Hugging Face's logo

Litzy619
/
V0413TUNE

Safetensors
Generated from Trainer
Model card Files Community
Litzy619 commited on
Commit
83a9228
·
verified ·
1 Parent(s): 1d9aaa3

End of training

Browse files
Files changed (5) hide show
  1. README.md +26 -37
  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: 0.0659
19
 
20
  ## Model description
21
 
@@ -34,7 +34,7 @@ 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
@@ -42,47 +42,36 @@ The following hyperparameters were used during training:
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: 60
46
- - num_epochs: 3
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
- | 0.4057 | 0.09 | 20 | 0.1912 |
54
- | 3.1643 | 0.18 | 40 | 3.5631 |
55
- | 1.7137 | 0.27 | 60 | 0.7116 |
56
- | 0.4077 | 0.36 | 80 | 0.3601 |
57
- | 0.2647 | 0.45 | 100 | 0.2633 |
58
- | 0.2043 | 0.54 | 120 | 0.1965 |
59
- | 0.1735 | 0.63 | 140 | 0.1777 |
60
- | 0.1666 | 0.73 | 160 | 0.1946 |
61
- | 0.1466 | 0.82 | 180 | 0.1591 |
62
- | 0.1599 | 0.91 | 200 | 0.1447 |
63
- | 0.1384 | 1.0 | 220 | 0.1248 |
64
- | 0.1252 | 1.09 | 240 | 0.1200 |
65
- | 0.1191 | 1.18 | 260 | 0.1280 |
66
- | 0.1194 | 1.27 | 280 | 0.1161 |
67
- | 0.1086 | 1.36 | 300 | 0.1034 |
68
- | 0.1191 | 1.45 | 320 | 0.1003 |
69
- | 0.1072 | 1.54 | 340 | 0.1124 |
70
- | 0.0878 | 1.63 | 360 | 0.1226 |
71
- | 0.0952 | 1.72 | 380 | 0.0894 |
72
- | 0.0783 | 1.81 | 400 | 0.0916 |
73
- | 0.087 | 1.9 | 420 | 0.0957 |
74
- | 0.0863 | 1.99 | 440 | 0.0817 |
75
- | 0.0965 | 2.08 | 460 | 0.0910 |
76
- | 0.0842 | 2.18 | 480 | 0.0840 |
77
- | 0.0773 | 2.27 | 500 | 0.0812 |
78
- | 0.0737 | 2.36 | 520 | 0.0794 |
79
- | 0.0736 | 2.45 | 540 | 0.0724 |
80
- | 0.0753 | 2.54 | 560 | 0.0693 |
81
- | 0.0725 | 2.63 | 580 | 0.0677 |
82
- | 0.0688 | 2.72 | 600 | 0.0659 |
83
- | 0.0701 | 2.81 | 620 | 0.0656 |
84
- | 0.0672 | 2.9 | 640 | 0.0659 |
85
- | 0.0628 | 2.99 | 660 | 0.0659 |
86
 
87
 
88
  ### 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: 0.1522
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
 
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: 2
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | 0.6884 | 0.09 | 20 | 0.1584 |
54
+ | 0.1153 | 0.18 | 40 | 0.0993 |
55
+ | 0.096 | 0.27 | 60 | 0.0854 |
56
+ | 0.1014 | 0.36 | 80 | 0.0820 |
57
+ | 0.0813 | 0.45 | 100 | 0.0795 |
58
+ | 0.1016 | 0.54 | 120 | 0.0772 |
59
+ | 0.0957 | 0.63 | 140 | 0.0804 |
60
+ | 0.076 | 0.73 | 160 | 0.0816 |
61
+ | 0.0872 | 0.82 | 180 | 0.0851 |
62
+ | 0.0836 | 0.91 | 200 | 0.0715 |
63
+ | 0.0916 | 1.0 | 220 | 0.0800 |
64
+ | 0.0849 | 1.09 | 240 | 0.0822 |
65
+ | 1.7258 | 1.18 | 260 | 0.2365 |
66
+ | 0.2299 | 1.27 | 280 | 0.1816 |
67
+ | 0.1833 | 1.36 | 300 | 0.1711 |
68
+ | 0.1657 | 1.45 | 320 | 0.1619 |
69
+ | 0.1601 | 1.54 | 340 | 0.1557 |
70
+ | 0.1522 | 1.63 | 360 | 0.1565 |
71
+ | 0.1553 | 1.72 | 380 | 0.1532 |
72
+ | 0.1547 | 1.81 | 400 | 0.1525 |
73
+ | 0.1548 | 1.9 | 420 | 0.1521 |
74
+ | 0.1532 | 1.99 | 440 | 0.1522 |
 
 
 
 
 
 
 
 
 
 
 
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:c257b2f18621f7cbbbb4f2992df20d59e35cfd87db29e6666c02b57da48ad335
3
- size 77888436
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d02c1c7d7b3ae424e4762ec9cfa89831a531eeab4626a9bbcf86c660383b54df
3
+ size 84237364
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:315c3d017443fee2cfa959c581e1584a70d1fcd47a1e608bd850c09b8a8036e0
3
- size 5637295888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b155556b0890a7ec59f06ed4bbb575d6e8c7dccd6a12db8f1bdb92bc7afad02
3
+ size 5643644816
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f67ca9150275046a835c862bcc8ec073373740337187a867ad0f9a0e08bf613
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e883bc2a82c1c15a22629bc29ddd888bbfd1a0cdf082fc3a57fc5aee566f580
3
  size 5112