End of training

README.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+base_model: google/bigbird-pegasus-large-arxiv
+tags:
+- generated_from_trainer
+datasets:
+- scientific_papers
+model-index:
+- name: summarizer
+  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. -->
+
+# summarizer
+
+This model is a fine-tuned version of [google/bigbird-pegasus-large-arxiv](https://huggingface.co/google/bigbird-pegasus-large-arxiv) on the scientific_papers dataset.
+
+## 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
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 51   | 1.7488          |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "google/bigbird-pegasus-large-arxiv",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "BigBirdPegasusForConditionalGeneration"
+  ],
+  "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": "4.38.1",
+  "use_bias": false,
+  "use_cache": true,
+  "vocab_size": 96103
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 1,
+  "length_penalty": 0.8,
+  "max_length": 256,
+  "num_beams": 5,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbd1998080a3d6b36f3e6de203be3b9a3538a663f0616d3fcefd076ed83daf36
+size 2308009868

runs/Mar03_23-02-12_4feed1865354/events.out.tfevents.1709506935.4feed1865354.512.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69da9ee2dd28ae11d38ffca141a985392d3e29ebc7681fa98e80d31e8b5f319e
+size 5770

special_tokens_map.json

@@ -0,0 +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
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1b40df7e8825709c0172639c47338a68d5622e9e3b6cc0fae516537cae738b
+size 1915455

tokenizer_config.json

@@ -0,0 +1,74 @@
+{
+  "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>",
+  "padding": "max_length",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PegasusTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8d7c269720eb6473874ab0c15e126e56d2141ebde779677d3c59f5131930e11
+size 5048