harish3742/bert-base-cnn-ft-1

README.md

@@ -0,0 +1,65 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: bert-base-cnn-ft
+  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. -->
+
+# bert-base-cnn-ft
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0012
+- Rouge1: 0.0328
+- Rouge2: 0.0
+- Rougel: 0.0303
+- Rougelsum: 0.0303
+- Gen Len: 60.0
+
+## 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: 12
+- eval_batch_size: 12
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1
+- training_steps: 200
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
+|:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
+| 0.0383        | 0.0167 | 100  | 0.0019          | 0.0331 | 0.0    | 0.0306 | 0.0306    | 60.0    |
+| 0.0177        | 0.0334 | 200  | 0.0012          | 0.0328 | 0.0    | 0.0303 | 0.0303    | 60.0    |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "decoder_start_token_id": 101,
+  "early_stopping": true,
+  "eos_token_id": 102,
+  "length_penalty": 2.0,
+  "max_length": 60,
+  "min_length": 10,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 0,
+  "transformers_version": "4.40.1"
+}