End of training

README.md

@@ -0,0 +1,65 @@
+---
+base_model: ccdv/lsg-bart-base-16384-mediasum
+tags:
+- generated_from_trainer
+datasets:
+- pubmed-summarization
+model-index:
+- name: bart-fine-tuned-on-summarization
+  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-fine-tuned-on-summarization
+
+This model is a fine-tuned version of [ccdv/lsg-bart-base-16384-mediasum](https://huggingface.co/ccdv/lsg-bart-base-16384-mediasum) on the pubmed-summarization dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.7293
+
+## 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: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.4477        | 0.2   | 100  | 3.1109          |
+| 3.0893        | 0.4   | 200  | 2.8719          |
+| 2.8441        | 0.6   | 300  | 2.7832          |
+| 2.9203        | 0.8   | 400  | 2.7402          |
+| 2.9796        | 1.0   | 500  | 2.7293          |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,94 @@
+{
+  "_name_or_path": "ccdv/lsg-bart-base-16384-mediasum",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "adaptive": true,
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "auto_map": {
+    "AutoConfig": "ccdv/lsg-bart-base-16384-mediasum--modeling_lsg_bart.LSGBartConfig",
+    "AutoModel": "ccdv/lsg-bart-base-16384-mediasum--modeling_lsg_bart.LSGBartModel",
+    "AutoModelForCausalLM": "ccdv/lsg-bart-base-16384-mediasum--modeling_lsg_bart.LSGBartForCausalLM",
+    "AutoModelForQuestionAnswering": "ccdv/lsg-bart-base-16384-mediasum--modeling_lsg_bart.LSGBartForQuestionAnswering",
+    "AutoModelForSeq2SeqLM": "ccdv/lsg-bart-base-16384-mediasum--modeling_lsg_bart.LSGBartForConditionalGeneration",
+    "AutoModelForSequenceClassification": "ccdv/lsg-bart-base-16384-mediasum--modeling_lsg_bart.LSGBartForSequenceClassification"
+  },
+  "base_model_prefix": "lsg",
+  "block_size": 256,
+  "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
+  },
+  "lsh_num_pre_rounds": 1,
+  "mask_first_token": false,
+  "max_position_embeddings": 16384,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_global_tokens": 64,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "pass_global_tokens_to_decoder": true,
+  "pool_with_global": true,
+  "scale_embedding": false,
+  "sparse_block_size": 0,
+  "sparsity_factor": 4,
+  "sparsity_type": "none",
+  "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": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "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": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a83399b093736f4056181c7dd481656b44181be0828a613d93d854b0c8cdbb2
+size 652284532

runs/Mar12_06-30-09_11f0685bcb24/events.out.tfevents.1710225015.11f0685bcb24.286.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:146af844c5779760f02fc51fb4769f99f9261a318d2bb4cf6ab63cb57f418042
+size 5598

runs/Mar12_06-45-26_11f0685bcb24/events.out.tfevents.1710225932.11f0685bcb24.9348.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe9c99dbf6e23903fe29759dddce066d928aa2704cbd629968cdf0c1f4e71e6d
+size 18901

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "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": 16384,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c2dc9aa7fae1484e974134d62fe6692211774bc2f9617e12400ee1124d72967
+size 4920