jaewoongy commited on
Commit
a5c8be3
1 Parent(s): 4f4a046

jaewoongy/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: 1.9111
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
- | 4.5953 | 0.9231 | 3 | 3.9704 |
55
- | 4.0578 | 1.8462 | 6 | 3.4542 |
56
- | 3.4931 | 2.7692 | 9 | 3.0091 |
57
- | 2.2808 | 4.0 | 13 | 2.5854 |
58
- | 2.7047 | 4.9231 | 16 | 2.3410 |
59
- | 2.3813 | 5.8462 | 19 | 2.1513 |
60
- | 2.1956 | 6.7692 | 22 | 2.0353 |
61
- | 1.5823 | 8.0 | 26 | 1.9894 |
62
- | 2.0532 | 8.9231 | 29 | 1.9214 |
63
- | 1.4066 | 9.2308 | 30 | 1.9111 |
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: 1.8763
20
 
21
  ## Model description
22
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 4.593 | 0.9231 | 3 | 3.9590 |
55
+ | 4.0403 | 1.8462 | 6 | 3.4249 |
56
+ | 3.4588 | 2.7692 | 9 | 2.9732 |
57
+ | 2.2521 | 4.0 | 13 | 2.5500 |
58
+ | 2.6689 | 4.9231 | 16 | 2.3030 |
59
+ | 2.3419 | 5.8462 | 19 | 2.1148 |
60
+ | 2.1294 | 6.7692 | 22 | 1.9798 |
61
+ | 1.5309 | 8.0 | 26 | 1.9374 |
62
+ | 1.9897 | 8.9231 | 29 | 1.8893 |
63
+ | 1.3786 | 9.2308 | 30 | 1.8763 |
64
 
65
 
66
  ### Framework versions
runs/May22_02-06-46_4fdec434ef12/events.out.tfevents.1716343607.4fdec434ef12.415.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b3baea4be94e5323408415dba7baaa21fb61b5dd3de342f5e87832ac82fd1b4
3
+ size 10394
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:653c9e662f7bc99a43377d3e4f8a0faf86b9fafd2cc8bee30759cbdaa43e403e
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56ad4db50916d9a314cdde7c7ebf042eeaf5461a0cf44543bdf6b2e51d2afbd0
3
  size 4984