End of training

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: google-t5/t5-small
 tags:
 - generated_from_trainer
+metrics:
+- rouge
 model-index:
 - name: t5_confidential_masking
   results: []
@@ -15,6 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
 # t5_confidential_masking
 
 This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6940
+- Rouge1: 74.7713
+- Rouge2: 59.6864
+- Rougel: 74.4126
+- Rougelsum: 74.3867
+- Gen Len: 17.5891
 
 ## Model description
 

all_results.json

@@ -6,14 +6,14 @@
     "eval_rouge2": 59.6864,
     "eval_rougeL": 74.4126,
     "eval_rougeLsum": 74.3867,
-    "eval_runtime": 27.8192,
+    "eval_runtime": 28.0495,
     "eval_samples": 1750,
-    "eval_samples_per_second": 62.906,
-    "eval_steps_per_second": 3.954,
+    "eval_samples_per_second": 62.39,
+    "eval_steps_per_second": 3.922,
     "total_flos": 2757779000721408.0,
     "train_loss": 0.21498731050334993,
-    "train_runtime": 244.6028,
+    "train_runtime": 248.6198,
     "train_samples": 3902,
-    "train_samples_per_second": 398.81,
-    "train_steps_per_second": 12.469
+    "train_samples_per_second": 392.366,
+    "train_steps_per_second": 12.268
 }

eval_results.json

@@ -6,8 +6,8 @@
     "eval_rouge2": 59.6864,
     "eval_rougeL": 74.4126,
     "eval_rougeLsum": 74.3867,
-    "eval_runtime": 27.8192,
+    "eval_runtime": 28.0495,
     "eval_samples": 1750,
-    "eval_samples_per_second": 62.906,
-    "eval_steps_per_second": 3.954
+    "eval_samples_per_second": 62.39,
+    "eval_steps_per_second": 3.922
 }

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 25.0,
     "total_flos": 2757779000721408.0,
     "train_loss": 0.21498731050334993,
-    "train_runtime": 244.6028,
+    "train_runtime": 248.6198,
     "train_samples": 3902,
-    "train_samples_per_second": 398.81,
-    "train_steps_per_second": 12.469
+    "train_samples_per_second": 392.366,
+    "train_steps_per_second": 12.268
 }

trainer_state.json

@@ -55,9 +55,9 @@
       "step": 3050,
       "total_flos": 2757779000721408.0,
       "train_loss": 0.21498731050334993,
-      "train_runtime": 244.6028,
-      "train_samples_per_second": 398.81,
-      "train_steps_per_second": 12.469
+      "train_runtime": 248.6198,
+      "train_samples_per_second": 392.366,
+      "train_steps_per_second": 12.268
     }
   ],
   "logging_steps": 500,