strongpear/llama3.0-8B_finetune_QA_EDU_36k_samples_r64
Browse files- README.md +472 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,472 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: llama3
|
| 4 |
+
base_model: meta-llama/Meta-Llama-3-8B
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: llama3.0-8B_finetune_QA_EDU_36k_samples_r64
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# llama3.0-8B_finetune_QA_EDU_36k_samples_r64
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.4130
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 3.6e-05
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 4
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 5
|
| 45 |
+
- mixed_precision_training: Native AMP
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
| 51 |
+
| 1.0648 | 0.0055 | 50 | 0.9501 |
|
| 52 |
+
| 0.7039 | 0.0109 | 100 | 0.9215 |
|
| 53 |
+
| 0.7897 | 0.0164 | 150 | 0.9036 |
|
| 54 |
+
| 0.8434 | 0.0219 | 200 | 0.8875 |
|
| 55 |
+
| 0.7746 | 0.0273 | 250 | 0.8835 |
|
| 56 |
+
| 0.6896 | 0.0328 | 300 | 0.8671 |
|
| 57 |
+
| 0.824 | 0.0383 | 350 | 0.8548 |
|
| 58 |
+
| 1.0038 | 0.0437 | 400 | 0.8458 |
|
| 59 |
+
| 0.6472 | 0.0492 | 450 | 0.8378 |
|
| 60 |
+
| 0.8127 | 0.0547 | 500 | 0.8314 |
|
| 61 |
+
| 0.4811 | 0.0601 | 550 | 0.8286 |
|
| 62 |
+
| 0.8293 | 0.0656 | 600 | 0.8193 |
|
| 63 |
+
| 0.5957 | 0.0711 | 650 | 0.8136 |
|
| 64 |
+
| 0.7233 | 0.0765 | 700 | 0.8085 |
|
| 65 |
+
| 0.7291 | 0.0820 | 750 | 0.8020 |
|
| 66 |
+
| 0.822 | 0.0875 | 800 | 0.7976 |
|
| 67 |
+
| 0.6432 | 0.0929 | 850 | 0.7935 |
|
| 68 |
+
| 0.811 | 0.0984 | 900 | 0.7898 |
|
| 69 |
+
| 0.7663 | 0.1039 | 950 | 0.7878 |
|
| 70 |
+
| 1.0561 | 0.1093 | 1000 | 0.7835 |
|
| 71 |
+
| 0.5032 | 0.1148 | 1050 | 0.7826 |
|
| 72 |
+
| 0.8217 | 0.1203 | 1100 | 0.7813 |
|
| 73 |
+
| 0.6665 | 0.1257 | 1150 | 0.7722 |
|
| 74 |
+
| 0.9122 | 0.1312 | 1200 | 0.7701 |
|
| 75 |
+
| 0.7676 | 0.1367 | 1250 | 0.7683 |
|
| 76 |
+
| 0.6259 | 0.1421 | 1300 | 0.7648 |
|
| 77 |
+
| 0.6051 | 0.1476 | 1350 | 0.7614 |
|
| 78 |
+
| 0.8253 | 0.1531 | 1400 | 0.7540 |
|
| 79 |
+
| 0.7211 | 0.1585 | 1450 | 0.7529 |
|
| 80 |
+
| 0.6831 | 0.1640 | 1500 | 0.7473 |
|
| 81 |
+
| 0.6355 | 0.1695 | 1550 | 0.7476 |
|
| 82 |
+
| 0.7132 | 0.1749 | 1600 | 0.7456 |
|
| 83 |
+
| 0.7474 | 0.1804 | 1650 | 0.7418 |
|
| 84 |
+
| 0.928 | 0.1859 | 1700 | 0.7396 |
|
| 85 |
+
| 0.9145 | 0.1913 | 1750 | 0.7330 |
|
| 86 |
+
| 0.794 | 0.1968 | 1800 | 0.7357 |
|
| 87 |
+
| 0.477 | 0.2023 | 1850 | 0.7315 |
|
| 88 |
+
| 0.9995 | 0.2077 | 1900 | 0.7287 |
|
| 89 |
+
| 0.8334 | 0.2132 | 1950 | 0.7267 |
|
| 90 |
+
| 0.9413 | 0.2187 | 2000 | 0.7264 |
|
