Hugging Face's logo

MathiasBrussow
/
shawgpt-ft

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
MathiasBrussow commited on
Commit
0eefe18
•
1 Parent(s): d7e3a73

MathiasBrussow/shawgpt-ft

Browse files
Files changed (3) hide show
  1. README.md +27 -27
  2. runs/Oct24_14-16-18_c9e665a1658b/events.out.tfevents.1729779378.c9e665a1658b.1073.1 +3 -0
  3. 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: 1.3327
20
 
21
  ## Model description
22
 
@@ -51,32 +51,32 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-------:|:----:|:---------------:|
54
- | 4.9892 | 0.8571 | 3 | 4.1652 |
55
- | 3.4756 | 2.0 | 7 | 3.7140 |
56
- | 4.1288 | 2.8571 | 10 | 3.3485 |
57
- | 2.74 | 4.0 | 14 | 2.9038 |
58
- | 3.2574 | 4.8571 | 17 | 2.6228 |
59
- | 2.1252 | 6.0 | 21 | 2.2779 |
60
- | 2.4458 | 6.8571 | 24 | 2.0512 |
61
- | 1.6206 | 8.0 | 28 | 1.7919 |
62
- | 1.9223 | 8.8571 | 31 | 1.6560 |
63
- | 1.2633 | 10.0 | 35 | 1.5061 |
64
- | 1.6093 | 10.8571 | 38 | 1.4323 |
65
- | 1.0947 | 12.0 | 42 | 1.3917 |
66
- | 1.4763 | 12.8571 | 45 | 1.3740 |
67
- | 1.0425 | 14.0 | 49 | 1.3550 |
68
- | 1.4106 | 14.8571 | 52 | 1.3455 |
69
- | 1.0377 | 16.0 | 56 | 1.3378 |
70
- | 1.3563 | 16.8571 | 59 | 1.3361 |
71
- | 0.9793 | 18.0 | 63 | 1.3342 |
72
- | 1.3045 | 18.8571 | 66 | 1.3328 |
73
- | 0.942 | 20.0 | 70 | 1.3332 |
74
- | 1.3308 | 20.8571 | 73 | 1.3338 |
75
- | 0.9164 | 22.0 | 77 | 1.3343 |
76
- | 1.2619 | 22.8571 | 80 | 1.3345 |
77
- | 0.9497 | 24.0 | 84 | 1.3335 |
78
- | 1.2863 | 24.8571 | 87 | 1.3328 |
79
- | 0.8351 | 25.7143 | 90 | 1.3327 |
80
 
81
 
82
  ### 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: 1.3302
20
 
21
  ## Model description
22
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-------:|:----:|:---------------:|
54
+ | 4.9895 | 0.8571 | 3 | 4.1658 |
55
+ | 3.4778 | 2.0 | 7 | 3.7207 |
56
+ | 4.1399 | 2.8571 | 10 | 3.3552 |
57
+ | 2.747 | 4.0 | 14 | 2.9052 |
58
+ | 3.2593 | 4.8571 | 17 | 2.6105 |
59
+ | 2.1018 | 6.0 | 21 | 2.2608 |
60
+ | 2.4159 | 6.8571 | 24 | 2.0093 |
61
+ | 1.6044 | 8.0 | 28 | 1.7780 |
62
+ | 1.9126 | 8.8571 | 31 | 1.6498 |
63
+ | 1.2575 | 10.0 | 35 | 1.5062 |
64
+ | 1.6232 | 10.8571 | 38 | 1.4496 |
65
+ | 1.1013 | 12.0 | 42 | 1.3928 |
66
+ | 1.4709 | 12.8571 | 45 | 1.3688 |
67
+ | 1.0337 | 14.0 | 49 | 1.3495 |
68
+ | 1.4037 | 14.8571 | 52 | 1.3399 |
69
+ | 1.0328 | 16.0 | 56 | 1.3307 |
70
+ | 1.3526 | 16.8571 | 59 | 1.3277 |
71
+ | 0.9745 | 18.0 | 63 | 1.3259 |
72
+ | 1.299 | 18.8571 | 66 | 1.3254 |
73
+ | 0.9387 | 20.0 | 70 | 1.3259 |
74
+ | 1.3275 | 20.8571 | 73 | 1.3271 |
75
+ | 0.9127 | 22.0 | 77 | 1.3290 |
76
+ | 1.2574 | 22.8571 | 80 | 1.3300 |
77
+ | 0.9474 | 24.0 | 84 | 1.3305 |
78
+ | 1.2843 | 24.8571 | 87 | 1.3302 |
79
+ | 0.8341 | 25.7143 | 90 | 1.3302 |
80
 
81
 
82
  ### Framework versions
runs/Oct24_14-16-18_c9e665a1658b/events.out.tfevents.1729779378.c9e665a1658b.1073.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ca38c5b1f1b45b2322a43efa32190c8b20bc9085fe0114e302015eac17fad06
3
+ size 18228
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4364efe670a0f15277002a359873c1eb08fa4beb6e4cd35994eb0094db85793
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b104814c6b87554a1e95a6b9ab24336576aa7d5568eeee420c00145507dcb32a
3
  size 5176