Hugging Face's logo

KrithikV
/
phi-3-mini-LoRA-MEDQA-Extended-V2

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
KrithikV commited on
Commit
2164c1c
•
1 Parent(s): f605ec5

HuggingFaceUser/adapter-medmobile-MEDQA-Extended-V2

Browse files
Files changed (4) hide show
  1. README.md +14 -14
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.6514
22
 
23
  ## Model description
24
 
@@ -52,19 +52,19 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:------:|:----:|:---------------:|
55
- | 0.7812 | 0.2205 | 100 | 0.6947 |
56
- | 0.6795 | 0.4410 | 200 | 0.6694 |
57
- | 0.6686 | 0.6615 | 300 | 0.6633 |
58
- | 0.662 | 0.8820 | 400 | 0.6597 |
59
- | 0.6603 | 1.1025 | 500 | 0.6578 |
60
- | 0.6586 | 1.3230 | 600 | 0.6566 |
61
- | 0.6538 | 1.5436 | 700 | 0.6552 |
62
- | 0.6551 | 1.7641 | 800 | 0.6539 |
63
- | 0.6542 | 1.9846 | 900 | 0.6535 |
64
- | 0.65 | 2.2051 | 1000 | 0.6525 |
65
- | 0.6522 | 2.4256 | 1100 | 0.6519 |
66
- | 0.6526 | 2.6461 | 1200 | 0.6515 |
67
- | 0.6501 | 2.8666 | 1300 | 0.6514 |
68
 
69
 
70
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.6515
22
 
23
  ## Model description
24
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:------:|:----:|:---------------:|
55
+ | 0.7812 | 0.2205 | 100 | 0.6948 |
56
+ | 0.6796 | 0.4410 | 200 | 0.6695 |
57
+ | 0.6687 | 0.6615 | 300 | 0.6632 |
58
+ | 0.662 | 0.8820 | 400 | 0.6599 |
59
+ | 0.6603 | 1.1025 | 500 | 0.6579 |
60
+ | 0.6587 | 1.3230 | 600 | 0.6568 |
61
+ | 0.6539 | 1.5436 | 700 | 0.6553 |
62
+ | 0.6552 | 1.7641 | 800 | 0.6540 |
63
+ | 0.6542 | 1.9846 | 900 | 0.6537 |
64
+ | 0.6501 | 2.2051 | 1000 | 0.6526 |
65
+ | 0.6523 | 2.4256 | 1100 | 0.6521 |
66
+ | 0.6527 | 2.6461 | 1200 | 0.6517 |
67
+ | 0.6502 | 2.8666 | 1300 | 0.6515 |
68
 
69
 
70
  ### Framework versions
adapter_config.json CHANGED
@@ -20,10 +20,10 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "k_proj",
24
- "o_proj",
25
  "down_proj",
26
  "v_proj",
 
 
27
  "gate_proj",
28
  "up_proj",
29
  "q_proj"
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
23
  "down_proj",
24
  "v_proj",
25
+ "k_proj",
26
+ "o_proj",
27
  "gate_proj",
28
  "up_proj",
29
  "q_proj"
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae7a6cefb918ee896b41b1913036d37c90b13eb5eb60921c7bf04efd382bd474
3
  size 35668592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa39a531c2b2f0a18c6ba3c1f94111d242353a300700bdb12d0e3078b36ecd3e
3
  size 35668592
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3200cacdbf6038841f7a633c935b621d26820e1bf43a0e670e09af0144f38b36
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff735684cabecace78715d302be331934f135e61db17a81c0a36bb73e4fd1fbb
3
  size 5432