Training in progress, step 100

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+base_model: Gayathri142214002/Question_Generation_ComQ_14
+tags:
+- generated_from_trainer
+model-index:
+- name: Question_Generation_ComQ_15
+  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. -->
+
+# Question_Generation_ComQ_15
+
+This model is a fine-tuned version of [Gayathri142214002/Question_Generation_ComQ_14](https://huggingface.co/Gayathri142214002/Question_Generation_ComQ_14) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2026
+
+## 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: 4
+- total_train_batch_size: 16
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.1656        | 0.79  | 100  | 0.1602          |
+| 0.1582        | 1.57  | 200  | 0.1739          |
+| 0.1532        | 2.36  | 300  | 0.1860          |
+| 0.1477        | 3.15  | 400  | 0.1880          |
+| 0.1426        | 3.94  | 500  | 0.1932          |
+| 0.1358        | 4.72  | 600  | 0.1990          |
+| 0.1389        | 5.51  | 700  | 0.1995          |
+| 0.1333        | 6.3   | 800  | 0.2026          |
+
+
+### Framework versions
+
+- Transformers 4.39.2
+- Pytorch 2.2.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "Gayathri142214002/Question_Generation_ComQ_15",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "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": "4.39.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

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": "4.39.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a9ff1aa5fea2a9ed30881033187c09a3121527296a98241b068b69ed3618b1
+size 891644712

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6294b890d15b5d33c6c6f5bdaea1e12d5c4d2f7ca613deb7bba992a180d926b4
+size 5048