metadata
license: apache-2.0
base_model: EleutherAI/pythia-410m
tags:
- generated_from_trainer
model-index:
- name: instruction_finetuned_1200_steps
results: []
instruction_finetuned_1200_steps
This model is a fine-tuned version of EleutherAI/pythia-410m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1967
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- training_steps: 1200
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4451 | 0.05 | 120 | 1.2970 |
| 1.2442 | 0.11 | 240 | 1.2837 |
| 1.2821 | 0.16 | 360 | 1.2557 |
| 1.2628 | 0.21 | 480 | 1.2451 |
| 1.2579 | 0.27 | 600 | 1.2359 |
| 1.3943 | 0.32 | 720 | 1.2239 |
| 1.11 | 0.37 | 840 | 1.2141 |
| 1.2382 | 0.43 | 960 | 1.2079 |
| 1.54 | 0.48 | 1080 | 1.1994 |
| 1.0787 | 0.53 | 1200 | 1.1967 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1