Model save
Browse files- README.md +68 -134
- 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-fold8
|
| 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 |
|
|
@@ -46,143 +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 |
-
|
|
| 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 |
-
| 0.007 | 5.0043 | 3300 | 0.0558 |
|
| 121 |
-
| 0.0022 | 5.0801 | 3350 | 0.0605 |
|
| 122 |
-
| 0.0025 | 5.1559 | 3400 | 0.0655 |
|
| 123 |
-
| 0.0079 | 5.2317 | 3450 | 0.0561 |
|
| 124 |
-
| 0.0072 | 5.3076 | 3500 | 0.0618 |
|
| 125 |
-
| 0.0085 | 5.3834 | 3550 | 0.0662 |
|
| 126 |
-
| 0.0043 | 5.4592 | 3600 | 0.0699 |
|
| 127 |
-
| 0.0091 | 5.5350 | 3650 | 0.0660 |
|
| 128 |
-
| 0.0041 | 5.6108 | 3700 | 0.0573 |
|
| 129 |
-
| 0.0079 | 5.6867 | 3750 | 0.0602 |
|
| 130 |
-
| 0.009 | 5.7625 | 3800 | 0.0614 |
|
| 131 |
-
| 0.0021 | 5.8383 | 3850 | 0.0678 |
|
| 132 |
-
| 0.0025 | 5.9141 | 3900 | 0.0744 |
|
| 133 |
-
| 0.0039 | 5.9900 | 3950 | 0.0688 |
|
| 134 |
-
| 0.0041 | 6.0658 | 4000 | 0.0687 |
|
| 135 |
-
| 0.0022 | 6.1416 | 4050 | 0.0742 |
|
| 136 |
-
| 0.0012 | 6.2174 | 4100 | 0.0700 |
|
| 137 |
-
| 0.002 | 6.2932 | 4150 | 0.0693 |
|
| 138 |
-
| 0.0037 | 6.3691 | 4200 | 0.0698 |
|
| 139 |
-
| 0.0019 | 6.4449 | 4250 | 0.0687 |
|
| 140 |
-
| 0.0007 | 6.5207 | 4300 | 0.0781 |
|
| 141 |
-
| 0.0035 | 6.5965 | 4350 | 0.0845 |
|
| 142 |
-
| 0.0028 | 6.6724 | 4400 | 0.0806 |
|
| 143 |
-
| 0.0029 | 6.7482 | 4450 | 0.0770 |
|
| 144 |
-
| 0.0036 | 6.8240 | 4500 | 0.0747 |
|
| 145 |
-
| 0.003 | 6.8998 | 4550 | 0.0750 |
|
| 146 |
-
| 0.001 | 6.9756 | 4600 | 0.0661 |
|
| 147 |
-
| 0.0013 | 7.0515 | 4650 | 0.0728 |
|
| 148 |
-
| 0.0016 | 7.1273 | 4700 | 0.0745 |
|
| 149 |
-
| 0.0007 | 7.2031 | 4750 | 0.0780 |
|
| 150 |
-
| 0.0014 | 7.2789 | 4800 | 0.0816 |
|
| 151 |
-
| 0.0005 | 7.3548 | 4850 | 0.0857 |
|
| 152 |
-
| 0.0026 | 7.4306 | 4900 | 0.0921 |
|
| 153 |
-
| 0.0005 | 7.5064 | 4950 | 0.0896 |
|
| 154 |
-
| 0.0014 | 7.5822 | 5000 | 0.0884 |
|
| 155 |
-
| 0.0004 | 7.6580 | 5050 | 0.0811 |
|
| 156 |
-
| 0.0003 | 7.7339 | 5100 | 0.0823 |
|
| 157 |
-
| 0.0015 | 7.8097 | 5150 | 0.0889 |
|
| 158 |
-
| 0.0007 | 7.8855 | 5200 | 0.0820 |
|
| 159 |
-
| 0.0001 | 7.9613 | 5250 | 0.0845 |
|
| 160 |
-
| 0.0002 | 8.0372 | 5300 | 0.0830 |
|
| 161 |
-
| 0.001 | 8.1130 | 5350 | 0.0848 |
