|
--- |
|
license: cc-by-nc-4.0 |
|
base_model: AIDC-ai-business/Marcoroni-7B |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: results |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# results |
|
|
|
This model is a fine-tuned version of [AIDC-ai-business/Marcoroni-7B](https://huggingface.co/AIDC-ai-business/Marcoroni-7B) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.7324 |
|
|
|
## 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: 8e-06 |
|
- train_batch_size: 48 |
|
- eval_batch_size: 6 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 96 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.6335 | 0.02 | 4 | 2.8691 | |
|
| 1.5666 | 0.03 | 8 | 2.8173 | |
|
| 1.4985 | 0.05 | 12 | 2.8003 | |
|
| 1.4244 | 0.06 | 16 | 2.7800 | |
|
| 1.4245 | 0.08 | 20 | 2.7674 | |
|
| 1.3865 | 0.09 | 24 | 2.7675 | |
|
| 1.3887 | 0.11 | 28 | 2.7687 | |
|
| 1.3794 | 0.12 | 32 | 2.7641 | |
|
| 1.3581 | 0.14 | 36 | 2.7628 | |
|
| 1.3712 | 0.15 | 40 | 2.7578 | |
|
| 1.328 | 0.17 | 44 | 2.7535 | |
|
| 1.3937 | 0.19 | 48 | 2.7494 | |
|
| 1.3843 | 0.2 | 52 | 2.7387 | |
|
| 1.2925 | 0.22 | 56 | 2.7368 | |
|
| 1.3135 | 0.23 | 60 | 2.7375 | |
|
| 1.3633 | 0.25 | 64 | 2.7335 | |
|
| 1.326 | 0.26 | 68 | 2.7365 | |
|
| 1.3392 | 0.28 | 72 | 2.7361 | |
|
| 1.2583 | 0.29 | 76 | 2.7316 | |
|
| 1.2652 | 0.31 | 80 | 2.7353 | |
|
| 1.2756 | 0.32 | 84 | 2.7394 | |
|
| 1.2966 | 0.34 | 88 | 2.7400 | |
|
| 1.359 | 0.36 | 92 | 2.7348 | |
|
| 1.3704 | 0.37 | 96 | 2.7342 | |
|
| 1.3389 | 0.39 | 100 | 2.7330 | |
|
| 1.3471 | 0.4 | 104 | 2.7336 | |
|
| 1.3288 | 0.42 | 108 | 2.7380 | |
|
| 1.2856 | 0.43 | 112 | 2.7382 | |
|
| 1.3277 | 0.45 | 116 | 2.7380 | |
|
| 1.2779 | 0.46 | 120 | 2.7414 | |
|
| 1.2967 | 0.48 | 124 | 2.7403 | |
|
| 1.2586 | 0.5 | 128 | 2.7433 | |
|
| 1.2652 | 0.51 | 132 | 2.7407 | |
|
| 1.3011 | 0.53 | 136 | 2.7399 | |
|
| 1.3377 | 0.54 | 140 | 2.7415 | |
|
| 1.295 | 0.56 | 144 | 2.7384 | |
|
| 1.3342 | 0.57 | 148 | 2.7344 | |
|
| 1.3309 | 0.59 | 152 | 2.7409 | |
|
| 1.3463 | 0.6 | 156 | 2.7394 | |
|
| 1.3104 | 0.62 | 160 | 2.7353 | |
|
| 1.2692 | 0.63 | 164 | 2.7380 | |
|
| 1.364 | 0.65 | 168 | 2.7386 | |
|
| 1.2888 | 0.67 | 172 | 2.7370 | |
|
| 1.3238 | 0.68 | 176 | 2.7380 | |
|
| 1.2687 | 0.7 | 180 | 2.7371 | |
|
| 1.2405 | 0.71 | 184 | 2.7396 | |
|
| 1.3065 | 0.73 | 188 | 2.7388 | |
|
| 1.2774 | 0.74 | 192 | 2.7424 | |
|
| 1.3195 | 0.76 | 196 | 2.7382 | |
|
| 1.2521 | 0.77 | 200 | 2.7413 | |
|
| 1.2922 | 0.79 | 204 | 2.7393 | |
|
| 1.3293 | 0.8 | 208 | 2.7394 | |
|
| 1.3062 | 0.82 | 212 | 2.7362 | |
|
| 1.2978 | 0.84 | 216 | 2.7394 | |
|
| 1.3054 | 0.85 | 220 | 2.7359 | |
|
| 1.3377 | 0.87 | 224 | 2.7383 | |
|
| 1.3088 | 0.88 | 228 | 2.7363 | |
|
| 1.296 | 0.9 | 232 | 2.7347 | |
|
| 1.3099 | 0.91 | 236 | 2.7394 | |
|
| 1.3008 | 0.93 | 240 | 2.7358 | |
|
| 1.2943 | 0.94 | 244 | 2.7417 | |
|
| 1.3035 | 0.96 | 248 | 2.7398 | |
|
| 1.3877 | 0.97 | 252 | 2.7390 | |
|
| 1.3324 | 0.99 | 256 | 2.7324 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.0.dev0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.6.dev0 |
|
- Tokenizers 0.14.0 |
|
|
