Model save
Browse files- README.md +67 -132
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# Llama-3.1-8B-Instruct-PsyCourse-fold2
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -46,141 +46,76 @@ The following hyperparameters were used during training:
|
|
| 46 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
- lr_scheduler_type: cosine
|
| 48 |
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
-
- num_epochs:
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
|:-------------:|:------:|:----:|:---------------:|
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.
|
| 109 |
-
| 0.
|
| 110 |
-
| 0.
|
| 111 |
-
| 0.
|
| 112 |
-
| 0.
|
| 113 |
-
| 0.
|
| 114 |
-
| 0.
|
| 115 |
-
| 0.
|
| 116 |
-
| 0.
|
| 117 |
-
| 0.
|
| 118 |
-
| 0.
|
| 119 |
-
| 0.0021 | 5.0388 | 3250 | 0.0598 |
|
| 120 |
-
| 0.0061 | 5.1163 | 3300 | 0.0650 |
|
| 121 |
-
| 0.0038 | 5.1938 | 3350 | 0.0643 |
|
| 122 |
-
| 0.0052 | 5.2713 | 3400 | 0.0659 |
|
| 123 |
-
| 0.0058 | 5.3488 | 3450 | 0.0596 |
|
| 124 |
-
| 0.0081 | 5.4264 | 3500 | 0.0595 |
|
| 125 |
-
| 0.0051 | 5.5039 | 3550 | 0.0610 |
|
| 126 |
-
| 0.0036 | 5.5814 | 3600 | 0.0608 |
|
| 127 |
-
| 0.003 | 5.6589 | 3650 | 0.0687 |
|
| 128 |
-
| 0.0056 | 5.7364 | 3700 | 0.0545 |
|
| 129 |
-
| 0.0039 | 5.8140 | 3750 | 0.0496 |
|
| 130 |
-
| 0.0027 | 5.8915 | 3800 | 0.0624 |
|
| 131 |
-
| 0.0123 | 5.9690 | 3850 | 0.0626 |
|
| 132 |
-
| 0.0015 | 6.0465 | 3900 | 0.0734 |
|
| 133 |
-
| 0.0008 | 6.1240 | 3950 | 0.0713 |
|
| 134 |
-
| 0.0057 | 6.2016 | 4000 | 0.0687 |
|
| 135 |
-
| 0.0034 | 6.2791 | 4050 | 0.0698 |
|
| 136 |
-
| 0.003 | 6.3566 | 4100 | 0.0693 |
|
| 137 |
-
| 0.0008 | 6.4341 | 4150 | 0.0747 |
|
| 138 |
-
| 0.0019 | 6.5116 | 4200 | 0.0691 |
|
| 139 |
-
| 0.0049 | 6.5891 | 4250 | 0.0662 |
|
| 140 |
-
| 0.0021 | 6.6667 | 4300 | 0.0630 |
|
| 141 |
-
| 0.0042 | 6.7442 | 4350 | 0.0642 |
|
| 142 |
-
| 0.0046 | 6.8217 | 4400 | 0.0689 |
|
| 143 |
-
| 0.0057 | 6.8992 | 4450 | 0.0728 |
|
| 144 |
-
| 0.0015 | 6.9767 | 4500 | 0.0754 |
|
| 145 |
-
| 0.0011 | 7.0543 | 4550 | 0.0815 |
|
| 146 |
-
| 0.002 | 7.1318 | 4600 | 0.0866 |
|
| 147 |
-
| 0.0006 | 7.2093 | 4650 | 0.0944 |
|
| 148 |
-
| 0.0011 | 7.2868 | 4700 | 0.0902 |
|
| 149 |
-
| 0.0013 | 7.3643 | 4750 | 0.0838 |
|
| 150 |
-
| 0.0002 | 7.4419 | 4800 | 0.0897 |
|
| 151 |
-
| 0.001 | 7.5194 | 4850 | 0.0826 |
|
| 152 |
-
| 0.0031 | 7.5969 | 4900 | 0.0855 |
|
| 153 |
-
| 0.0005 | 7.6744 | 4950 | 0.0851 |
|
| 154 |
-
| 0.0002 | 7.7519 | 5000 | 0.0884 |
|
| 155 |
-
| 0.0008 | 7.8295 | 5050 | 0.0886 |
|
| 156 |