|
| 162 |
-
| 0.0002 | 8.1888 | 5400 | 0.0859 |
|
| 163 |
-
| 0.0005 | 8.2646 | 5450 | 0.0874 |
|
| 164 |
-
| 0.0006 | 8.3404 | 5500 | 0.0886 |
|
| 165 |
-
| 0.0006 | 8.4163 | 5550 | 0.0910 |
|
| 166 |
-
| 0.0024 | 8.4921 | 5600 | 0.0928 |
|
| 167 |
-
| 0.0001 | 8.5679 | 5650 | 0.0933 |
|
| 168 |
-
| 0.0008 | 8.6437 | 5700 | 0.0938 |
|
| 169 |
-
| 0.001 | 8.7196 | 5750 | 0.0934 |
|
| 170 |
-
| 0.0041 | 8.7954 | 5800 | 0.0925 |
|
| 171 |
-
| 0.0006 | 8.8712 | 5850 | 0.0936 |
|
| 172 |
-
| 0.001 | 8.9470 | 5900 | 0.0947 |
|
| 173 |
-
| 0.0001 | 9.0228 | 5950 | 0.0951 |
|
| 174 |
-
| 0.0001 | 9.0987 | 6000 | 0.0958 |
|
| 175 |
-
| 0.001 | 9.1745 | 6050 | 0.0966 |
|
| 176 |
-
| 0.0001 | 9.2503 | 6100 | 0.0967 |
|
| 177 |
-
| 0.0002 | 9.3261 | 6150 | 0.0969 |
|
| 178 |
-
| 0.0008 | 9.4020 | 6200 | 0.0974 |
|
| 179 |
-
| 0.0004 | 9.4778 | 6250 | 0.0973 |
|
| 180 |
-
| 0.0005 | 9.5536 | 6300 | 0.0975 |
|
| 181 |
-
| 0.0003 | 9.6294 | 6350 | 0.0977 |
|
| 182 |
-
| 0.0009 | 9.7052 | 6400 | 0.0979 |
|
| 183 |
-
| 0.0001 | 9.7811 | 6450 | 0.0977 |
|
| 184 |
-
| 0.0001 | 9.8569 | 6500 | 0.0979 |
|
| 185 |
-
| 0.0001 | 9.9327 | 6550 | 0.0978 |
|
| 186 |
|
| 187 |
|
| 188 |
### Framework versions
|
|
|
|
| 16 |
|
| 17 |
# Llama-3.1-8B-Instruct-PsyCourse-fold8
|
| 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: 0.0604
|
| 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 |
+
| 0.6782 | 0.0758 | 50 | 0.4323 |
|
| 56 |
+
| 0.1528 | 0.1516 | 100 | 0.0901 |
|
| 57 |
+
| 0.0741 | 0.2275 | 150 | 0.0665 |
|
| 58 |
+
| 0.0544 | 0.3033 | 200 | 0.0563 |
|
| 59 |
+
| 0.053 | 0.3791 | 250 | 0.0572 |
|
| 60 |
+
| 0.0626 | 0.4549 | 300 | 0.0589 |
|
| 61 |
+
| 0.0646 | 0.5308 | 350 | 0.0462 |
|
| 62 |
+
| 0.0336 | 0.6066 | 400 | 0.0449 |
|
| 63 |
+
| 0.0426 | 0.6824 | 450 | 0.0435 |
|
| 64 |
+
| 0.0354 | 0.7582 | 500 | 0.0468 |
|
| 65 |
+
| 0.0506 | 0.8340 | 550 | 0.0444 |
|
| 66 |
+
| 0.0346 | 0.9099 | 600 | 0.0411 |
|
| 67 |
+
| 0.0514 | 0.9857 | 650 | 0.0443 |
|
| 68 |
+
| 0.0323 | 1.0615 | 700 | 0.0412 |
|
| 69 |
+
| 0.0261 | 1.1373 | 750 | 0.0431 |
|
| 70 |
+
| 0.0307 | 1.2132 | 800 | 0.0398 |
|
| 71 |
+
| 0.0284 | 1.2890 | 850 | 0.0416 |
|
| 72 |
+
| 0.0316 | 1.3648 | 900 | 0.0398 |
|
| 73 |
+
| 0.0288 | 1.4406 | 950 | 0.0397 |
|
| 74 |
+
| 0.0306 | 1.5164 | 1000 | 0.0411 |
