End of training

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: allenai/led-large-16384
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: led-large-16384-finetune-paperLedBASE
+  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. -->
+
+# led-large-16384-finetune-paperLedBASE
+
+This model is a fine-tuned version of [allenai/led-large-16384](https://huggingface.co/allenai/led-large-16384) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.9013
+- Rouge1: 0.0
+- Rouge2: 0.0
+- Rougel: 0.0
+- Rougelsum: 0.0
+- Gen Len: 1.0
+
+## 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
+|:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
+| 2.9243        | 0.9993 | 1128 | 2.9579          | 0.0    | 0.0    | 0.0    | 0.0       | 1.0     |
+| 2.7355        | 1.9993 | 2256 | 2.8871          | 0.0    | 0.0    | 0.0    | 0.0       | 1.0     |
+| 2.6113        | 2.9993 | 3384 | 2.9013          | 0.0    | 0.0    | 0.0    | 0.0       | 1.0     |
+
+
+### Framework versions
+
+- Transformers 4.48.3
+- Pytorch 2.6.0+cu124
+- Datasets 2.14.4
+- Tokenizers 0.21.1

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 0,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "is_encoder_decoder": true,
+  "length_penalty": 2.0,
+  "max_length": 1024,
+  "max_new_tokens": 1024,
+  "min_new_tokens": 100,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.48.3"
+}

runs/May28_15-08-27_f86ba7fd1895/events.out.tfevents.1748444932.f86ba7fd1895.1465.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fb5c908d98327f1eea82618e6aac76b951adb5234da6d9569c6fcc9cf909fa5
-size 10340
+oid sha256:52dccb62f3a9161c17d660259d83fde484c1ac57127fc3bf17998999541490a2
+size 11219