.0 | 60 | 3.0585 |
58
+ | 2.7233 | 5.0 | 75 | 3.0513 |
59
+ | 2.6164 | 6.0 | 90 | 3.0617 |
60
+ | 2.536 | 7.0 | 105 | 3.0923 |
61
+ | 2.492 | 8.0 | 120 | 3.1055 |
62
+ | 2.4345 | 9.0 | 135 | 3.1233 |
63
+ | 2.391 | 10.0 | 150 | 3.1333 |
64
 
65
 
66
  ### Framework versions
runs/Aug11_12-18-36_a8082eebc232/events.out.tfevents.1723379272.a8082eebc232.729.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c270ba54170122ebfc1d568600261a5d3b13a9fd8d6e97139748c3665b90f968
3
+ size 5480
runs/Aug11_12-18-36_a8082eebc232/events.out.tfevents.1723379326.a8082eebc232.729.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0039a90d98455d529e3a94f1a3c63a2ab84c543e96a0f8d06657ce514a273f42
3
+ size 5480
runs/Aug11_13-16-26_a8082eebc232/events.out.tfevents.1723382232.a8082eebc232.729.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7445a2d508bf437b979c1ba72fc408ca088c2a0695dcbc57ae593209f96180e
3
+ size 5479
runs/Aug11_13-16-26_a8082eebc232/events.out.tfevents.1723382249.a8082eebc232.729.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65d4232f39fd4f0e7d3568aeaac0bc69fd0cd855940f1f88738d42a75cb7e191
3
+ size 5479
runs/Aug11_13-18-53_a8082eebc232/events.out.tfevents.1723382335.a8082eebc232.729.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5f48050be134233d793f1ba8a0501df81f0d800cda699e460a4810e9e166870
3
+ size 5479
runs/Aug11_13-20-26_a8082eebc232/events.out.tfevents.1723382426.a8082eebc232.729.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5111e8ab0838f941d249cebdbdf6f8da67165ac22494a2fffc9c46bb81c33ac4
3
+ size 5479
runs/Aug11_13-28-17_a8082eebc232/events.out.tfevents.1723382898.a8082eebc232.729.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15ba9f07843d8100c1d21ae55861a08a96fe032fe9b3d2ebb9692c97ae34bc88
3
+ size 5476
runs/Aug11_13-55-29_a8082eebc232/events.out.tfevents.1723384539.a8082eebc232.729.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dab79ea8bf1a27217c19f1c55dfac4744ad92232e7370d4d7444f6a763f16a0c
3
+ size 10582
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e879c01ae59912fd210dfbf4aea4f1006b4366ba9d0effcdc4f837966025c194
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:363e12f48112513db7279900301a23b6aa3522bb9cc036c1b72f81afd76e01b3
3
  size 5112