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-fold10
|
| 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 |
-
| 0.0114 | 5.0024 | 3250 | 0.0509 |
|
| 120 |
-
| 0.0094 | 5.0794 | 3300 | 0.0544 |
|
| 121 |
-
| 0.0068 | 5.1563 | 3350 | 0.0576 |
|
| 122 |
-
| 0.008 | 5.2333 | 3400 | 0.0621 |
|
| 123 |
-
| 0.0043 | 5.3102 | 3450 | 0.0562 |
|
| 124 |
-
| 0.0052 | 5.3872 | 3500 | 0.0636 |
|
| 125 |
-
| 0.0106 | 5.4642 | 3550 | 0.0624 |
|
| 126 |
-
| 0.0071 | 5.5411 | 3600 | 0.0550 |
|
| 127 |
-
| 0.0071 | 5.6181 | 3650 | 0.0575 |
|
| 128 |
-
| 0.0037 | 5.6950 | 3700 | 0.0676 |
|
| 129 |
-
| 0.0048 | 5.7720 | 3750 | 0.0585 |
|
| 130 |
-
| 0.0095 | 5.8490 | 3800 | 0.0627 |
|
| 131 |
-
| 0.0044 | 5.9259 | 3850 | 0.0622 |
|
| 132 |
-
| 0.0059 | 6.0029 | 3900 | 0.0537 |
|
| 133 |
-
| 0.0027 | 6.0798 | 3950 | 0.0611 |
|
| 134 |
-
| 0.0014 | 6.1568 | 4000 | 0.0681 |
|
| 135 |
-
| 0.0027 | 6.2338 | 4050 | 0.0721 |
|
| 136 |
-
| 0.0015 | 6.3107 | 4100 | 0.0669 |
|
| 137 |
-
| 0.0052 | 6.3877 | 4150 | 0.0680 |
|
| 138 |
-
| 0.0043 | 6.4646 | 4200 | 0.0635 |
|
| 139 |
-
| 0.0038 | 6.5416 | 4250 | 0.0666 |
|
| 140 |
-
| 0.0044 | 6.6186 | 4300 | 0.0672 |
|
| 141 |
-
| 0.0012 | 6.6955 | 4350 | 0.0659 |
|
| 142 |
-
| 0.0017 | 6.7725 | 4400 | 0.0688 |
|
| 143 |
-
| 0.0072 | 6.8494 | 4450 | 0.0691 |
|
| 144 |
-
| 0.0036 | 6.9264 | 4500 | 0.0659 |
|
| 145 |
-
| 0.0006 | 7.0034 | 4550 | 0.0667 |
|
| 146 |
-
| 0.0012 | 7.0803 | 4600 | 0.0716 |
|
| 147 |
-
| 0.0018 | 7.1573 | 4650 | 0.0735 |
|
| 148 |
-
| 0.002 | 7.2342 | 4700 | 0.0761 |
|
| 149 |
-
| 0.0006 | 7.3112 | 4750 | 0.0762 |
|
| 150 |
-
| 0.0002 | 7.3882 | 4800 | 0.0765 |
|
| 151 |
-
| 0.0003 | 7.4651 | 4850 | 0.0802 |
|
| 152 |
-
| 0.0002 | 7.5421 | 4900 | 0.0789 |
|
| 153 |
-
| 0.0025 | 7.6190 | 4950 | 0.0805 |
|
| 154 |
-
| 0.0003 | 7.6960 | 5000 | 0.0750 |
|
| 155 |
-
| 0.0006 | 7.7730 | 5050 | 0.0741 |
|
| 156 |
-
| 0.0011 | 7.8499 | 5100 | 0.0746 |
|
| 157 |
-
| 0.0002 | 7.9269 | 5150 | 0.0748 |
|
| 158 |
-
| 0.0016 | 8.0038 | 5200 | 0.0746 |
|
| 159 |
-
| 0.0011 | 8.0808 | 5250 | 0.0755 |
|
| 160 |
-
| 0.0002 | 8.1578 | 5300 | 0.0791 |
|
| 161 |
-
| 0.0001 | 8.2347 | 5350 | 0.0823 |
|
| 162 |
-
| 0.0 | 8.3117 | 5400 | 0.0834 |
