End of training

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the samsum dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2493
+- Loss: 0.1344
 
 ## Model description
 
@@ -48,12 +48,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.113         | 1.0   | 148  | 0.2493          |
+| 0.0887        | 1.0   | 37   | 0.1344          |
 
 
 ### Framework versions
 
-- Transformers 4.33.1
-- Pytorch 2.0.1+cu118
-- Datasets 2.14.5
-- Tokenizers 0.13.3
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -64,7 +64,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.33.1",
+  "transformers_version": "4.41.1",
   "use_cache": true,
   "vocab_size": 50264
 }

generation_config.json

@@ -12,5 +12,5 @@
   "no_repeat_ngram_size": 3,
   "num_beams": 4,
   "pad_token_id": 1,
-  "transformers_version": "4.33.1"
+  "transformers_version": "4.41.1"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8616a541a86c2e5ad35c1b33af9f77ac2778c99fc129ca5a4e861867303bfb9c
+size 1625422896

runs/Jun03_21-06-45_7f82a0ff45c9/events.out.tfevents.1717448807.7f82a0ff45c9.181.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d21325c1e3935d292cd55ac7202e3d89c201a7ff8041e2205ffbe578b145130d
+size 5861

runs/Jun03_21-10-21_7f82a0ff45c9/events.out.tfevents.1717449024.7f82a0ff45c9.181.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77549fcd9c5256b74b59e5632cb51cc2f7b5c6579b936c138f1eb6184cffaf70
+size 5861

runs/Jun03_21-16-55_7f82a0ff45c9/events.out.tfevents.1717449419.7f82a0ff45c9.181.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16d6ee40ccf8d2a5bf6944d4b839cdc9f165fb6f040f9c47e9e9fe79643fd749
+size 5861

runs/Jun03_21-19-37_7f82a0ff45c9/events.out.tfevents.1717449580.7f82a0ff45c9.181.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0156ed51f11c3e78c0e998428c88abbc8843f10490a5656812a24c29b6706d84
+size 12869

special_tokens_map.json

@@ -5,7 +5,7 @@
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 1024,
+    "max_length": 512,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 1024
+      "Fixed": 512
     },
     "direction": "Right",
     "pad_to_multiple_of": null,
@@ -23,7 +23,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -32,7 +32,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -41,7 +41,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -50,7 +50,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -59,7 +59,7 @@
       "single_word": false,
       "lstrip": true,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     }
   ],
@@ -97,6 +97,7 @@
     "end_of_word_suffix": "",
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "<s>": 0,
       "<pad>": 1,

tokenizer_config.json

@@ -1,13 +1,55 @@
 {
   "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
   "errors": "replace",
   "mask_token": "<mask>",
-  "model_max_length": 1024,
-  "pad_token": "<pad>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
   "sep_token": "</s>",
   "tokenizer_class": "BartTokenizer",
   "trim_offsets": true,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48e6ca0adaa6e28081880ae1b634c1cfe3b01c84607c4dfe8f6ef33908bec09d
-size 4091
+oid sha256:a44c1d6ee4aa8384d5dcb544ce3bc5762ae862eca050d4d190da287a4067fdf9
+size 5176