| 91 |
+
| 0.6294 | 0.2241 | 2050 | 0.7289 |
|
| 92 |
+
| 0.5025 | 0.2296 | 2100 | 0.7229 |
|
| 93 |
+
| 0.5802 | 0.2350 | 2150 | 0.7183 |
|
| 94 |
+
| 0.5811 | 0.2405 | 2200 | 0.7112 |
|
| 95 |
+
| 1.049 | 0.2460 | 2250 | 0.7085 |
|
| 96 |
+
| 0.6275 | 0.2514 | 2300 | 0.7045 |
|
| 97 |
+
| 0.5112 | 0.2569 | 2350 | 0.7006 |
|
| 98 |
+
| 0.8751 | 0.2624 | 2400 | 0.7032 |
|
| 99 |
+
| 0.6469 | 0.2678 | 2450 | 0.7019 |
|
| 100 |
+
| 0.7677 | 0.2733 | 2500 | 0.6989 |
|
| 101 |
+
| 0.8143 | 0.2788 | 2550 | 0.6988 |
|
| 102 |
+
| 1.2143 | 0.2842 | 2600 | 0.6997 |
|
| 103 |
+
| 0.8023 | 0.2897 | 2650 | 0.6942 |
|
| 104 |
+
| 0.5641 | 0.2952 | 2700 | 0.6904 |
|
| 105 |
+
| 0.8155 | 0.3006 | 2750 | 0.6943 |
|
| 106 |
+
| 0.5784 | 0.3061 | 2800 | 0.6861 |
|
| 107 |
+
| 0.7558 | 0.3116 | 2850 | 0.6778 |
|
| 108 |
+
| 0.6899 | 0.3170 | 2900 | 0.6795 |
|
| 109 |
+
| 0.5752 | 0.3225 | 2950 | 0.6781 |
|
| 110 |
+
| 0.8825 | 0.3280 | 3000 | 0.6786 |
|
| 111 |
+
| 0.6724 | 0.3334 | 3050 | 0.6765 |
|
| 112 |
+
| 0.6598 | 0.3389 | 3100 | 0.6738 |
|
| 113 |
+
| 0.6229 | 0.3444 | 3150 | 0.6721 |
|
| 114 |
+
| 0.5764 | 0.3498 | 3200 | 0.6686 |
|
| 115 |
+
| 0.5497 | 0.3553 | 3250 | 0.6706 |
|
| 116 |
+
| 0.3927 | 0.3608 | 3300 | 0.6668 |
|
| 117 |
+
| 0.4647 | 0.3662 | 3350 | 0.6667 |
|
| 118 |
+
| 0.3929 | 0.3717 | 3400 | 0.6648 |
|
| 119 |
+
| 0.8083 | 0.3772 | 3450 | 0.6652 |
|
| 120 |
+
| 0.5741 | 0.3826 | 3500 | 0.6615 |
|
| 121 |
+
| 0.6214 | 0.3881 | 3550 | 0.6576 |
|
| 122 |
+
| 0.7467 | 0.3936 | 3600 | 0.6566 |
|
| 123 |
+
| 0.9464 | 0.3990 | 3650 | 0.6546 |
|
| 124 |
+
| 0.841 | 0.4045 | 3700 | 0.6509 |
|
| 125 |
+
| 0.6993 | 0.4100 | 3750 | 0.6444 |
|
| 126 |
+
| 0.6812 | 0.4154 | 3800 | 0.6406 |
|
| 127 |
+
| 0.7938 | 0.4209 | 3850 | 0.6378 |
|
| 128 |
+
| 0.9625 | 0.4264 | 3900 | 0.6352 |
|
| 129 |
+
| 0.6543 | 0.4318 | 3950 | 0.6343 |
|
| 130 |
+
| 0.6272 | 0.4373 | 4000 | 0.6359 |
|
| 131 |
+
| 1.0398 | 0.4428 | 4050 | 0.6340 |
|
| 132 |
+
| 0.7372 | 0.4482 | 4100 | 0.6341 |
|
| 133 |
+
| 0.4583 | 0.4537 | 4150 | 0.6288 |
|
| 134 |
+
| 0.8163 | 0.4592 | 4200 | 0.6251 |
|
| 135 |
+
| 0.7215 | 0.4646 | 4250 | 0.6221 |
|
| 136 |
+
| 0.516 | 0.4701 | 4300 | 0.6261 |
|
| 137 |
+
| 0.9572 | 0.4756 | 4350 | 0.6216 |
|
| 138 |
+
| 0.6965 | 0.4810 | 4400 | 0.6191 |
|
| 139 |
+
| 0.8783 | 0.4865 | 4450 | 0.6188 |
|
| 140 |
+
| 0.6163 | 0.4920 | 4500 | 0.6172 |
|
| 141 |
+
| 0.7207 | 0.4974 | 4550 | 0.6177 |
|
| 142 |
+
| 0.4977 | 0.5029 | 4600 | 0.6158 |
|
| 143 |
+
| 0.6102 | 0.5084 | 4650 | 0.6125 |
|
| 144 |
+
| 0.9167 | 0.5138 | 4700 | 0.6116 |
|
| 145 |
+
| 0.5921 | 0.5193 | 4750 | 0.6107 |
|
| 146 |
+
