End of training

README.md

@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 # summarize_by_bart
 
 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: 1.7698
 
 ## Model description
 
@@ -33,18 +35,22 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 5
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| No log        | 1.0   | 248  | 1.5782          | 0.1863 | 0.106  | 0.1629 | 0.1678    | 20.0    |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 495  | 1.8562          |
+| 2.2793        | 2.0   | 990  | 1.7942          |
+| 2.1004        | 3.0   | 1485 | 1.7751          |
+| 2.0356        | 4.0   | 1980 | 1.7703          |
+| 2.0074        | 5.0   | 2475 | 1.7698          |
 
 
 ### Framework versions

config.json

@@ -67,7 +67,7 @@
       "num_beams": 6
     }
   },
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.41.2",
   "use_cache": true,
   "vocab_size": 50265

generation_config.json

@@ -1,4 +1,5 @@
 {
+  "_from_model_config": true,
   "bos_token_id": 0,
   "decoder_start_token_id": 2,
   "early_stopping": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca9616622397fdb5334bb161aa42e523a873cfc6ea4e24a3ad3d22ba86eab721
-size 1625426996
+oid sha256:f370da18a5df1e9fb5434cff0a181120e91025eb6be8f4dfc29a96bfad078c8e
+size 812743714

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91e0fbecefa0bbbe2d8b263c45125ab6e9fdc2295dcb27058be5dabcbe0f588b
+oid sha256:7d708871fac9e107f4f2a5b8ce206c142b8247ebfcd9c55265cf56a40ba94aaa
 size 5240