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-fold7
|
| 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 |
-
| 0.0049 | 5.0420 | 3300 | 0.0503 |
|
| 121 |
-
| 0.006 | 5.1184 | 3350 | 0.0521 |
|
| 122 |
-
| 0.0037 | 5.1948 | 3400 | 0.0545 |
|
| 123 |
-
| 0.0032 | 5.2712 | 3450 | 0.0743 |
|
| 124 |
-
| 0.0047 | 5.3476 | 3500 | 0.0558 |
|
| 125 |
-
| 0.0037 | 5.4240 | 3550 | 0.0517 |
|
| 126 |
-
| 0.0054 | 5.5004 | 3600 | 0.0526 |
|
| 127 |
-
| 0.0053 | 5.5768 | 3650 | 0.0507 |
|
| 128 |
-
| 0.0094 | 5.6532 | 3700 | 0.0504 |
|
| 129 |
-
| 0.0067 | 5.7296 | 3750 | 0.0492 |
|
| 130 |
-
| 0.0038 | 5.8060 | 3800 | 0.0524 |
|
| 131 |
-
| 0.0091 | 5.8824 | 3850 | 0.0443 |
|
| 132 |
-
| 0.006 | 5.9587 | 3900 | 0.0490 |
|
| 133 |
-
| 0.0042 | 6.0351 | 3950 | 0.0518 |
|
| 134 |
-
| 0.0023 | 6.1115 | 4000 | 0.0607 |
|
| 135 |
-
| 0.0012 | 6.1879 | 4050 | 0.0625 |
|
| 136 |
-
| 0.0046 | 6.2643 | 4100 | 0.0562 |
|
| 137 |
-
| 0.0017 | 6.3407 | 4150 | 0.0639 |
|
| 138 |
-
| 0.0029 | 6.4171 | 4200 | 0.0585 |
|
| 139 |
-
| 0.0023 | 6.4935 | 4250 | 0.0586 |
|
| 140 |
-
| 0.0021 | 6.5699 | 4300 | 0.0601 |
|
| 141 |
-
| 0.0004 | 6.6463 | 4350 | 0.0675 |
|
| 142 |
-
| 0.0021 | 6.7227 | 4400 | 0.0667 |
|
| 143 |
-
| 0.0024 | 6.7991 | 4450 | 0.0701 |
|
| 144 |
-
| 0.0022 | 6.8755 | 4500 | 0.0674 |
|
| 145 |
-
| 0.0033 | 6.9519 | 4550 | 0.0609 |
|
| 146 |
-
| 0.0009 | 7.0283 | 4600 | 0.0551 |
|
| 147 |
-
| 0.0011 | 7.1047 | 4650 | 0.0607 |
|
| 148 |
-
| 0.0014 | 7.1811 | 4700 | 0.0657 |
|
| 149 |
-
| 0.0003 | 7.2574 | 4750 | 0.0645 |
|
| 150 |
-
| 0.0013 | 7.3338 | 4800 | 0.0692 |
|
| 151 |
-
| 0.0004 | 7.4102 | 4850 | 0.0737 |
|
| 152 |
-
| 0.0004 | 7.4866 | 4900 | 0.0669 |
|
| 153 |
-
| 0.0028 | 7.5630 | 4950 | 0.0651 |
|
| 154 |
-
| 0.0008 | 7.6394 | 5000 | 0.0633 |
|
| 155 |
-
| 0.0014 | 7.7158 | 5050 | 0.0643 |
|
| 156 |
-
| 0.0012 | 7.7922 | 5100 | 0.0659 |
|
| 157 |
-
| 0.0006 | 7.8686 | 5150 | 0.0663 |
|
| 158 |
-
| 0.0005 | 7.9450 | 5200 | 0.0700 |
|
| 159 |
-
| 0.0007 | 8.0214 | 5250 | 0.0659 |
|
| 160 |
-
| 0.0009 | 8.0978 | 5300 | 0.0691 |
|
| 161 |
-
| 0.0002 | 8.1742 | 5350 | 0.0709 |
|
| 162 |
-
| 0.0004 | 8.2506 | 5400 | 0.0735 |
|
| 163 |
-
| 0.0006 | 8.3270 | 5450 | 0.0750 |
