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: 1.4560
 
 ## Model description
 

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 1.99,
     "eval_loss": 1.4559680223464966,
-    "eval_runtime": 73.9626,
+    "eval_runtime": 73.4318,
     "eval_samples": 8961,
-    "eval_samples_per_second": 121.156,
-    "eval_steps_per_second": 15.156,
+    "eval_samples_per_second": 122.032,
+    "eval_steps_per_second": 15.266,
     "train_loss": 0.0,
-    "train_runtime": 1.482,
+    "train_runtime": 1.4602,
     "train_samples": 52135,
-    "train_samples_per_second": 175892.181,
-    "train_steps_per_second": 2749.633
+    "train_samples_per_second": 178521.398,
+    "train_steps_per_second": 2790.734
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.99,
     "eval_loss": 1.4559680223464966,
-    "eval_runtime": 73.9626,
+    "eval_runtime": 73.4318,
     "eval_samples": 8961,
-    "eval_samples_per_second": 121.156,
-    "eval_steps_per_second": 15.156
+    "eval_samples_per_second": 122.032,
+    "eval_steps_per_second": 15.266
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.99,
     "train_loss": 0.0,
-    "train_runtime": 1.482,
+    "train_runtime": 1.4602,
     "train_samples": 52135,
-    "train_samples_per_second": 175892.181,
-    "train_steps_per_second": 2749.633
+    "train_samples_per_second": 178521.398,
+    "train_steps_per_second": 2790.734
 }

trainer_state.json

@@ -637,9 +637,9 @@
       "step": 52000,
       "total_flos": 1.0556660514816e+16,
       "train_loss": 0.0,
-      "train_runtime": 1.482,
-      "train_samples_per_second": 175892.181,
-      "train_steps_per_second": 2749.633
+      "train_runtime": 1.4602,
+      "train_samples_per_second": 178521.398,
+      "train_steps_per_second": 2790.734
     }
   ],
   "logging_steps": 500,