Instructions to use Gaoussin/trainer_output with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Gaoussin/trainer_output with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Gaoussin/trainer_output") model = AutoModelForSeq2SeqLM.from_pretrained("Gaoussin/trainer_output", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files
README.md
CHANGED
|
@@ -4,6 +4,8 @@ license: cc-by-nc-4.0
|
|
| 4 |
base_model: facebook/nllb-200-distilled-600M
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: trainer_output
|
| 9 |
results: []
|
|
@@ -16,6 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
# trainer_output
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -45,6 +50,20 @@ The following hyperparameters were used during training:
|
|
| 45 |
- lr_scheduler_warmup_ratio: 0.1
|
| 46 |
- num_epochs: 8
|
| 47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
### Framework versions
|
| 49 |
|
| 50 |
- Transformers 4.57.1
|
|
|
|
| 4 |
base_model: facebook/nllb-200-distilled-600M
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- bleu
|
| 9 |
model-index:
|
| 10 |
- name: trainer_output
|
| 11 |
results: []
|
|
|
|
| 18 |
# trainer_output
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on an unknown dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 1.9593
|
| 23 |
+
- Bleu: 19.2115
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 50 |
- lr_scheduler_warmup_ratio: 0.1
|
| 51 |
- num_epochs: 8
|
| 52 |
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|
| 56 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|
|
| 57 |
+
| 2.4325 | 1.0 | 2530 | 2.3181 | 14.7619 |
|
| 58 |
+
| 2.1169 | 2.0 | 5060 | 2.1132 | 16.3770 |
|
| 59 |
+
| 1.9219 | 3.0 | 7590 | 2.0205 | 17.7188 |
|
| 60 |
+
| 1.7669 | 4.0 | 10120 | 1.9751 | 18.3566 |
|
| 61 |
+
| 1.66 | 5.0 | 12650 | 1.9687 | 18.7496 |
|
| 62 |
+
| 1.582 | 6.0 | 15180 | 1.9591 | 18.9917 |
|
| 63 |
+
| 1.541 | 7.0 | 17710 | 1.9554 | 19.0968 |
|
| 64 |
+
| 1.5046 | 8.0 | 20240 | 1.9593 | 19.2115 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
### Framework versions
|
| 68 |
|
| 69 |
- Transformers 4.57.1
|