Hugging Face's logo

xuanye
/
llama3_question

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
xuanye commited on
Commit
ee7a0b9
•
1 Parent(s): 102aa4e

end of training

Browse files
Files changed (3) hide show
  1. README.md +44 -51
  2. adapter_model.safetensors +1 -1
  3. runs/Jun10_21-28-07_ml/events.out.tfevents.1718026089.ml.3177663.0 +2 -2
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model was trained from scratch on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.9281
18
 
19
  ## Model description
20
 
@@ -52,61 +52,54 @@ The following hyperparameters were used during training:
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: constant
54
  - lr_scheduler_warmup_ratio: 0.03
55
- - num_epochs: 7
56
 
57
  ### Training results
58
 
59
  | Training Loss | Epoch | Step | Validation Loss |
60
  |:-------------:|:-----:|:----:|:---------------:|
61
- | 2.9644 | 0.14 | 1 | 2.8242 |
62
- | 2.83 | 0.29 | 2 | 2.6599 |
63
- | 2.6298 | 0.43 | 3 | 2.4977 |
64
- | 2.5886 | 0.57 | 4 | 2.3641 |
65
- | 2.3748 | 0.71 | 5 | 2.2390 |
66
- | 2.2532 | 0.86 | 6 | 2.1221 |
67
- | 2.5349 | 1.0 | 7 | 2.0140 |
68
- | 2.0095 | 1.14 | 8 | 1.9114 |
69
- | 1.9099 | 1.29 | 9 | 1.8180 |
70
- | 1.8959 | 1.43 | 10 | 1.7305 |
71
- | 1.8349 | 1.57 | 11 | 1.6499 |
72
- | 1.5787 | 1.71 | 12 | 1.5829 |
73
- | 1.5687 | 1.86 | 13 | 1.5243 |
74
- | 1.615 | 2.0 | 14 | 1.4736 |
75
- | 1.4481 | 2.14 | 15 | 1.4259 |
76
- | 1.4322 | 2.29 | 16 | 1.3778 |
77
- | 1.3623 | 2.43 | 17 | 1.3297 |
78
- | 1.3033 | 2.57 | 18 | 1.2797 |
79
- | 1.3481 | 2.71 | 19 | 1.2290 |
80
- | 1.2088 | 2.86 | 20 | 1.1819 |
81
- | 1.0726 | 3.0 | 21 | 1.1398 |
82
- | 1.1058 | 3.14 | 22 | 1.0997 |
83
- | 1.1279 | 3.29 | 23 | 1.0603 |
84
- | 1.013 | 3.43 | 24 | 1.0261 |
85
- | 0.9371 | 3.57 | 25 | 0.9980 |
86
- | 0.8697 | 3.71 | 26 | 0.9776 |
87
- | 1.0295 | 3.86 | 27 | 0.9648 |
88
- | 1.1583 | 4.0 | 28 | 0.9581 |
89
- | 0.865 | 4.14 | 29 | 0.9520 |
90
- | 0.9343 | 4.29 | 30 | 0.9455 |
91
- | 0.7596 | 4.43 | 31 | 0.9411 |
92
- | 0.8868 | 4.57 | 32 | 0.9374 |
93
- | 0.8944 | 4.71 | 33 | 0.9342 |
94
- | 0.9534 | 4.86 | 34 | 0.9310 |
95
- | 0.8833 | 5.0 | 35 | 0.9276 |
96
- | 0.7918 | 5.14 | 36 | 0.9248 |
97
- | 0.7921 | 5.29 | 37 | 0.9228 |
98
- | 0.8793 | 5.43 | 38 | 0.9223 |
99
- | 0.8272 | 5.57 | 39 | 0.9220 |
100
- | 0.9098 | 5.71 | 40 | 0.9213 |
101
- | 0.7525 | 5.86 | 41 | 0.9208 |
102
- | 0.9416 | 6.0 | 42 | 0.9215 |
103
- | 0.7309 | 6.14 | 43 | 0.9235 |
104
- | 0.7301 | 6.29 | 44 | 0.9236 |
105
- | 0.8327 | 6.43 | 45 | 0.9252 |
106
- | 0.7904 | 6.57 | 46 | 0.9257 |
107
- | 0.7649 | 6.71 | 47 | 0.9260 |
108
- | 0.837 | 6.86 | 48 | 0.9275 |
109
- | 0.8265 | 7.0 | 49 | 0.9281 |
110
 
