End of training

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+base_model: notBanana/SummarEaseFocus
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: SummarEaseFocusV2
+  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. -->
+
+# SummarEaseFocusV2
+
+This model is a fine-tuned version of [notBanana/SummarEaseFocus](https://huggingface.co/notBanana/SummarEaseFocus) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8433
+- Rouge1: 0.1827
+- Rouge2: 0.0704
+- Rougel: 0.1516
+- Rougelsum: 0.1494
+- Gen Len: 20.0
+
+## 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: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
+| No log        | 1.0   | 1    | 2.0431          | 0.1766 | 0.0679 | 0.1479 | 0.1457    | 20.0    |
+| No log        | 2.0   | 2    | 1.9573          | 0.1766 | 0.0679 | 0.1479 | 0.1457    | 20.0    |
+| No log        | 3.0   | 3    | 1.8788          | 0.1766 | 0.0679 | 0.1479 | 0.1457    | 20.0    |
+| No log        | 4.0   | 4    | 1.8433          | 0.1827 | 0.0704 | 0.1516 | 0.1494    | 20.0    |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "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,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.42.4"
+}