End of training

README.md

@@ -3,11 +3,23 @@ license: apache-2.0
 base_model: google-t5/t5-base
 tags:
 - generated_from_trainer
+datasets:
+- fedora-copr/pep-sum
 metrics:
 - rouge
 model-index:
 - name: pep_summarization
-  results: []
+  results:
+  - task:
+      name: Summarization
+      type: summarization
+    dataset:
+      name: fedora-copr/pep-sum
+      type: fedora-copr/pep-sum
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 39.7591
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,7 +27,7 @@ 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.
 It achieves the following results on the evaluation set:
 - Loss: 0.9288
 - Rouge1: 39.7591

all_results.json

@@ -1,18 +1,18 @@
 {
     "epoch": 5.0,
-    "eval_gen_len": 62.05797101449275,
-    "eval_loss": 0.0359114333987236,
-    "eval_rouge1": 84.8601,
-    "eval_rouge2": 84.2185,
-    "eval_rougeL": 84.7842,
-    "eval_rougeLsum": 84.8657,
-    "eval_runtime": 9.4102,
+    "eval_gen_len": 68.04347826086956,
+    "eval_loss": 0.9288389682769775,
+    "eval_rouge1": 39.7591,
+    "eval_rouge2": 24.1983,
+    "eval_rougeL": 32.2869,
+    "eval_rougeLsum": 36.1493,
+    "eval_runtime": 9.8095,
     "eval_samples": 69,
-    "eval_samples_per_second": 7.332,
-    "eval_steps_per_second": 1.913,
-    "train_loss": 0.16054312664529552,
-    "train_runtime": 120.7301,
+    "eval_samples_per_second": 7.034,
+    "eval_steps_per_second": 1.835,
+    "train_loss": 0.8950336843297102,
+    "train_runtime": 114.301,
     "train_samples": 276,
-    "train_samples_per_second": 11.43,
-    "train_steps_per_second": 2.858
+    "train_samples_per_second": 12.073,
+    "train_steps_per_second": 3.018
 }

eval_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 5.0,
-    "eval_gen_len": 62.05797101449275,
-    "eval_loss": 0.0359114333987236,
-    "eval_rouge1": 84.8601,
-    "eval_rouge2": 84.2185,
-    "eval_rougeL": 84.7842,
-    "eval_rougeLsum": 84.8657,
-    "eval_runtime": 9.4102,
+    "eval_gen_len": 68.04347826086956,
+    "eval_loss": 0.9288389682769775,
+    "eval_rouge1": 39.7591,
+    "eval_rouge2": 24.1983,
+    "eval_rougeL": 32.2869,
+    "eval_rougeLsum": 36.1493,
+    "eval_runtime": 9.8095,
     "eval_samples": 69,
-    "eval_samples_per_second": 7.332,
-    "eval_steps_per_second": 1.913
+    "eval_samples_per_second": 7.034,
+    "eval_steps_per_second": 1.835
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
-    "train_loss": 0.16054312664529552,
-    "train_runtime": 120.7301,
+    "train_loss": 0.8950336843297102,
+    "train_runtime": 114.301,
     "train_samples": 276,
-    "train_samples_per_second": 11.43,
-    "train_steps_per_second": 2.858
+    "train_samples_per_second": 12.073,
+    "train_steps_per_second": 3.018
 }

