End of training

README.md

@@ -15,7 +15,7 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2631
+- Loss: 0.2818
 
 ## Model description
 
@@ -34,10 +34,10 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
-- seed: 42
+- learning_rate: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 7
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 5
@@ -46,11 +46,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.0954        | 1.0   | 74   | 0.1527          |
-| 0.0544        | 2.0   | 148  | 0.1748          |
-| 0.0332        | 3.0   | 222  | 0.1932          |
-| 0.0199        | 4.0   | 296  | 0.2371          |
-| 0.0119        | 5.0   | 370  | 0.2631          |
+| 0.0129        | 1.0   | 37   | 0.2748          |
+| 0.0098        | 2.0   | 74   | 0.2811          |
+| 0.0079        | 3.0   | 111  | 0.2858          |
+| 0.0069        | 4.0   | 148  | 0.2801          |
+| 0.0066        | 5.0   | 185  | 0.2818          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff7dc660bb72fff5fb53365d99c6e48e8f9d63d1ab9f236965cdfa797526c47f
+oid sha256:0895751b77b32ed71785340d3d0cf4bc1d8314d9a37e53c547c5e431147c088b
 size 1625422896

runs/Apr12_08-55-20_2e9e57912d49/events.out.tfevents.1712912126.2e9e57912d49.541.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22a2b30dfc183b558367a72d156c8994f9e6ba2fdb3ddd85f0ae65b852d819fb
+size 11080

special_tokens_map.json

@@ -1,7 +1,25 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -9,7 +27,25 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 1024,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 1024
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 2,
-    "pad_type_id": 0,
-    "pad_token": "</s>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -48,10 +48,17 @@
   "eos_token": "</s>",
   "errors": "replace",
   "mask_token": "<mask>",
+  "max_length": 1024,
   "model_max_length": 1024,
+  "pad_to_multiple_of": null,
   "pad_token": "</s>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "</s>",
+  "stride": 0,
   "tokenizer_class": "BartTokenizer",
   "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f18380c6d5616ca9fbc44cb64c46df80251164f67bbc35658ca7e113fb881d2b
+oid sha256:e757654d94563b052c7f6b265a5d4643f8aa2a13664cedcada839dc4571b8ef8
 size 4920