Training complete

README.md

@@ -0,0 +1,63 @@
+---
+license: mit
+base_model: facebook/mbart-large-50
+tags:
+- simplification
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: mbart-gsm8k
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# mbart-gsm8k
+
+This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9236
+- Bleu: 28.8931
+- Gen Len: 87.5959
+
+## 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: 5.6e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
+| 1.4784        | 1.0   | 935  | 1.0135          | 25.551  | 83.9826 |
+| 0.7957        | 2.0   | 1870 | 0.9236          | 28.8931 | 87.5959 |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "max_length": 200,
+  "num_beams": 5,
+  "pad_token_id": 1,
+  "transformers_version": "4.40.0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8daaf77ec1c242d053e55e54a4f986298f11fdda86a0369e1aa02ee4cf8a6d36
+oid sha256:f5a5469def8a3922e7ff0f4a709c4ad49418d8d71e296876d9334a4803b34dbe
 size 2444578688