End of training

README.md

@@ -0,0 +1,63 @@
+---
+license: apache-2.0
+base_model: mrm8488/bert-mini2bert-mini-finetuned-cnn_daily_mail-summarization
+tags:
+- generated_from_trainer
+model-index:
+- name: bert2bert
+  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. -->
+
+# bert2bert
+
+This model is a fine-tuned version of [mrm8488/bert-mini2bert-mini-finetuned-cnn_daily_mail-summarization](https://huggingface.co/mrm8488/bert-mini2bert-mini-finetuned-cnn_daily_mail-summarization) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1196
+
+## 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: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.1386        | 1.0   | 3677  | 0.1256          |
+| 0.1294        | 2.0   | 7355  | 0.1227          |
+| 0.1233        | 3.0   | 11032 | 0.1210          |
+| 0.1204        | 4.0   | 14710 | 0.1200          |
+| 0.1191        | 5.0   | 18385 | 0.1196          |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Tokenizers 0.15.2

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 101,
+  "early_stopping": true,
+  "eos_token_id": 102,
+  "length_penalty": 2.0,
+  "max_length": 142,
+  "min_length": 56,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}