End of training

README.md

@@ -1,9 +1,8 @@
 ---
 license: apache-2.0
-base_model: google/flan-t5-small
+base_model: t5-small
 tags:
 - generated_from_trainer
-library_name: peft
 model-index:
 - name: indian-constitution-qa
   results: []
@@ -14,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # indian-constitution-qa
 
-This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the Dhiraj223/IndianConstitutionData dataset.
+This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the Dhiraj223/IndianConstitutionData dataset.
 
 ## Model description
 
@@ -33,13 +32,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 0.001
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 8
+- num_epochs: 10
 
 ### Training results
 
@@ -47,8 +46,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.7.1
 - Transformers 4.36.2
 - Pytorch 2.5.1+cu121
 - Datasets 2.15.0
-- Tokenizers 0.15.2
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "t5-small",
+  "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": 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": "4.36.2",
+  "use_cache": false,
+  "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": "4.36.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cae9cff9190c431964879861324639a8c26186fc07c1cd1976bbfd62bef76a95
+size 242041896

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c101e3c4223da2a18d639ab84aebb09086d318f2ad8e71e4d5af8f92e37e9231
+oid sha256:5695a58371290a31ff02b079af50492e6518200f0d57b1029e4e9bb72e68fb54
 size 4856