ykeselman commited on
Commit
764f2c4
·
verified ·
1 Parent(s): 70f722f

ykeselman/shawgpt-ft

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: 1.7481
20
 
21
  ## Model description
22
 
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
- | 4.5906 | 0.9231 | 3 | 3.9591 |
55
- | 4.0332 | 1.8462 | 6 | 3.4281 |
56
- | 3.4449 | 2.7692 | 9 | 2.9666 |
57
- | 2.2374 | 4.0 | 13 | 2.5460 |
58
- | 2.6475 | 4.9231 | 16 | 2.2995 |
59
- | 2.3153 | 5.8462 | 19 | 2.0970 |
60
- | 2.0673 | 6.7692 | 22 | 1.9296 |
61
- | 1.4405 | 8.0 | 26 | 1.7996 |
62
- | 1.8224 | 8.9231 | 29 | 1.7535 |
63
- | 1.2669 | 9.2308 | 30 | 1.7481 |
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: 1.7286
20
 
21
  ## Model description
22
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 4.5912 | 0.9231 | 3 | 3.9649 |
55
+ | 4.0436 | 1.8462 | 6 | 3.4483 |
56
+ | 3.4693 | 2.7692 | 9 | 2.9914 |
57
+ | 2.2513 | 4.0 | 13 | 2.5516 |
58
+ | 2.6391 | 4.9231 | 16 | 2.2852 |
59
+ | 2.2998 | 5.8462 | 19 | 2.0547 |
60
+ | 2.017 | 6.7692 | 22 | 1.8842 |
61
+ | 1.4172 | 8.0 | 26 | 1.7734 |
62
+ | 1.8045 | 8.9231 | 29 | 1.7333 |
63
+ | 1.2588 | 9.2308 | 30 | 1.7286 |
64
 
65
 
66
  ### Framework versions
runs/Jun03_01-52-31_ecfb50d735fa/events.out.tfevents.1717379552.ecfb50d735fa.2419.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c24bc754cdd798a890b662e95bc95fa0e4ad91f2b96685c384afd5b8b8cb130
3
+ size 10532
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97fcc56fa2317ae1cf1d34710472dae8068359a1fccc082876b378a5cc28c4de
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bb0645f4650c568093e4b911f2a9b3fcebe49be5ffe193abef37043fe28e893
3
  size 5112