|
| 164 |
-
| 0.0007 | 8.4034 | 5500 | 0.0772 |
|
| 165 |
-
| 0.0001 | 8.4798 | 5550 | 0.0785 |
|
| 166 |
-
| 0.0007 | 8.5561 | 5600 | 0.0807 |
|
| 167 |
-
| 0.0013 | 8.6325 | 5650 | 0.0787 |
|
| 168 |
-
| 0.0005 | 8.7089 | 5700 | 0.0770 |
|
| 169 |
-
| 0.0012 | 8.7853 | 5750 | 0.0768 |
|
| 170 |
-
| 0.0004 | 8.8617 | 5800 | 0.0756 |
|
| 171 |
-
| 0.0032 | 8.9381 | 5850 | 0.0763 |
|
| 172 |
-
| 0.0008 | 9.0145 | 5900 | 0.0764 |
|
| 173 |
-
| 0.0002 | 9.0909 | 5950 | 0.0777 |
|
| 174 |
-
| 0.0002 | 9.1673 | 6000 | 0.0781 |
|
| 175 |
-
| 0.0003 | 9.2437 | 6050 | 0.0786 |
|
| 176 |
-
| 0.0007 | 9.3201 | 6100 | 0.0790 |
|
| 177 |
-
| 0.0002 | 9.3965 | 6150 | 0.0798 |
|
| 178 |
-
| 0.0003 | 9.4729 | 6200 | 0.0796 |
|
| 179 |
-
| 0.0008 | 9.5493 | 6250 | 0.0798 |
|
| 180 |
-
| 0.0002 | 9.6257 | 6300 | 0.0800 |
|
| 181 |
-
| 0.0012 | 9.7021 | 6350 | 0.0801 |
|
| 182 |
-
| 0.0008 | 9.7785 | 6400 | 0.0801 |
|
| 183 |
-
| 0.0001 | 9.8549 | 6450 | 0.0801 |
|
| 184 |
-
| 0.0005 | 9.9312 | 6500 | 0.0802 |
|
| 185 |
|
| 186 |
|
| 187 |
### Framework versions
|
|
|
|
| 16 |
|
| 17 |
# Llama-3.1-8B-Instruct-PsyCourse-fold7
|
| 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: 0.0536
|
| 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 |
+
| 0.6247 | 0.0764 | 50 | 0.4018 |
|
| 56 |
+
| 0.1081 | 0.1528 | 100 | 0.0778 |
|
| 57 |
+
| 0.0687 | 0.2292 | 150 | 0.0614 |
|
| 58 |
+
| 0.0565 | 0.3056 | 200 | 0.0577 |
|
| 59 |
+
| 0.0612 | 0.3820 | 250 | 0.0510 |
|
| 60 |
+
| 0.0426 | 0.4584 | 300 | 0.0490 |
|
| 61 |
+
| 0.0657 | 0.5348 | 350 | 0.0489 |
|
| 62 |
+
| 0.0423 | 0.6112 | 400 | 0.0453 |
|
| 63 |
+
| 0.056 | 0.6875 | 450 | 0.0438 |
|
| 64 |
+
| 0.0393 | 0.7639 | 500 | 0.0396 |
|
| 65 |
+
| 0.0321 | 0.8403 | 550 | 0.0387 |
|
| 66 |
+
| 0.0493 | 0.9167 | 600 | 0.0400 |
|
| 67 |
+
| 0.0578 | 0.9931 | 650 | 0.0393 |
|
| 68 |
+
| 0.0371 | 1.0695 | 700 | 0.0376 |
|
| 69 |
+
| 0.0228 | 1.1459 | 750 | 0.0364 |
|
| 70 |
+
| 0.0301 | 1.2223 | 800 | 0.0388 |
|
| 71 |
+
| 0.0383 | 1.2987 | 850 | 0.0371 |
|
| 72 |
+
| 0.0403 | 1.3751 | 900 | 0.0364 |
|
| 73 |
+
| 0.0446 | 1.4515 | 950 | 0.0381 |
|
| 74 |
+
| 0.0282 | 1.5279 | 1000 | 0.0352 |
|
| 75 |
+
| 0.0303 | 1.6043 | 1050 | 0.0363 |
|
| 76 |
+
