End of training

README.md

@@ -0,0 +1,57 @@
+---
+license: apache-2.0
+base_model: google/bigbird-pegasus-large-pubmed
+tags:
+- generated_from_trainer
+model-index:
+- name: my_awesome_qa_model
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# my_awesome_qa_model
+
+This model is a fine-tuned version of [google/bigbird-pegasus-large-pubmed](https://huggingface.co/google/bigbird-pegasus-large-pubmed) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.9818
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 4.9967        | 1.0   | 1000 | 4.9818          |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.1.2
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -1,43 +1,43 @@
-{
-  "_name_or_path": "google/bigbird-pegasus-large-pubmed",
-  "activation_dropout": 0.0,
-  "activation_function": "gelu_new",
-  "architectures": [
-    "BigBirdPegasusForQuestionAnswering"
-  ],
-  "attention_dropout": 0.0,
-  "attention_type": "block_sparse",
-  "block_size": 64,
-  "bos_token_id": 2,
-  "classifier_dropout": 0.0,
-  "d_model": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 16,
-  "decoder_start_token_id": 2,
-  "dropout": 0.1,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 16,
-  "eos_token_id": 1,
-  "gradient_checkpointing": false,
-  "init_std": 0.02,
-  "is_encoder_decoder": true,
-  "length_penalty": 0.8,
-  "max_length": 256,
-  "max_position_embeddings": 4096,
-  "model_type": "bigbird_pegasus",
-  "num_beams": 5,
-  "num_hidden_layers": 16,
-  "num_random_blocks": 3,
-  "pad_token_id": 0,
-  "scale_embedding": true,
-  "tokenizer_class": "PegasusTokenizer",
-  "torch_dtype": "float16",
-  "transformers_version": "4.41.2",
-  "use_bias": false,
-  "use_cache": true,
-  "vocab_size": 96103
-}
+{
+  "_name_or_path": "google/bigbird-pegasus-large-pubmed",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "BigBirdPegasusForQuestionAnswering"
+  ],
+  "attention_dropout": 0.0,
+  "attention_type": "block_sparse",
+  "block_size": 64,
+  "bos_token_id": 2,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 16,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 16,
+  "eos_token_id": 1,
+  "gradient_checkpointing": false,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "length_penalty": 0.8,
+  "max_length": 256,
+  "max_position_embeddings": 4096,
+  "model_type": "bigbird_pegasus",
+  "num_beams": 5,
+  "num_hidden_layers": 16,
+  "num_random_blocks": 3,
+  "pad_token_id": 0,
+  "scale_embedding": true,
+  "tokenizer_class": "PegasusTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_bias": false,
+  "use_cache": true,
+  "vocab_size": 96103
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bdbcb83f9f4e13eedfb2da918ba391f24ab66c02a9ca64f2b9efb77777246de
-size 1153845340
+oid sha256:b7ed193bb74e6c8bcc91a0192476909e0429fbb77da6a1d6ebfd018df0e73206
+size 2307633752

special_tokens_map.json

@@ -1,51 +1,51 @@
-{
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "[CLS]",
-    "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,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
-}
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "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,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -1,73 +1,73 @@
-{
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "</s>",
-      "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
-    },
-    "65": {
-      "content": "[CLS]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "66": {
-      "content": "[SEP]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "67": {
-      "content": "[MASK]",
-      "lstrip": true,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "105": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "additional_special_tokens": [],
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "eos_token": "</s>",
-  "mask_token": "[MASK]",
-  "mask_token_sent": null,
-  "model_max_length": 4096,
-  "offset": 0,
-  "pad_token": "<pad>",
-  "sep_token": "[SEP]",
-  "tokenizer_class": "PegasusTokenizer",
-  "unk_token": "<unk>"
-}
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "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
+    },
+    "65": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "66": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "67": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "105": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "eos_token": "</s>",
+  "mask_token": "[MASK]",
+  "mask_token_sent": null,
+  "model_max_length": 4096,
+  "offset": 0,
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PegasusTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a7a5822511063bcb486f8826f0b2d16d844a5f61067c9234838924bfad51732
+oid sha256:f30372cc0156aa8c95ac4e76aa3db410490a4e31eacda6fe1f0efc0e29255ca8
 size 5112