# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("NiGuLa/google-bert_bert-base-multilingual-cased_ep10_lr1e-06_batchpergpu16_gpu1")
model = AutoModelForSequenceClassification.from_pretrained("NiGuLa/google-bert_bert-base-multilingual-cased_ep10_lr1e-06_batchpergpu16_gpu1", device_map="auto")Quick Links
google-bert_bert-base-multilingual-cased_ep10_lr1e-06_batchpergpu16_gpu1
This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2388
- F1 Micro: 0.5255
- F1 Macro: 0.1106
- Exact Match: 0.6231
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-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | Exact Match |
|---|---|---|---|---|---|---|
| 0.4211 | 0.9924 | 131 | 0.3909 | 0.0694 | 0.0167 | 0.5 |
| 0.3268 | 1.9848 | 262 | 0.3120 | 0.2602 | 0.0594 | 0.5473 |
| 0.3003 | 2.9773 | 393 | 0.2844 | 0.5030 | 0.1063 | 0.6136 |
| 0.2908 | 3.9697 | 524 | 0.2677 | 0.4589 | 0.0985 | 0.5966 |
| 0.2578 | 4.9621 | 655 | 0.2563 | 0.5437 | 0.1135 | 0.6231 |
| 0.2526 | 5.9545 | 786 | 0.2483 | 0.5760 | 0.1185 | 0.6345 |
| 0.2503 | 6.9470 | 917 | 0.2424 | 0.5667 | 0.1175 | 0.6364 |
| 0.2455 | 7.9394 | 1048 | 0.2388 | 0.5255 | 0.1106 | 0.6231 |
Framework versions
- Transformers 5.6.2
- Pytorch 2.11.0+cu130
- Datasets 4.8.4
- Tokenizers 0.22.2
- Downloads last month
- 4
Model tree for NiGuLa/google-bert_bert-base-multilingual-cased_ep10_lr1e-06_batchpergpu16_gpu1
Base model
google-bert/bert-base-multilingual-cased
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="NiGuLa/google-bert_bert-base-multilingual-cased_ep10_lr1e-06_batchpergpu16_gpu1")