Model save
Browse files- README.md +68 -133
- 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-fold9
|
| 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 |
|
|
@@ -46,142 +46,77 @@ 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.
|
| 120 |
-
| 0.0074 | 5.0662 | 3300 | 0.0597 |
|
| 121 |
-
| 0.0083 | 5.1430 | 3350 | 0.0606 |
|
| 122 |
-
| 0.0098 | 5.2197 | 3400 | 0.0558 |
|
| 123 |
-
| 0.0059 | 5.2965 | 3450 | 0.0664 |
|
| 124 |
-
| 0.0041 | 5.3732 | 3500 | 0.0677 |
|
| 125 |
-
| 0.0041 | 5.4500 | 3550 | 0.0691 |
|
| 126 |
-
| 0.0041 | 5.5268 | 3600 | 0.0600 |
|
| 127 |
-
| 0.0083 | 5.6035 | 3650 | 0.0580 |
|
| 128 |
-
| 0.0048 | 5.6803 | 3700 | 0.0692 |
|
| 129 |
-
| 0.0029 | 5.7571 | 3750 | 0.0703 |
|
| 130 |
-
| 0.0063 | 5.8338 | 3800 | 0.0645 |
|
| 131 |
-
| 0.0055 | 5.9106 | 3850 | 0.0648 |
|
| 132 |
-
| 0.0078 | 5.9873 | 3900 | 0.0547 |
|
| 133 |
-
| 0.001 | 6.0641 | 3950 | 0.0663 |
|
| 134 |
-
| 0.0016 | 6.1409 | 4000 | 0.0693 |
|
| 135 |
-
| 0.001 | 6.2176 | 4050 | 0.0700 |
|
| 136 |
-
| 0.0028 | 6.2944 | 4100 | 0.0686 |
|
| 137 |
-
| 0.0019 | 6.3711 | 4150 | 0.0702 |
|
| 138 |
-
| 0.0009 | 6.4479 | 4200 | 0.0807 |
|
| 139 |
-
| 0.0049 | 6.5247 | 4250 | 0.0665 |
|
| 140 |
-
| 0.0035 | 6.6014 | 4300 | 0.0651 |
|
| 141 |
-
| 0.0013 | 6.6782 | 4350 | 0.0695 |
|
| 142 |
-
| 0.0007 | 6.7549 | 4400 | 0.0751 |
|
| 143 |
-
| 0.0024 | 6.8317 | 4450 | 0.0752 |
|
| 144 |
-
| 0.0019 | 6.9085 | 4500 | 0.0749 |
|
| 145 |
-
| 0.0006 | 6.9852 | 4550 | 0.0694 |
|
| 146 |
-
| 0.0001 | 7.0620 | 4600 | 0.0726 |
|
| 147 |
-
| 0.0005 | 7.1387 | 4650 | 0.0762 |
|
| 148 |
-
| 0.0002 | 7.2155 | 4700 | 0.0835 |
|
| 149 |
-
| 0.0005 | 7.2923 | 4750 | 0.0820 |
|
| 150 |
-
| 0.0012 | 7.3690 | 4800 | 0.0846 |
|
| 151 |
-
| 0.0041 | 7.4458 | 4850 | 0.0824 |
|
| 152 |
-
| 0.0004 | 7.5225 | 4900 | 0.0836 |
|
| 153 |
-
| 0.0003 | 7.5993 | 4950 | 0.0844 |
|
| 154 |
-
| 0.0003 | 7.6761 | 5000 | 0.0845 |
|
| 155 |
-
| 0.0005 | 7.7528 | 5050 | 0.0823 |
|
| 156 |
-
| 0.0021 | 7.8296 | 5100 | 0.0832 |
|
| 157 |
-
| 0.0002 | 7.9064 | 5150 | 0.0827 |
|
| 158 |
-
| 0.0002 | 7.9831 | 5200 | 0.0843 |
|
| 159 |
-
| 0.0001 | 8.0599 | 5250 | 0.0875 |
|
| 160 |
-
| 0.0002 | 8.1366 | 5300 | 0.0888 |
|
| 161 |
-
| 0.0002 | 8.2134 | 5350 | 0.0912 |
|
| 162 |
-
