|
--- |
|
license: apache-2.0 |
|
base_model: EleutherAI/pythia-410m-deduped-v0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: eleuter-foodie-test-2 |
|
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. --> |
|
|
|
# eleuter-foodie-test-2 |
|
|
|
This model is a fine-tuned version of [EleutherAI/pythia-410m-deduped-v0](https://huggingface.co/EleutherAI/pythia-410m-deduped-v0) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.3148 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant |
|
- lr_scheduler_warmup_ratio: 0.03 |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.3434 | 0.06 | 200 | 1.4594 | |
|
| 1.2535 | 0.11 | 400 | 1.4383 | |
|
| 1.2794 | 0.17 | 600 | 1.4265 | |
|
| 1.2913 | 0.22 | 800 | 1.4185 | |
|
| 1.2776 | 0.28 | 1000 | 1.4054 | |
|
| 1.2929 | 0.34 | 1200 | 1.3950 | |
|
| 1.2357 | 0.39 | 1400 | 1.3975 | |
|
| 1.2235 | 0.45 | 1600 | 1.3886 | |
|
| 1.2609 | 0.5 | 1800 | 1.3854 | |
|
| 1.2002 | 0.56 | 2000 | 1.3774 | |
|
| 1.2729 | 0.61 | 2200 | 1.3745 | |
|
| 1.2143 | 0.67 | 2400 | 1.3680 | |
|
| 1.2011 | 0.73 | 2600 | 1.3670 | |
|
| 1.2697 | 0.78 | 2800 | 1.3625 | |
|
| 1.2499 | 0.84 | 3000 | 1.3593 | |
|
| 1.2409 | 0.89 | 3200 | 1.3536 | |
|
| 1.2393 | 0.95 | 3400 | 1.3497 | |
|
| 1.3622 | 1.01 | 3600 | 1.3411 | |
|
| 1.2965 | 1.06 | 3800 | 1.3408 | |
|
| 1.3515 | 1.12 | 4000 | 1.3366 | |
|
| 1.3451 | 1.17 | 4200 | 1.3359 | |
|
| 1.3427 | 1.23 | 4400 | 1.3343 | |
|
| 1.3735 | 1.28 | 4600 | 1.3344 | |
|
| 1.348 | 1.34 | 4800 | 1.3322 | |
|
| 1.3536 | 1.4 | 5000 | 1.3315 | |
|
| 1.284 | 1.45 | 5200 | 1.3281 | |
|
| 1.2912 | 1.51 | 5400 | 1.3272 | |
|
| 1.3119 | 1.56 | 5600 | 1.3261 | |
|
| 1.3422 | 1.62 | 5800 | 1.3221 | |
|
| 1.3139 | 1.68 | 6000 | 1.3201 | |
|
| 1.3222 | 1.73 | 6200 | 1.3181 | |
|
| 1.3038 | 1.79 | 6400 | 1.3181 | |
|
| 1.296 | 1.84 | 6600 | 1.3169 | |
|
| 1.3562 | 1.9 | 6800 | 1.3166 | |
|
| 1.2887 | 1.95 | 7000 | 1.3148 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
