|
--- |
|
license: gemma |
|
base_model: google/gemma-2-2b |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: collapse_gemma-2-2b_hs2_iter1_sftsd1 |
|
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. --> |
|
|
|
# collapse_gemma-2-2b_hs2_iter1_sftsd1 |
|
|
|
This model is a fine-tuned version of [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0645 |
|
- Num Input Tokens Seen: 5709936 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 16 |
|
- seed: 1 |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant_with_warmup |
|
- lr_scheduler_warmup_ratio: 0.05 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen | |
|
|:-------------:|:------:|:----:|:---------------:|:-----------------:| |
|
| No log | 0 | 0 | 1.3956 | 0 | |
|
| 1.2754 | 0.0511 | 5 | 1.2634 | 285512 | |
|
| 1.2153 | 0.1021 | 10 | 1.1738 | 578296 | |
|
| 1.1556 | 0.1532 | 15 | 1.1356 | 873440 | |
|
| 1.1445 | 0.2042 | 20 | 1.1093 | 1168560 | |
|
| 1.0672 | 0.2553 | 25 | 1.0991 | 1463952 | |
|
| 1.1502 | 0.3063 | 30 | 1.0940 | 1754024 | |
|
| 1.0342 | 0.3574 | 35 | 1.0895 | 2046160 | |
|
| 1.0635 | 0.4084 | 40 | 1.0863 | 2341224 | |
|
| 1.1419 | 0.4595 | 45 | 1.0834 | 2635056 | |
|
| 1.0155 | 0.5105 | 50 | 1.0805 | 2927424 | |
|
| 1.0927 | 0.5616 | 55 | 1.0777 | 3221968 | |
|
| 1.1001 | 0.6126 | 60 | 1.0756 | 3519568 | |
|
| 1.0711 | 0.6637 | 65 | 1.0734 | 3816688 | |
|
| 1.0622 | 0.7147 | 70 | 1.0717 | 4117768 | |
|
| 1.0785 | 0.7658 | 75 | 1.0702 | 4418488 | |
|
| 1.154 | 0.8168 | 80 | 1.0691 | 4709408 | |
|
| 1.1034 | 0.8679 | 85 | 1.0678 | 5000912 | |
|
| 1.0458 | 0.9190 | 90 | 1.0663 | 5295112 | |
|
| 1.0685 | 0.9700 | 95 | 1.0651 | 5591032 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
