Model save

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+base_model: facebook/bart-base
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: bart-base-finetuned-explanation
+  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. -->
+
+# bart-base-finetuned-explanation
+
+This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2107
+- Rouge1: 0.1997
+- Rouge2: 0.0756
+- Rougel: 0.1954
+- Rougelsum: 0.1967
+
+## 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: 5.6e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
+| 0.0145        | 1.0   | 41   | 0.2460          | 0.1886 | 0.0580 | 0.1780 | 0.1793    |
+| 0.1112        | 2.0   | 82   | 0.2085          | 0.2492 | 0.0815 | 0.2478 | 0.2480    |
+| 0.0801        | 3.0   | 123  | 0.2107          | 0.1997 | 0.0756 | 0.1954 | 0.1967    |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 1.11.0
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "facebook/bart-base",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.41.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53855de3f5aedcdc6d91105ab99bd728130e81418d689e76519b74d8212e2f43
+size 557912620

runs/Jul23_10-52-28_cn4330/events.out.tfevents.1721746383.cn4330.1870248.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0901f06330d32e36b470ca6bd25f2ff260f0d4458d5b3694bf7dd36bdbe47b6
+size 6231

runs/Jul23_10-52-28_cn4330/events.out.tfevents.1721746828.cn4330.1870248.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f5497df7c0e48713f13aaf3d1aaaecde46074816da4717c34aeebec03fb378
+size 6231

runs/Jul23_10-52-28_cn4330/events.out.tfevents.1721747430.cn4330.1870248.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:084f40f9d77fff06a41489ccb7ee4ab3d07635296372a3646ad02c1776046ec4
+size 6231

runs/Jul23_10-52-28_cn4330/events.out.tfevents.1721748068.cn4330.1870248.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc62e830e527162613ab163f7216aa76b0a2ff4f9a12f6a9c712b5d449a1a92e
+size 6231

runs/Jul23_11-29-43_cn4330/events.out.tfevents.1721748709.cn4330.1870248.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77bf4ac7daa01f460f918bc825a33cba43808e269d91b0d9a15f3ef451d7b966
+size 6231

runs/Jul23_11-29-43_cn4330/events.out.tfevents.1721749629.cn4330.1870248.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30cac77f0aa2144a3adebb7d1d3622a829dc446b47f693712ce4aa11de246ebf
+size 6231

runs/Jul23_11-29-43_cn4330/events.out.tfevents.1721750196.cn4330.1870248.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cab016284b95512ca0f28ab4722ed1a2da6f491d10f2af5270dbcc1fd65644b
+size 6231

runs/Jul23_11-29-43_cn4330/events.out.tfevents.1721750758.cn4330.1870248.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3a262c6755f17a1c0fe64960f66ef654ba20f6f3557d87661aad178ce178d57
+size 6231

runs/Jul23_11-29-43_cn4330/events.out.tfevents.1721751476.cn4330.1870248.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaf7cb3c0b8a037a5fea0d3d109ee1af5c188560f633578a7ae8c0e29d288cd9
+size 6231

runs/Jul23_11-29-43_cn4330/events.out.tfevents.1721752071.cn4330.1870248.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9269db99018c0b17494adee7e916723c75cb9467483ea33917c690765bcfb104
+size 8388

runs/Jul23_11-29-43_cn4330/events.out.tfevents.1721753799.cn4330.1870248.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b675f339e8b17cde729952e320ddfc565b2272642b17931f53e7d77309fcfca
+size 505

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "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,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "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_config.json

@@ -0,0 +1,56 @@
+{
+  "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": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:511309098ad0576db079354a8868c9051dba3debb15d9300bc16cd059a3f60bc
+size 4783