led-question-generator

README.md

@@ -0,0 +1,49 @@
+---
+license: apache-2.0
+base_model: allenai/led-base-16384
+tags:
+- generated_from_trainer
+model-index:
+- name: results
+ 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. -->
+
+# results
+
+This model is a fine-tuned version of [allenai/led-base-16384](https://huggingface.co/allenai/led-base-16384) on the None 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: 5e-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
+- lr_scheduler_warmup_steps: 200
+- num_epochs: 1
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,54 @@
+{
+ "_name_or_path": "allenai/led-base-16384",
+ "activation_dropout": 0.0,
+ "activation_function": "gelu",
+ "architectures": [
+ "LEDForConditionalGeneration"
+ ],
+ "attention_dropout": 0.0,
+ "attention_window": [
+ 1024,
+ 1024,
+ 1024,
+ 1024,
+ 1024,
+ 1024
+ ],
+ "bos_token_id": 0,
+ "classif_dropout": 0.0,
+ "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,
+ "encoder_attention_heads": 12,
+ "encoder_ffn_dim": 3072,
+ "encoder_layerdrop": 0.0,
+ "encoder_layers": 6,
+ "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_decoder_position_embeddings": 1024,
+ "max_encoder_position_embeddings": 16384,
+ "model_type": "led",
+ "num_hidden_layers": 6,
+ "pad_token_id": 1,
+ "torch_dtype": "float32",
+ "transformers_version": "4.38.2",
+ "use_cache": true,
+ "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 0,
+ "decoder_start_token_id": 2,
+ "eos_token_id": 2,
+ "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:c009e824b2a23209bf15fc0d6e7ecfefdde24fd992593e4b340d11d9aedfa217
+size 647614116

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1bea7061909a544b28a49311be0582556e341ec6dcf3d5d7dcde3a06435c833
+size 4856