FrederikKlinkby commited on
Commit
b2e4b0b
1 Parent(s): f1a1ee8

shawgpt-ft-lr0.0002-wd0.001

Browse files
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: 1.3126
20
 
21
  ## Model description
22
 
@@ -51,18 +51,18 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-------:|:----:|:---------------:|
54
- | 3.0381 | 0.9231 | 3 | 2.4992 |
55
- | 2.3477 | 1.8462 | 6 | 1.9579 |
56
- | 1.8587 | 2.7692 | 9 | 1.6834 |
57
- | 1.1848 | 4.0 | 13 | 1.4879 |
58
- | 1.4757 | 4.9231 | 16 | 1.4086 |
59
- | 1.3626 | 5.8462 | 19 | 1.3707 |
60
- | 1.3014 | 6.7692 | 22 | 1.3461 |
61
- | 0.9799 | 8.0 | 26 | 1.3250 |
62
- | 1.279 | 8.9231 | 29 | 1.3174 |
63
- | 1.2422 | 9.8462 | 32 | 1.3141 |
64
- | 1.2599 | 10.7692 | 35 | 1.3127 |
65
- | 0.2131 | 11.0769 | 36 | 1.3126 |
66
 
67
 
68
  ### 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: 1.7845
20
 
21
  ## Model description
22
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-------:|:----:|:---------------:|
54
+ | 4.6121 | 0.9231 | 3 | 4.0587 |
55
+ | 4.2126 | 1.8462 | 6 | 3.6493 |
56
+ | 3.7297 | 2.7692 | 9 | 3.2522 |
57
+ | 2.4733 | 4.0 | 13 | 2.8156 |
58
+ | 2.9598 | 4.9231 | 16 | 2.5689 |
59
+ | 2.6551 | 5.8462 | 19 | 2.3614 |
60
+ | 2.3985 | 6.7692 | 22 | 2.1826 |
61
+ | 1.6623 | 8.0 | 26 | 1.9991 |
62
+ | 2.0403 | 8.9231 | 29 | 1.8808 |
63
+ | 1.9001 | 9.8462 | 32 | 1.8158 |
64
+ | 1.8688 | 10.7692 | 35 | 1.7877 |
65
+ | 0.3703 | 11.0769 | 36 | 1.7845 |
66
 
67
 
68
  ### Framework versions
runs/Oct22_10-26-50_99867d27916d/events.out.tfevents.1729592811.99867d27916d.882.38 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b421011bd118628bde1250243cde17f8917071b40b898c246a3a9bd45593eeb
3
+ size 10364
runs/Oct22_11-37-15_99867d27916d/events.out.tfevents.1729597035.99867d27916d.882.62 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:696d65c92bb9e716a91639f8d0c4c2b53dea1f858f3701b892413ff57075cfe7
3
+ size 11658
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27e768fc2c94b170a238402db2ffb74fd9ac14e61d43447c0c76e5da983eae3a
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2f70c555ef2459170c1ee079e591abdbb5147fcaa9a6362402e35d11a28f531
3
  size 5240