End of training

README.md

@@ -3,6 +3,8 @@ license: mit
 base_model: unicamp-dl/ptt5-small-t5-vocab
 tags:
 - generated_from_trainer
+datasets:
+- tiagoblima/qg_squad_v1_pt
 model-index:
 - name: t5_small-qg-ctx-a
   results: []
@@ -13,7 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # t5_small-qg-ctx-a
 
-This model is a fine-tuned version of [unicamp-dl/ptt5-small-t5-vocab](https://huggingface.co/unicamp-dl/ptt5-small-t5-vocab) on an unknown dataset.
+This model is a fine-tuned version of [unicamp-dl/ptt5-small-t5-vocab](https://huggingface.co/unicamp-dl/ptt5-small-t5-vocab) on the tiagoblima/qg_squad_v1_pt dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5839
 
 ## Model description
 

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 2.0,
     "eval_loss": 1.5838885307312012,
-    "eval_runtime": 78.2351,
+    "eval_runtime": 77.8366,
     "eval_samples": 8890,
-    "eval_samples_per_second": 113.632,
-    "eval_steps_per_second": 14.214,
+    "eval_samples_per_second": 114.214,
+    "eval_steps_per_second": 14.286,
     "train_loss": 1.563031800902716,
-    "train_runtime": 2367.9689,
+    "train_runtime": 2354.5427,
     "train_samples": 51704,
-    "train_samples_per_second": 43.669,
-    "train_steps_per_second": 0.682
+    "train_samples_per_second": 43.919,
+    "train_steps_per_second": 0.686
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.0,
     "eval_loss": 1.5838885307312012,
-    "eval_runtime": 78.2351,
+    "eval_runtime": 77.8366,
     "eval_samples": 8890,
-    "eval_samples_per_second": 113.632,
-    "eval_steps_per_second": 14.214
+    "eval_samples_per_second": 114.214,
+    "eval_steps_per_second": 14.286
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.0,
     "train_loss": 1.563031800902716,
-    "train_runtime": 2367.9689,
+    "train_runtime": 2354.5427,
     "train_samples": 51704,
-    "train_samples_per_second": 43.669,
-    "train_steps_per_second": 0.682
+    "train_samples_per_second": 43.919,
+    "train_steps_per_second": 0.686
 }

trainer_state.json

@@ -31,9 +31,9 @@
       "step": 1616,
       "total_flos": 1.0496568754962432e+16,
       "train_loss": 1.563031800902716,
-      "train_runtime": 2367.9689,
-      "train_samples_per_second": 43.669,
-      "train_steps_per_second": 0.682
+      "train_runtime": 2354.5427,
+      "train_samples_per_second": 43.919,
+      "train_steps_per_second": 0.686
     }
   ],
   "logging_steps": 500,