aparajitha/bart-base-sci-tr

README.md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+base_model: facebook/bart-base
+tags:
+- generated_from_trainer
+model-index:
+- name: bart-base-sci-tr
+  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-sci-tr
+
+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: 2.7617
+
+## 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: 30
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 3.5107        | 1.0   | 1393  | 3.0242          |
+| 3.1138        | 2.0   | 2786  | 2.8770          |
+| 2.9345        | 3.0   | 4179  | 2.8069          |
+| 2.8044        | 4.0   | 5572  | 2.7668          |
+| 2.7227        | 5.0   | 6965  | 2.7336          |
+| 2.6341        | 6.0   | 8358  | 2.7276          |
+| 2.5523        | 7.0   | 9751  | 2.7026          |
+| 2.4846        | 8.0   | 11144 | 2.6961          |
+| 2.4409        | 9.0   | 12537 | 2.6894          |
+| 2.3699        | 10.0  | 13930 | 2.6853          |
+| 2.3305        | 11.0  | 15323 | 2.6869          |
+| 2.2822        | 12.0  | 16716 | 2.6924          |
+| 2.2392        | 13.0  | 18109 | 2.7042          |
+| 2.1889        | 14.0  | 19502 | 2.6943          |
+| 2.1593        | 15.0  | 20895 | 2.6988          |
+| 2.1228        | 16.0  | 22288 | 2.7032          |
+| 2.0791        | 17.0  | 23681 | 2.7083          |
+| 2.0594        | 18.0  | 25074 | 2.7034          |
+| 2.0239        | 19.0  | 26467 | 2.7182          |
+| 1.9943        | 20.0  | 27860 | 2.7235          |
+| 1.9746        | 21.0  | 29253 | 2.7279          |
+| 1.9624        | 22.0  | 30646 | 2.7337          |
+| 1.9433        | 23.0  | 32039 | 2.7400          |
+| 1.9138        | 24.0  | 33432 | 2.7457          |
+| 1.8971        | 25.0  | 34825 | 2.7489          |
+| 1.8896        | 26.0  | 36218 | 2.7527          |
+| 1.873         | 27.0  | 37611 | 2.7576          |
+| 1.8585        | 28.0  | 39004 | 2.7577          |
+| 1.8564        | 29.0  | 40397 | 2.7594          |
+| 1.852         | 30.0  | 41790 | 2.7617          |
+
+
+### Framework versions
+
+- Transformers 4.43.4
+- Pytorch 1.13.1
+- Datasets 2.12.0
+- 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": "4.43.4",
+  "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": "4.43.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89931dde77e6e98b76977db3a7f9c6046dd95fce835dca69153b7681d15da1b6
+size 557912620

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5b5baab49dd2f1f45d5921780132a1d81ae941df68bb7736db9290f4692a891
+size 4859