Hugging Face's logo

Litzy619
/
V0413TUNE

Safetensors
Generated from Trainer
Model card Files
xet
 Community
Litzy619 commited on
Commit
9137f92
·
verified ·
1 Parent(s): 8307bd5

End of training

Browse files
Files changed (5) hide show
  1. README.md +27 -49
  2. adapter_config.json +1 -1
  3. adapter_model.bin +2 -2
  4. model.safetensors +2 -2
  5. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.0636
19
 
20
  ## Model description
21
 
@@ -34,15 +34,15 @@ More information needed
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
- - learning_rate: 0.03
38
  - train_batch_size: 8
39
  - eval_batch_size: 8
40
  - seed: 42
41
- - gradient_accumulation_steps: 8
42
- - total_train_batch_size: 64
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: cosine_with_restarts
45
- - lr_scheduler_warmup_steps: 100
46
  - num_epochs: 4
47
  - mixed_precision_training: Native AMP
48
 
@@ -50,50 +50,28 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
- | 0.1876 | 0.09 | 20 | 0.2016 |
54
- | 4.5112 | 0.18 | 40 | 1.8999 |
55
- | 0.7446 | 0.27 | 60 | 0.4058 |
56
- | 0.3379 | 0.36 | 80 | 0.3014 |
57
- | 0.2506 | 0.45 | 100 | 0.2398 |
58
- | 0.1933 | 0.54 | 120 | 0.2279 |
59
- | 0.2005 | 0.63 | 140 | 0.1848 |
60
- | 0.1367 | 0.73 | 160 | 0.1201 |
61
- | 0.1361 | 0.82 | 180 | 0.0999 |
62
- | 0.1106 | 0.91 | 200 | 0.0905 |
63
- | 0.093 | 1.0 | 220 | 0.0935 |
64
- | 0.1242 | 1.09 | 240 | 0.0901 |
65
- | 0.1143 | 1.18 | 260 | 0.1028 |
66
- | 0.0818 | 1.27 | 280 | 0.0830 |
67
- | 0.0722 | 1.36 | 300 | 0.0709 |
68
- | 0.0897 | 1.45 | 320 | 0.0690 |
69
- | 0.2688 | 1.54 | 340 | 0.2063 |
70
- | 0.1379 | 1.63 | 360 | 0.1408 |
71
- | 0.0929 | 1.72 | 380 | 0.1110 |
72
- | 0.0888 | 1.81 | 400 | 0.0990 |
73
- | 0.1141 | 1.9 | 420 | 0.1052 |
74
- | 0.135 | 1.99 | 440 | 0.0935 |
75
- | 0.0927 | 2.08 | 460 | 0.0930 |
76
- | 0.0926 | 2.18 | 480 | 0.0848 |
77
- | 0.0846 | 2.27 | 500 | 0.0716 |
78
- | 0.0753 | 2.36 | 520 | 0.0791 |
79
- | 0.0785 | 2.45 | 540 | 0.0737 |
80
- | 0.0814 | 2.54 | 560 | 0.0757 |
81
- | 0.0734 | 2.63 | 580 | 0.0707 |
82
- | 0.0764 | 2.72 | 600 | 0.0745 |
83
- | 0.0811 | 2.81 | 620 | 0.0766 |
84
- | 0.0901 | 2.9 | 640 | 0.0672 |
85
- | 0.0638 | 2.99 | 660 | 0.0646 |
86
- | 0.0672 | 3.08 | 680 | 0.0668 |
87
- | 0.0742 | 3.17 | 700 | 0.0655 |
88
- | 0.0682 | 3.26 | 720 | 0.0649 |
89
- | 0.0688 | 3.35 | 740 | 0.0653 |
90
- | 0.0687 | 3.44 | 760 | 0.0650 |
91
- | 0.0718 | 3.54 | 780 | 0.0657 |
92
- | 0.0704 | 3.63 | 800 | 0.0666 |
93
- | 0.0698 | 3.72 | 820 | 0.0642 |
94
- | 0.0665 | 3.81 | 840 | 0.0638 |
95
- | 0.0677 | 3.9 | 860 | 0.0636 |
96
- | 0.0688 | 3.99 | 880 | 0.0636 |
97
 
98
 
99
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0627
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - learning_rate: 0.003
38
  - train_batch_size: 8
39
  - eval_batch_size: 8
40
  - seed: 42
41
+ - gradient_accumulation_steps: 16
42
+ - total_train_batch_size: 128
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: cosine_with_restarts
45
+ - lr_scheduler_warmup_steps: 60
46
  - num_epochs: 4
47
  - mixed_precision_training: Native AMP
48
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | 0.3029 | 0.18 | 20 | 0.1446 |
54
+ | 0.1104 | 0.36 | 40 | 0.0922 |
55
+ | 0.1097 | 0.54 | 60 | 0.0957 |
56
+ | 0.0823 | 0.73 | 80 | 0.0792 |
57
+ | 0.0772 | 0.91 | 100 | 0.0679 |
58
+ | 0.0717 | 1.09 | 120 | 0.0672 |
59
+ | 0.0716 | 1.27 | 140 | 0.0666 |
60
+ | 0.0729 | 1.45 | 160 | 0.0667 |
61
+ | 0.069 | 1.63 | 180 | 0.0634 |
62
+ | 0.065 | 1.81 | 200 | 0.0628 |
63
+ | 0.0644 | 1.99 | 220 | 0.0637 |
64
+ | 0.0592 | 2.18 | 240 | 0.0605 |
65
+ | 0.0587 | 2.36 | 260 | 0.0630 |
66
+ | 0.0518 | 2.54 | 280 | 0.0652 |
67
+ | 0.0636 | 2.72 | 300 | 0.0612 |
68
+ | 0.0522 | 2.9 | 320 | 0.0634 |
69
+ | 0.05 | 3.08 | 340 | 0.0626 |
70
+ | 0.0541 | 3.26 | 360 | 0.0679 |
71
+ | 0.0506 | 3.44 | 380 | 0.0630 |
72
+ | 0.0527 | 3.63 | 400 | 0.0627 |
73
+ | 0.0503 | 3.81 | 420 | 0.0627 |
74
+ | 0.0463 | 3.99 | 440 | 0.0627 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
 
76
 
77
  ### Framework versions
adapter_config.json CHANGED
@@ -15,7 +15,7 @@
15
  "ot_diversified_prefix": false,
16
  "peft_type": "M_PREFIX",
17
  "prefix_projection": true,
18
- "scale": 128,
19
  "task_type": "CAUSAL_LM",
20
  "token_dim": 2560
21
  }
 
15
  "ot_diversified_prefix": false,
16
  "peft_type": "M_PREFIX",
17
  "prefix_projection": true,
18
+ "scale": 64,
19
  "task_type": "CAUSAL_LM",
20
  "token_dim": 2560
21
  }
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53671f5b075411ebc6c760dcd5f8e93b55cd272fe0509be6223ea4ca2316fa86
3
- size 77888436
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cf4f787fe570501cff5d0c3578053024e6e74db307873ffd00e512da96fd3f5
3
+ size 84237364
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2c52b29ec49261e1193b0b42d88175b5ae5d75b7ee24c903accdd0967f353dd
3
- size 5637295888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9a46fa164cbcfdfe1c284818369c611b431218f73a19d8507b38f648d275e3d
3
+ size 5643644816
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cb10f3239a76fbf26c050872ecad13cd9bbef273900fa4757369da9cd3f44a8
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77719a1b871ea8aea0933d9dfa6d7f01ae41f29794f5e5d22e5c99a88d9ef559
3
  size 5112