End of training

README.md

@@ -3,6 +3,8 @@ license: mit
 base_model: facebook/mbart-large-50
 tags:
 - generated_from_trainer
+datasets:
+- tiagoblima/qg_squad_v1_pt
 model-index:
 - name: mbart50-qg-aas
   results: []
@@ -13,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mbart50-qg-aas
 
-This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
+This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on the tiagoblima/qg_squad_v1_pt dataset.
 It achieves the following results on the evaluation set:
 - Loss: 5.1971
 

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 5.0,
     "eval_loss": 5.197052955627441,
-    "eval_runtime": 198.4096,
+    "eval_runtime": 198.6642,
     "eval_samples": 6327,
-    "eval_samples_per_second": 31.889,
-    "eval_steps_per_second": 7.973,
+    "eval_samples_per_second": 31.848,
+    "eval_steps_per_second": 7.963,
     "train_loss": 4.983092109755714,
-    "train_runtime": 9308.9617,
+    "train_runtime": 9355.0169,
     "train_samples": 51704,
-    "train_samples_per_second": 27.771,
-    "train_steps_per_second": 0.434
+    "train_samples_per_second": 27.634,
+    "train_steps_per_second": 0.432
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "eval_loss": 5.197052955627441,
-    "eval_runtime": 198.4096,
+    "eval_runtime": 198.6642,
     "eval_samples": 6327,
-    "eval_samples_per_second": 31.889,
-    "eval_steps_per_second": 7.973
+    "eval_samples_per_second": 31.848,
+    "eval_steps_per_second": 7.963
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "train_loss": 4.983092109755714,
-    "train_runtime": 9308.9617,
+    "train_runtime": 9355.0169,
     "train_samples": 51704,
-    "train_samples_per_second": 27.771,
-    "train_steps_per_second": 0.434
+    "train_samples_per_second": 27.634,
+    "train_steps_per_second": 0.432
 }

trainer_state.json

@@ -59,9 +59,9 @@
     {
       "epoch": 1.0,
       "eval_loss": 8.01647663116455,
-      "eval_runtime": 198.6559,
-      "eval_samples_per_second": 31.849,
-      "eval_steps_per_second": 7.964,
+      "eval_runtime": 198.4343,
+      "eval_samples_per_second": 31.885,
+      "eval_steps_per_second": 7.972,
       "step": 808
     },
     {
@@ -115,9 +115,9 @@
     {
       "epoch": 2.0,
       "eval_loss": 7.2192888259887695,
-      "eval_runtime": 198.5597,
-      "eval_samples_per_second": 31.864,
-      "eval_steps_per_second": 7.967,
+      "eval_runtime": 198.6961,
+      "eval_samples_per_second": 31.843,
+      "eval_steps_per_second": 7.962,
       "step": 1616
     },
     {
@@ -171,9 +171,9 @@
     {
       "epoch": 3.0,
       "eval_loss": 6.484571933746338,
-      "eval_runtime": 198.533,
-      "eval_samples_per_second": 31.869,
-      "eval_steps_per_second": 7.968,
+      "eval_runtime": 198.9778,
+      "eval_samples_per_second": 31.798,
+      "eval_steps_per_second": 7.951,
       "step": 2424
     },
     {
@@ -227,9 +227,9 @@
     {
       "epoch": 4.0,
       "eval_loss": 5.73320198059082,
-      "eval_runtime": 198.2238,
-      "eval_samples_per_second": 31.918,
-      "eval_steps_per_second": 7.981,
+      "eval_runtime": 198.6381,
+      "eval_samples_per_second": 31.852,
+      "eval_steps_per_second": 7.964,
       "step": 3232
     },
     {
@@ -283,9 +283,9 @@
     {
       "epoch": 5.0,
       "eval_loss": 5.197052955627441,
-      "eval_runtime": 198.3119,
-      "eval_samples_per_second": 31.904,
-      "eval_steps_per_second": 7.977,
+      "eval_runtime": 198.6931,
+      "eval_samples_per_second": 31.843,
+      "eval_steps_per_second": 7.962,
       "step": 4040
     },
     {
@@ -293,9 +293,9 @@
       "step": 4040,
       "total_flos": 3.6330926562607104e+17,
       "train_loss": 4.983092109755714,
-      "train_runtime": 9308.9617,
-      "train_samples_per_second": 27.771,
-      "train_steps_per_second": 0.434
+      "train_runtime": 9355.0169,
+      "train_samples_per_second": 27.634,
+      "train_steps_per_second": 0.432
     }
   ],
   "logging_steps": 100,