| 0.0287 | 1.6807 | 1100 | 0.0400 |
|
| 77 |
+
| 0.0562 | 1.7571 | 1150 | 0.0355 |
|
| 78 |
+
| 0.0354 | 1.8335 | 1200 | 0.0350 |
|
| 79 |
+
| 0.0379 | 1.9099 | 1250 | 0.0377 |
|
| 80 |
+
| 0.0272 | 1.9862 | 1300 | 0.0353 |
|
| 81 |
+
| 0.0232 | 2.0626 | 1350 | 0.0356 |
|
| 82 |
+
| 0.0203 | 2.1390 | 1400 | 0.0356 |
|
| 83 |
+
| 0.0156 | 2.2154 | 1450 | 0.0388 |
|
| 84 |
+
| 0.0207 | 2.2918 | 1500 | 0.0344 |
|
| 85 |
+
| 0.0202 | 2.3682 | 1550 | 0.0345 |
|
| 86 |
+
| 0.0196 | 2.4446 | 1600 | 0.0345 |
|
| 87 |
+
| 0.0244 | 2.5210 | 1650 | 0.0345 |
|
| 88 |
+
| 0.0199 | 2.5974 | 1700 | 0.0355 |
|
| 89 |
+
| 0.0221 | 2.6738 | 1750 | 0.0338 |
|
| 90 |
+
| 0.0271 | 2.7502 | 1800 | 0.0324 |
|
| 91 |
+
| 0.0265 | 2.8266 | 1850 | 0.0324 |
|
| 92 |
+
| 0.0214 | 2.9030 | 1900 | 0.0343 |
|
| 93 |
+
| 0.0214 | 2.9794 | 1950 | 0.0354 |
|
| 94 |
+
| 0.0159 | 3.0558 | 2000 | 0.0351 |
|
| 95 |
+
| 0.0147 | 3.1322 | 2050 | 0.0364 |
|
| 96 |
+
| 0.0125 | 3.2086 | 2100 | 0.0382 |
|
| 97 |
+
| 0.0135 | 3.2850 | 2150 | 0.0398 |
|
| 98 |
+
| 0.0138 | 3.3613 | 2200 | 0.0406 |
|
| 99 |
+
| 0.0143 | 3.4377 | 2250 | 0.0450 |
|
| 100 |
+
| 0.0082 | 3.5141 | 2300 | 0.0436 |
|
| 101 |
+
| 0.0177 | 3.5905 | 2350 | 0.0426 |
|
| 102 |
+
| 0.0119 | 3.6669 | 2400 | 0.0396 |
|
| 103 |
+
| 0.0061 | 3.7433 | 2450 | 0.0407 |
|
| 104 |
+
| 0.0101 | 3.8197 | 2500 | 0.0403 |
|
| 105 |
+
| 0.0105 | 3.8961 | 2550 | 0.0398 |
|
| 106 |
+
| 0.0087 | 3.9725 | 2600 | 0.0390 |
|
| 107 |
+
| 0.0058 | 4.0489 | 2650 | 0.0419 |
|
| 108 |
+
| 0.0065 | 4.1253 | 2700 | 0.0461 |
|
| 109 |
+
| 0.0072 | 4.2017 | 2750 | 0.0491 |
|
| 110 |
+
| 0.0018 | 4.2781 | 2800 | 0.0508 |
|
| 111 |
+
| 0.0053 | 4.3545 | 2850 | 0.0508 |
|
| 112 |
+
| 0.0024 | 4.4309 | 2900 | 0.0524 |
|
| 113 |
+
| 0.0042 | 4.5073 | 2950 | 0.0534 |
|
| 114 |
+
| 0.0056 | 4.5837 | 3000 | 0.0535 |
|
| 115 |
+
| 0.0023 | 4.6600 | 3050 | 0.0541 |
|
| 116 |
+
| 0.0028 | 4.7364 | 3100 | 0.0541 |
|
| 117 |
+
| 0.0063 | 4.8128 | 3150 | 0.0538 |
|
| 118 |
+
| 0.0034 | 4.8892 | 3200 | 0.0534 |
|
| 119 |
+
| 0.0077 | 4.9656 | 3250 | 0.0536 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 sha256:0283c03d34113075dbd9daf49d0ae78771e18eaa7ea6ea6200511e564223b991
|
| 3 |
size 83945296
|