EricWesthoff commited on
Commit
33a0473
·
1 Parent(s): f35ef93

End of training

Browse files
Files changed (2) hide show
  1. README.md +47 -2
  2. adapter_model.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-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: 1.4282
19
 
20
  ## Model description
21
 
@@ -40,7 +40,7 @@ The following hyperparameters were used during training:
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: cosine
43
- - training_steps: 1500
44
 
45
  ### Training results
46
 
@@ -61,6 +61,51 @@ The following hyperparameters were used during training:
61
  | 1.4476 | 5.2 | 1300 | 1.4337 |
62
  | 1.4321 | 5.6 | 1400 | 1.4287 |
63
  | 1.4393 | 6.0 | 1500 | 1.4282 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
64
 
65
 
66
  ### Framework versions
 
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: 0.3403
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
+ - training_steps: 6000
44
 
45
  ### Training results
46
 
 
61
  | 1.4476 | 5.2 | 1300 | 1.4337 |
62
  | 1.4321 | 5.6 | 1400 | 1.4287 |
63
  | 1.4393 | 6.0 | 1500 | 1.4282 |
64
+ | 1.4956 | 6.4 | 1600 | 1.4504 |
65
+ | 1.5252 | 6.8 | 1700 | 1.4311 |
66
+ | 1.4864 | 7.2 | 1800 | 1.3654 |
67
+ | 1.4092 | 7.6 | 1900 | 1.3112 |
68
+ | 1.4063 | 8.0 | 2000 | 1.2925 |
69
+ | 1.2657 | 8.4 | 2100 | 1.2123 |
70
+ | 1.312 | 8.8 | 2200 | 1.1824 |
71
+ | 1.2451 | 9.2 | 2300 | 1.1223 |
72
+ | 1.1777 | 9.6 | 2400 | 1.0857 |
73
+ | 1.1913 | 10.0 | 2500 | 1.0422 |
74
+ | 1.0452 | 10.4 | 2600 | 0.9842 |
75
+ | 1.082 | 10.8 | 2700 | 0.9442 |
76
+ | 0.9814 | 11.2 | 2800 | 0.9002 |
77
+ | 0.9496 | 11.6 | 2900 | 0.8559 |
78
+ | 0.9639 | 12.0 | 3000 | 0.8163 |
79
+ | 0.823 | 12.4 | 3100 | 0.7827 |
80
+ | 0.8395 | 12.8 | 3200 | 0.7384 |
81
+ | 0.8038 | 13.2 | 3300 | 0.6971 |
82
+ | 0.7458 | 13.6 | 3400 | 0.6641 |
83
+ | 0.7495 | 14.0 | 3500 | 0.6328 |
84
+ | 0.6575 | 14.4 | 3600 | 0.6017 |
85
+ | 0.6448 | 14.8 | 3700 | 0.5829 |
86
+ | 0.6268 | 15.2 | 3800 | 0.5412 |
87
+ | 0.5738 | 15.6 | 3900 | 0.5233 |
88
+ | 0.5989 | 16.0 | 4000 | 0.5008 |
89
+ | 0.5033 | 16.4 | 4100 | 0.4781 |
90
+ | 0.5343 | 16.8 | 4200 | 0.4572 |
91
+ | 0.4881 | 17.2 | 4300 | 0.4390 |
92
+ | 0.4676 | 17.6 | 4400 | 0.4254 |
93
+ | 0.4683 | 18.0 | 4500 | 0.4171 |
94
+ | 0.4188 | 18.4 | 4600 | 0.3987 |
95
+ | 0.4245 | 18.8 | 4700 | 0.3869 |
96
+ | 0.4136 | 19.2 | 4800 | 0.3777 |
97
+ | 0.3938 | 19.6 | 4900 | 0.3694 |
98
+ | 0.3986 | 20.0 | 5000 | 0.3627 |
99
+ | 0.3661 | 20.4 | 5100 | 0.3571 |
100
+ | 0.3743 | 20.8 | 5200 | 0.3516 |
101
+ | 0.3668 | 21.2 | 5300 | 0.3482 |
102
+ | 0.3613 | 21.6 | 5400 | 0.3455 |
103
+ | 0.3542 | 22.0 | 5500 | 0.3430 |
104
+ | 0.3505 | 22.4 | 5600 | 0.3419 |
105
+ | 0.3495 | 22.8 | 5700 | 0.3410 |
106
+ | 0.3396 | 23.2 | 5800 | 0.3405 |
107
+ | 0.3481 | 23.6 | 5900 | 0.3403 |
108
+ | 0.3444 | 24.0 | 6000 | 0.3403 |
109
 
110
 
111
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68dee483558b3f06fb92839c3292a22071be219750633087392c3fc6e5800251
3
  size 18908110
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16ebb39b96bd7e643813cb761512971024947d5116e41fe577213dd70ef85b54
3
  size 18908110