End of training

README.md

@@ -3,6 +3,8 @@ license: mit
 base_model: unicamp-dl/ptt5-base-t5-vocab
 tags:
 - generated_from_trainer
+datasets:
+- tiagoblima/qg_squad_v1_pt
 model-index:
 - name: debug_t5-base_squad
   results: []
@@ -13,7 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # debug_t5-base_squad
 
-This model is a fine-tuned version of [unicamp-dl/ptt5-base-t5-vocab](https://huggingface.co/unicamp-dl/ptt5-base-t5-vocab) on an unknown dataset.
+This model is a fine-tuned version of [unicamp-dl/ptt5-base-t5-vocab](https://huggingface.co/unicamp-dl/ptt5-base-t5-vocab) on the tiagoblima/qg_squad_v1_pt dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3438
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 1.3437808752059937,
+    "eval_runtime": 396.9308,
+    "eval_samples": 14945,
+    "eval_samples_per_second": 37.651,
+    "eval_steps_per_second": 2.356,
+    "train_loss": 1.1475538333198987,
+    "train_runtime": 10232.2752,
+    "train_samples": 87599,
+    "train_samples_per_second": 17.122,
+    "train_steps_per_second": 0.535
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 1.3437808752059937,
+    "eval_runtime": 396.9308,
+    "eval_samples": 14945,
+    "eval_samples_per_second": 37.651,
+    "eval_steps_per_second": 2.356
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af088933a074ff531639886a2737d5a42b01ba8d6b59632036477161a80b2429
+oid sha256:0c690ab26e7e3620fca848ca50d538fee3fede5fc9e95b4ec98baf4564cb7af2
 size 891644712

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 1.1475538333198987,
+    "train_runtime": 10232.2752,
+    "train_samples": 87599,
+    "train_samples_per_second": 17.122,
+    "train_steps_per_second": 0.535
+}

trainer_state.json

@@ -0,0 +1,88 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 5476,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.086924762600438e-05,
+      "loss": 1.4977,
+      "step": 500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 8.173849525200878e-05,
+      "loss": 1.2444,
+      "step": 1000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 7.260774287801315e-05,
+      "loss": 1.1926,
+      "step": 1500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 6.347699050401752e-05,
+      "loss": 1.1644,
+      "step": 2000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.434623813002192e-05,
+      "loss": 1.1414,
+      "step": 2500
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 4.52154857560263e-05,
+      "loss": 1.0927,
+      "step": 3000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 3.6084733382030684e-05,
+      "loss": 1.0721,
+      "step": 3500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 2.695398100803506e-05,
+      "loss": 1.0598,
+      "step": 4000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.7823228634039447e-05,
+      "loss": 1.0517,
+      "step": 4500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 8.692476260043827e-06,
+      "loss": 1.0524,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "step": 5476,
+      "total_flos": 8.001615338274816e+16,
+      "train_loss": 1.1475538333198987,
+      "train_runtime": 10232.2752,
+      "train_samples_per_second": 17.122,
+      "train_steps_per_second": 0.535
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5476,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 8.001615338274816e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37ec252aad0dbe1da31ad9046d1b45a8346d9a6b65263697586e27f62c199221
-size 4792
+oid sha256:65b47c6dde5ddcd8ab1748fc10708895c324939d1e9b5c2ef274486c5e6aea3e
+size 4347