| 0.6261 | 0.5248 | 4800 | 0.6061 |
|
| 147 |
+
| 0.5889 | 0.5302 | 4850 | 0.6064 |
|
| 148 |
+
| 0.3506 | 0.5357 | 4900 | 0.6012 |
|
| 149 |
+
| 0.3856 | 0.5412 | 4950 | 0.6037 |
|
| 150 |
+
| 0.6855 | 0.5466 | 5000 | 0.5985 |
|
| 151 |
+
| 0.6345 | 0.5521 | 5050 | 0.6021 |
|
| 152 |
+
| 0.8208 | 0.5576 | 5100 | 0.5984 |
|
| 153 |
+
| 0.5655 | 0.5630 | 5150 | 0.5958 |
|
| 154 |
+
| 0.4587 | 0.5685 | 5200 | 0.5952 |
|
| 155 |
+
| 0.5134 | 0.5740 | 5250 | 0.5946 |
|
| 156 |
+
| 0.3903 | 0.5794 | 5300 | 0.5955 |
|
| 157 |
+
| 0.5257 | 0.5849 | 5350 | 0.5925 |
|
| 158 |
+
| 0.6125 | 0.5904 | 5400 | 0.5913 |
|
| 159 |
+
| 0.6799 | 0.5958 | 5450 | 0.5903 |
|
| 160 |
+
| 0.7916 | 0.6013 | 5500 | 0.5884 |
|
| 161 |
+
| 0.7222 | 0.6068 | 5550 | 0.5863 |
|
| 162 |
+
| 0.4425 | 0.6122 | 5600 | 0.5821 |
|
| 163 |
+
| 0.6597 | 0.6177 | 5650 | 0.5839 |
|
| 164 |
+
| 0.4371 | 0.6232 | 5700 | 0.5815 |
|
| 165 |
+
| 0.4633 | 0.6286 | 5750 | 0.5804 |
|
| 166 |
+
| 0.6525 | 0.6341 | 5800 | 0.5808 |
|
| 167 |
+
| 0.5727 | 0.6396 | 5850 | 0.5803 |
|
| 168 |
+
| 0.424 | 0.6450 | 5900 | 0.5758 |
|
| 169 |
+
| 0.6045 | 0.6505 | 5950 | 0.5776 |
|
| 170 |
+
| 0.4846 | 0.6560 | 6000 | 0.5783 |
|
| 171 |
+
| 0.5949 | 0.6614 | 6050 | 0.5747 |
|
| 172 |
+
| 0.5127 | 0.6669 | 6100 | 0.5751 |
|
| 173 |
+
| 0.4289 | 0.6724 | 6150 | 0.5718 |
|
| 174 |
+
| 1.1129 | 0.6778 | 6200 | 0.5734 |
|
| 175 |
+
| 0.6932 | 0.6833 | 6250 | 0.5757 |
|
| 176 |
+
| 0.7736 | 0.6888 | 6300 | 0.5752 |
|
| 177 |
+
| 0.4592 | 0.6942 | 6350 | 0.5752 |
|
| 178 |
+
| 0.2358 | 0.6997 | 6400 | 0.5688 |
|
| 179 |
+
| 0.764 | 0.7051 | 6450 | 0.5659 |
|
| 180 |
+
| 0.6635 | 0.7106 | 6500 | 0.5671 |
|
| 181 |
+
| 0.5054 | 0.7161 | 6550 | 0.5679 |
|
| 182 |
+
| 0.5181 | 0.7215 | 6600 | 0.5697 |
|
| 183 |
+
| 0.5062 | 0.7270 | 6650 | 0.5699 |
|
| 184 |
+
| 0.3872 | 0.7325 | 6700 | 0.5665 |
|
| 185 |
+
| 0.6949 | 0.7379 | 6750 | 0.5649 |
|
| 186 |
+
| 0.8365 | 0.7434 | 6800 | 0.5661 |
|
| 187 |
+
| 0.5633 | 0.7489 | 6850 | 0.5626 |
|
| 188 |
+
| 0.889 | 0.7543 | 6900 | 0.5606 |
|
| 189 |
+
| 0.7509 | 0.7598 | 6950 | 0.5574 |
|
| 190 |
+
| 1.193 | 0.7653 | 7000 | 0.5550 |
|
| 191 |
+
| 0.6633 | 0.7707 | 7050 | 0.5529 |
|
| 192 |
+
| 0.3857 | 0.7762 | 7100 | 0.5591 |
|
| 193 |
+
| 0.3379 | 0.7817 | 7150 | 0.5504 |
|
| 194 |
+
| 0.7843 | 0.7871 | 7200 | 0.5501 |
|
| 195 |
+
| 0.4472 | 0.7926 | 7250 | 0.5520 |
|
| 196 |
+
| 0.3562 | 0.7981 | 7300 | 0.5472 |
|
| 197 |
+
| 0.3685 | 0.8035 | 7350 | 0.5472 |
|
| 198 |
+
| 0.5075 | 0.8090 | 7400 | 0.5477 |
|
| 199 |
+
| 0.5256 | 0.8145 | 7450 | 0.5465 |
|
| 200 |
+
| 0.5499 | 0.8199 | 7500 | 0.5452 |
|
| 201 |
+
