Hugging Face's logo

grounded-ai
/
phi3.5-hallucination-judge

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
 Metrics Community
1
Jlonge4 commited on
Commit
7b94199
·
verified ·
1 Parent(s): e7e4308

Jlonge4/outputs

Browse files
Files changed (5) hide show
  1. README.md +15 -20
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. runs/Sep08_14-08-07_b806891ca16b/events.out.tfevents.1725804489.b806891ca16b.4379.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -14,16 +14,12 @@ model-index:
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
  should probably proofread and complete it, then remove this comment. -->
16
 
17
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/7sv9jcq1)
18
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/7sv9jcq1)
19
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/dsbpmror)
20
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/tt98djcy)
21
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/tt98djcy)
22
  # outputs
23
 
24
  This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on the None dataset.
25
  It achieves the following results on the evaluation set:
26
- - Loss: 1.2249
27
 
28
  ## Model description
29
 
@@ -57,20 +53,19 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss |
59
  |:-------------:|:------:|:----:|:---------------:|
60
- | 1.979 | 0.5882 | 5 | 2.1552 |
61
- | 1.5649 | 1.1765 | 10 | 1.7044 |
62
- | 1.5355 | 1.7647 | 15 | 1.3163 |
63
- | 0.9301 | 2.3529 | 20 | 1.0521 |
64
- | 0.7935 | 2.9412 | 25 | 0.9929 |
65
- | 0.6411 | 3.5294 | 30 | 0.9735 |
66
- | 0.6521 | 4.1176 | 35 | 0.9699 |
67
- | 0.4867 | 4.7059 | 40 | 0.9812 |
68
- | 0.6112 | 5.2941 | 45 | 1.0029 |
69
- | 0.5041 | 5.8824 | 50 | 1.1055 |
70
- | 0.4784 | 6.4706 | 55 | 1.0859 |
71
- | 0.3787 | 7.0588 | 60 | 1.1113 |
72
- | 0.2676 | 7.6471 | 65 | 1.3963 |
73
- | 0.3066 | 8.2353 | 70 | 1.2249 |
74
 
75
 
76
  ### Framework versions
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
  should probably proofread and complete it, then remove this comment. -->
16
 
17
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/phi3.5-hallucination/runs/re0kg3gs)
 
 
 
 
18
  # outputs
19
 
20
  This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 1.3147
23
 
24
  ## Model description
25
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:------:|:----:|:---------------:|
56
+ | 2.2594 | 0.5263 | 5 | 2.2572 |
57
+ | 1.6785 | 1.0526 | 10 | 1.8170 |
58
+ | 1.6015 | 1.5789 | 15 | 1.4296 |
59
+ | 1.0556 | 2.1053 | 20 | 1.1199 |
60
+ | 0.9412 | 2.6316 | 25 | 1.0660 |
61
+ | 0.8872 | 3.1579 | 30 | 1.0523 |
62
+ | 0.9157 | 3.6842 | 35 | 1.0713 |
63
+ | 0.7735 | 4.2105 | 40 | 1.0983 |
64
+ | 0.6182 | 4.7368 | 45 | 1.0816 |
65
+ | 0.734 | 5.2632 | 50 | 1.1017 |
66
+ | 0.4736 | 5.7895 | 55 | 1.2109 |
67
+ | 0.3138 | 6.3158 | 60 | 1.2195 |
68
+ | 0.5315 | 6.8421 | 65 | 1.3147 |
 
69
 
70
 
71
  ### Framework versions
adapter_config.json CHANGED
@@ -22,9 +22,9 @@
22
  "target_modules": [
23
  "v_proj",
24
  "k_proj",
25
- "down_proj",
26
- "up_proj",
27
  "q_proj",
 
 
28
  "gate_proj",
29
  "o_proj"
30
  ],
 
22
  "target_modules": [
23
  "v_proj",
24
  "k_proj",
 
 
25
  "q_proj",
26
+ "up_proj",
27
+ "down_proj",
28
  "gate_proj",
29
  "o_proj"
30
  ],
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa0ee5d1cd74a882e54ea6740f67e2475df2f768c58d30859d5bc7041e49462e
3
  size 71320216
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16e318949cc27e82925fabdb5a23637cdf30959e69c3654b599c36c681a096f4
3
  size 71320216
runs/Sep08_14-08-07_b806891ca16b/events.out.tfevents.1725804489.b806891ca16b.4379.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c89650f8e1c9b746395af06b6cd59755ad19ec0363925902d4f01fe00d7c8b2
3
+ size 25336
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d6a63621a4deaf4f2435c3108521be660f015cdcbdf0e69d4626b98f36798d3
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00dcee86bb6127fb564089c887075fdbffe7cdac891f7689297b6ec5d7820104
3
  size 5432