End of training

README.md

@@ -5,6 +5,7 @@ tags:
 - generated_from_trainer
 metrics:
 - rouge
+- sacrebleu
 model-index:
 - name: mT5-TextSimp-LT-BatchSize8-lr5e-5
   results: []
@@ -17,10 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0969
-- Rouge1: 0.6185
-- Rouge2: 0.4427
-- Rougel: 0.6087
+- Loss: 0.0983
+- Rouge1: 0.6245
+- Rouge2: 0.4439
+- Rougel: 0.6142
+- Sacrebleu: 35.7192
 - Gen Len: 38.0501
 
 ## Model description
@@ -51,21 +53,21 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Gen Len |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:-------:|
-| 32.3498       | 0.96  | 200  | 26.0719         | 0.0008 | 0.0    | 0.0008 | 512.0   |
-| 5.8297        | 1.91  | 400  | 4.1306          | 0.0059 | 0.0    | 0.0058 | 45.0573 |
-| 0.7087        | 2.87  | 600  | 0.6039          | 0.003  | 0.0    | 0.0029 | 39.0501 |
-| 0.4166        | 3.83  | 800  | 0.1958          | 0.3954 | 0.2416 | 0.3823 | 39.0501 |
-| 0.2193        | 4.78  | 1000 | 0.1172          | 0.5244 | 0.3536 | 0.514  | 38.0501 |
-| 0.1371        | 5.74  | 1200 | 0.1029          | 0.5936 | 0.4122 | 0.5839 | 38.0501 |
-| 0.1971        | 6.7   | 1400 | 0.0974          | 0.6077 | 0.4302 | 0.5984 | 38.0501 |
-| 0.1653        | 7.66  | 1600 | 0.0969          | 0.6185 | 0.4427 | 0.6087 | 38.0501 |
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Sacrebleu | Gen Len  |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:--------:|
+| 35.3898       | 0.96  | 200  | 27.6372         | 0.0019 | 0.0    | 0.0018 | 0.0003    | 512.0    |
+| 3.5712        | 1.91  | 400  | 1.9615          | 0.0171 | 0.0    | 0.0167 | 0.0225    | 39.0501  |
+| 0.6489        | 2.87  | 600  | 0.5638          | 0.0052 | 0.0    | 0.0051 | 0.0256    | 39.0501  |
+| 0.6017        | 3.83  | 800  | 3.2823          | 0.2419 | 0.1287 | 0.2318 | 0.6457    | 130.3556 |
+| 0.3784        | 4.78  | 1000 | 0.1340          | 0.5092 | 0.3277 | 0.4978 | 26.7005   | 38.0549  |
+| 0.1521        | 5.74  | 1200 | 0.1092          | 0.5782 | 0.3973 | 0.5672 | 33.2443   | 38.0501  |
+| 0.2096        | 6.7   | 1400 | 0.1001          | 0.6149 | 0.4342 | 0.6046 | 34.6518   | 38.0501  |
+| 0.1719        | 7.66  | 1600 | 0.0983          | 0.6245 | 0.4439 | 0.6142 | 35.7192   | 38.0501  |
 
 
 ### Framework versions
 
-- Transformers 4.36.2
-- Pytorch 2.1.1
-- Datasets 2.16.1
-- Tokenizers 0.15.0
+- Transformers 4.33.0
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.4
+- Tokenizers 0.13.3

generation_config.json

@@ -3,5 +3,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.36.2"
+  "transformers_version": "4.33.0"
 }

special_tokens_map.json

@@ -1,23 +1,5 @@
 {
-  "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_config.json

@@ -1,31 +1,5 @@
 {
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "additional_special_tokens": [],
+  "additional_special_tokens": null,
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 0,
@@ -34,5 +8,6 @@
   "pad_token": "<pad>",
   "sp_model_kwargs": {},
   "tokenizer_class": "T5Tokenizer",
+  "tokenizer_file": null,
   "unk_token": "<unk>"
 }