Training complete!

README.md

@@ -1,4 +1,5 @@
 ---
+library_name: transformers
 base_model: google/pegasus-cnn_dailymail
 tags:
 - generated_from_trainer
@@ -16,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/pegasus-cnn_dailymail](https://huggingface.co/google/pegasus-cnn_dailymail) on the samsum dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4882
+- Loss: 1.4854
 
 ## Model description
 
@@ -48,14 +49,14 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.6287        | 0.54  | 500  | 1.4882          |
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.6718        | 0.5430 | 500  | 1.4854          |
 
 
 ### Framework versions
 
-- Transformers 4.34.1
-- Pytorch 2.1.0+cu121
-- Datasets 2.14.6
-- Tokenizers 0.14.1
+- Transformers 4.45.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.20.0

config.json

@@ -36,20 +36,20 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "length_penalty": 0.8,
-  "max_length": 128,
+  "length_penalty": null,
+  "max_length": null,
   "max_position_embeddings": 1024,
-  "min_length": 32,
+  "min_length": null,
   "model_type": "pegasus",
   "normalize_before": true,
   "normalize_embedding": false,
-  "num_beams": 8,
+  "num_beams": null,
   "num_hidden_layers": 16,
   "pad_token_id": 0,
   "scale_embedding": true,
   "static_position_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.34.1",
+  "transformers_version": "4.45.2",
   "use_cache": true,
   "vocab_size": 96103
 }

generation_config.json

@@ -9,5 +9,5 @@
   "min_length": 32,
   "num_beams": 8,
   "pad_token_id": 0,
-  "transformers_version": "4.34.1"
+  "transformers_version": "4.45.2"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e9be6c317ece041a28bc5b2ff16f4760b5f11672e0c0525cd1d75c917d024a9
+size 2283652852

runs/Oct20_16-23-43_84cda4c74c56/1666283033.8020647/events.out.tfevents.1666283033.84cda4c74c56.90220.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a01358ab07ad10fafe3a325e38d84ac86af3d8b757c66649a53ffdde601aaa
+size 5409

runs/Oct20_16-23-43_84cda4c74c56/1666284074.368571/events.out.tfevents.1666284074.84cda4c74c56.90220.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dbf5e452f66496634a0dac9cc0105c887d918e28e5810bc0baeedcc5a4e0646
+size 5409

runs/Oct20_16-23-43_84cda4c74c56/events.out.tfevents.1666283033.84cda4c74c56.90220.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef8060d3346ed4b3fe8113942a43c84a659c2a2d40f723969c4e10e0d3b1723a
+size 4334

runs/Oct20_16-23-43_84cda4c74c56/events.out.tfevents.1666284074.84cda4c74c56.90220.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea7c996c6e19f9ba652917fd3b589388c8b881096acc0108c66f549f2410c20c
+size 4334

runs/Oct20_17-47-06_84cda4c74c56/1666288033.7993069/events.out.tfevents.1666288033.84cda4c74c56.90773.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac5d4d0519af3ce680bf20c99acfe9ab3f3644a351c9d5a1340d43bcb778113
+size 5409

runs/Oct20_17-47-06_84cda4c74c56/events.out.tfevents.1666288033.84cda4c74c56.90773.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3650cf17756eae45416a6e9c5765b805a40dc1af08bd0c7cc0c5699cea1edd1
+size 4334

runs/Oct20_18-21-43_84cda4c74c56/1666290111.0084915/events.out.tfevents.1666290111.84cda4c74c56.91035.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7025589276cd324fa6d34e5d56a88069d724e98fd076be3ebdee08342034ca2
+size 5409

runs/Oct20_18-21-43_84cda4c74c56/events.out.tfevents.1666290110.84cda4c74c56.91035.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb3e7f59e35a1e6899f52a62dab36ec762cea88782728a6912f50da88512ba12
+size 4334

runs/Oct20_19-44-18_84cda4c74c56/1666295059.7752225/events.out.tfevents.1666295059.84cda4c74c56.91609.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d7167bcd6dfbc3788675b0a8c8126fe1ef61b7ed013b25564ee0410250dd9b1
+size 5409

runs/Oct20_19-44-18_84cda4c74c56/events.out.tfevents.1666295059.84cda4c74c56.91609.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba06b4377d7ea98307f691f36be98720643a724ce12b095a8a76406ee7c72ee3
+size 4335

tokenizer_config.json

@@ -847,6 +847,14 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "106": {
+      "content": "<n>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
   "additional_special_tokens": [
@@ -953,7 +961,7 @@
     "<unk_101>",
     "<unk_102>"
   ],
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "full_tokenizer_file": null,
   "mask_token": "<mask_2>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01e49aad50515f1e4d0b690698e786a4654676e51f8dc9c96f3b5f9f0f9d19c9
-size 4472
+oid sha256:904b9775eb3570ba7d2326c89fe0a83e3fbb5917ab1aa8ec7fd2a761cea9c5ba
+size 5176