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 [Praveen76/FinetunedT5Model](https://huggingface.co/Praveen76/FinetunedT5Model) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9396
-- Rouge1: 0.0145
-- Rouge2: 0.008
-- Rougel: 0.0131
-- Rougelsum: 0.0126
+- Loss: 0.9334
+- Rouge1: 0.0174
+- Rouge2: 0.01
+- Rougel: 0.0154
+- Rougelsum: 0.0155
 - Gen Len: 1.0556
 
 ## Model description
@@ -53,26 +53,26 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| No log        | 1.0   | 27   | 4.2661          | 0.2624 | 0.1369 | 0.2205 | 0.2193    | 19.0    |
-| No log        | 2.0   | 54   | 1.2000          | 0.0215 | 0.0065 | 0.0178 | 0.0177    | 1.9352  |
-| No log        | 3.0   | 81   | 1.0934          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
-| No log        | 4.0   | 108  | 1.0780          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
-| No log        | 5.0   | 135  | 1.0576          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
-| No log        | 6.0   | 162  | 1.0351          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
-| No log        | 7.0   | 189  | 1.0138          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
-| No log        | 8.0   | 216  | 0.9938          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
-| No log        | 9.0   | 243  | 0.9777          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
-| No log        | 10.0  | 270  | 0.9673          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
-| No log        | 11.0  | 297  | 0.9576          | 0.0069 | 0.0026 | 0.0062 | 0.0061    | 0.7037  |
-| No log        | 12.0  | 324  | 0.9500          | 0.0069 | 0.0026 | 0.0062 | 0.0061    | 0.7037  |
-| No log        | 13.0  | 351  | 0.9442          | 0.0145 | 0.008  | 0.0131 | 0.0126    | 1.0556  |
-| No log        | 14.0  | 378  | 0.9407          | 0.0145 | 0.008  | 0.0131 | 0.0126    | 1.0556  |
-| No log        | 15.0  | 405  | 0.9396          | 0.0145 | 0.008  | 0.0131 | 0.0126    | 1.0556  |
+| No log        | 1.0   | 27   | 4.2291          | 0.276  | 0.1499 | 0.2309 | 0.2304    | 19.0    |
+| No log        | 2.0   | 54   | 1.1911          | 0.0223 | 0.0119 | 0.0202 | 0.0197    | 1.7593  |
+| No log        | 3.0   | 81   | 1.0887          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
+| No log        | 4.0   | 108  | 1.0708          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
+| No log        | 5.0   | 135  | 1.0551          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
+| No log        | 6.0   | 162  | 1.0332          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
+| No log        | 7.0   | 189  | 1.0104          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
+| No log        | 8.0   | 216  | 0.9919          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
+| No log        | 9.0   | 243  | 0.9757          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
+| No log        | 10.0  | 270  | 0.9610          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
+| No log        | 11.0  | 297  | 0.9501          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
+| No log        | 12.0  | 324  | 0.9424          | 0.0    | 0.0    | 0.0    | 0.0       | 0.0     |
+| No log        | 13.0  | 351  | 0.9378          | 0.0133 | 0.0086 | 0.0122 | 0.0117    | 0.7037  |
+| No log        | 14.0  | 378  | 0.9346          | 0.0174 | 0.01   | 0.0154 | 0.0155    | 1.0556  |
+| No log        | 15.0  | 405  | 0.9334          | 0.0174 | 0.01   | 0.0154 | 0.0155    | 1.0556  |
 
 
 ### Framework versions
 
-- Transformers 4.38.2
+- Transformers 4.33.1
 - Pytorch 2.2.1+cu121
 - Datasets 2.18.0
-- Tokenizers 0.15.2
+- Tokenizers 0.13.3

config.json

@@ -55,7 +55,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.33.1",
   "use_cache": true,
   "vocab_size": 32128
 }

generation_config.json

@@ -2,5 +2,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.38.2"
+  "transformers_version": "4.33.1"
 }

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d77a6b10c39cb664f79e386fb18d476d0417a7c2029668e486449f64bd52058
+size 242072086

special_tokens_map.json

@@ -101,25 +101,7 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
 }

tokenizer.json

@@ -956,8 +956,7 @@
       {
         "type": "Metaspace",
         "replacement": "▁",
-        "add_prefix_space": true,
-        "prepend_scheme": "always"
+        "add_prefix_space": true
       }
     ]
   },
@@ -1018,8 +1017,7 @@
   "decoder": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true,
-    "prepend_scheme": "always"
+    "add_prefix_space": true
   },
   "model": {
     "type": "Unigram",
@@ -129425,7 +129423,6 @@
         "<extra_id_0>",
         0.0
       ]
-    ],
-    "byte_fallback": false
+    ]
   }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:325f0da0f5248a23397fa8687bf00b8b48f2990810eff19ade2a2e30cadc2bd6
-size 5048
+oid sha256:9879b637d4f12898bffb098cfa83f9c79481c7430a748329094098a39ec32b13
+size 4664