Hugging Face's logo

Gunslinger3D
/
fine-tuning-Phi2-with-webglm-qa-with-lora

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
Community
Gunslinger3D commited on
Commit
ebf0a24
·
verified ·
1 Parent(s): f94b43b

fine-tuning-Phi2-with-webglm-qa-with-lora

Browse files
Files changed (4) hide show
  1. README.md +23 -8
  2. adapter_config.json +4 -4
  3. adapter_model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.5112
20
 
21
  ## Model description
22
 
@@ -43,19 +43,34 @@ The following hyperparameters were used during training:
43
  - total_train_batch_size: 10
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
- - lr_scheduler_warmup_steps: 10
47
- - training_steps: 50
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
- | 8.0656 | 0.2 | 10 | 6.1207 |
55
- | 3.4473 | 0.4 | 20 | 0.9409 |
56
- | 0.6293 | 0.6 | 30 | 0.5648 |
57
- | 0.455 | 0.8 | 40 | 0.5257 |
58
- | 0.4325 | 1.0 | 50 | 0.5112 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
 
60
 
61
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.2084
20
 
21
  ## Model description
22
 
 
43
  - total_train_batch_size: 10
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 20
47
+ - training_steps: 200
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
+ | No log | 0.2 | 10 | 7.3955 |
55
+ | 7.0321 | 0.4 | 20 | 2.6772 |
56
+ | 7.0321 | 0.6 | 30 | 0.5779 |
57
+ | 0.751 | 0.8 | 40 | 0.5021 |
58
+ | 0.751 | 1.0 | 50 | 0.4501 |
59
+ | 0.3719 | 1.2 | 60 | 0.4067 |
60
+ | 0.3719 | 1.39 | 70 | 0.3655 |
61
+ | 0.3398 | 1.59 | 80 | 0.3302 |
62
+ | 0.3398 | 1.79 | 90 | 0.3029 |
63
+ | 0.2285 | 1.99 | 100 | 0.2831 |
64
+ | 0.2285 | 2.19 | 110 | 0.2666 |
65
+ | 0.2156 | 2.39 | 120 | 0.2549 |
66
+ | 0.2156 | 2.59 | 130 | 0.2435 |
67
+ | 0.2049 | 2.79 | 140 | 0.2324 |
68
+ | 0.2049 | 2.99 | 150 | 0.2246 |
69
+ | 0.177 | 3.19 | 160 | 0.2197 |
70
+ | 0.177 | 3.39 | 170 | 0.2149 |
71
+ | 0.1745 | 3.59 | 180 | 0.2112 |
72
+ | 0.1745 | 3.78 | 190 | 0.2091 |
73
+ | 0.1742 | 3.98 | 200 | 0.2084 |
74
 
75
 
76
  ### Framework versions
adapter_config.json CHANGED
@@ -19,12 +19,12 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
 
22
  "k_proj",
23
  "v_proj",
24
- "fc1",
25
- "fc2",
26
- "q_proj",
27
- "dense"
28
  ],
29
  "task_type": "CAUSAL_LM"
30
  }
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "q_proj",
23
+ "fc1",
24
  "k_proj",
25
  "v_proj",
26
+ "dense",
27
+ "fc2"
 
 
28
  ],
29
  "task_type": "CAUSAL_LM"
30
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20b26d06164cbc59c6eb5c608e01279ec6aafc6e98021551dc840350210cb582
3
  size 94422368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:642bc97daf234a6c3585b392cde64c46485745914a0c28276e04be19cc11c18c
3
  size 94422368
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e5612a777b0fa79303c9a2432f3a86539e7e19bb8723dde492cfaf93aff3767
3
  size 4283
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a033dae6c1f16aa354b5a33bbad2a7b0332a8a83d882ff79922e8195f69e1e9
3
  size 4283