End of training

README.md

@@ -0,0 +1,73 @@
+---
+library_name: transformers
+license: mit
+base_model: facebook/bart-large-cnn
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: amb-dataset-factor
+  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. -->
+
+# amb-dataset-factor
+
+This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7555
+- Rouge1: 0.6069
+- Rouge2: 0.3982
+- Rougel: 0.5368
+- Rougelsum: 0.5368
+- Gen Len: 107.5
+
+## 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: 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: 8
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
+| No log        | 1.0   | 1    | 1.1218          | 0.4868 | 0.2167 | 0.3132 | 0.3132    | 64.0    |
+| No log        | 2.0   | 2    | 0.9299          | 0.5037 | 0.2624 | 0.3424 | 0.3424    | 70.0    |
+| No log        | 3.0   | 3    | 0.9299          | 0.5037 | 0.2624 | 0.3424 | 0.3424    | 70.0    |
+| No log        | 4.0   | 4    | 0.8556          | 0.5364 | 0.2785 | 0.3874 | 0.3874    | 83.0    |
+| No log        | 5.0   | 5    | 0.8089          | 0.6657 | 0.4244 | 0.5452 | 0.5452    | 98.5    |
+| No log        | 6.0   | 6    | 0.7854          | 0.5876 | 0.3707 | 0.5024 | 0.5024    | 115.0   |
+| No log        | 7.0   | 7    | 0.7680          | 0.6012 | 0.4155 | 0.541  | 0.541     | 113.0   |
+| No log        | 8.0   | 8    | 0.7555          | 0.6069 | 0.3982 | 0.5368 | 0.5368    | 107.5   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.19.1

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "length_penalty": 2.0,
+  "max_length": 142,
+  "min_length": 56,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.44.2"
+}