End of training

README.md

@@ -0,0 +1,76 @@
+---
+license: apache-2.0
+base_model: facebook/bart-large
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: bart-large-finetuned-question-to-answer
+  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-large-finetuned-question-to-answer
+
+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: 0.3715
+- Bleu: 33.0345
+- Gen Len: 18.7967
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
+| 2.7764        | 1.0   | 516  | 1.6543          | 18.7782 | 19.48   |
+| 2.146         | 2.0   | 1032 | 1.3654          | 20.903  | 18.7367 |
+| 1.8588        | 3.0   | 1548 | 1.1539          | 23.3646 | 19.1067 |
+| 1.6513        | 4.0   | 2064 | 0.9755          | 23.4902 | 19.3267 |
+| 1.492         | 5.0   | 2580 | 0.8703          | 25.5851 | 19.2067 |
+| 1.3272        | 6.0   | 3096 | 0.7595          | 25.3403 | 18.95   |
+| 1.2287        | 7.0   | 3612 | 0.6719          | 26.9343 | 19.21   |
+| 1.1248        | 8.0   | 4128 | 0.6046          | 27.8768 | 19.24   |
+| 1.0318        | 9.0   | 4644 | 0.5496          | 29.6378 | 18.89   |
+| 0.9651        | 10.0  | 5160 | 0.4849          | 31.2889 | 18.9967 |
+| 0.8987        | 11.0  | 5676 | 0.4418          | 30.9236 | 18.9167 |
+| 0.8442        | 12.0  | 6192 | 0.4151          | 31.9543 | 18.8    |
+| 0.8042        | 13.0  | 6708 | 0.3917          | 32.7293 | 18.8533 |
+| 0.7682        | 14.0  | 7224 | 0.3777          | 32.463  | 18.85   |
+| 0.7435        | 15.0  | 7740 | 0.3715          | 33.0345 | 18.7967 |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.0.0
+- Datasets 2.1.0
+- Tokenizers 0.15.0

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": "4.36.2"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67afee59cde4f93c8b9e838da006086cdec44af52423b1b54b60c4979b3470b3
+oid sha256:3e602724f9453b05c48b77595a2522f8676e05c4e2eea86eb75a0545f485f40d
 size 1625426996

runs/Jan23_21-03-51_02380236fc31/events.out.tfevents.1706043832.02380236fc31.27.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dca6e8af4148532c7bc7b75f002bbe04ea8e3e4365fb388d30c51bb6c8b97efd
-size 13143
+oid sha256:d7a1bbde6d20ffce8b3d029c2fe6093640df48837535341d0e24bdc8439b813d
+size 13867