ahmed792002/Finetuning_T5_HealthCare_Chatbot

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: t5-base
+base_model: t5-small
 tags:
 - generated_from_trainer
 model-index:
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Finetuning_T5_HealthCare_Chatbot
 
-This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
+This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2150
+- Loss: 0.1304
 
 ## Model description
 
@@ -41,17 +41,22 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 0.1708        | 1.0   | 5660  | 0.2271          |
-| 0.1558        | 2.0   | 11320 | 0.2192          |
-| 0.1454        | 3.0   | 16980 | 0.2166          |
-| 0.1445        | 4.0   | 22640 | 0.2154          |
-| 0.1456        | 5.0   | 28300 | 0.2150          |
+| 0.1198        | 1.0   | 5660  | 0.1464          |
+| 0.1098        | 2.0   | 11320 | 0.1402          |
+| 0.1032        | 3.0   | 16980 | 0.1373          |
+| 0.1016        | 4.0   | 22640 | 0.1349          |
+| 0.1019        | 5.0   | 28300 | 0.1331          |
+| 0.0972        | 6.0   | 33960 | 0.1321          |
+| 0.0964        | 7.0   | 39620 | 0.1313          |
+| 0.0947        | 8.0   | 45280 | 0.1308          |
+| 0.0959        | 9.0   | 50940 | 0.1305          |
+| 0.0933        | 10.0  | 56600 | 0.1304          |
 
 
 ### Framework versions

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "t5-base",
+  "_name_or_path": "t5-small",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 3072,
+  "d_ff": 2048,
   "d_kv": 64,
-  "d_model": 768,
+  "d_model": 512,
   "decoder_start_token_id": 0,
   "dense_act_fn": "relu",
   "dropout_rate": 0.1,
@@ -18,9 +18,9 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce93101ebcb8c414862489f6553f29d1d2be9aca5a18d5bfec819004f6d15e56
-size 891644712
+oid sha256:88dab67523a8bf081c9f424202f6e36f0a5aed56bded2f63b681d8f8fa9597b4
+size 242041896

runs/Dec17_12-28-34_9b798e091f23/events.out.tfevents.1734438516.9b798e091f23.23.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66238bdd22308cd246f0e390051ad1d357309b7b0fa03152b8d0383603868c08
+size 33219

tokenizer_config.json

@@ -928,11 +928,11 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
   "legacy": true,
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 512,
   "pad_token": "<pad>",
   "sp_model_kwargs": {},
   "tokenizer_class": "T5Tokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38b61d45ec9be7ea46453c176618bf9e92880a5ff44bb840e9a7972a87e80655
+oid sha256:0c1bb0920cf6c7b6fe5fad1c829ec1f476c5d037119f2ceb4b2beee0f4245927
 size 5304