Hugging Face's logo

Stern5497
/
org_modelorg_model

PEFT
Safetensors
Generated from Trainer
Model card Files Community
Stern5497 commited on
Commit
7bd338b
·
verified ·
1 Parent(s): 5387d00

mistral-lp2-org_org_b

Browse files
Files changed (3) hide show
  1. README.md +20 -20
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +2 -2
README.md CHANGED
@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.0772
20
- - F1 Micro: 0.5885
21
- - F1 Macro: 0.5884
22
- - F1 Weighted: 0.5884
23
 
24
  ## Model description
25
 
@@ -50,22 +50,22 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | F1 Weighted |
52
  |:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|:-----------:|
53
- | 1.6909 | 0.0064 | 25 | 1.5440 | 0.5095 | 0.5089 | 0.5089 |
54
- | 1.4631 | 0.0127 | 50 | 1.4130 | 0.5483 | 0.5458 | 0.5458 |
55
- | 1.3764 | 0.0191 | 75 | 1.2988 | 0.5543 | 0.5543 | 0.5543 |
56
- | 1.2402 | 0.0255 | 100 | 1.2464 | 0.5623 | 0.5621 | 0.5621 |
57
- | 1.1982 | 0.0318 | 125 | 1.2415 | 0.5580 | 0.5544 | 0.5544 |
58
- | 1.1759 | 0.0382 | 150 | 1.1822 | 0.5732 | 0.5728 | 0.5728 |
59
- | 1.0769 | 0.0446 | 175 | 1.1590 | 0.5788 | 0.5787 | 0.5787 |
60
- | 1.0388 | 0.0510 | 200 | 1.1416 | 0.5821 | 0.5820 | 0.5820 |
61
- | 1.1786 | 0.0573 | 225 | 1.1273 | 0.5815 | 0.5806 | 0.5806 |
62
- | 1.2269 | 0.0637 | 250 | 1.1233 | 0.5823 | 0.5798 | 0.5798 |
63
- | 1.1746 | 0.0701 | 275 | 1.1105 | 0.5833 | 0.5819 | 0.5819 |
64
- | 1.1455 | 0.0764 | 300 | 1.0927 | 0.5868 | 0.5864 | 0.5864 |
65
- | 1.0494 | 0.0828 | 325 | 1.0905 | 0.5873 | 0.5867 | 0.5867 |
66
- | 1.0199 | 0.0892 | 350 | 1.0853 | 0.5845 | 0.5836 | 0.5836 |
67
- | 1.1086 | 0.0955 | 375 | 1.0789 | 0.5852 | 0.5849 | 0.5849 |
68
- | 1.0726 | 0.1019 | 400 | 1.0772 | 0.5885 | 0.5884 | 0.5884 |
69
 
70
 
71
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.9110
20
+ - F1 Micro: 0.8214
21
+ - F1 Macro: 0.8156
22
+ - F1 Weighted: 0.8234
23
 
24
  ## Model description
25
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | F1 Weighted |
52
  |:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|:-----------:|
53
+ | 1.979 | 0.0154 | 25 | 1.4043 | 0.7220 | 0.7197 | 0.7259 |
54
+ | 1.3006 | 0.0308 | 50 | 1.2184 | 0.7775 | 0.7754 | 0.7807 |
55
+ | 1.1099 | 0.0462 | 75 | 1.1320 | 0.8010 | 0.7970 | 0.8040 |
56
+ | 1.1383 | 0.0615 | 100 | 1.0762 | 0.8039 | 0.8007 | 0.8072 |
57
+ | 1.0121 | 0.0769 | 125 | 1.0230 | 0.8010 | 0.7967 | 0.8037 |
58
+ | 1.0296 | 0.0923 | 150 | 0.9966 | 0.8099 | 0.8056 | 0.8130 |
59
+ | 1.0485 | 0.1077 | 175 | 0.9745 | 0.8111 | 0.8063 | 0.8139 |
60
+ | 0.9996 | 0.1231 | 200 | 0.9647 | 0.8030 | 0.7984 | 0.8052 |
61
+ | 0.9815 | 0.1385 | 225 | 0.9490 | 0.8160 | 0.8099 | 0.8178 |
62
+ | 0.9456 | 0.1538 | 250 | 0.9378 | 0.8073 | 0.8033 | 0.8099 |
63
+ | 0.8896 | 0.1692 | 275 | 0.9298 | 0.8143 | 0.8091 | 0.8164 |
64
+ | 0.994 | 0.1846 | 300 | 0.9239 | 0.8064 | 0.8030 | 0.8094 |
65
+ | 0.8588 | 0.2 | 325 | 0.9142 | 0.8119 | 0.8079 | 0.8145 |
66
+ | 0.8971 | 0.2154 | 350 | 0.9139 | 0.8216 | 0.8158 | 0.8236 |
67
+ | 0.9647 | 0.2308 | 375 | 0.9133 | 0.8223 | 0.8163 | 0.8242 |
68
+ | 0.9352 | 0.2462 | 400 | 0.9110 | 0.8214 | 0.8156 | 0.8234 |
69
 
70
 
71
  ### Framework versions
adapter_config.json CHANGED
@@ -21,9 +21,9 @@
21
  "revision": null,
22
  "target_modules": [
23
  "k_proj",
24
- "o_proj",
25
  "q_proj",
26
- "v_proj"
 
27
  ],
28
  "task_type": "SEQ_CLS",
29
  "use_dora": false,
 
21
  "revision": null,
22
  "target_modules": [
23
  "k_proj",
 
24
  "q_proj",
25
+ "v_proj",
26
+ "o_proj"
27
  ],
28
  "task_type": "SEQ_CLS",
29
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7e9e1fb8e1abe63fe0d987d382ffdc272daebad148deafa2db923fe3c642e17
3
- size 578881968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d287f3e911660a53e7f747ea43f5714abadb39a0ac9ea29328dfffd8e531d587
3
+ size 578898352