End of training

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: facebook/bart-base
 tags:
 - generated_from_trainer
+datasets:
+- learn3r/gov_report_memsum_oracle
 model-index:
 - name: bart_memsum
   results: []
@@ -13,7 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bart_memsum
 
-This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
+This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the learn3r/gov_report_memsum_oracle dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7431
 
 ## Model description
 

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 9.96,
-    "eval_loss": 1.7506826566204836e-07,
-    "eval_runtime": 2.4534,
+    "eval_loss": 1.7430976629257202,
+    "eval_runtime": 16.7302,
     "eval_samples": 972,
-    "eval_samples_per_second": 396.186,
-    "eval_steps_per_second": 12.636,
-    "train_loss": 0.08629453677293734,
-    "train_runtime": 13279.1496,
+    "eval_samples_per_second": 58.099,
+    "eval_steps_per_second": 1.853,
+    "train_loss": 2.0321115493774413,
+    "train_runtime": 22233.3267,
     "train_samples": 17457,
-    "train_samples_per_second": 13.146,
-    "train_steps_per_second": 0.013
+    "train_samples_per_second": 7.852,
+    "train_steps_per_second": 0.008
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 9.96,
-    "eval_loss": 1.7506826566204836e-07,
-    "eval_runtime": 2.4534,
+    "eval_loss": 1.7430976629257202,
+    "eval_runtime": 16.7302,
     "eval_samples": 972,
-    "eval_samples_per_second": 396.186,
-    "eval_steps_per_second": 12.636
+    "eval_samples_per_second": 58.099,
+    "eval_steps_per_second": 1.853
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 9.96,
-    "train_loss": 0.08629453677293734,
-    "train_runtime": 13279.1496,
+    "train_loss": 2.0321115493774413,
+    "train_runtime": 22233.3267,
     "train_samples": 17457,
-    "train_samples_per_second": 13.146,
-    "train_steps_per_second": 0.013
+    "train_samples_per_second": 7.852,
+    "train_steps_per_second": 0.008
 }

trainer_state.json

@@ -10,118 +10,118 @@
     {
       "epoch": 0.59,
       "learning_rate": 0.00018823529411764707,
-      "loss": 1.4378,
+      "loss": 3.2221,
       "step": 10
     },
     {
       "epoch": 1.17,
       "learning_rate": 0.00017647058823529413,
-      "loss": 0.0123,
+      "loss": 2.3963,
       "step": 20
     },
     {
       "epoch": 1.76,
       "learning_rate": 0.0001647058823529412,
-      "loss": 0.0039,
+      "loss": 2.1803,
       "step": 30
     },
     {
       "epoch": 2.34,
       "learning_rate": 0.00015294117647058822,
-      "loss": 0.0014,
+      "loss": 2.0863,
       "step": 40
     },
     {
       "epoch": 2.93,
       "learning_rate": 0.0001411764705882353,
-      "loss": 0.0011,
+      "loss": 2.0213,
       "step": 50
     },
     {
       "epoch": 3.52,
       "learning_rate": 0.00012941176470588237,
-      "loss": 0.0042,
+      "loss": 1.9832,
       "step": 60
     },
     {
       "epoch": 4.1,
       "learning_rate": 0.00011764705882352942,
-      "loss": 0.0009,
+      "loss": 1.9548,
       "step": 70
     },
     {
       "epoch": 4.69,
       "learning_rate": 0.00010588235294117647,
-      "loss": 0.0011,
+      "loss": 1.9278,
       "step": 80
     },
     {
       "epoch": 5.27,
       "learning_rate": 9.411764705882353e-05,
-      "loss": 0.0013,
+      "loss": 1.908,
       "step": 90
     },
     {
       "epoch": 5.86,
       "learning_rate": 8.23529411764706e-05,
-      "loss": 0.0009,
+      "loss": 1.8947,
       "step": 100
     },
     {
       "epoch": 6.45,
       "learning_rate": 7.058823529411765e-05,
-      "loss": 0.0003,
+      "loss": 1.8833,
       "step": 110
     },
     {
       "epoch": 7.03,
       "learning_rate": 5.882352941176471e-05,
-      "loss": 0.0006,
+      "loss": 1.8635,
       "step": 120
     },
     {
       "epoch": 7.62,
       "learning_rate": 4.705882352941177e-05,
-      "loss": 0.0004,
+      "loss": 1.8532,
       "step": 130
     },
     {
       "epoch": 8.21,
       "learning_rate": 3.529411764705883e-05,
-      "loss": 0.0005,
+      "loss": 1.8499,
       "step": 140
     },
     {
       "epoch": 8.79,
       "learning_rate": 2.3529411764705884e-05,
-      "loss": 0.0001,
+      "loss": 1.8394,
       "step": 150
     },
     {
       "epoch": 9.38,
       "learning_rate": 1.1764705882352942e-05,
-      "loss": 0.0002,
+      "loss": 1.8459,
       "step": 160
     },
     {
       "epoch": 9.96,
       "learning_rate": 0.0,
-      "loss": 0.0001,
+      "loss": 1.8359,
       "step": 170
     },
     {
       "epoch": 9.96,
       "step": 170,
-      "total_flos": 1359589640048640.0,
-      "train_loss": 0.08629453677293734,
-      "train_runtime": 13279.1496,
-      "train_samples_per_second": 13.146,
-      "train_steps_per_second": 0.013
+      "total_flos": 1.059141821617152e+17,
+      "train_loss": 2.0321115493774413,
+      "train_runtime": 22233.3267,
+      "train_samples_per_second": 7.852,
+      "train_steps_per_second": 0.008
     }
   ],
   "max_steps": 170,
   "num_train_epochs": 10,
-  "total_flos": 1359589640048640.0,
+  "total_flos": 1.059141821617152e+17,
   "trial_name": null,
   "trial_params": null
 }