trainer_state.json

@@ -10,77 +10,77 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_gen_len": 49.08695652173913,
-      "eval_loss": 0.2411632537841797,
-      "eval_rouge1": 74.9533,
-      "eval_rouge2": 71.1831,
-      "eval_rougeL": 74.2512,
-      "eval_rougeLsum": 74.5914,
-      "eval_runtime": 9.2355,
-      "eval_samples_per_second": 7.471,
-      "eval_steps_per_second": 1.949,
+      "eval_gen_len": 68.04347826086956,
+      "eval_loss": 0.9288747310638428,
+      "eval_rouge1": 39.7591,
+      "eval_rouge2": 24.1983,
+      "eval_rougeL": 32.2869,
+      "eval_rougeLsum": 36.1493,
+      "eval_runtime": 9.3009,
+      "eval_samples_per_second": 7.419,
+      "eval_steps_per_second": 1.935,
       "step": 69
     },
     {
       "epoch": 2.0,
-      "eval_gen_len": 88.17391304347827,
-      "eval_loss": 0.08010436594486237,
-      "eval_rouge1": 78.7144,
-      "eval_rouge2": 77.7186,
-      "eval_rougeL": 78.6962,
-      "eval_rougeLsum": 78.6452,
-      "eval_runtime": 11.7911,
-      "eval_samples_per_second": 5.852,
-      "eval_steps_per_second": 1.527,
+      "eval_gen_len": 68.04347826086956,
+      "eval_loss": 0.9288538694381714,
+      "eval_rouge1": 39.7591,
+      "eval_rouge2": 24.1983,
+      "eval_rougeL": 32.2869,
+      "eval_rougeLsum": 36.1493,
+      "eval_runtime": 9.2625,
+      "eval_samples_per_second": 7.449,
+      "eval_steps_per_second": 1.943,
       "step": 138
     },
     {
       "epoch": 3.0,
-      "eval_gen_len": 73.0,
-      "eval_loss": 0.08717019110918045,
-      "eval_rouge1": 83.0112,
-      "eval_rouge2": 82.1689,
-      "eval_rougeL": 82.8847,
-      "eval_rougeLsum": 82.9534,
-      "eval_runtime": 10.9663,
-      "eval_samples_per_second": 6.292,
-      "eval_steps_per_second": 1.641,
+      "eval_gen_len": 68.04347826086956,
+      "eval_loss": 0.9288433790206909,
+      "eval_rouge1": 39.7591,
+      "eval_rouge2": 24.1983,
+      "eval_rougeL": 32.2869,
+      "eval_rougeLsum": 36.1493,
+      "eval_runtime": 9.3044,
+      "eval_samples_per_second": 7.416,
+      "eval_steps_per_second": 1.935,
       "step": 207
     },
     {
       "epoch": 4.0,
-      "eval_gen_len": 60.88405797101449,
-      "eval_loss": 0.06106267869472504,
-      "eval_rouge1": 86.2191,
-      "eval_rouge2": 85.8311,
-      "eval_rougeL": 86.308,
-      "eval_rougeLsum": 86.4542,
-      "eval_runtime": 9.6061,
-      "eval_samples_per_second": 7.183,
-      "eval_steps_per_second": 1.874,
+      "eval_gen_len": 68.04347826086956,
+      "eval_loss": 0.9288394451141357,
+      "eval_rouge1": 39.7591,
+      "eval_rouge2": 24.1983,
+      "eval_rougeL": 32.2869,
+      "eval_rougeLsum": 36.1493,
+      "eval_runtime": 9.3367,
+      "eval_samples_per_second": 7.39,
+      "eval_steps_per_second": 1.928,
       "step": 276
     },
     {
       "epoch": 5.0,
-      "eval_gen_len": 62.05797101449275,
-      "eval_loss": 0.0359114333987236,
-      "eval_rouge1": 84.8601,
-      "eval_rouge2": 84.2185,
-      "eval_rougeL": 84.7842,
-      "eval_rougeLsum": 84.8657,
-      "eval_runtime": 9.6516,
-      "eval_samples_per_second": 7.149,
-      "eval_steps_per_second": 1.865,
+      "eval_gen_len": 68.04347826086956,
+      "eval_loss": 0.9288389682769775,
+      "eval_rouge1": 39.7591,
+      "eval_rouge2": 24.1983,
+      "eval_rougeL": 32.2869,
+      "eval_rougeLsum": 36.1493,
+      "eval_runtime": 9.2668,
+      "eval_samples_per_second": 7.446,
+      "eval_steps_per_second": 1.942,
       "step": 345
     },
     {
       "epoch": 5.0,
       "step": 345,
       "total_flos": 1680723777945600.0,
-      "train_loss": 0.16054312664529552,
-      "train_runtime": 120.7301,
-      "train_samples_per_second": 11.43,
-      "train_steps_per_second": 2.858
+      "train_loss": 0.8950336843297102,
+      "train_runtime": 114.301,
+      "train_samples_per_second": 12.073,
+      "train_steps_per_second": 3.018
     }
   ],
   "logging_steps": 500,