|
| 75 |
+
| 0.0449 | 1.5923 | 1050 | 0.0384 |
|
| 76 |
+
| 0.0281 | 1.6681 | 1100 | 0.0385 |
|
| 77 |
+
| 0.038 | 1.7439 | 1150 | 0.0376 |
|
| 78 |
+
| 0.0277 | 1.8197 | 1200 | 0.0354 |
|
| 79 |
+
| 0.0381 | 1.8956 | 1250 | 0.0377 |
|
| 80 |
+
| 0.0278 | 1.9714 | 1300 | 0.0359 |
|
| 81 |
+
| 0.0194 | 2.0472 | 1350 | 0.0393 |
|
| 82 |
+
| 0.0149 | 2.1230 | 1400 | 0.0375 |
|
| 83 |
+
| 0.0243 | 2.1988 | 1450 | 0.0402 |
|
| 84 |
+
| 0.0234 | 2.2747 | 1500 | 0.0396 |
|
| 85 |
+
| 0.0189 | 2.3505 | 1550 | 0.0392 |
|
| 86 |
+
| 0.0195 | 2.4263 | 1600 | 0.0396 |
|
| 87 |
+
| 0.0221 | 2.5021 | 1650 | 0.0475 |
|
| 88 |
+
| 0.0179 | 2.5780 | 1700 | 0.0408 |
|
| 89 |
+
| 0.0225 | 2.6538 | 1750 | 0.0386 |
|
| 90 |
+
| 0.0207 | 2.7296 | 1800 | 0.0398 |
|
| 91 |
+
| 0.015 | 2.8054 | 1850 | 0.0410 |
|
| 92 |
+
| 0.0295 | 2.8812 | 1900 | 0.0372 |
|
| 93 |
+
| 0.0227 | 2.9571 | 1950 | 0.0380 |
|
| 94 |
+
| 0.0128 | 3.0329 | 2000 | 0.0398 |
|
| 95 |
+
| 0.0096 | 3.1087 | 2050 | 0.0432 |
|
| 96 |
+
| 0.0076 | 3.1845 | 2100 | 0.0488 |
|
| 97 |
+
| 0.0122 | 3.2604 | 2150 | 0.0451 |
|
| 98 |
+
| 0.0101 | 3.3362 | 2200 | 0.0467 |
|
| 99 |
+
| 0.0124 | 3.4120 | 2250 | 0.0464 |
|
| 100 |
+
| 0.0113 | 3.4878 | 2300 | 0.0480 |
|
| 101 |
+
| 0.0126 | 3.5636 | 2350 | 0.0480 |
|
| 102 |
+
| 0.0114 | 3.6395 | 2400 | 0.0436 |
|
| 103 |
+
| 0.0071 | 3.7153 | 2450 | 0.0472 |
|
| 104 |
+
| 0.0117 | 3.7911 | 2500 | 0.0490 |
|
| 105 |
+
| 0.0145 | 3.8669 | 2550 | 0.0475 |
|
| 106 |
+
| 0.008 | 3.9428 | 2600 | 0.0459 |
|
| 107 |
+
| 0.0044 | 4.0186 | 2650 | 0.0480 |
|
| 108 |
+
| 0.0061 | 4.0944 | 2700 | 0.0542 |
|
| 109 |
+
| 0.0048 | 4.1702 | 2750 | 0.0556 |
|
| 110 |
+
| 0.0043 | 4.2460 | 2800 | 0.0557 |
|
| 111 |
+
| 0.0049 | 4.3219 | 2850 | 0.0570 |
|
| 112 |
+
| 0.0019 | 4.3977 | 2900 | 0.0587 |
|
| 113 |
+
| 0.0053 | 4.4735 | 2950 | 0.0595 |
|
| 114 |
+
| 0.0072 | 4.5493 | 3000 | 0.0597 |
|
| 115 |
+
| 0.0047 | 4.6252 | 3050 | 0.0599 |
|
| 116 |
+
| 0.003 | 4.7010 | 3100 | 0.0602 |
|
| 117 |
+
| 0.0025 | 4.7768 | 3150 | 0.0603 |
|
| 118 |
+
| 0.0027 | 4.8526 | 3200 | 0.0604 |
|
| 119 |
+
| 0.0022 | 4.9284 | 3250 | 0.0604 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 sha256:8802731e188ee4e218cfc53219a500cf08561e558a93d330f73cd9e14ef5bf9a
|
| 3 |
size 83945296
|