Hugging Face's logo

sazirarrwth99
/
kangoroo-no-subgraph-phi-3-mini-LoRA

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
sazirarrwth99 commited on
Commit
7b57b5e
·
verified ·
1 Parent(s): 1deef25

HuggingFaceUser/adapter-name

Browse files
Files changed (5) hide show
  1. README.md +11 -11
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. tokenizer.json +1 -6
  5. 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-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.2347
22
 
23
  ## Model description
24
 
@@ -52,16 +52,16 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:------:|:----:|:---------------:|
55
- | 1.4504 | 0.2892 | 100 | 1.0898 |
56
- | 0.8583 | 0.5785 | 200 | 0.6481 |
57
- | 0.5379 | 0.8677 | 300 | 0.4534 |
58
- | 0.4042 | 1.1569 | 400 | 0.3593 |
59
- | 0.335 | 1.4461 | 500 | 0.3093 |
60
- | 0.2927 | 1.7354 | 600 | 0.2779 |
61
- | 0.2728 | 2.0246 | 700 | 0.2590 |
62
- | 0.251 | 2.3138 | 800 | 0.2468 |
63
- | 0.2374 | 2.6030 | 900 | 0.2388 |
64
- | 0.236 | 2.8923 | 1000 | 0.2347 |
65
 
66
 
67
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.2338
22
 
23
  ## Model description
24
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:------:|:----:|:---------------:|
55
+ | 1.4504 | 0.2892 | 100 | 1.0894 |
56
+ | 0.8508 | 0.5785 | 200 | 0.6406 |
57
+ | 0.5328 | 0.8677 | 300 | 0.4493 |
58
+ | 0.4011 | 1.1569 | 400 | 0.3575 |
59
+ | 0.3328 | 1.4461 | 500 | 0.3085 |
60
+ | 0.291 | 1.7354 | 600 | 0.2769 |
61
+ | 0.2711 | 2.0246 | 700 | 0.2585 |
62
+ | 0.2494 | 2.3138 | 800 | 0.2453 |
63
+ | 0.2361 | 2.6030 | 900 | 0.2378 |
64
+ | 0.2348 | 2.8923 | 1000 | 0.2338 |
65
 
66
 
67
  ### Framework versions
adapter_config.json CHANGED
@@ -21,11 +21,11 @@
21
  "revision": null,
22
  "target_modules": [
23
  "q_proj",
 
 
24
  "o_proj",
25
  "up_proj",
26
- "gate_proj",
27
  "v_proj",
28
- "k_proj",
29
  "down_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
 
21
  "revision": null,
22
  "target_modules": [
23
  "q_proj",
24
+ "k_proj",
25
+ "gate_proj",
26
  "o_proj",
27
  "up_proj",
 
28
  "v_proj",
 
29
  "down_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa8c3e396f9d65f516404e364ad3e7b5d8708ae8f79de5f1476f923cad8fffa8
3
  size 35668592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79ba21bef598b7ff38e5b954d50b43531c9e568515c58d1fff239190482e54be
3
  size 35668592
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 512,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32b70e00533bebcbf93f8152c4c9136a3d95126383957e08baee8354de5dcb14
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61922441eeff57590b66cb2f5ced52a2642e7096ba9d81b02421ba0ee8a6020b
3
  size 5496