-
| 0.001 | 7.9070 | 5100 | 0.0906 |
|
| 157 |
-
| 0.0012 | 7.9845 | 5150 | 0.0919 |
|
| 158 |
-
| 0.0001 | 8.0620 | 5200 | 0.0926 |
|
| 159 |
-
| 0.0002 | 8.1395 | 5250 | 0.0963 |
|
| 160 |
-
| 0.0 | 8.2171 | 5300 | 0.0980 |
|
| 161 |
-
| 0.0 | 8.2946 | 5350 | 0.0994 |
|
| 162 |
-
| 0.0008 | 8.3721 | 5400 | 0.1010 |
|
| 163 |
-
| 0.0002 | 8.4496 | 5450 | 0.1000 |
|
| 164 |
-
| 0.0005 | 8.5271 | 5500 | 0.0997 |
|
| 165 |
-
| 0.0001 | 8.6047 | 5550 | 0.1001 |
|
| 166 |
-
| 0.0001 | 8.6822 | 5600 | 0.1004 |
|
| 167 |
-
| 0.0013 | 8.7597 | 5650 | 0.1010 |
|
| 168 |
-
| 0.0003 | 8.8372 | 5700 | 0.1009 |
|
| 169 |
-
| 0.0 | 8.9147 | 5750 | 0.1009 |
|
| 170 |
-
| 0.0003 | 8.9922 | 5800 | 0.1009 |
|
| 171 |
-
| 0.0001 | 9.0698 | 5850 | 0.1013 |
|
| 172 |
-
| 0.0004 | 9.1473 | 5900 | 0.1021 |
|
| 173 |
-
| 0.0 | 9.2248 | 5950 | 0.1028 |
|
| 174 |
-
| 0.0002 | 9.3023 | 6000 | 0.1034 |
|
| 175 |
-
| 0.0 | 9.3798 | 6050 | 0.1040 |
|
| 176 |
-
| 0.0001 | 9.4574 | 6100 | 0.1040 |
|
| 177 |
-
| 0.0 | 9.5349 | 6150 | 0.1040 |
|
| 178 |
-
| 0.0 | 9.6124 | 6200 | 0.1042 |
|
| 179 |
-
| 0.0004 | 9.6899 | 6250 | 0.1042 |
|
| 180 |
-
| 0.0006 | 9.7674 | 6300 | 0.1044 |
|
| 181 |
-
| 0.0006 | 9.8450 | 6350 | 0.1044 |
|
| 182 |
-
| 0.0003 | 9.9225 | 6400 | 0.1046 |
|
| 183 |
-
| 0.0002 | 10.0 | 6450 | 0.1044 |
|
| 184 |
|
| 185 |
|
| 186 |
### Framework versions
|
|
|
|
| 16 |
|
| 17 |
# Llama-3.1-8B-Instruct-PsyCourse-fold2
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0619
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 46 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
- lr_scheduler_type: cosine
|
| 48 |
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 5.0
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
|:-------------:|:------:|:----:|:---------------:|
|
| 55 |
+
| 0.5122 | 0.0775 | 50 | 0.4118 |
|
| 56 |
+
| 0.0913 | 0.1550 | 100 | 0.0831 |
|
| 57 |
+
| 0.0638 | 0.2326 | 150 | 0.0662 |
|
| 58 |
+
| 0.0589 | 0.3101 | 200 | 0.0558 |
|
| 59 |
+
| 0.0628 | 0.3876 | 250 | 0.0528 |
|
| 60 |
+
| 0.0482 | 0.4651 | 300 | 0.0484 |
|
| 61 |
+
| 0.0429 | 0.5426 | 350 | 0.0443 |
|
| 62 |
+
| 0.0526 | 0.6202 | 400 | 0.0432 |
|
| 63 |
+
| 0.0446 | 0.6977 | 450 | 0.0391 |
|
| 64 |
+
| 0.0503 | 0.7752 | 500 | 0.0377 |
|
| 65 |
+
| 0.048 | 0.8527 | 550 | 0.0386 |
|
| 66 |
+
| 0.0636 | 0.9302 | 600 | 0.0439 |
|
| 67 |
+
| 0.0333 | 1.0078 | 650 | 0.0361 |
|
| 68 |
+
| 0.0319 | 1.0853 | 700 | 0.0385 |
|
| 69 |
+
| 0.033 | 1.1628 | 750 | 0.0357 |
|
| 70 |
+
| 0.0242 | 1.2403 | 800 | 0.0371 |
|
| 71 |
+
