DiwasDiwas/t5-small-MedicoSummarizer

README.md

@@ -1,19 +1,28 @@
 ---
+license: apache-2.0
+base_model: t5-small
 tags:
-- generated_from_keras_callback
+- generated_from_trainer
+metrics:
+- rouge
 model-index:
 - name: t5-small-MedicoSummarizer
   results: []
 ---
 
-<!-- This model card has been generated automatically according to the information Keras had access to. You should
-probably proofread and complete it, then remove this comment. -->
+<!-- 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. -->
 
 # t5-small-MedicoSummarizer
 
-This model was trained from scratch on an unknown 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: 2.9721
+- Rouge1: 0.3222
+- Rouge2: 0.0728
+- Rougel: 0.1933
+- Rougelsum: 0.1932
+- Gen Len: 122.633
 
 ## Model description
 
@@ -32,16 +41,34 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: None
-- training_precision: float32
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+- mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
+| 3.4732        | 1.0   | 625  | 3.1206          | 0.295  | 0.0629 | 0.1743 | 0.1743    | 117.058 |
+| 3.2979        | 2.0   | 1250 | 3.0677          | 0.3031 | 0.0677 | 0.1821 | 0.1821    | 116.531 |
+| 3.2329        | 3.0   | 1875 | 3.0342          | 0.31   | 0.0696 | 0.1862 | 0.1861    | 119.239 |
+| 3.1848        | 4.0   | 2500 | 3.0100          | 0.3122 | 0.0699 | 0.186  | 0.1858    | 119.044 |
+| 3.1689        | 5.0   | 3125 | 2.9970          | 0.3188 | 0.0713 | 0.1908 | 0.1907    | 122.084 |
+| 3.153         | 6.0   | 3750 | 2.9855          | 0.3187 | 0.0703 | 0.1927 | 0.1926    | 122.33  |
+| 3.1564        | 7.0   | 4375 | 2.9801          | 0.32   | 0.0706 | 0.1929 | 0.1928    | 122.479 |
+| 3.136         | 8.0   | 5000 | 2.9747          | 0.3228 | 0.0727 | 0.1936 | 0.1935    | 122.804 |
+| 3.1248        | 9.0   | 5625 | 2.9726          | 0.321  | 0.0721 | 0.1926 | 0.1925    | 122.685 |
+| 3.1309        | 10.0  | 6250 | 2.9721          | 0.3222 | 0.0728 | 0.1933 | 0.1932    | 122.633 |
 
 
 ### Framework versions
 
 - Transformers 4.35.2
-- TensorFlow 2.14.0
+- Pytorch 2.1.0+cu118
 - Datasets 2.15.0
 - Tokenizers 0.15.0

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 10.0,
-    "eval_gen_len": 122.957,
-    "eval_loss": 2.9784293174743652,
-    "eval_rouge1": 0.326,
-    "eval_rouge2": 0.0772,
-    "eval_rougeL": 0.1955,
-    "eval_rougeLsum": 0.1956,
-    "eval_runtime": 166.3431,
-    "eval_samples_per_second": 6.012,
-    "eval_steps_per_second": 0.379
+    "eval_gen_len": 122.633,
+    "eval_loss": 2.972090721130371,
+    "eval_rouge1": 0.3222,
+    "eval_rouge2": 0.0728,
+    "eval_rougeL": 0.1933,
+    "eval_rougeLsum": 0.1932,
+    "eval_runtime": 169.7847,
+    "eval_samples_per_second": 5.89,
+    "eval_steps_per_second": 0.371
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e186e4cef0e63e5fe7ed9db4d33c4087561a9b79f66d9e481b9fa55cd65fad6a
-size 242041904
+oid sha256:49a8c9343f09310cec45c4402da19adfe439523c11c48479060997b3c3fd3671
+size 242041896

runs/Dec11_23-40-51_b90ba2bbe6f9/events.out.tfevents.1702338060.b90ba2bbe6f9.525.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41e7b2b658597a0f3073d63a2ba65874dc26a802ca17e482ee55e1cb341f8c1d
+size 12707

runs/Dec11_23-40-51_b90ba2bbe6f9/events.out.tfevents.1702345311.b90ba2bbe6f9.525.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d321670daf5a94dab32ddac03f025e02ad1a6e9ca1f897878daa8f7dc08674fd
+size 613

special_tokens_map.json

@@ -101,25 +101,7 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -931,12 +931,8 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
-  "max_length": 128,
   "model_max_length": 512,
   "pad_token": "<pad>",
-  "stride": 0,
   "tokenizer_class": "T5Tokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0427ff56d63b412706fb908700359a5bcb36d2f85207da5887b17e20650b185
-size 4728
+oid sha256:f1a30541da037788c1b3cb624e1eccd2d8c54b283a414f9fc1258837dec33647
+size 4856