Model save
Browse files- README.md +69 -135
- 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-fold3
|
| 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 |
|
|
@@ -46,144 +46,78 @@ 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.
|
| 121 |
-
| 0.0042 | 5.0428 | 3350 | 0.0596 |
|
| 122 |
-
| 0.0059 | 5.1181 | 3400 | 0.0585 |
|
| 123 |
-
| 0.0041 | 5.1933 | 3450 | 0.0657 |
|
| 124 |
-
| 0.0027 | 5.2686 | 3500 | 0.0646 |
|
| 125 |
-
| 0.0021 | 5.3439 | 3550 | 0.0598 |
|
| 126 |
-
| 0.0011 | 5.4191 | 3600 | 0.0593 |
|
| 127 |
-
| 0.0028 | 5.4944 | 3650 | 0.0583 |
|
| 128 |
-
| 0.0069 | 5.5697 | 3700 | 0.0527 |
|
| 129 |
-
| 0.0044 | 5.6449 | 3750 | 0.0575 |
|
| 130 |
-
| 0.005 | 5.7202 | 3800 | 0.0603 |
|
| 131 |
-
| 0.0034 | 5.7955 | 3850 | 0.0663 |
|
| 132 |
-
| 0.007 | 5.8707 | 3900 | 0.0544 |
|
| 133 |
-
| 0.0059 | 5.9460 | 3950 | 0.0533 |
|
| 134 |
-
| 0.0021 | 6.0213 | 4000 | 0.0597 |
|
| 135 |
-
| 0.0017 | 6.0965 | 4050 | 0.0612 |
|
| 136 |
-
| 0.0065 | 6.1718 | 4100 | 0.0606 |
|
| 137 |
-
| 0.001 | 6.2471 | 4150 | 0.0655 |
|
| 138 |
-
| 0.0035 | 6.3223 | 4200 | 0.0675 |
|
| 139 |
-
| 0.0058 | 6.3976 | 4250 | 0.0619 |
|
| 140 |
-
| 0.0025 | 6.4729 | 4300 | 0.0636 |
|
| 141 |
-
| 0.002 | 6.5481 | 4350 | 0.0681 |
|
| 142 |
-
| 0.0008 | 6.6234 | 4400 | 0.0721 |
|
| 143 |
-
| 0.0025 | 6.6987 | 4450 | 0.0603 |
|
| 144 |
-
| 0.0021 | 6.7739 | 4500 | 0.0615 |
|
| 145 |
-
| 0.0032 | 6.8492 | 4550 | 0.0608 |
|
| 146 |
-
| 0.0046 | 6.9245 | 4600 | 0.0656 |
|
| 147 |
-
| 0.0021 | 6.9997 | 4650 | 0.0695 |
|
| 148 |
-
| 0.0008 | 7.0750 | 4700 | 0.0669 |
|
| 149 |
-
| 0.0001 | 7.1502 | 4750 | 0.0729 |
|
| 150 |
-
| 0.0016 | 7.2255 | 4800 | 0.0755 |
|
| 151 |
-
| 0.0011 | 7.3008 | 4850 | 0.0772 |
|
| 152 |
-
| 0.0037 | 7.3760 | 4900 | 0.0756 |
|
| 153 |
-
| 0.0002 | 7.4513 | 4950 | 0.0770 |
|
| 154 |
-
| 0.0013 | 7.5266 | 5000 | 0.0709 |
|
| 155 |
-
| 0.0016 | 7.6018 | 5050 | 0.0706 |
|
| 156 |
-
| 0.0003 | 7.6771 | 5100 | 0.0718 |
|
| 157 |
-
| 0.0024 | 7.7524 | 5150 | 0.0724 |
|
| 158 |
-
| 0.0024 | 7.8276 | 5200 | 0.0750 |
|
| 159 |
-
| 0.0003 | 7.9029 | 5250 | 0.0753 |
|
| 160 |
-
| 0.0008 | 7.9782 | 5300 | 0.0762 |
|
| 161 |
-
| 0.0002 | 8.0534 | 5350 | 0.0798 |
|
| 162 |
-
| 0.0014 | 8.1287 | 5400 | 0.0810 |
|
| 163 |
-
| 0.0001 | 8.2040 | 5450 | 0.0807 |
|
| 164 |
-
