Hugging Face's logo

masta-g3
/
phi-1_5-psychology

Text Generation
Transformers
PyTorch
mixformer-sequential
Generated from Trainer
custom_code
Model card Files Community
masta-g3 commited on
Commit
c3a9631
•
1 Parent(s): d4781c4

End of training

Browse files
Files changed (2) hide show
  1. README.md +55 -1
  2. adapter_model.bin +1 -1
README.md CHANGED
@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
14
  # phi-1_5-psychology
15
 
16
  This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the None dataset.
 
 
17
 
18
  ## Model description
19
 
@@ -38,10 +40,62 @@ The following hyperparameters were used during training:
38
  - seed: 42
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
  - lr_scheduler_type: cosine
41
- - training_steps: 1000
42
 
43
  ### Training results
44
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
 
46
 
47
  ### Framework versions
 
14
  # phi-1_5-psychology
15
 
16
  This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.7574
19
 
20
  ## Model description
21
 
 
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: cosine
43
+ - num_epochs: 3
44
 
45
  ### Training results
46
 
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | 0.8667 | 0.04 | 100 | 0.8554 |
50
+ | 0.8401 | 0.09 | 200 | 0.8524 |
51
+ | 0.8492 | 0.13 | 300 | 0.8437 |
52
+ | 0.8563 | 0.18 | 400 | 0.8393 |
53
+ | 0.8353 | 0.22 | 500 | 0.8367 |
54
+ | 0.8232 | 0.26 | 600 | 0.8305 |
55
+ | 0.8299 | 0.31 | 700 | 0.8226 |
56
+ | 0.8307 | 0.35 | 800 | 0.8233 |
57
+ | 0.8087 | 0.39 | 900 | 0.8170 |
58
+ | 0.8124 | 0.44 | 1000 | 0.8160 |
59
+ | 0.7943 | 0.48 | 1100 | 0.8103 |
60
+ | 0.7924 | 0.53 | 1200 | 0.8076 |
61
+ | 0.7918 | 0.57 | 1300 | 0.8026 |
62
+ | 0.807 | 0.61 | 1400 | 0.8012 |
63
+ | 0.788 | 0.66 | 1500 | 0.8034 |
64
+ | 0.7946 | 0.7 | 1600 | 0.7946 |
65
+ | 0.7959 | 0.75 | 1700 | 0.7926 |
66
+ | 0.7878 | 0.79 | 1800 | 0.7921 |
67
+ | 0.754 | 0.83 | 1900 | 0.7890 |
68
+ | 0.7762 | 0.88 | 2000 | 0.7850 |
69
+ | 0.7651 | 0.92 | 2100 | 0.7849 |
70
+ | 0.7868 | 0.97 | 2200 | 0.7855 |
71
+ | 0.7651 | 1.01 | 2300 | 0.7820 |
72
+ | 0.7323 | 1.05 | 2400 | 0.7818 |
73
+ | 0.7316 | 1.1 | 2500 | 0.7804 |
74
+ | 0.7311 | 1.14 | 2600 | 0.7808 |
75
+ | 0.7221 | 1.18 | 2700 | 0.7782 |
76
+ | 0.722 | 1.23 | 2800 | 0.7736 |
77
+ | 0.7217 | 1.27 | 2900 | 0.7780 |
78
+ | 0.7226 | 1.32 | 3000 | 0.7730 |
79
+ | 0.7305 | 1.36 | 3100 | 0.7731 |
80
+ | 0.7237 | 1.4 | 3200 | 0.7712 |
81
+ | 0.7127 | 1.45 | 3300 | 0.7710 |
82
+ | 0.7252 | 1.49 | 3400 | 0.7699 |
83
+ | 0.7076 | 1.54 | 3500 | 0.7687 |
84
+ | 0.7185 | 1.58 | 3600 | 0.7672 |
85
+ | 0.6921 | 1.62 | 3700 | 0.7639 |
86
+ | 0.6882 | 1.67 | 3800 | 0.7642 |
87
+ | 0.7184 | 1.71 | 3900 | 0.7633 |
88
+ | 0.7048 | 1.76 | 4000 | 0.7601 |
89
+ | 0.7136 | 1.8 | 4100 | 0.7598 |
90
+ | 0.7063 | 1.84 | 4200 | 0.7591 |
91
+ | 0.7054 | 1.89 | 4300 | 0.7589 |
92
+ | 0.6945 | 1.93 | 4400 | 0.7564 |
93
+ | 0.6955 | 1.97 | 4500 | 0.7544 |
94
+ | 0.6869 | 2.02 | 4600 | 0.7536 |
95
+ | 0.6477 | 2.06 | 4700 | 0.7566 |
96
+ | 0.6593 | 2.11 | 4800 | 0.7568 |
97
+ | 0.6441 | 2.15 | 4900 | 0.7562 |
98
+ | 0.6527 | 2.19 | 5000 | 0.7574 |
99
 
100
 
101
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:319ebf30ca3f929c58527b277960aa3e47c206e5afe5d80f6173788452b4e39e
3
  size 18907665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:babbe45bece14ff36b54102b68a54604bb4b848bb81794f5d0a0f70ebf7e34fe
3
  size 18907665