| 0.7681 | 0.8254 | 7550 | 0.5462 |
|
| 202 |
+
| 0.7673 | 0.8309 | 7600 | 0.5495 |
|
| 203 |
+
| 0.4798 | 0.8363 | 7650 | 0.5441 |
|
| 204 |
+
| 0.5003 | 0.8418 | 7700 | 0.5445 |
|
| 205 |
+
| 0.5173 | 0.8473 | 7750 | 0.5440 |
|
| 206 |
+
| 0.3333 | 0.8527 | 7800 | 0.5426 |
|
| 207 |
+
| 0.4621 | 0.8582 | 7850 | 0.5382 |
|
| 208 |
+
| 0.4846 | 0.8637 | 7900 | 0.5413 |
|
| 209 |
+
| 0.4184 | 0.8691 | 7950 | 0.5408 |
|
| 210 |
+
| 0.4504 | 0.8746 | 8000 | 0.5386 |
|
| 211 |
+
| 0.5621 | 0.8801 | 8050 | 0.5362 |
|
| 212 |
+
| 0.4928 | 0.8855 | 8100 | 0.5336 |
|
| 213 |
+
| 0.4746 | 0.8910 | 8150 | 0.5311 |
|
| 214 |
+
| 0.4835 | 0.8965 | 8200 | 0.5304 |
|
| 215 |
+
| 0.3912 | 0.9019 | 8250 | 0.5292 |
|
| 216 |
+
| 0.621 | 0.9074 | 8300 | 0.5287 |
|
| 217 |
+
| 0.8945 | 0.9129 | 8350 | 0.5275 |
|
| 218 |
+
| 0.4848 | 0.9183 | 8400 | 0.5277 |
|
| 219 |
+
| 0.8911 | 0.9238 | 8450 | 0.5268 |
|
| 220 |
+
| 0.6915 | 0.9293 | 8500 | 0.5258 |
|
| 221 |
+
| 0.6046 | 0.9347 | 8550 | 0.5256 |
|
| 222 |
+
| 0.5119 | 0.9402 | 8600 | 0.5253 |
|
| 223 |
+
| 0.8352 | 0.9457 | 8650 | 0.5249 |
|
| 224 |
+
| 0.7015 | 0.9511 | 8700 | 0.5263 |
|
| 225 |
+
| 0.4502 | 0.9566 | 8750 | 0.5233 |
|
| 226 |
+
| 0.5712 | 0.9621 | 8800 | 0.5218 |
|
| 227 |
+
| 0.8441 | 0.9675 | 8850 | 0.5193 |
|
| 228 |
+
| 0.6835 | 0.9730 | 8900 | 0.5211 |
|
| 229 |
+
| 0.5472 | 0.9785 | 8950 | 0.5199 |
|
| 230 |
+
| 0.316 | 0.9839 | 9000 | 0.5175 |
|
| 231 |
+
| 0.7185 | 0.9894 | 9050 | 0.5169 |
|
| 232 |
+
| 0.3761 | 0.9949 | 9100 | 0.5178 |
|
| 233 |
+
| 0.5343 | 1.0003 | 9150 | 0.5164 |
|
| 234 |
+
| 0.7962 | 1.0058 | 9200 | 0.5161 |
|
| 235 |
+
| 0.3389 | 1.0113 | 9250 | 0.5138 |
|
| 236 |
+
| 0.4794 | 1.0167 | 9300 | 0.5131 |
|
| 237 |
+
| 0.5351 | 1.0222 | 9350 | 0.5169 |
|
| 238 |
+
| 0.3571 | 1.0277 | 9400 | 0.5178 |
|
| 239 |
+
| 0.3144 | 1.0331 | 9450 | 0.5136 |
|
| 240 |
+
| 0.5541 | 1.0386 | 9500 | 0.5144 |
|
| 241 |
+
| 0.3353 | 1.0441 | 9550 | 0.5119 |
|
| 242 |
+
| 0.4068 | 1.0495 | 9600 | 0.5134 |
|
| 243 |
+
| 0.3882 | 1.0550 | 9650 | 0.5100 |
|
| 244 |
+
| 0.2819 | 1.0605 | 9700 | 0.5082 |
|
| 245 |
+
| 0.3234 | 1.0659 | 9750 | 0.5094 |
|
| 246 |
+
| 0.3772 | 1.0714 | 9800 | 0.5063 |
|
| 247 |
+
| 0.4083 | 1.0769 | 9850 | 0.5090 |
|
| 248 |
+
| 0.4886 | 1.0823 | 9900 | 0.5069 |
|
| 249 |
+
| 0.283 | 1.0878 | 9950 | 0.5082 |
|
| 250 |
+
| 0.7671 | 1.0933 | 10000 | 0.5068 |
|
| 251 |
+
| 0.3055 | 1.0987 | 10050 | 0.5056 |
|
| 252 |
+
| 0.4367 | 1.1042 | 10100 | 0.5071 |
|
| 253 |
+
| 0.5444 | 1.1097 | 10150 | 0.5057 |
|
| 254 |
+
| 0.4949 | 1.1151 | 10200 | 0.5061 |
|
| 255 |
+
| 0.3558 | 1.1206 | 10250 | 0.5086 |
|
| 256 |
+