111
 
112
  ### Framework versions
 
14
 
15
  This model was trained from scratch on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.9219
18
 
19
  ## Model description
20
 
 
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: constant
54
  - lr_scheduler_warmup_ratio: 0.03
55
+ - num_epochs: 6
56
 
57
  ### Training results
58
 
59
  | Training Loss | Epoch | Step | Validation Loss |
60
  |:-------------:|:-----:|:----:|:---------------:|
61
+ | 2.9644 | 0.14 | 1 | 2.8251 |
62
+ | 2.8305 | 0.29 | 2 | 2.6593 |
63
+ | 2.6303 | 0.43 | 3 | 2.5000 |
64
+ | 2.5879 | 0.57 | 4 | 2.3661 |
65
+ | 2.3771 | 0.71 | 5 | 2.2414 |
66
+ | 2.2551 | 0.86 | 6 | 2.1226 |
67
+ | 2.5345 | 1.0 | 7 | 2.0163 |
68
+ | 2.0127 | 1.14 | 8 | 1.9162 |
69
+ | 1.9111 | 1.29 | 9 | 1.8193 |
70
+ | 1.8992 | 1.43 | 10 | 1.7328 |
71
+ | 1.8365 | 1.57 | 11 | 1.6515 |
72
+ | 1.5802 | 1.71 | 12 | 1.5855 |
73
+ | 1.5701 | 1.86 | 13 | 1.5264 |
74
+ | 1.6198 | 2.0 | 14 | 1.4761 |
75
+ | 1.4501 | 2.14 | 15 | 1.4274 |
76
+ | 1.4337 | 2.29 | 16 | 1.3790 |
77
+ | 1.3655 | 2.43 | 17 | 1.3319 |
78
+ | 1.3056 | 2.57 | 18 | 1.2820 |
79
+ | 1.3507 | 2.71 | 19 | 1.2314 |
80
+ | 1.2097 | 2.86 | 20 | 1.1834 |
81
+ | 1.0763 | 3.0 | 21 | 1.1399 |
82
+ | 1.1076 | 3.14 | 22 | 1.0996 |
83
+ | 1.1287 | 3.29 | 23 | 1.0602 |
84
+ | 1.0127 | 3.43 | 24 | 1.0254 |
85
+ | 0.9368 | 3.57 | 25 | 0.9962 |
86
+ | 0.8688 | 3.71 | 26 | 0.9760 |
87
+ | 1.0289 | 3.86 | 27 | 0.9634 |
88
+ | 1.1598 | 4.0 | 28 | 0.9573 |
89
+ | 0.8651 | 4.14 | 29 | 0.9504 |
90
+ | 0.9333 | 4.29 | 30 | 0.9462 |
91
+ | 0.76 | 4.43 | 31 | 0.9414 |
92
+ | 0.8858 | 4.57 | 32 | 0.9381 |
93
+ | 0.8953 | 4.71 | 33 | 0.9344 |
94
+ | 0.9548 | 4.86 | 34 | 0.9318 |
95
+ | 0.8858 | 5.0 | 35 | 0.9293 |
96
+ | 0.7921 | 5.14 | 36 | 0.9263 |
97
+ | 0.7928 | 5.29 | 37 | 0.9238 |
98
+ | 0.8796 | 5.43 | 38 | 0.9231 |
99
+ | 0.8282 | 5.57 | 39 | 0.9225 |
100
+ | 0.9103 | 5.71 | 40 | 0.9223 |
101
+ | 0.7536 | 5.86 | 41 | 0.9201 |
102
+ | 0.9409 | 6.0 | 42 | 0.9219 |
 
 
 
 
 
 
 
103
 
104
 
105
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:767c893bf214f59aa76d19fcc0f34ea4de571bab533a621e73f95ef5f9ca3ca0
3
  size 109069176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:917d024bb15d47d0b2e4e5f4b77b96a3e233e24fea6ceed777bce3effb87f90e
3
  size 109069176
runs/Jun10_21-28-07_ml/events.out.tfevents.1718026089.ml.3177663.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b76999c216f416fb2299fc61946303e8ad3d8ef1e1e20650a59f806725f2e25
3
- size 20401
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aec2517a2e08d62d0c789249bb57d5e447fb132f65f48fb23c3e2e7dc5dfcfde
3
+ size 22849