Upload 6 files

README.md

@@ -0,0 +1,79 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- squad_modified_for_t5_qg
+model-index:
+- name: t5-end2end-questions-answers-generation
+  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. -->
+
+# t5-end2end-questions-answers-generation
+
+This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the squad_modified_for_t5_qg dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3810
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.5388        | 0.34  | 100  | 1.7772          |
+| 1.8647        | 0.68  | 200  | 1.6304          |
+| 1.7367        | 1.02  | 300  | 1.5443          |
+| 1.6048        | 1.36  | 400  | 1.4884          |
+| 1.5559        | 1.69  | 500  | 1.4590          |
+| 1.5309        | 2.03  | 600  | 1.4440          |
+| 1.465         | 2.37  | 700  | 1.4215          |
+| 1.4601        | 2.71  | 800  | 1.4078          |
+| 1.4439        | 3.05  | 900  | 1.4123          |
+| 1.3988        | 3.39  | 1000 | 1.4108          |
+| 1.3896        | 3.73  | 1100 | 1.3915          |
+| 1.3781        | 4.07  | 1200 | 1.3927          |
+| 1.3557        | 4.41  | 1300 | 1.3849          |
+| 1.3476        | 4.75  | 1400 | 1.3877          |
+| 1.3419        | 5.08  | 1500 | 1.3836          |
+| 1.3203        | 5.42  | 1600 | 1.3765          |
+| 1.3135        | 5.76  | 1700 | 1.3754          |
+| 1.3251        | 6.1   | 1800 | 1.3794          |
+| 1.3004        | 6.44  | 1900 | 1.3786          |
+| 1.299         | 6.78  | 2000 | 1.3810          |
+
+
+### Framework versions
+
+- Transformers 4.23.1
+- Pytorch 1.12.1+cu113
+- Datasets 2.6.1
+- Tokenizers 0.13.1

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "t5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "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_max_distance": 128,
+  "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": "4.23.1",
+  "use_cache": true,
+  "vocab_size": 32101
+}

index.gitattributes

@@ -0,0 +1,32 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

index.gitignore

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

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37e8cf68de32181022431c3a1bafe0e2ceb8c0422d345c0f0e63c4d5a9db23ef
+size 891617855

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c44549aa47dc0dc7701ef5635fa40427902aa110243c3abff077435e3a0dd2b0
+size 3439