t5-end2end-questions-generation

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- squad
+model-index:
+- name: t5-end2end-question-generation
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+    dataset:
+      name: squad
+      type: squad
+      args: plain_text
+---
+
+<!-- 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. -->
+
+# t5-end2end-question-generation
+
+This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the squad dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5691
+
+## 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: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 7
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.5834        | 0.34  | 100  | 1.9107          |
+| 1.9642        | 0.68  | 200  | 1.7227          |
+| 1.8526        | 1.02  | 300  | 1.6627          |
+| 1.7383        | 1.36  | 400  | 1.6354          |
+| 1.7223        | 1.69  | 500  | 1.6154          |
+| 1.6871        | 2.03  | 600  | 1.6096          |
+| 1.6309        | 2.37  | 700  | 1.6048          |
+| 1.6242        | 2.71  | 800  | 1.5923          |
+| 1.6226        | 3.05  | 900  | 1.5855          |
+| 1.5645        | 3.39  | 1000 | 1.5874          |
+| 1.5705        | 3.73  | 1100 | 1.5822          |
+| 1.5543        | 4.07  | 1200 | 1.5817          |
+| 1.5284        | 4.41  | 1300 | 1.5841          |
+| 1.5275        | 4.75  | 1400 | 1.5741          |
+| 1.5269        | 5.08  | 1500 | 1.5715          |
+| 1.5079        | 5.42  | 1600 | 1.5701          |
+| 1.4876        | 5.76  | 1700 | 1.5754          |
+| 1.498         | 6.1   | 1800 | 1.5699          |
+| 1.4852        | 6.44  | 1900 | 1.5693          |
+| 1.4776        | 6.78  | 2000 | 1.5691          |
+
+
+### Framework versions
+
+- Transformers 4.10.3
+- Pytorch 1.9.0+cu102
+- Datasets 1.12.1
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "t5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.3",
+  "use_cache": true,
+  "vocab_size": 32101
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeaf116a47c0aa8760ab159f859c2cd6c06c6eb55afcca18f2ef9b44053f49e6
+size 891647935

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f73781b96870b20b64ff8e88639710bade397a4aeff84d690387dae89421ec1
+size 2671