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-fold1
|
| 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 |
-
| 0.0055 | 5.0019 | 3250 | 0.0464 |
|
| 120 |
-
| 0.0056 | 5.0789 | 3300 | 0.0561 |
|
| 121 |
-
| 0.0033 | 5.1558 | 3350 | 0.0575 |
|
| 122 |
-
| 0.0035 | 5.2328 | 3400 | 0.0597 |
|
| 123 |
-
| 0.004 | 5.3097 | 3450 | 0.0622 |
|
| 124 |
-
| 0.0052 | 5.3867 | 3500 | 0.0530 |
|
| 125 |
-
| 0.0025 | 5.4636 | 3550 | 0.0536 |
|
| 126 |
-
| 0.006 | 5.5406 | 3600 | 0.0567 |
|
| 127 |
-
| 0.0103 | 5.6175 | 3650 | 0.0531 |
|
| 128 |
-
| 0.0046 | 5.6945 | 3700 | 0.0585 |
|
| 129 |
-
| 0.0077 | 5.7715 | 3750 | 0.0547 |
|
| 130 |
-
| 0.0058 | 5.8484 | 3800 | 0.0545 |
|
| 131 |
-
| 0.0033 | 5.9254 | 3850 | 0.0545 |
|
| 132 |
-
| 0.0041 | 6.0023 | 3900 | 0.0512 |
|
| 133 |
-
| 0.0024 | 6.0793 | 3950 | 0.0595 |
|
| 134 |
-
| 0.0018 | 6.1562 | 4000 | 0.0629 |
|
| 135 |
-
| 0.0046 | 6.2332 | 4050 | 0.0674 |
|
| 136 |
-
| 0.0003 | 6.3101 | 4100 | 0.0636 |
|
| 137 |
-
| 0.001 | 6.3871 | 4150 | 0.0662 |
|
| 138 |
-
| 0.0004 | 6.4640 | 4200 | 0.0726 |
|
| 139 |
-
| 0.0027 | 6.5410 | 4250 | 0.0641 |
|
| 140 |
-
| 0.0033 | 6.6179 | 4300 | 0.0715 |
|
| 141 |
-
| 0.004 | 6.6949 | 4350 | 0.0666 |
|
| 142 |
-
| 0.0028 | 6.7718 | 4400 | 0.0737 |
|
| 143 |
-
| 0.0015 | 6.8488 | 4450 | 0.0720 |
|
| 144 |
-
| 0.0017 | 6.9257 | 4500 | 0.0645 |
|
| 145 |
-
| 0.0025 | 7.0027 | 4550 | 0.0586 |
|
| 146 |
-
| 0.0003 | 7.0796 | 4600 | 0.0643 |
|
| 147 |
-
| 0.0009 | 7.1566 | 4650 | 0.0701 |
|
| 148 |
-
| 0.0005 | 7.2336 | 4700 | 0.0749 |
|
| 149 |
-
| 0.0003 | 7.3105 | 4750 | 0.0769 |
|
| 150 |
-
| 0.0002 | 7.3875 | 4800 | 0.0769 |
|
| 151 |
-
| 0.0019 | 7.4644 | 4850 | 0.0791 |
|
| 152 |
-
| 0.0025 | 7.5414 | 4900 | 0.0791 |
|
| 153 |
-
| 0.0023 | 7.6183 | 4950 | 0.0682 |
|
| 154 |
-
| 0.0001 | 7.6953 | 5000 | 0.0733 |
|
| 155 |
-
| 0.0013 | 7.7722 | 5050 | 0.0719 |
|
| 156 |
-
| 0.0004 | 7.8492 | 5100 | 0.0716 |
|
| 157 |
-
| 0.0008 | 7.9261 | 5150 | 0.0736 |
|
| 158 |
-
| 0.0017 | 8.0031 | 5200 | 0.0732 |
|
| 159 |
-
| 0.0007 | 8.0800 | 5250 | 0.0744 |
|
| 160 |
-
| 0.0006 | 8.1570 | 5300 | 0.0763 |
|
| 161 |
-
| 0.0021 | 8.2339 | 5350 | 0.0778 |
|
| 162 |
-
| 0.0013 | 8.3109 | 5400 | 0.0789 |
