|
|
--- |
|
|
library_name: transformers |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: cllm-1.0.0 |
|
|
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. --> |
|
|
|
|
|
# cllm-1.0.0 |
|
|
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 2.7403 |
|
|
|
|
|
## 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: 1 |
|
|
- seed: 42 |
|
|
- distributed_type: multi-GPU |
|
|
- num_devices: 8 |
|
|
- gradient_accumulation_steps: 2 |
|
|
- total_train_batch_size: 64 |
|
|
- total_eval_batch_size: 8 |
|
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 50 |
|
|
- num_epochs: 1 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:------:|:-----:|:---------------:| |
|
|
| No log | 0.0044 | 2000 | 3.8105 | |
|
|
| 4.2179 | 0.0089 | 4000 | 3.4461 | |
|
|
| 4.2179 | 0.0133 | 6000 | 3.2612 | |
|
|
| 3.2341 | 0.0178 | 8000 | 3.1610 | |
|
|
| 3.2341 | 0.0222 | 10000 | 3.0834 | |
|
|
| 3.0422 | 0.0267 | 12000 | 3.0260 | |
|
|
| 3.0422 | 0.0311 | 14000 | 2.9872 | |
|
|
| 2.9347 | 0.0356 | 16000 | 2.9444 | |
|
|
| 2.9347 | 0.0400 | 18000 | 2.9090 | |
|
|
| 2.874 | 0.0445 | 20000 | 2.8854 | |
|
|
| 2.874 | 0.0489 | 22000 | 2.8585 | |
|
|
| 2.8204 | 0.0534 | 24000 | 2.8405 | |
|
|
| 2.8204 | 0.0578 | 26000 | 2.8245 | |
|
|
| 2.7825 | 0.0622 | 28000 | 2.8106 | |
|
|
| 2.7825 | 0.0667 | 30000 | 2.7993 | |
|
|
| 2.7555 | 0.0711 | 32000 | 2.7867 | |
|
|
| 2.7555 | 0.0756 | 34000 | 2.7738 | |
|
|
| 2.7285 | 0.0800 | 36000 | 2.7700 | |
|
|
| 2.7285 | 0.0845 | 38000 | 2.7597 | |
|
|
| 2.7179 | 0.0889 | 40000 | 2.7591 | |
|
|
| 2.7179 | 0.0934 | 42000 | 2.7488 | |
|
|
| 2.7119 | 0.0978 | 44000 | 2.7512 | |
|
|
| 2.7119 | 0.1023 | 46000 | 2.7487 | |
|
|
| 2.7043 | 0.1067 | 48000 | 2.7436 | |
|
|
| 2.7043 | 0.1111 | 50000 | 2.7422 | |
|
|
| 2.7013 | 0.1156 | 52000 | 2.7435 | |
|
|
| 2.7013 | 0.1200 | 54000 | 2.7388 | |
|
|
| 2.7029 | 0.1245 | 56000 | 2.7380 | |
|
|
| 2.7029 | 0.1289 | 58000 | 2.7403 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.49.0 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Datasets 3.3.2 |
|
|
- Tokenizers 0.21.1 |
|
|
|