| 0.4746 | 1.1261 | 10300 | 0.5089 |
|
| 257 |
+
| 0.4472 | 1.1315 | 10350 | 0.5026 |
|
| 258 |
+
| 0.4686 | 1.1370 | 10400 | 0.5024 |
|
| 259 |
+
| 0.4081 | 1.1425 | 10450 | 0.5042 |
|
| 260 |
+
| 0.2828 | 1.1479 | 10500 | 0.5017 |
|
| 261 |
+
| 0.749 | 1.1534 | 10550 | 0.5011 |
|
| 262 |
+
| 0.2499 | 1.1588 | 10600 | 0.5013 |
|
| 263 |
+
| 0.3395 | 1.1643 | 10650 | 0.5021 |
|
| 264 |
+
| 0.3409 | 1.1698 | 10700 | 0.4978 |
|
| 265 |
+
| 0.674 | 1.1752 | 10750 | 0.4987 |
|
| 266 |
+
| 0.5194 | 1.1807 | 10800 | 0.4948 |
|
| 267 |
+
| 0.3518 | 1.1862 | 10850 | 0.4944 |
|
| 268 |
+
| 0.6073 | 1.1916 | 10900 | 0.4919 |
|
| 269 |
+
| 0.3766 | 1.1971 | 10950 | 0.4946 |
|
| 270 |
+
| 0.4954 | 1.2026 | 11000 | 0.4956 |
|
| 271 |
+
| 0.2772 | 1.2080 | 11050 | 0.4988 |
|
| 272 |
+
| 0.4468 | 1.2135 | 11100 | 0.4929 |
|
| 273 |
+
| 0.4541 | 1.2190 | 11150 | 0.4932 |
|
| 274 |
+
| 0.5671 | 1.2244 | 11200 | 0.4947 |
|
| 275 |
+
| 0.4888 | 1.2299 | 11250 | 0.4910 |
|
| 276 |
+
| 0.568 | 1.2354 | 11300 | 0.4907 |
|
| 277 |
+
| 0.3026 | 1.2408 | 11350 | 0.4911 |
|
| 278 |
+
| 0.3755 | 1.2463 | 11400 | 0.4896 |
|
| 279 |
+
| 0.498 | 1.2518 | 11450 | 0.4910 |
|
| 280 |
+
| 0.3694 | 1.2572 | 11500 | 0.4901 |
|
| 281 |
+
| 0.5963 | 1.2627 | 11550 | 0.4890 |
|
| 282 |
+
| 0.4029 | 1.2682 | 11600 | 0.4875 |
|
| 283 |
+
| 0.4503 | 1.2736 | 11650 | 0.4878 |
|
| 284 |
+
| 0.57 | 1.2791 | 11700 | 0.4850 |
|
| 285 |
+
| 0.4235 | 1.2846 | 11750 | 0.4843 |
|
| 286 |
+
| 0.2921 | 1.2900 | 11800 | 0.4840 |
|
| 287 |
+
| 0.7008 | 1.2955 | 11850 | 0.4853 |
|
| 288 |
+
| 0.4751 | 1.3010 | 11900 | 0.4865 |
|
| 289 |
+
| 0.2681 | 1.3064 | 11950 | 0.4854 |
|
| 290 |
+
| 0.342 | 1.3119 | 12000 | 0.4834 |
|
| 291 |
+
| 0.4396 | 1.3174 | 12050 | 0.4841 |
|
| 292 |
+
| 0.4525 | 1.3228 | 12100 | 0.4823 |
|
| 293 |
+
| 0.3439 | 1.3283 | 12150 | 0.4806 |
|
| 294 |
+
| 0.4636 | 1.3338 | 12200 | 0.4816 |
|
| 295 |
+
| 0.5279 | 1.3392 | 12250 | 0.4787 |
|
| 296 |
+
| 0.4047 | 1.3447 | 12300 | 0.4798 |
|
| 297 |
+
| 0.3597 | 1.3502 | 12350 | 0.4786 |
|
| 298 |
+
| 0.5365 | 1.3556 | 12400 | 0.4762 |
|
| 299 |
+
| 0.6849 | 1.3611 | 12450 | 0.4748 |
|
| 300 |
+
| 0.3914 | 1.3666 | 12500 | 0.4725 |
|
| 301 |
+
| 0.5433 | 1.3720 | 12550 | 0.4725 |
|
| 302 |
+
| 0.3853 | 1.3775 | 12600 | 0.4726 |
|
| 303 |
+
| 0.2984 | 1.3830 | 12650 | 0.4732 |
|
| 304 |
+
| 0.3082 | 1.3884 | 12700 | 0.4728 |
|
| 305 |
+
| 0.3704 | 1.3939 | 12750 | 0.4739 |
|
| 306 |
+
| 0.4911 | 1.3994 | 12800 | 0.4739 |
|
| 307 |
+
| 0.3299 | 1.4048 | 12850 | 0.4757 |
|
| 308 |
+
| 0.3212 | 1.4103 | 12900 | 0.4768 |
|
| 309 |
+
| 0.5281 | 1.4158 | 12950 | 0.4762 |
|
| 310 |
+
| 0.3491 | 1.4212 | 13000 | 0.4751 |