| 0.0022 | 8.2792 | 5500 | 0.0826 |
|
| 165 |
-
| 0.0011 | 8.3545 | 5550 | 0.0840 |
|
| 166 |
-
| 0.0001 | 8.4298 | 5600 | 0.0858 |
|
| 167 |
-
| 0.0012 | 8.5050 | 5650 | 0.0878 |
|
| 168 |
-
| 0.0006 | 8.5803 | 5700 | 0.0870 |
|
| 169 |
-
| 0.0005 | 8.6556 | 5750 | 0.0883 |
|
| 170 |
-
| 0.0016 | 8.7308 | 5800 | 0.0883 |
|
| 171 |
-
| 0.0004 | 8.8061 | 5850 | 0.0892 |
|
| 172 |
-
| 0.0003 | 8.8814 | 5900 | 0.0878 |
|
| 173 |
-
| 0.0009 | 8.9566 | 5950 | 0.0877 |
|
| 174 |
-
| 0.0007 | 9.0319 | 6000 | 0.0878 |
|
| 175 |
-
| 0.0001 | 9.1072 | 6050 | 0.0888 |
|
| 176 |
-
| 0.0013 | 9.1824 | 6100 | 0.0888 |
|
| 177 |
-
| 0.0006 | 9.2577 | 6150 | 0.0888 |
|
| 178 |
-
| 0.0006 | 9.3330 | 6200 | 0.0891 |
|
| 179 |
-
| 0.0003 | 9.4082 | 6250 | 0.0894 |
|
| 180 |
-
| 0.0 | 9.4835 | 6300 | 0.0897 |
|
| 181 |
-
| 0.0001 | 9.5588 | 6350 | 0.0902 |
|
| 182 |
-
| 0.0004 | 9.6340 | 6400 | 0.0901 |
|
| 183 |
-
| 0.0008 | 9.7093 | 6450 | 0.0900 |
|
| 184 |
-
| 0.0002 | 9.7846 | 6500 | 0.0901 |
|
| 185 |
-
| 0.0003 | 9.8598 | 6550 | 0.0902 |
|
| 186 |
-
| 0.0001 | 9.9351 | 6600 | 0.0904 |
|
| 187 |
|
| 188 |
|
| 189 |
### Framework versions
|
|
|
|
| 16 |
|
| 17 |
# Llama-3.1-8B-Instruct-PsyCourse-fold3
|
| 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: 0.0553
|
| 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 |
+
| 0.5742 | 0.0753 | 50 | 0.4037 |
|
| 56 |
+
| 0.0981 | 0.1505 | 100 | 0.0890 |
|
| 57 |
+
| 0.0775 | 0.2258 | 150 | 0.0663 |
|
| 58 |
+
| 0.075 | 0.3011 | 200 | 0.0574 |
|
| 59 |
+
| 0.0587 | 0.3763 | 250 | 0.0533 |
|
| 60 |
+
| 0.0617 | 0.4516 | 300 | 0.0547 |
|
| 61 |
+
| 0.0431 | 0.5269 | 350 | 0.0519 |
|
| 62 |
+
| 0.0573 | 0.6021 | 400 | 0.0479 |
|
| 63 |
+
| 0.0504 | 0.6774 | 450 | 0.0438 |
|
| 64 |
+
| 0.0341 | 0.7527 | 500 | 0.0428 |
|
| 65 |
+
| 0.0448 | 0.8279 | 550 | 0.0440 |
|
| 66 |
+
| 0.0373 | 0.9032 | 600 | 0.0414 |
|
| 67 |
+
| 0.0369 | 0.9785 | 650 | 0.0414 |
|
| 68 |
+
| 0.0266 | 1.0537 | 700 | 0.0422 |
|
| 69 |
+
| 0.0337 | 1.1290 | 750 | 0.0380 |
|
| 70 |
+
| 0.0379 | 1.2043 | 800 | 0.0424 |
|
| 71 |
+
| 0.0297 | 1.2795 | 850 | 0.0413 |
|
| 72 |
+
| 0.0417 | 1.3548 | 900 | 0.0389 |
|
| 73 |
+
| 0.0342 | 1.4300 | 950 | 0.0393 |
|
| 74 |
+
| 0.033 | 1.5053 | 1000 | 0.0387 |
|
| 75 |
+
| 0.0304 | 1.5806 | 1050 | 0.0412 |
|
| 76 |
+
| 0.0225 | 1.6558 | 1100 | 0.0380 |
