End of training

README.md

@@ -3,6 +3,8 @@ license: mit
 library_name: peft
 tags:
 - generated_from_trainer
+datasets:
+- tiagoblima/qg_squad_v1_pt
 base_model: unicamp-dl/ptt5-large-t5-vocab
 model-index:
 - name: t5_large-qg-aap
@@ -14,7 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # t5_large-qg-aap
 
-This model is a fine-tuned version of [unicamp-dl/ptt5-large-t5-vocab](https://huggingface.co/unicamp-dl/ptt5-large-t5-vocab) on an unknown dataset.
+This model is a fine-tuned version of [unicamp-dl/ptt5-large-t5-vocab](https://huggingface.co/unicamp-dl/ptt5-large-t5-vocab) on the tiagoblima/qg_squad_v1_pt dataset.
+It achieves the following results on the evaluation set:
+- Loss: 9.9893
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 9.98930835723877,
+    "eval_runtime": 1084.569,
+    "eval_samples": 8869,
+    "eval_samples_per_second": 8.177,
+    "eval_steps_per_second": 4.089,
+    "train_loss": 8.507731522663985,
+    "train_runtime": 5914.0661,
+    "train_samples": 51704,
+    "train_samples_per_second": 8.743,
+    "train_steps_per_second": 0.068
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 9.98930835723877,
+    "eval_runtime": 1084.569,
+    "eval_samples": 8869,
+    "eval_samples_per_second": 8.177,
+    "eval_steps_per_second": 4.089
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 8.507731522663985,
+    "train_runtime": 5914.0661,
+    "train_samples": 51704,
+    "train_samples_per_second": 8.743,
+    "train_steps_per_second": 0.068
+}

trainer_state.json

@@ -0,0 +1,30 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 404,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "step": 404,
+      "total_flos": 8.815639295478989e+16,
+      "train_loss": 8.507731522663985,
+      "train_runtime": 5914.0661,
+      "train_samples_per_second": 8.743,
+      "train_steps_per_second": 0.068
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 404,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 8.815639295478989e+16,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}