finetuned-baseline

README.md

@@ -0,0 +1,61 @@
+---
+license: mit
+base_model: valhalla/t5-small-e2e-qg
+tags:
+- generated_from_trainer
+model-index:
+- name: finetuned-baseline
+  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. -->
+
+# finetuned-baseline
+
+This model is a fine-tuned version of [valhalla/t5-small-e2e-qg](https://huggingface.co/valhalla/t5-small-e2e-qg) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.4731
+
+## 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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.9133        | 2.87  | 100  | 3.5685          |
+| 3.7034        | 5.75  | 200  | 3.4987          |
+| 3.6402        | 8.62  | 300  | 3.4731          |
+
+
+### Framework versions
+
+- Transformers 4.33.3
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,66 @@
+{
+  "_name_or_path": "valhalla/t5-small-e2e-qg",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "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": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "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": 1.5,
+      "max_length": 256,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "generate questions: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "length_penalty": 1.5,
+      "max_length": 256,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "generate questions: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "length_penalty": 1.5,
+      "max_length": 256,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "generate questions: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "length_penalty": 1.5,
+      "max_length": 256,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "generate questions: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 32102
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.33.3"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00b3b9c47d1fe0dde01d74ec639c9119ba4fa520af523bc83880bdc7f28e1bea
+size 242018393

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0afe5de5af27bcc4607f162714194f81fa747a459c82dfdecc230bb77b784227
+size 4091