|
| 77 |
+
| 0.0406 | 1.7311 | 1150 | 0.0359 |
|
| 78 |
+
| 0.0314 | 1.8064 | 1200 | 0.0378 |
|
| 79 |
+
| 0.0345 | 1.8816 | 1250 | 0.0352 |
|
| 80 |
+
| 0.0314 | 1.9569 | 1300 | 0.0352 |
|
| 81 |
+
| 0.0232 | 2.0322 | 1350 | 0.0370 |
|
| 82 |
+
| 0.0298 | 2.1074 | 1400 | 0.0358 |
|
| 83 |
+
| 0.0224 | 2.1827 | 1450 | 0.0376 |
|
| 84 |
+
| 0.0251 | 2.2580 | 1500 | 0.0403 |
|
| 85 |
+
| 0.0303 | 2.3332 | 1550 | 0.0377 |
|
| 86 |
+
| 0.0174 | 2.4085 | 1600 | 0.0399 |
|
| 87 |
+
| 0.02 | 2.4838 | 1650 | 0.0393 |
|
| 88 |
+
| 0.0239 | 2.5590 | 1700 | 0.0386 |
|
| 89 |
+
| 0.0377 | 2.6343 | 1750 | 0.0377 |
|
| 90 |
+
| 0.0266 | 2.7096 | 1800 | 0.0373 |
|
| 91 |
+
| 0.0229 | 2.7848 | 1850 | 0.0356 |
|
| 92 |
+
| 0.0257 | 2.8601 | 1900 | 0.0409 |
|
| 93 |
+
| 0.021 | 2.9354 | 1950 | 0.0365 |
|
| 94 |
+
| 0.0137 | 3.0106 | 2000 | 0.0382 |
|
| 95 |
+
| 0.0119 | 3.0859 | 2050 | 0.0439 |
|
| 96 |
+
| 0.0116 | 3.1612 | 2100 | 0.0427 |
|
| 97 |
+
| 0.0131 | 3.2364 | 2150 | 0.0435 |
|
| 98 |
+
| 0.0132 | 3.3117 | 2200 | 0.0436 |
|
| 99 |
+
| 0.0095 | 3.3870 | 2250 | 0.0448 |
|
| 100 |
+
| 0.0101 | 3.4622 | 2300 | 0.0486 |
|
| 101 |
+
| 0.0068 | 3.5375 | 2350 | 0.0472 |
|
| 102 |
+
| 0.0133 | 3.6128 | 2400 | 0.0447 |
|
| 103 |
+
| 0.0155 | 3.6880 | 2450 | 0.0423 |
|
| 104 |
+
| 0.0118 | 3.7633 | 2500 | 0.0446 |
|
| 105 |
+
| 0.0104 | 3.8386 | 2550 | 0.0464 |
|
| 106 |
+
| 0.0149 | 3.9138 | 2600 | 0.0434 |
|
| 107 |
+
| 0.0126 | 3.9891 | 2650 | 0.0439 |
|
| 108 |
+
| 0.0066 | 4.0644 | 2700 | 0.0464 |
|
| 109 |
+
| 0.0048 | 4.1396 | 2750 | 0.0502 |
|
| 110 |
+
| 0.0052 | 4.2149 | 2800 | 0.0543 |
|
| 111 |
+
| 0.0051 | 4.2901 | 2850 | 0.0537 |
|
| 112 |
+
| 0.0102 | 4.3654 | 2900 | 0.0547 |
|
| 113 |
+
| 0.0052 | 4.4407 | 2950 | 0.0546 |
|
| 114 |
+
| 0.0029 | 4.5159 | 3000 | 0.0548 |
|
| 115 |
+
| 0.0085 | 4.5912 | 3050 | 0.0552 |
|
| 116 |
+
| 0.0049 | 4.6665 | 3100 | 0.0551 |
|
| 117 |
+
| 0.0054 | 4.7417 | 3150 | 0.0553 |
|
| 118 |
+
| 0.0035 | 4.8170 | 3200 | 0.0553 |
|
| 119 |
+
| 0.0041 | 4.8923 | 3250 | 0.0554 |
|
| 120 |
+
| 0.0045 | 4.9675 | 3300 | 0.0553 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 121 |
|
| 122 |
|
| 123 |
### 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:d13dcdb9220e47c3d277ed0a475c996b267ae5545d0e24e88f91e02e4b51c502
|
| 3 |
size 83945296
|