|
| 163 |
-
| 0.0001 | 8.3886 | 5450 | 0.0856 |
|
| 164 |
-
| 0.0002 | 8.4656 | 5500 | 0.0842 |
|
| 165 |
-
| 0.0002 | 8.5426 | 5550 | 0.0853 |
|
| 166 |
-
| 0.0014 | 8.6195 | 5600 | 0.0852 |
|
| 167 |
-
| 0.0009 | 8.6965 | 5650 | 0.0854 |
|
| 168 |
-
| 0.0006 | 8.7734 | 5700 | 0.0849 |
|
| 169 |
-
| 0.0003 | 8.8504 | 5750 | 0.0848 |
|
| 170 |
-
| 0.0007 | 8.9274 | 5800 | 0.0857 |
|
| 171 |
-
| 0.0 | 9.0043 | 5850 | 0.0865 |
|
| 172 |
-
| 0.0 | 9.0813 | 5900 | 0.0873 |
|
| 173 |
-
| 0.0006 | 9.1582 | 5950 | 0.0876 |
|
| 174 |
-
| 0.0003 | 9.2352 | 6000 | 0.0879 |
|
| 175 |
-
| 0.0002 | 9.3122 | 6050 | 0.0882 |
|
| 176 |
-
| 0.0004 | 9.3891 | 6100 | 0.0885 |
|
| 177 |
-
| 0.0003 | 9.4661 | 6150 | 0.0884 |
|
| 178 |
-
| 0.0005 | 9.5430 | 6200 | 0.0887 |
|
| 179 |
-
| 0.0003 | 9.6200 | 6250 | 0.0887 |
|
| 180 |
-
| 0.0001 | 9.6970 | 6300 | 0.0890 |
|
| 181 |
-
| 0.0004 | 9.7739 | 6350 | 0.0889 |
|
| 182 |
-
| 0.001 | 9.8509 | 6400 | 0.0889 |
|
| 183 |
-
| 0.0 | 9.9278 | 6450 | 0.0890 |
|
| 184 |
|
| 185 |
|
| 186 |
### Framework versions
|
|
|
|
| 16 |
|
| 17 |
# Llama-3.1-8B-Instruct-PsyCourse-fold10
|
| 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: 0.0545
|
| 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 |
+
| 0.6238 | 0.0770 | 50 | 0.3911 |
|
| 56 |
+
| 0.0941 | 0.1539 | 100 | 0.0845 |
|
| 57 |
+
| 0.087 | 0.2309 | 150 | 0.0577 |
|
| 58 |
+
| 0.0643 | 0.3078 | 200 | 0.0540 |
|
| 59 |
+
| 0.0718 | 0.3848 | 250 | 0.0550 |
|
| 60 |
+
| 0.0561 | 0.4618 | 300 | 0.0480 |
|
| 61 |
+
| 0.0517 | 0.5387 | 350 | 0.0457 |
|
| 62 |
+
| 0.0473 | 0.6157 | 400 | 0.0444 |
|
| 63 |
+
| 0.0486 | 0.6926 | 450 | 0.0480 |
|
| 64 |
+
| 0.0579 | 0.7696 | 500 | 0.0443 |
|
| 65 |
+
| 0.0433 | 0.8466 | 550 | 0.0422 |
|
| 66 |
+
| 0.0464 | 0.9235 | 600 | 0.0384 |
|
| 67 |
+
| 0.0542 | 1.0005 | 650 | 0.0373 |
|
| 68 |
+
| 0.0365 | 1.0774 | 700 | 0.0419 |
|
| 69 |
+
| 0.0303 | 1.1544 | 750 | 0.0383 |
|
| 70 |
+
| 0.0281 | 1.2314 | 800 | 0.0357 |
|
| 71 |
+
| 0.0293 | 1.3083 | 850 | 0.0360 |
|
| 72 |
+
| 0.0408 | 1.3853 | 900 | 0.0362 |
|
| 73 |
+
| 0.0358 | 1.4622 | 950 | 0.0379 |
|
| 74 |
+
| 0.0277 | 1.5392 | 1000 | 0.0406 |
|
| 75 |
+
| 0.0401 | 1.6162 | 1050 | 0.0346 |
|
| 76 |
+