|
| 163 |
-
| 0.0008 | 8.3878 | 5450 | 0.0801 |
|
| 164 |
-
| 0.0013 | 8.4648 | 5500 | 0.0794 |
|
| 165 |
-
| 0.0002 | 8.5417 | 5550 | 0.0810 |
|
| 166 |
-
| 0.0005 | 8.6187 | 5600 | 0.0816 |
|
| 167 |
-
| 0.0 | 8.6957 | 5650 | 0.0819 |
|
| 168 |
-
| 0.0002 | 8.7726 | 5700 | 0.0827 |
|
| 169 |
-
| 0.0002 | 8.8496 | 5750 | 0.0826 |
|
| 170 |
-
| 0.0001 | 8.9265 | 5800 | 0.0829 |
|
| 171 |
-
| 0.0001 | 9.0035 | 5850 | 0.0829 |
|
| 172 |
-
| 0.0001 | 9.0804 | 5900 | 0.0833 |
|
| 173 |
-
| 0.0001 | 9.1574 | 5950 | 0.0842 |
|
| 174 |
-
| 0.0004 | 9.2343 | 6000 | 0.0847 |
|
| 175 |
-
| 0.0007 | 9.3113 | 6050 | 0.0851 |
|
| 176 |
-
| 0.0002 | 9.3882 | 6100 | 0.0856 |
|
| 177 |
-
| 0.0001 | 9.4652 | 6150 | 0.0855 |
|
| 178 |
-
| 0.0001 | 9.5421 | 6200 | 0.0859 |
|
| 179 |
-
| 0.0003 | 9.6191 | 6250 | 0.0859 |
|
| 180 |
-
| 0.0001 | 9.6960 | 6300 | 0.0859 |
|
| 181 |
-
| 0.0003 | 9.7730 | 6350 | 0.0861 |
|
| 182 |
-
| 0.0008 | 9.8499 | 6400 | 0.0859 |
|
| 183 |
-
| 0.0006 | 9.9269 | 6450 | 0.0859 |
|
| 184 |
|
| 185 |
|
| 186 |
### Framework versions
|
|
|
|
| 16 |
|
| 17 |
# Llama-3.1-8B-Instruct-PsyCourse-fold1
|
| 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: 0.0577
|
| 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 |
+
| 0.5562 | 0.0770 | 50 | 0.4070 |
|
| 56 |
+
| 0.1226 | 0.1539 | 100 | 0.0915 |
|
| 57 |
+
| 0.0859 | 0.2309 | 150 | 0.0644 |
|
| 58 |
+
| 0.0714 | 0.3078 | 200 | 0.0530 |
|
| 59 |
+
| 0.054 | 0.3848 | 250 | 0.0493 |
|
| 60 |
+
| 0.0553 | 0.4617 | 300 | 0.0478 |
|
| 61 |
+
| 0.053 | 0.5387 | 350 | 0.0479 |
|
| 62 |
+
| 0.0645 | 0.6156 | 400 | 0.0487 |
|
| 63 |
+
| 0.0391 | 0.6926 | 450 | 0.0451 |
|
| 64 |
+
| 0.0339 | 0.7695 | 500 | 0.0405 |
|
| 65 |
+
| 0.0513 | 0.8465 | 550 | 0.0405 |
|
| 66 |
+
| 0.0374 | 0.9234 | 600 | 0.0385 |
|
| 67 |
+
| 0.0334 | 1.0004 | 650 | 0.0381 |
|
| 68 |
+
| 0.0405 | 1.0773 | 700 | 0.0403 |
|
| 69 |
+
| 0.0337 | 1.1543 | 750 | 0.0361 |
|
| 70 |
+
| 0.0344 | 1.2312 | 800 | 0.0359 |
|
| 71 |
+
| 0.0344 | 1.3082 | 850 | 0.0373 |
|
| 72 |
+
| 0.0221 | 1.3851 | 900 | 0.0357 |
|
| 73 |
+
| 0.0457 | 1.4621 | 950 | 0.0375 |
|
| 74 |
+
| 0.0357 | 1.5391 | 1000 | 0.0365 |
|
| 75 |
+
| 0.034 | 1.6160 | 1050 | 0.0356 |
|
| 76 |
+
