End of training

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: google-t5/t5-base
 tags:
 - generated_from_trainer
+datasets:
+- fedora-copr/pep-sum
 model-index:
 - name: pep_summarization
   results: []
@@ -13,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # pep_summarization
 
-This model is a fine-tuned version of [google-t5/t5-base](https://huggingface.co/google-t5/t5-base) on an unknown dataset.
+This model is a fine-tuned version of [google-t5/t5-base](https://huggingface.co/google-t5/t5-base) on the fedora-copr/pep-sum dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
-    "train_loss": 0.12154519965593842,
-    "train_runtime": 52.1406,
+    "train_loss": 0.06454240335686796,
+    "train_runtime": 163.8058,
     "train_samples": 345,
-    "train_samples_per_second": 66.167,
-    "train_steps_per_second": 16.686
+    "train_samples_per_second": 21.062,
+    "train_steps_per_second": 5.311
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
-    "train_loss": 0.12154519965593842,
-    "train_runtime": 52.1406,
+    "train_loss": 0.06454240335686796,
+    "train_runtime": 163.8058,
     "train_samples": 345,
-    "train_samples_per_second": 66.167,
-    "train_steps_per_second": 16.686
+    "train_samples_per_second": 21.062,
+    "train_steps_per_second": 5.311
 }

trainer_state.json

@@ -11,17 +11,17 @@
     {
       "epoch": 5.75,
       "learning_rate": 2.1264367816091954e-05,
-      "loss": 0.2109,
+      "loss": 0.1123,
       "step": 500
     },
     {
       "epoch": 10.0,
       "step": 870,
-      "total_flos": 933667048390656.0,
-      "train_loss": 0.12154519965593842,
-      "train_runtime": 52.1406,
-      "train_samples_per_second": 66.167,
-      "train_steps_per_second": 16.686
+      "total_flos": 4200948340346880.0,
+      "train_loss": 0.06454240335686796,
+      "train_runtime": 163.8058,
+      "train_samples_per_second": 21.062,
+      "train_steps_per_second": 5.311
     }
   ],
   "logging_steps": 500,
@@ -29,7 +29,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 933667048390656.0,
+  "total_flos": 4200948340346880.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null