End of training

README.md

@@ -3,11 +3,23 @@ license: apache-2.0
 base_model: facebook/bart-large
 tags:
 - generated_from_trainer
+datasets:
+- learn3r/gov_report_memsum_oracle
 metrics:
 - rouge
 model-index:
 - name: bart_large_gov
-  results: []
+  results:
+  - task:
+      name: Summarization
+      type: summarization
+    dataset:
+      name: learn3r/gov_report_memsum_oracle
+      type: learn3r/gov_report_memsum_oracle
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 71.9948
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,14 +27,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bart_large_gov
 
-This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
+This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on the learn3r/gov_report_memsum_oracle dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4351
-- Rouge1: 72.0397
-- Rouge2: 40.9431
-- Rougel: 38.4161
-- Rougelsum: 69.5028
-- Gen Len: 744.4588
+- Loss: 1.4266
+- Rouge1: 71.9948
+- Rouge2: 41.0084
+- Rougel: 38.0938
+- Rougelsum: 69.4488
+- Gen Len: 751.0288
 
 ## Model description
 

all_results.json

@@ -1,18 +1,18 @@
 {
     "epoch": 19.94,
-    "eval_gen_len": 128.50617283950618,
-    "eval_loss": 1.445023536682129,
-    "eval_rouge1": 56.2783,
-    "eval_rouge2": 31.1387,
-    "eval_rougeL": 39.2121,
-    "eval_rougeLsum": 51.8068,
-    "eval_runtime": 214.343,
+    "eval_gen_len": 751.0288065843621,
+    "eval_loss": 1.4266291856765747,
+    "eval_rouge1": 71.9948,
+    "eval_rouge2": 41.0084,
+    "eval_rougeL": 38.0938,
+    "eval_rougeLsum": 69.4488,
+    "eval_runtime": 1649.8925,
     "eval_samples": 972,
-    "eval_samples_per_second": 4.535,
-    "eval_steps_per_second": 0.569,
-    "train_loss": 1.0796797680504182,
-    "train_runtime": 51892.12,
+    "eval_samples_per_second": 0.589,
+    "eval_steps_per_second": 0.074,
+    "train_loss": 1.4114765528370352,
+    "train_runtime": 122523.8715,
     "train_samples": 17457,
-    "train_samples_per_second": 6.728,
-    "train_steps_per_second": 0.052
+    "train_samples_per_second": 2.85,
+    "train_steps_per_second": 0.022
 }

eval_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 19.94,
-    "eval_gen_len": 128.50617283950618,
-    "eval_loss": 1.445023536682129,
-    "eval_rouge1": 56.2783,
-    "eval_rouge2": 31.1387,
-    "eval_rougeL": 39.2121,
-    "eval_rougeLsum": 51.8068,
-    "eval_runtime": 214.343,
+    "eval_gen_len": 751.0288065843621,
+    "eval_loss": 1.4266291856765747,
+    "eval_rouge1": 71.9948,
+    "eval_rouge2": 41.0084,
+    "eval_rougeL": 38.0938,
+    "eval_rougeLsum": 69.4488,
+    "eval_runtime": 1649.8925,
     "eval_samples": 972,
-    "eval_samples_per_second": 4.535,
-    "eval_steps_per_second": 0.569
+    "eval_samples_per_second": 0.589,
+    "eval_steps_per_second": 0.074
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 19.94,
-    "train_loss": 1.0796797680504182,
-    "train_runtime": 51892.12,
+    "train_loss": 1.4114765528370352,
+    "train_runtime": 122523.8715,
     "train_samples": 17457,
-    "train_samples_per_second": 6.728,
-    "train_steps_per_second": 0.052
+    "train_samples_per_second": 2.85,
+    "train_steps_per_second": 0.022
 }