| 0.0015 | 8.2902 | 5400 | 0.0934 |
|
| 163 |
-
| 0.0008 | 8.3669 | 5450 | 0.0954 |
|
| 164 |
-
| 0.0007 | 8.4437 | 5500 | 0.0978 |
|
| 165 |
-
| 0.0 | 8.5204 | 5550 | 0.0947 |
|
| 166 |
-
| 0.0001 | 8.5972 | 5600 | 0.0950 |
|
| 167 |
-
| 0.0009 | 8.6740 | 5650 | 0.0951 |
|
| 168 |
-
| 0.0001 | 8.7507 | 5700 | 0.0942 |
|
| 169 |
-
| 0.0001 | 8.8275 | 5750 | 0.0955 |
|
| 170 |
-
| 0.0001 | 8.9042 | 5800 | 0.0967 |
|
| 171 |
-
| 0.0008 | 8.9810 | 5850 | 0.0962 |
|
| 172 |
-
| 0.0001 | 9.0578 | 5900 | 0.0964 |
|
| 173 |
-
| 0.0 | 9.1345 | 5950 | 0.0960 |
|
| 174 |
-
| 0.0001 | 9.2113 | 6000 | 0.0969 |
|
| 175 |
-
| 0.0 | 9.2880 | 6050 | 0.0971 |
|
| 176 |
-
| 0.0008 | 9.3648 | 6100 | 0.0975 |
|
| 177 |
-
| 0.0005 | 9.4416 | 6150 | 0.0979 |
|
| 178 |
-
| 0.0 | 9.5183 | 6200 | 0.0981 |
|
| 179 |
-
| 0.0001 | 9.5951 | 6250 | 0.0982 |
|
| 180 |
-
| 0.0 | 9.6718 | 6300 | 0.0986 |
|
| 181 |
-
| 0.0001 | 9.7486 | 6350 | 0.0987 |
|
| 182 |
-
| 0.0 | 9.8254 | 6400 | 0.0984 |
|
| 183 |
-
| 0.0001 | 9.9021 | 6450 | 0.0982 |
|
| 184 |
-
| 0.0001 | 9.9789 | 6500 | 0.0986 |
|
| 185 |
|
| 186 |
|
| 187 |
### Framework versions
|
|
|
|
| 16 |
|
| 17 |
# Llama-3.1-8B-Instruct-PsyCourse-fold9
|
| 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: 0.0639
|
| 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 |
+
| 0.6165 | 0.0768 | 50 | 0.3983 |
|
| 56 |
+
| 0.1035 | 0.1535 | 100 | 0.0830 |
|
| 57 |
+
| 0.0746 | 0.2303 | 150 | 0.0682 |
|
| 58 |
+
| 0.0591 | 0.3070 | 200 | 0.0593 |
|
| 59 |
+
| 0.0716 | 0.3838 | 250 | 0.0530 |
|
| 60 |
+
| 0.0571 | 0.4606 | 300 | 0.0475 |
|
| 61 |
+
| 0.0499 | 0.5373 | 350 | 0.0483 |
|
| 62 |
+
| 0.0421 | 0.6141 | 400 | 0.0470 |
|
| 63 |
+
| 0.0514 | 0.6908 | 450 | 0.0473 |
|
| 64 |
+
| 0.042 | 0.7676 | 500 | 0.0463 |
|
| 65 |
+
| 0.0672 | 0.8444 | 550 | 0.0476 |
|
| 66 |
+
| 0.0388 | 0.9211 | 600 | 0.0446 |
|
| 67 |
+
| 0.0391 | 0.9979 | 650 | 0.0403 |
|
| 68 |
+
| 0.0304 | 1.0746 | 700 | 0.0424 |
|
| 69 |
+
| 0.0396 | 1.1514 | 750 | 0.0430 |
|
| 70 |
+
| 0.0347 | 1.2282 | 800 | 0.0395 |
|
| 71 |
+
| 0.0356 | 1.3049 | 850 | 0.0410 |
|
| 72 |
+
| 0.0333 | 1.3817 | 900 | 0.0384 |
|
| 73 |
+
| 0.0318 | 1.4585 | 950 | 0.0376 |
|
| 74 |
+
| 0.0309 | 1.5352 | 1000 | 0.0383 |
|
| 75 |
+
| 0.0216 | 1.6120 | 1050 | 0.0373 |
|
| 76 |
+
