training completed[dev]: 1024 128

README.md

@@ -0,0 +1,72 @@
+---
+license: apache-2.0
+base_model: facebook/bart-large
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+- wer
+model-index:
+- name: bart_baseline_1024
+  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. -->
+
+# bart_baseline_1024
+
+This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0100
+- Rouge1: 0.6961
+- Rouge2: 0.4369
+- Rougel: 0.6352
+- Rougelsum: 0.6352
+- Wer: 0.4562
+
+## 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: 6
+- eval_batch_size: 6
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:------:|
+| No log        | 0.13  | 250  | 1.2180          | 0.6601 | 0.3882 | 0.5954 | 0.5952    | 0.4981 |
+| 2.1099        | 0.27  | 500  | 1.1152          | 0.68   | 0.4133 | 0.6165 | 0.6164    | 0.4806 |
+| 2.1099        | 0.4   | 750  | 1.0765          | 0.6817 | 0.4177 | 0.6181 | 0.618     | 0.4723 |
+| 1.1853        | 0.53  | 1000 | 1.0552          | 0.6915 | 0.4283 | 0.6284 | 0.6283    | 0.4664 |
+| 1.1853        | 0.66  | 1250 | 1.0315          | 0.6958 | 0.4327 | 0.6328 | 0.6326    | 0.4622 |
+| 1.1179        | 0.8   | 1500 | 1.0227          | 0.6912 | 0.4317 | 0.6297 | 0.6296    | 0.4582 |
+| 1.1179        | 0.93  | 1750 | 1.0100          | 0.6961 | 0.4369 | 0.6352 | 0.6352    | 0.4562 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "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": "4.38.2"
+}

runs/Mar22_05-47-38_9164c72d17ee/events.out.tfevents.1711086530.9164c72d17ee.1634.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce94b480ce330047251c6d9d086845ccc803decb47d4abaf713dbf8155e65f58
-size 8282
+oid sha256:66ebce49c8bb5ed208ad7841961277c483d5c35ee4808e178bb7ad5a3876081c
+size 10410