| 0.0394 | 1.6930 | 1100 | 0.0364 |
|
| 77 |
+
| 0.0244 | 1.7699 | 1150 | 0.0360 |
|
| 78 |
+
| 0.023 | 1.8469 | 1200 | 0.0371 |
|
| 79 |
+
| 0.0339 | 1.9238 | 1250 | 0.0358 |
|
| 80 |
+
| 0.0252 | 2.0008 | 1300 | 0.0344 |
|
| 81 |
+
| 0.019 | 2.0777 | 1350 | 0.0338 |
|
| 82 |
+
| 0.0297 | 2.1547 | 1400 | 0.0361 |
|
| 83 |
+
| 0.0142 | 2.2316 | 1450 | 0.0371 |
|
| 84 |
+
| 0.0227 | 2.3086 | 1500 | 0.0354 |
|
| 85 |
+
| 0.0179 | 2.3855 | 1550 | 0.0411 |
|
| 86 |
+
| 0.0189 | 2.4625 | 1600 | 0.0363 |
|
| 87 |
+
| 0.0246 | 2.5394 | 1650 | 0.0360 |
|
| 88 |
+
| 0.0244 | 2.6164 | 1700 | 0.0354 |
|
| 89 |
+
| 0.0295 | 2.6933 | 1750 | 0.0355 |
|
| 90 |
+
| 0.0257 | 2.7703 | 1800 | 0.0354 |
|
| 91 |
+
| 0.0313 | 2.8472 | 1850 | 0.0339 |
|
| 92 |
+
| 0.0208 | 2.9242 | 1900 | 0.0348 |
|
| 93 |
+
| 0.0314 | 3.0012 | 1950 | 0.0349 |
|
| 94 |
+
| 0.0119 | 3.0781 | 2000 | 0.0392 |
|
| 95 |
+
| 0.0147 | 3.1551 | 2050 | 0.0425 |
|
| 96 |
+
| 0.011 | 3.2320 | 2100 | 0.0402 |
|
| 97 |
+
| 0.012 | 3.3090 | 2150 | 0.0416 |
|
| 98 |
+
| 0.0205 | 3.3859 | 2200 | 0.0398 |
|
| 99 |
+
| 0.0127 | 3.4629 | 2250 | 0.0399 |
|
| 100 |
+
| 0.0141 | 3.5398 | 2300 | 0.0419 |
|
| 101 |
+
| 0.0081 | 3.6168 | 2350 | 0.0435 |
|
| 102 |
+
| 0.0132 | 3.6937 | 2400 | 0.0412 |
|
| 103 |
+
| 0.0111 | 3.7707 | 2450 | 0.0433 |
|
| 104 |
+
| 0.0069 | 3.8476 | 2500 | 0.0446 |
|
| 105 |
+
| 0.0135 | 3.9246 | 2550 | 0.0454 |
|
| 106 |
+
| 0.0093 | 4.0015 | 2600 | 0.0452 |
|
| 107 |
+
| 0.0024 | 4.0785 | 2650 | 0.0488 |
|
| 108 |
+
| 0.0082 | 4.1554 | 2700 | 0.0550 |
|
| 109 |
+
| 0.004 | 4.2324 | 2750 | 0.0540 |
|
| 110 |
+
| 0.0044 | 4.3093 | 2800 | 0.0571 |
|
| 111 |
+
| 0.0027 | 4.3863 | 2850 | 0.0591 |
|
| 112 |
+
| 0.0044 | 4.4633 | 2900 | 0.0599 |
|
| 113 |
+
| 0.0017 | 4.5402 | 2950 | 0.0583 |
|
| 114 |
+
| 0.0034 | 4.6172 | 3000 | 0.0581 |
|
| 115 |
+
| 0.0048 | 4.6941 | 3050 | 0.0578 |
|
| 116 |
+
| 0.0051 | 4.7711 | 3100 | 0.0577 |
|
| 117 |
+
| 0.0053 | 4.8480 | 3150 | 0.0578 |
|
| 118 |
+
| 0.0033 | 4.9250 | 3200 | 0.0577 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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:a9a05b7e2705b952fa223a9a819f33a8059c0efc57d59c8366c3cf68ee3e5537
|
| 3 |
size 83945296
|