metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.2
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Summary4500_M2_1000steps_1e8rate_SFT
results: []
Summary4500_M2_1000steps_1e8rate_SFT
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.1332
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-08
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1335 | 0.0112 | 50 | 2.1446 |
| 2.1332 | 0.0224 | 100 | 2.1433 |
| 2.1306 | 0.0336 | 150 | 2.1414 |
| 2.1283 | 0.0448 | 200 | 2.1388 |
| 2.1267 | 0.0559 | 250 | 2.1362 |
| 2.1252 | 0.0671 | 300 | 2.1353 |
| 2.1247 | 0.0783 | 350 | 2.1345 |
| 2.1237 | 0.0895 | 400 | 2.1356 |
| 2.124 | 0.1007 | 450 | 2.1344 |
| 2.1238 | 0.1119 | 500 | 2.1344 |
| 2.1236 | 0.1231 | 550 | 2.1340 |
| 2.1235 | 0.1343 | 600 | 2.1341 |
| 2.1232 | 0.1454 | 650 | 2.1354 |
| 2.1231 | 0.1566 | 700 | 2.1337 |
| 2.1227 | 0.1678 | 750 | 2.1332 |
| 2.1225 | 0.1790 | 800 | 2.1332 |
| 2.1225 | 0.1902 | 850 | 2.1332 |
| 2.1225 | 0.2014 | 900 | 2.1332 |
| 2.1225 | 0.2126 | 950 | 2.1332 |
| 2.1225 | 0.2238 | 1000 | 2.1332 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.0.0+cu117
- Datasets 2.20.0
- Tokenizers 0.19.1