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": 2.0,
-    "eval_loss": 1.4559422731399536,
-    "eval_runtime": 78.5069,
+    "epoch": 1.99,
+    "eval_loss": 1.4559680223464966,
+    "eval_runtime": 73.9626,
     "eval_samples": 8961,
-    "eval_samples_per_second": 114.143,
-    "eval_steps_per_second": 14.279,
-    "train_loss": 1.3101274637649682,
-    "train_runtime": 7625.5065,
+    "eval_samples_per_second": 121.156,
+    "eval_steps_per_second": 15.156,
+    "train_loss": 0.0,
+    "train_runtime": 1.482,
     "train_samples": 52135,
-    "train_samples_per_second": 13.674,
-    "train_steps_per_second": 6.837
+    "train_samples_per_second": 175892.181,
+    "train_steps_per_second": 2749.633
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.0,
-    "eval_loss": 1.4559422731399536,
-    "eval_runtime": 78.5069,
+    "epoch": 1.99,
+    "eval_loss": 1.4559680223464966,
+    "eval_runtime": 73.9626,
     "eval_samples": 8961,
-    "eval_samples_per_second": 114.143,
-    "eval_steps_per_second": 14.279
+    "eval_samples_per_second": 121.156,
+    "eval_steps_per_second": 15.156
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.0,
-    "train_loss": 1.3101274637649682,
-    "train_runtime": 7625.5065,
+    "epoch": 1.99,
+    "train_loss": 0.0,
+    "train_runtime": 1.482,
     "train_samples": 52135,
-    "train_samples_per_second": 13.674,
-    "train_steps_per_second": 6.837
+    "train_samples_per_second": 175892.181,
+    "train_steps_per_second": 2749.633
 }

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9999616380550493,
+  "epoch": 1.9948211374316678,
   "eval_steps": 500,
-  "global_step": 52134,
+  "global_step": 52000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -633,20 +633,20 @@
       "step": 52000
     },
     {
-      "epoch": 2.0,
-      "step": 52134,
-      "total_flos": 1.0583864216911872e+16,
-      "train_loss": 1.3101274637649682,
-      "train_runtime": 7625.5065,
-      "train_samples_per_second": 13.674,
-      "train_steps_per_second": 6.837
+      "epoch": 1.99,
+      "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
     }
   ],
   "logging_steps": 500,
-  "max_steps": 52134,
-  "num_train_epochs": 2,
+  "max_steps": 4075,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1.0583864216911872e+16,
+  "total_flos": 1.0556660514816e+16,
   "trial_name": null,
   "trial_params": null
 }