finetuned-baseline-phase-0.0

README.md

@@ -0,0 +1,86 @@
+---
+license: mit
+base_model: valhalla/t5-small-e2e-qg
+tags:
+- generated_from_trainer
+model-index:
+- name: finetuned-baseline-phase-0.0
+  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-phase-0.0
+
+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: 4.0205
+
+## 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: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 5.2173        | 0.66  | 5    | 4.8296          |
+| 4.8604        | 1.32  | 10   | 4.5708          |
+| 4.6755        | 1.98  | 15   | 4.4653          |
+| 4.6046        | 2.64  | 20   | 4.4006          |
+| 4.5457        | 3.31  | 25   | 4.3465          |
+| 4.502         | 3.97  | 30   | 4.2920          |
+| 4.4677        | 4.63  | 35   | 4.2398          |
+| 4.3849        | 5.29  | 40   | 4.2034          |
+| 4.3815        | 5.95  | 45   | 4.1794          |
+| 4.3412        | 6.61  | 50   | 4.1628          |
+| 4.3026        | 7.27  | 55   | 4.1417          |
+| 4.3104        | 7.93  | 60   | 4.1198          |
+| 4.2791        | 8.6   | 65   | 4.1001          |
+| 4.2523        | 9.26  | 70   | 4.0855          |
+| 4.235         | 9.92  | 75   | 4.0724          |
+| 4.2201        | 10.58 | 80   | 4.0610          |
+| 4.1716        | 11.24 | 85   | 4.0534          |
+| 4.2005        | 11.9  | 90   | 4.0489          |
+| 4.1902        | 12.56 | 95   | 4.0450          |
+| 4.1632        | 13.22 | 100  | 4.0399          |
+| 4.1467        | 13.88 | 105  | 4.0349          |
+| 4.1347        | 14.55 | 110  | 4.0310          |
+| 4.1606        | 15.21 | 115  | 4.0277          |
+| 4.1425        | 15.87 | 120  | 4.0255          |
+| 4.1289        | 16.53 | 125  | 4.0235          |
+| 4.126         | 17.19 | 130  | 4.0218          |
+| 4.1551        | 17.85 | 135  | 4.0209          |
+| 4.1567        | 18.51 | 140  | 4.0205          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

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": "4.34.1",
+  "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": "4.34.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2844817dcbdd93b37c723e95459353742cbefa1cc66d7996c04a80ea46992527
+size 242018838

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b1a129800d1b133606cfc5ca2a9b5d4a8b6326f1b1b22cc1debb3680238361f
+size 4600