| 0.0315 | 1.6887 | 1100 | 0.0370 |
|
| 77 |
+
| 0.0273 | 1.7655 | 1150 | 0.0389 |
|
| 78 |
+
| 0.0188 | 1.8423 | 1200 | 0.0379 |
|
| 79 |
+
| 0.0362 | 1.9190 | 1250 | 0.0371 |
|
| 80 |
+
| 0.0435 | 1.9958 | 1300 | 0.0368 |
|
| 81 |
+
| 0.0212 | 2.0725 | 1350 | 0.0396 |
|
| 82 |
+
| 0.0184 | 2.1493 | 1400 | 0.0393 |
|
| 83 |
+
| 0.0205 | 2.2261 | 1450 | 0.0381 |
|
| 84 |
+
| 0.0316 | 2.3028 | 1500 | 0.0390 |
|
| 85 |
+
| 0.0234 | 2.3796 | 1550 | 0.0400 |
|
| 86 |
+
| 0.0258 | 2.4563 | 1600 | 0.0387 |
|
| 87 |
+
| 0.0273 | 2.5331 | 1650 | 0.0393 |
|
| 88 |
+
| 0.0199 | 2.6099 | 1700 | 0.0385 |
|
| 89 |
+
| 0.0167 | 2.6866 | 1750 | 0.0394 |
|
| 90 |
+
| 0.0288 | 2.7634 | 1800 | 0.0427 |
|
| 91 |
+
| 0.022 | 2.8401 | 1850 | 0.0376 |
|
| 92 |
+
| 0.0237 | 2.9169 | 1900 | 0.0384 |
|
| 93 |
+
| 0.0176 | 2.9937 | 1950 | 0.0372 |
|
| 94 |
+
| 0.0057 | 3.0704 | 2000 | 0.0443 |
|
| 95 |
+
| 0.0148 | 3.1472 | 2050 | 0.0436 |
|
| 96 |
+
| 0.0153 | 3.2239 | 2100 | 0.0499 |
|
| 97 |
+
| 0.0116 | 3.3007 | 2150 | 0.0444 |
|
| 98 |
+
| 0.0116 | 3.3775 | 2200 | 0.0473 |
|
| 99 |
+
| 0.0133 | 3.4542 | 2250 | 0.0502 |
|
| 100 |
+
| 0.0095 | 3.5310 | 2300 | 0.0501 |
|
| 101 |
+
| 0.011 | 3.6078 | 2350 | 0.0467 |
|
| 102 |
+
| 0.0136 | 3.6845 | 2400 | 0.0513 |
|
| 103 |
+
| 0.0074 | 3.7613 | 2450 | 0.0478 |
|
| 104 |
+
| 0.0104 | 3.8380 | 2500 | 0.0492 |
|
| 105 |
+
| 0.0131 | 3.9148 | 2550 | 0.0514 |
|
| 106 |
+
| 0.0113 | 3.9916 | 2600 | 0.0484 |
|
| 107 |
+
| 0.0028 | 4.0683 | 2650 | 0.0536 |
|
| 108 |
+
| 0.0046 | 4.1451 | 2700 | 0.0576 |
|
| 109 |
+
| 0.0038 | 4.2218 | 2750 | 0.0616 |
|
| 110 |
+
| 0.0029 | 4.2986 | 2800 | 0.0621 |
|
| 111 |
+
| 0.0025 | 4.3754 | 2850 | 0.0640 |
|
| 112 |
+
| 0.0037 | 4.4521 | 2900 | 0.0638 |
|
| 113 |
+
| 0.0071 | 4.5289 | 2950 | 0.0648 |
|
| 114 |
+
| 0.0015 | 4.6056 | 3000 | 0.0653 |
|
| 115 |
+
| 0.002 | 4.6824 | 3050 | 0.0651 |
|
| 116 |
+
| 0.0073 | 4.7592 | 3100 | 0.0645 |
|
| 117 |
+
| 0.0061 | 4.8359 | 3150 | 0.0640 |
|
| 118 |
+
| 0.0024 | 4.9127 | 3200 | 0.0639 |
|
| 119 |
+
| 0.0054 | 4.9894 | 3250 | 0.0639 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 120 |
|
| 121 |
|
| 122 |
### 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 sha256:346bb3826b7325c30cbd2687a797a2852a933de2f3271d8d0c7eca464017349c
|
| 3 |
size 83945296
|