metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- generated_from_trainer
model-index:
- name: Mistral_Sparse_refined_web_70p_2024-03-12
results: []
Mistral_Sparse_refined_web_70p_2024-03-12
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.1418
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 0
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 2100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.7221 | 0.0 | 25 | 2.8218 |
| 2.4266 | 0.01 | 50 | 2.6972 |
| 2.4153 | 0.01 | 75 | 2.6181 |
| 2.3588 | 0.02 | 100 | 2.5695 |
| 2.3274 | 0.02 | 125 | 2.5427 |
| 2.4054 | 0.02 | 150 | 2.5244 |
| 2.3274 | 0.03 | 175 | 2.5144 |
| 2.3042 | 0.03 | 200 | 2.4995 |
| 2.3296 | 0.04 | 225 | 2.4898 |
| 2.3621 | 0.04 | 250 | 2.4844 |
| 2.2825 | 0.04 | 275 | 2.4756 |
| 2.2932 | 0.05 | 300 | 2.4704 |
| 2.3015 | 0.05 | 325 | 2.4693 |
| 2.139 | 0.06 | 350 | 2.4612 |
| 2.2953 | 0.06 | 375 | 2.4553 |
| 2.3358 | 0.06 | 400 | 2.4546 |
| 2.3302 | 0.07 | 425 | 2.4506 |
| 2.2814 | 0.07 | 450 | 2.4506 |
| 2.2014 | 0.08 | 475 | 2.4455 |
| 2.266 | 0.08 | 500 | 2.4434 |
| 2.3309 | 0.08 | 525 | 2.4430 |
| 2.2278 | 0.09 | 550 | 2.4417 |
| 2.3621 | 0.09 | 575 | 2.4384 |
| 2.1614 | 0.1 | 600 | 2.4385 |
| 2.2504 | 0.1 | 625 | 2.4370 |
| 2.3301 | 0.1 | 650 | 2.4350 |
| 2.3177 | 0.11 | 675 | 2.4331 |
| 2.2784 | 0.11 | 700 | 2.4307 |
| 2.2681 | 0.12 | 725 | 2.4305 |
| 2.1777 | 0.12 | 750 | 2.4314 |
| 2.2164 | 0.12 | 775 | 2.4321 |
| 2.3068 | 0.13 | 800 | 2.4292 |
| 2.3131 | 0.13 | 825 | 2.4267 |
| 2.2971 | 0.14 | 850 | 2.4256 |
| 2.1623 | 0.14 | 875 | 2.4231 |
| 2.2308 | 0.14 | 900 | 2.4246 |
| 2.1772 | 0.15 | 925 | 2.4259 |
| 2.3114 | 0.15 | 950 | 2.4226 |
| 2.2434 | 0.16 | 975 | 2.4268 |
| 2.2852 | 0.16 | 1000 | 2.4259 |
| 2.2924 | 0.16 | 1025 | 2.4262 |
| 2.3095 | 0.17 | 1050 | 2.4231 |
| 2.3378 | 0.17 | 1075 | 2.4225 |
| 2.265 | 0.18 | 1100 | 2.4181 |
| 2.2893 | 0.18 | 1125 | 2.4237 |
| 2.2577 | 0.18 | 1150 | 2.4176 |
| 2.3088 | 0.19 | 1175 | 2.4166 |
| 2.1623 | 0.19 | 1200 | 2.4139 |
| 2.2576 | 0.2 | 1225 | 2.4177 |
| 2.2411 | 0.2 | 1250 | 2.4160 |
| 2.28 | 0.2 | 1275 | 2.4171 |
| 2.3077 | 0.21 | 1300 | 2.4176 |
| 2.2814 | 0.21 | 1325 | 2.4186 |
| 2.1772 | 0.22 | 1350 | 2.4199 |
| 2.2554 | 0.22 | 1375 | 2.4190 |
| 2.2665 | 0.22 | 1400 | 2.4182 |
| 2.2058 | 0.23 | 1425 | 2.4171 |
| 2.1881 | 0.23 | 1450 | 2.4209 |
| 2.1567 | 0.24 | 1475 | 2.4186 |
| 2.2146 | 0.24 | 1500 | 2.4210 |
| 2.1493 | 0.24 | 1525 | 2.4207 |
| 2.2145 | 0.25 | 1550 | 2.4167 |
| 2.3312 | 0.25 | 1575 | 2.4187 |
| 2.2897 | 0.26 | 1600 | 2.4193 |
| 2.2592 | 0.26 | 1625 | 2.4170 |
| 2.3402 | 0.26 | 1650 | 2.4137 |
| 2.2354 | 0.27 | 1675 | 2.4165 |
| 2.2839 | 0.27 | 1700 | 2.4173 |
| 2.2681 | 0.28 | 1725 | 2.4177 |
| 2.2501 | 0.28 | 1750 | 2.4154 |
| 2.232 | 0.28 | 1775 | 2.4138 |
| 2.1882 | 0.29 | 1800 | 2.4142 |
| 2.2668 | 0.29 | 1825 | 2.4136 |
| 2.2641 | 0.3 | 1850 | 2.4110 |
| 2.2536 | 0.3 | 1875 | 2.4148 |
| 2.2732 | 0.3 | 1900 | 2.4159 |
| 2.3244 | 0.31 | 1925 | 2.4129 |
| 2.2639 | 0.31 | 1950 | 2.4135 |
| 2.2876 | 0.32 | 1975 | 2.4149 |
| 2.2108 | 0.32 | 2000 | 2.4116 |
| 2.233 | 0.32 | 2025 | 2.4163 |
| 2.2177 | 0.33 | 2050 | 2.4141 |
| 2.2132 | 0.33 | 2075 | 2.4143 |
| 2.3103 | 0.34 | 2100 | 2.4161 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0