| 0.0363 | 1.3178 | 850 | 0.0343 |
|
| 72 |
+
| 0.0419 | 1.3953 | 900 | 0.0360 |
|
| 73 |
+
| 0.0444 | 1.4729 | 950 | 0.0349 |
|
| 74 |
+
| 0.0297 | 1.5504 | 1000 | 0.0362 |
|
| 75 |
+
| 0.0348 | 1.6279 | 1050 | 0.0348 |
|
| 76 |
+
| 0.0271 | 1.7054 | 1100 | 0.0354 |
|
| 77 |
+
| 0.0362 | 1.7829 | 1150 | 0.0366 |
|
| 78 |
+
| 0.034 | 1.8605 | 1200 | 0.0344 |
|
| 79 |
+
| 0.039 | 1.9380 | 1250 | 0.0344 |
|
| 80 |
+
| 0.0248 | 2.0155 | 1300 | 0.0340 |
|
| 81 |
+
| 0.0209 | 2.0930 | 1350 | 0.0369 |
|
| 82 |
+
| 0.0211 | 2.1705 | 1400 | 0.0352 |
|
| 83 |
+
| 0.0178 | 2.2481 | 1450 | 0.0379 |
|
| 84 |
+
| 0.026 | 2.3256 | 1500 | 0.0355 |
|
| 85 |
+
| 0.0166 | 2.4031 | 1550 | 0.0375 |
|
| 86 |
+
| 0.0237 | 2.4806 | 1600 | 0.0355 |
|
| 87 |
+
| 0.037 | 2.5581 | 1650 | 0.0347 |
|
| 88 |
+
| 0.0161 | 2.6357 | 1700 | 0.0387 |
|
| 89 |
+
| 0.0174 | 2.7132 | 1750 | 0.0383 |
|
| 90 |
+
| 0.0222 | 2.7907 | 1800 | 0.0363 |
|
| 91 |
+
| 0.0217 | 2.8682 | 1850 | 0.0376 |
|
| 92 |
+
| 0.0198 | 2.9457 | 1900 | 0.0362 |
|
| 93 |
+
| 0.0105 | 3.0233 | 1950 | 0.0388 |
|
| 94 |
+
| 0.0097 | 3.1008 | 2000 | 0.0440 |
|
| 95 |
+
| 0.008 | 3.1783 | 2050 | 0.0482 |
|
| 96 |
+
| 0.0114 | 3.2558 | 2100 | 0.0435 |
|
| 97 |
+
| 0.0112 | 3.3333 | 2150 | 0.0401 |
|
| 98 |
+
| 0.0079 | 3.4109 | 2200 | 0.0448 |
|
| 99 |
+
| 0.0133 | 3.4884 | 2250 | 0.0483 |
|
| 100 |
+
| 0.0128 | 3.5659 | 2300 | 0.0471 |
|
| 101 |
+
| 0.012 | 3.6434 | 2350 | 0.0467 |
|
| 102 |
+
| 0.0143 | 3.7209 | 2400 | 0.0464 |
|
| 103 |
+
| 0.0063 | 3.7984 | 2450 | 0.0487 |
|
| 104 |
+
| 0.0098 | 3.8760 | 2500 | 0.0470 |
|
| 105 |
+
| 0.0088 | 3.9535 | 2550 | 0.0461 |
|
| 106 |
+
| 0.0057 | 4.0310 | 2600 | 0.0467 |
|
| 107 |
+
| 0.006 | 4.1085 | 2650 | 0.0506 |
|
| 108 |
+
| 0.0058 | 4.1860 | 2700 | 0.0565 |
|
| 109 |
+
| 0.0057 | 4.2636 | 2750 | 0.0592 |
|
| 110 |
+
| 0.0043 | 4.3411 | 2800 | 0.0595 |
|
| 111 |
+
| 0.0043 | 4.4186 | 2850 | 0.0612 |
|
| 112 |
+
| 0.0055 | 4.4961 | 2900 | 0.0617 |
|
| 113 |
+
| 0.0029 | 4.5736 | 2950 | 0.0608 |
|
| 114 |
+
| 0.0029 | 4.6512 | 3000 | 0.0615 |
|
| 115 |
+
| 0.0039 | 4.7287 | 3050 | 0.0620 |
|
| 116 |
+
| 0.0034 | 4.8062 | 3100 | 0.0620 |
|
| 117 |
+
| 0.0061 | 4.8837 | 3150 | 0.0618 |
|
| 118 |
+
| 0.0045 | 4.9612 | 3200 | 0.0619 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 119 |
|
| 120 |
|
| 121 |
### Framework versions
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83945296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:edf29add41e865a5b2b9bf8a748aa477a183fa4620959c3e749811e78f6d2e2c
|
| 3 |
size 83945296
|