metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- unsloth
- generated_from_trainer
base_model: unsloth/mistral-7b-instruct-v0.2-bnb-4bit
metrics:
- rouge
model-index:
- name: mistral_charttotext_FV
results: []
mistral_charttotext_FV
This model is a fine-tuned version of unsloth/mistral-7b-instruct-v0.2-bnb-4bit on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5696
- Rouge1: 0.8028
- Rougel: 0.7560
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: 1
- seed: 3407
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 5
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rougel |
|---|---|---|---|---|---|
| 0.6658 | 0.9980 | 380 | 0.5965 | 0.7724 | 0.7264 |
| 0.5686 | 1.9987 | 761 | 0.5753 | 0.7833 | 0.7375 |
| 0.5714 | 2.9980 | 1140 | 0.5517 | 0.8027 | 0.7613 |
| 0.5672 | 3.9980 | 1520 | 0.5664 | 0.8067 | 0.7564 |
| 0.5136 | 4.9980 | 1900 | 0.5672 | 0.8053 | 0.7572 |
| 0.5118 | 5.9980 | 2280 | 0.5696 | 0.8028 | 0.7560 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.2.0
- Datasets 2.16.0
- Tokenizers 0.19.1