| 0.0366 | 1.6931 | 1100 | 0.0379 |
|
| 77 |
+
| 0.0292 | 1.7701 | 1150 | 0.0357 |
|
| 78 |
+
| 0.0408 | 1.8470 | 1200 | 0.0368 |
|
| 79 |
+
| 0.0354 | 1.9240 | 1250 | 0.0367 |
|
| 80 |
+
| 0.0374 | 2.0010 | 1300 | 0.0378 |
|
| 81 |
+
| 0.0216 | 2.0779 | 1350 | 0.0356 |
|
| 82 |
+
| 0.0272 | 2.1549 | 1400 | 0.0355 |
|
| 83 |
+
| 0.0207 | 2.2318 | 1450 | 0.0360 |
|
| 84 |
+
| 0.0275 | 2.3088 | 1500 | 0.0357 |
|
| 85 |
+
| 0.0236 | 2.3858 | 1550 | 0.0361 |
|
| 86 |
+
| 0.0263 | 2.4627 | 1600 | 0.0371 |
|
| 87 |
+
| 0.0306 | 2.5397 | 1650 | 0.0352 |
|
| 88 |
+
| 0.0264 | 2.6166 | 1700 | 0.0349 |
|
| 89 |
+
| 0.0192 | 2.6936 | 1750 | 0.0347 |
|
| 90 |
+
| 0.0239 | 2.7706 | 1800 | 0.0359 |
|
| 91 |
+
| 0.0158 | 2.8475 | 1850 | 0.0374 |
|
| 92 |
+
| 0.019 | 2.9245 | 1900 | 0.0362 |
|
| 93 |
+
| 0.0218 | 3.0014 | 1950 | 0.0355 |
|
| 94 |
+
| 0.014 | 3.0784 | 2000 | 0.0406 |
|
| 95 |
+
| 0.0125 | 3.1554 | 2050 | 0.0427 |
|
| 96 |
+
| 0.0163 | 3.2323 | 2100 | 0.0419 |
|
| 97 |
+
| 0.0118 | 3.3093 | 2150 | 0.0408 |
|
| 98 |
+
| 0.0119 | 3.3862 | 2200 | 0.0422 |
|
| 99 |
+
| 0.0109 | 3.4632 | 2250 | 0.0453 |
|
| 100 |
+
| 0.013 | 3.5402 | 2300 | 0.0447 |
|
| 101 |
+
| 0.0108 | 3.6171 | 2350 | 0.0428 |
|
| 102 |
+
| 0.0132 | 3.6941 | 2400 | 0.0471 |
|
| 103 |
+
| 0.0098 | 3.7710 | 2450 | 0.0445 |
|
| 104 |
+
| 0.017 | 3.8480 | 2500 | 0.0410 |
|
| 105 |
+
| 0.0115 | 3.9250 | 2550 | 0.0408 |
|
| 106 |
+
| 0.0121 | 4.0019 | 2600 | 0.0412 |
|
| 107 |
+
| 0.0061 | 4.0789 | 2650 | 0.0451 |
|
| 108 |
+
| 0.0076 | 4.1558 | 2700 | 0.0485 |
|
| 109 |
+
| 0.0066 | 4.2328 | 2750 | 0.0524 |
|
| 110 |
+
| 0.0053 | 4.3098 | 2800 | 0.0534 |
|
| 111 |
+
| 0.0073 | 4.3867 | 2850 | 0.0541 |
|
| 112 |
+
| 0.0033 | 4.4637 | 2900 | 0.0533 |
|
| 113 |
+
| 0.004 | 4.5406 | 2950 | 0.0537 |
|
| 114 |
+
| 0.0055 | 4.6176 | 3000 | 0.0541 |
|
| 115 |
+
| 0.0106 | 4.6946 | 3050 | 0.0545 |
|
| 116 |
+
| 0.0025 | 4.7715 | 3100 | 0.0543 |
|
| 117 |
+
| 0.0053 | 4.8485 | 3150 | 0.0545 |
|
| 118 |
+
| 0.0033 | 4.9254 | 3200 | 0.0545 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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:a6b0ac39bd40c4389f5fdd0ec570282d71b084e94bdabcbb05b6ea0288abf59a
|
| 3 |
size 83945296
|