|
| 311 |
+
| 0.2243 | 1.4267 | 13050 | 0.4727 |
|
| 312 |
+
| 0.3651 | 1.4322 | 13100 | 0.4707 |
|
| 313 |
+
| 0.2275 | 1.4376 | 13150 | 0.4688 |
|
| 314 |
+
| 0.3817 | 1.4431 | 13200 | 0.4689 |
|
| 315 |
+
| 0.3759 | 1.4486 | 13250 | 0.4679 |
|
| 316 |
+
| 0.4378 | 1.4540 | 13300 | 0.4663 |
|
| 317 |
+
| 0.3523 | 1.4595 | 13350 | 0.4642 |
|
| 318 |
+
| 0.5074 | 1.4650 | 13400 | 0.4641 |
|
| 319 |
+
| 0.426 | 1.4704 | 13450 | 0.4660 |
|
| 320 |
+
| 0.3082 | 1.4759 | 13500 | 0.4618 |
|
| 321 |
+
| 0.2244 | 1.4814 | 13550 | 0.4662 |
|
| 322 |
+
| 0.5025 | 1.4868 | 13600 | 0.4646 |
|
| 323 |
+
| 0.3179 | 1.4923 | 13650 | 0.4641 |
|
| 324 |
+
| 0.275 | 1.4978 | 13700 | 0.4626 |
|
| 325 |
+
| 0.5281 | 1.5032 | 13750 | 0.4599 |
|
| 326 |
+
| 0.3667 | 1.5087 | 13800 | 0.4592 |
|
| 327 |
+
| 0.4539 | 1.5142 | 13850 | 0.4591 |
|
| 328 |
+
| 0.4156 | 1.5196 | 13900 | 0.4610 |
|
| 329 |
+
| 0.1621 | 1.5251 | 13950 | 0.4585 |
|
| 330 |
+
| 0.4954 | 1.5306 | 14000 | 0.4591 |
|
| 331 |
+
| 0.4589 | 1.5360 | 14050 | 0.4607 |
|
| 332 |
+
| 0.41 | 1.5415 | 14100 | 0.4583 |
|
| 333 |
+
| 0.4453 | 1.5470 | 14150 | 0.4545 |
|
| 334 |
+
| 0.244 | 1.5524 | 14200 | 0.4546 |
|
| 335 |
+
| 0.5205 | 1.5579 | 14250 | 0.4565 |
|
| 336 |
+
| 0.2065 | 1.5634 | 14300 | 0.4556 |
|
| 337 |
+
| 0.4503 | 1.5688 | 14350 | 0.4553 |
|
| 338 |
+
| 0.482 | 1.5743 | 14400 | 0.4524 |
|
| 339 |
+
| 0.2292 | 1.5798 | 14450 | 0.4525 |
|
| 340 |
+
| 0.4871 | 1.5852 | 14500 | 0.4517 |
|
| 341 |
+
| 0.4763 | 1.5907 | 14550 | 0.4539 |
|
| 342 |
+
| 0.2866 | 1.5962 | 14600 | 0.4552 |
|
| 343 |
+
| 0.4019 | 1.6016 | 14650 | 0.4557 |
|
| 344 |
+
| 0.5441 | 1.6071 | 14700 | 0.4551 |
|
| 345 |
+
| 0.4762 | 1.6126 | 14750 | 0.4533 |
|
| 346 |
+
| 0.3066 | 1.6180 | 14800 | 0.4526 |
|
| 347 |
+
| 0.4991 | 1.6235 | 14850 | 0.4526 |
|
| 348 |
+
| 0.311 | 1.6289 | 14900 | 0.4505 |
|
| 349 |
+
| 0.2365 | 1.6344 | 14950 | 0.4506 |
|
| 350 |
+
| 0.3477 | 1.6399 | 15000 | 0.4514 |
|
| 351 |
+
| 0.5098 | 1.6453 | 15050 | 0.4518 |
|
| 352 |
+
| 0.2939 | 1.6508 | 15100 | 0.4508 |
|
| 353 |
+
| 0.1844 | 1.6563 | 15150 | 0.4499 |
|
| 354 |
+
| 0.4786 | 1.6617 | 15200 | 0.4492 |
|
| 355 |
+
| 0.4923 | 1.6672 | 15250 | 0.4468 |
|
| 356 |
+
| 0.3181 | 1.6727 | 15300 | 0.4489 |
|
| 357 |
+
| 0.5213 | 1.6781 | 15350 | 0.4454 |
|
| 358 |
+
| 0.3283 | 1.6836 | 15400 | 0.4445 |
|
| 359 |
+
| 0.2816 | 1.6891 | 15450 | 0.4455 |
|
| 360 |
+
| 0.3369 | 1.6945 | 15500 | 0.4443 |
|
| 361 |
+
| 0.3503 | 1.7000 | 15550 | 0.4429 |
|
| 362 |
+
| 0.359 | 1.7055 | 15600 | 0.4439 |
|
| 363 |
+
| 0.3685 | 1.7109 | 15650 | 0.4426 |
|
| 364 |
+
| 0.2218 | 1.7164 | 15700 | 0.4440 |
