Hugging Face's logo

sofyc
/
Phi-3.5-MultiCap-tool-embedding-3

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
Community
sofyc commited on
Commit
0c71b78
·
verified ·
1 Parent(s): 861d4f0

commit

Browse files
Files changed (4) hide show
  1. README.md +14 -14
  2. adapter_config.json +5 -5
  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-3.5-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: 0.5231
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
- | 0.8788 | 0.2256 | 50 | 0.8798 |
56
- | 0.6183 | 0.4512 | 100 | 0.6252 |
57
- | 0.5702 | 0.6768 | 150 | 0.5789 |
58
- | 0.6166 | 0.9024 | 200 | 0.5593 |
59
- | 0.5435 | 1.1280 | 250 | 0.5481 |
60
- | 0.5317 | 1.3536 | 300 | 0.5401 |
61
- | 0.5013 | 1.5792 | 350 | 0.5345 |
62
- | 0.5488 | 1.8049 | 400 | 0.5307 |
63
- | 0.5368 | 2.0305 | 450 | 0.5280 |
64
- | 0.4823 | 2.2561 | 500 | 0.5259 |
65
- | 0.5289 | 2.4817 | 550 | 0.5245 |
66
- | 0.5358 | 2.7073 | 600 | 0.5237 |
67
- | 0.5462 | 2.9329 | 650 | 0.5231 |
68
 
69
 
70
  ### 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: 0.5221
22
 
23
  ## Model description
24
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:------:|:----:|:---------------:|
55
+ | 0.8799 | 0.2256 | 50 | 0.8806 |
56
+ | 0.6125 | 0.4512 | 100 | 0.6177 |
57
+ | 0.5659 | 0.6768 | 150 | 0.5733 |
58
+ | 0.6125 | 0.9024 | 200 | 0.5550 |
59
+ | 0.5402 | 1.1280 | 250 | 0.5448 |
60
+ | 0.5299 | 1.3536 | 300 | 0.5378 |
61
+ | 0.4997 | 1.5792 | 350 | 0.5331 |
62
+ | 0.549 | 1.8049 | 400 | 0.5296 |
63
+ | 0.5361 | 2.0305 | 450 | 0.5268 |
64
+ | 0.4821 | 2.2561 | 500 | 0.5249 |
65
+ | 0.5274 | 2.4817 | 550 | 0.5234 |
66
+ | 0.5344 | 2.7073 | 600 | 0.5227 |
67
+ | 0.546 | 2.9329 | 650 | 0.5221 |
68
 
69
 
70
  ### Framework versions
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "q_proj",
24
- "up_proj",
25
- "k_proj",
26
  "o_proj",
27
- "v_proj",
28
- "gate_proj",
29
- "down_proj"
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "v_proj",
24
  "q_proj",
 
 
25
  "o_proj",
26
+ "down_proj",
27
+ "k_proj",
28
+ "up_proj",
29
+ "gate_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c413dc3dcf0baedba774975f93b08ab86adb4cf1d644d82b5088ea50c1bd1b1
3
  size 35668592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3e19071bfc5c8fcc5c64ae77a9c64c5ca1474c94b89671c75cc0e2f2f803b22
3
  size 35668592
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7ea80feb8a2ff2b992fb9e3013b5abe59ebcf83a82ee40afbae3b78e5b99a29
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d2d90cf6c5ffa30dd14523c8aefb12bb129b42ab45f589808fac387e89e28e6
3
  size 5496