End of training

README.md

@@ -17,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [GuysTrans/bart-base-chat-512-seq](https://huggingface.co/GuysTrans/bart-base-chat-512-seq) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.7551
-- Rouge1: 12.1609
-- Rouge2: 3.3724
-- Rougel: 9.9373
-- Rougelsum: 11.7847
+- Loss: 2.7268
+- Rouge1: 12.2335
+- Rouge2: 3.456
+- Rougel: 10.0152
+- Rougelsum: 11.8651
 - Gen Len: 20.0
 
 ## Model description
@@ -51,14 +51,14 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Rouge1  | Rouge2 | Rougel | Rougelsum | Gen Len |
-|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 1.9676        | 1.0   | 14598 | 2.7551          | 12.1609 | 3.3724 | 9.9373 | 11.7847   | 20.0    |
+| Training Loss | Epoch | Step  | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
+| 2.0456        | 1.0   | 14598 | 2.7268          | 12.2335 | 3.456  | 10.0152 | 11.8651   | 20.0    |
 
 
 ### Framework versions
 
-- Transformers 4.34.1
-- Pytorch 2.1.0+cu118
-- Datasets 2.14.5
-- Tokenizers 0.14.1
+- Transformers 4.33.0
+- Pytorch 2.0.0
+- Datasets 2.1.0
+- Tokenizers 0.13.3

generation_config.json

@@ -8,5 +8,5 @@
   "no_repeat_ngram_size": 3,
   "num_beams": 4,
   "pad_token_id": 1,
-  "transformers_version": "4.34.1"
+  "transformers_version": "4.33.0"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76ae234527acafc00a5b16819cc58b47413de8edb5b829c58867e11c408ad4cc
+oid sha256:0173bf2fd427139d27a248a669897101ad61e21925a0fdd9c7bdf654a1d064bc
 size 557971229