|
| 365 |
+
| 0.3213 | 1.7219 | 15750 | 0.4417 |
|
| 366 |
+
| 0.5844 | 1.7273 | 15800 | 0.4404 |
|
| 367 |
+
| 0.461 | 1.7328 | 15850 | 0.4432 |
|
| 368 |
+
| 0.4323 | 1.7383 | 15900 | 0.4414 |
|
| 369 |
+
| 0.3304 | 1.7437 | 15950 | 0.4409 |
|
| 370 |
+
| 0.2571 | 1.7492 | 16000 | 0.4392 |
|
| 371 |
+
| 0.3406 | 1.7547 | 16050 | 0.4371 |
|
| 372 |
+
| 0.7021 | 1.7601 | 16100 | 0.4365 |
|
| 373 |
+
| 0.2579 | 1.7656 | 16150 | 0.4350 |
|
| 374 |
+
| 0.3533 | 1.7711 | 16200 | 0.4336 |
|
| 375 |
+
| 0.5392 | 1.7765 | 16250 | 0.4312 |
|
| 376 |
+
| 0.4225 | 1.7820 | 16300 | 0.4321 |
|
| 377 |
+
| 0.5097 | 1.7875 | 16350 | 0.4322 |
|
| 378 |
+
| 0.2512 | 1.7929 | 16400 | 0.4305 |
|
| 379 |
+
| 0.2924 | 1.7984 | 16450 | 0.4317 |
|
| 380 |
+
| 0.5928 | 1.8039 | 16500 | 0.4312 |
|
| 381 |
+
| 0.4437 | 1.8093 | 16550 | 0.4299 |
|
| 382 |
+
| 0.3437 | 1.8148 | 16600 | 0.4307 |
|
| 383 |
+
| 0.3557 | 1.8203 | 16650 | 0.4311 |
|
| 384 |
+
| 0.276 | 1.8257 | 16700 | 0.4294 |
|
| 385 |
+
| 0.3173 | 1.8312 | 16750 | 0.4294 |
|
| 386 |
+
| 0.2305 | 1.8367 | 16800 | 0.4309 |
|
| 387 |
+
| 0.372 | 1.8421 | 16850 | 0.4265 |
|
| 388 |
+
| 0.6609 | 1.8476 | 16900 | 0.4274 |
|
| 389 |
+
| 0.4588 | 1.8531 | 16950 | 0.4247 |
|
| 390 |
+
| 0.3001 | 1.8585 | 17000 | 0.4229 |
|
| 391 |
+
| 0.3603 | 1.8640 | 17050 | 0.4228 |
|
| 392 |
+
| 0.4153 | 1.8695 | 17100 | 0.4214 |
|
| 393 |
+
| 0.4851 | 1.8749 | 17150 | 0.4230 |
|
| 394 |
+
| 0.3846 | 1.8804 | 17200 | 0.4240 |
|
| 395 |
+
| 0.2041 | 1.8859 | 17250 | 0.4234 |
|
| 396 |
+
| 0.5593 | 1.8913 | 17300 | 0.4239 |
|
| 397 |
+
| 0.4937 | 1.8968 | 17350 | 0.4228 |
|
| 398 |
+
| 0.5448 | 1.9023 | 17400 | 0.4224 |
|
| 399 |
+
| 0.2487 | 1.9077 | 17450 | 0.4208 |
|
| 400 |
+
| 0.3078 | 1.9132 | 17500 | 0.4202 |
|
| 401 |
+
| 0.2279 | 1.9187 | 17550 | 0.4196 |
|
| 402 |
+
| 0.5487 | 1.9241 | 17600 | 0.4198 |
|
| 403 |
+
| 0.4874 | 1.9296 | 17650 | 0.4175 |
|
| 404 |
+
| 0.3608 | 1.9351 | 17700 | 0.4165 |
|
| 405 |
+
| 0.2441 | 1.9405 | 17750 | 0.4166 |
|
| 406 |
+
| 0.2644 | 1.9460 | 17800 | 0.4134 |
|
| 407 |
+
| 0.3575 | 1.9515 | 17850 | 0.4115 |
|
| 408 |
+
| 0.721 | 1.9569 | 17900 | 0.4133 |
|
| 409 |
+
| 0.4024 | 1.9624 | 17950 | 0.4130 |
|
| 410 |
+
| 0.4279 | 1.9679 | 18000 | 0.4140 |
|
| 411 |
+
| 0.7236 | 1.9733 | 18050 | 0.4117 |
|
| 412 |
+
| 0.3854 | 1.9788 | 18100 | 0.4117 |
|
| 413 |
+
| 0.3183 | 1.9843 | 18150 | 0.4098 |
|
| 414 |
+
| 0.3771 | 1.9897 | 18200 | 0.4112 |
|
| 415 |
+
| 0.2921 | 1.9952 | 18250 | 0.4112 |
|
| 416 |
+
| 0.2658 | 2.0007 | 18300 | 0.4126 |
|
| 417 |
+
| 0.1989 | 2.0061 | 18350 | 0.4202 |
|
| 418 |
+
| 0.262 | 2.0116 | 18400 | 0.4232 |
