80 lines
2.3 KiB
Markdown
80 lines
2.3 KiB
Markdown
---
|
|
license: apache-2.0
|
|
base_model: EleutherAI/pythia-410m
|
|
tags:
|
|
- generated_from_trainer
|
|
model-index:
|
|
- name: pythia410m-XYZCompany-1000-steps
|
|
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. -->
|
|
|
|
# pythia410m-XYZCompany-1000-steps
|
|
|
|
This model is a fine-tuned version of [EleutherAI/pythia-410m](https://huggingface.co/EleutherAI/pythia-410m) on an unknown dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 0.2944
|
|
|
|
## 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: 4
|
|
- eval_batch_size: 4
|
|
- seed: 42
|
|
- gradient_accumulation_steps: 2
|
|
- total_train_batch_size: 8
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
- lr_scheduler_type: linear
|
|
- lr_scheduler_warmup_steps: 1
|
|
- training_steps: 1000
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss |
|
|
|:-------------:|:-----:|:----:|:---------------:|
|
|
| 0.2939 | 0.32 | 50 | 0.2774 |
|
|
| 0.2993 | 0.63 | 100 | 0.2531 |
|
|
| 0.2538 | 0.95 | 150 | 0.2429 |
|
|
| 0.1829 | 1.27 | 200 | 0.2393 |
|
|
| 0.187 | 1.59 | 250 | 0.2326 |
|
|
| 0.1737 | 1.9 | 300 | 0.2308 |
|
|
| 0.1195 | 2.22 | 350 | 0.2405 |
|
|
| 0.1263 | 2.54 | 400 | 0.2392 |
|
|
| 0.1248 | 2.86 | 450 | 0.2374 |
|
|
| 0.069 | 3.17 | 500 | 0.2545 |
|
|
| 0.08 | 3.49 | 550 | 0.2530 |
|
|
| 0.0763 | 3.81 | 600 | 0.2553 |
|
|
| 0.0532 | 4.13 | 650 | 0.2690 |
|
|
| 0.0465 | 4.44 | 700 | 0.2727 |
|
|
| 0.0538 | 4.76 | 750 | 0.2734 |
|
|
| 0.037 | 5.08 | 800 | 0.2834 |
|
|
| 0.0334 | 5.4 | 850 | 0.2859 |
|
|
| 0.0299 | 5.71 | 900 | 0.2872 |
|
|
| 0.0318 | 6.03 | 950 | 0.2906 |
|
|
| 0.0256 | 6.35 | 1000 | 0.2944 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.32.1
|
|
- Pytorch 2.1.2
|
|
- Datasets 2.17.1
|
|
- Tokenizers 0.13.2
|