End of training

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: google-t5/t5-small
 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-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset.
+This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on the fedora-copr/pep-sum dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 0.41447729351876794,
-    "train_runtime": 15.2738,
+    "epoch": 10.0,
+    "train_loss": 0.12154519965593842,
+    "train_runtime": 52.1406,
     "train_samples": 345,
-    "train_samples_per_second": 67.763,
-    "train_steps_per_second": 17.088
+    "train_samples_per_second": 66.167,
+    "train_steps_per_second": 16.686
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 0.41447729351876794,
-    "train_runtime": 15.2738,
+    "epoch": 10.0,
+    "train_loss": 0.12154519965593842,
+    "train_runtime": 52.1406,
     "train_samples": 345,
-    "train_samples_per_second": 67.763,
-    "train_steps_per_second": 17.088
+    "train_samples_per_second": 66.167,
+    "train_steps_per_second": 16.686
 }

trainer_state.json

@@ -1,29 +1,35 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 261,
+  "global_step": 870,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.0,
-      "step": 261,
-      "total_flos": 280157529047040.0,
-      "train_loss": 0.41447729351876794,
-      "train_runtime": 15.2738,
-      "train_samples_per_second": 67.763,
-      "train_steps_per_second": 17.088
+      "epoch": 5.75,
+      "learning_rate": 2.1264367816091954e-05,
+      "loss": 0.2109,
+      "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
     }
   ],
   "logging_steps": 500,
-  "max_steps": 261,
+  "max_steps": 870,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 280157529047040.0,
+  "total_flos": 933667048390656.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null