|
| 419 |
+
| 0.2986 | 2.0171 | 18450 | 0.4209 |
|
| 420 |
+
| 0.2186 | 2.0225 | 18500 | 0.4226 |
|
| 421 |
+
| 0.3781 | 2.0280 | 18550 | 0.4204 |
|
| 422 |
+
| 0.4399 | 2.0335 | 18600 | 0.4186 |
|
| 423 |
+
| 0.2152 | 2.0389 | 18650 | 0.4219 |
|
| 424 |
+
| 0.2351 | 2.0444 | 18700 | 0.4242 |
|
| 425 |
+
| 0.2159 | 2.0499 | 18750 | 0.4195 |
|
| 426 |
+
| 0.3344 | 2.0553 | 18800 | 0.4177 |
|
| 427 |
+
| 0.3056 | 2.0608 | 18850 | 0.4182 |
|
| 428 |
+
| 0.1924 | 2.0663 | 18900 | 0.4204 |
|
| 429 |
+
| 0.315 | 2.0717 | 18950 | 0.4197 |
|
| 430 |
+
| 0.2728 | 2.0772 | 19000 | 0.4210 |
|
| 431 |
+
| 0.3754 | 2.0827 | 19050 | 0.4218 |
|
| 432 |
+
| 0.1673 | 2.0881 | 19100 | 0.4213 |
|
| 433 |
+
| 0.1615 | 2.0936 | 19150 | 0.4209 |
|
| 434 |
+
| 0.2859 | 2.0990 | 19200 | 0.4185 |
|
| 435 |
+
| 0.2025 | 2.1045 | 19250 | 0.4197 |
|
| 436 |
+
| 0.4237 | 2.1100 | 19300 | 0.4216 |
|
| 437 |
+
| 0.2878 | 2.1154 | 19350 | 0.4213 |
|
| 438 |
+
| 0.2416 | 2.1209 | 19400 | 0.4203 |
|
| 439 |
+
| 0.3055 | 2.1264 | 19450 | 0.4182 |
|
| 440 |
+
| 0.2704 | 2.1318 | 19500 | 0.4191 |
|
| 441 |
+
| 0.1831 | 2.1373 | 19550 | 0.4215 |
|
| 442 |
+
| 0.178 | 2.1428 | 19600 | 0.4202 |
|
| 443 |
+
| 0.2575 | 2.1482 | 19650 | 0.4139 |
|
| 444 |
+
| 0.1799 | 2.1537 | 19700 | 0.4171 |
|
| 445 |
+
| 0.3215 | 2.1592 | 19750 | 0.4153 |
|
| 446 |
+
| 0.2772 | 2.1646 | 19800 | 0.4154 |
|
| 447 |
+
| 0.2041 | 2.1701 | 19850 | 0.4142 |
|
| 448 |
+
| 0.2015 | 2.1756 | 19900 | 0.4148 |
|
| 449 |
+
| 0.2451 | 2.1810 | 19950 | 0.4198 |
|
| 450 |
+
| 0.1856 | 2.1865 | 20000 | 0.4192 |
|
| 451 |
+
| 0.2024 | 2.1920 | 20050 | 0.4145 |
|
| 452 |
+
| 0.2167 | 2.1974 | 20100 | 0.4138 |
|
| 453 |
+
| 0.2629 | 2.2029 | 20150 | 0.4120 |
|
| 454 |
+
| 0.1391 | 2.2084 | 20200 | 0.4168 |
|
| 455 |
+
| 0.2906 | 2.2138 | 20250 | 0.4154 |
|
| 456 |
+
| 0.3033 | 2.2193 | 20300 | 0.4154 |
|
| 457 |
+
| 0.3119 | 2.2248 | 20350 | 0.4149 |
|
| 458 |
+
| 0.2636 | 2.2302 | 20400 | 0.4179 |
|
| 459 |
+
| 0.1601 | 2.2357 | 20450 | 0.4148 |
|
| 460 |
+
| 0.1798 | 2.2412 | 20500 | 0.4145 |
|
| 461 |
+
| 0.2127 | 2.2466 | 20550 | 0.4147 |
|
| 462 |
+
| 0.3626 | 2.2521 | 20600 | 0.4174 |
|
| 463 |
+
| 0.3045 | 2.2576 | 20650 | 0.4130 |
|
| 464 |
+
|
| 465 |
+
|
| 466 |
+
### Framework versions
|
| 467 |
+
|
| 468 |
+
- PEFT 0.12.0
|
| 469 |
+
- Transformers 4.47.0
|
| 470 |
+
- Pytorch 2.5.1+cu124
|
| 471 |
+
- Datasets 3.0.0
|
| 472 |
+
- Tokenizers 0.21.0
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4873875808
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dcd87b5a14394e4615756bf166e2223158f72cbe941e98789b12785bf8f4a712
|
| 3 |
size 4873875808
|