End of training

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: facebook/bart-base
 tags:
 - generated_from_trainer
+datasets:
+- learn3r/summ_screen_fd_bp
 model-index:
 - name: summ_screen_fd_blueprint_epoch_10
   results: []
@@ -13,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # summ_screen_fd_blueprint_epoch_10
 
-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/summ_screen_fd_bp dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.0208
 

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 9.74,
-    "eval_loss": 1.9589176177978516,
-    "eval_runtime": 2.869,
+    "eval_loss": 2.020766019821167,
+    "eval_runtime": 3.1026,
     "eval_samples": 338,
-    "eval_samples_per_second": 117.812,
-    "eval_steps_per_second": 14.988,
-    "train_loss": 2.299447972433908,
-    "train_runtime": 1088.9846,
+    "eval_samples_per_second": 108.941,
+    "eval_steps_per_second": 13.859,
+    "train_loss": 2.210656370435442,
+    "train_runtime": 1086.7433,
     "train_samples": 3673,
-    "train_samples_per_second": 33.729,
+    "train_samples_per_second": 33.798,
     "train_steps_per_second": 0.129
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 9.74,
-    "eval_loss": 1.9589176177978516,
-    "eval_runtime": 2.869,
+    "eval_loss": 2.020766019821167,
+    "eval_runtime": 3.1026,
     "eval_samples": 338,
-    "eval_samples_per_second": 117.812,
-    "eval_steps_per_second": 14.988
+    "eval_samples_per_second": 108.941,
+    "eval_steps_per_second": 13.859
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 9.74,
-    "train_loss": 2.299447972433908,
-    "train_runtime": 1088.9846,
+    "train_loss": 2.210656370435442,
+    "train_runtime": 1086.7433,
     "train_samples": 3673,
-    "train_samples_per_second": 33.729,
+    "train_samples_per_second": 33.798,
     "train_steps_per_second": 0.129
 }

trainer_state.json

@@ -10,174 +10,174 @@
     {
       "epoch": 0.7,
       "learning_rate": 9.285714285714286e-05,
-      "loss": 3.519,
+      "loss": 3.382,
       "step": 10
     },
     {
       "epoch": 0.97,
-      "eval_loss": 2.3055925369262695,
-      "eval_runtime": 3.071,
-      "eval_samples_per_second": 110.064,
-      "eval_steps_per_second": 14.002,
+      "eval_loss": 2.3120291233062744,
+      "eval_runtime": 3.0033,
+      "eval_samples_per_second": 112.543,
+      "eval_steps_per_second": 14.318,
       "step": 14
     },
     {
       "epoch": 1.39,
       "learning_rate": 8.571428571428571e-05,
-      "loss": 2.6644,
+      "loss": 2.5354,
       "step": 20
     },
     {
       "epoch": 1.95,
-      "eval_loss": 2.1348636150360107,
-      "eval_runtime": 2.9701,
-      "eval_samples_per_second": 113.801,
-      "eval_steps_per_second": 14.478,
+      "eval_loss": 2.1625144481658936,
+      "eval_runtime": 2.8876,
+      "eval_samples_per_second": 117.052,
+      "eval_steps_per_second": 14.891,
       "step": 28
     },
     {
       "epoch": 2.09,
       "learning_rate": 7.857142857142858e-05,
-      "loss": 2.465,
+      "loss": 2.3745,
       "step": 30
     },
     {
       "epoch": 2.78,
       "learning_rate": 7.142857142857143e-05,
-      "loss": 2.3418,
+      "loss": 2.2504,
       "step": 40
     },
     {
       "epoch": 2.99,
-      "eval_loss": 2.0616259574890137,
-      "eval_runtime": 2.731,
-      "eval_samples_per_second": 123.764,
-      "eval_steps_per_second": 15.745,
+      "eval_loss": 2.103144645690918,
+      "eval_runtime": 2.866,
+      "eval_samples_per_second": 117.932,
+      "eval_steps_per_second": 15.003,
       "step": 43
     },
     {
       "epoch": 3.48,
       "learning_rate": 6.428571428571429e-05,
-      "loss": 2.258,
+      "loss": 2.1809,
       "step": 50
     },
     {
       "epoch": 3.97,
-      "eval_loss": 2.035996913909912,
-      "eval_runtime": 2.9612,
-      "eval_samples_per_second": 114.144,
-      "eval_steps_per_second": 14.521,
+      "eval_loss": 2.0733468532562256,
+      "eval_runtime": 2.6867,
+      "eval_samples_per_second": 125.803,
+      "eval_steps_per_second": 16.005,
       "step": 57
     },
     {
       "epoch": 4.17,
       "learning_rate": 5.714285714285714e-05,
-      "loss": 2.2166,
+      "loss": 2.1339,
       "step": 60
     },
     {
       "epoch": 4.87,
       "learning_rate": 5e-05,
-      "loss": 2.169,
+      "loss": 2.0889,
       "step": 70
     },
     {
       "epoch": 4.94,
-      "eval_loss": 1.9996529817581177,
-      "eval_runtime": 2.9471,
-      "eval_samples_per_second": 114.69,
-      "eval_steps_per_second": 14.591,
+      "eval_loss": 2.0512640476226807,
+      "eval_runtime": 2.8196,
+      "eval_samples_per_second": 119.875,
+      "eval_steps_per_second": 15.25,
       "step": 71
     },
     {
       "epoch": 5.57,
       "learning_rate": 4.2857142857142856e-05,
-      "loss": 2.1336,
+      "loss": 2.0586,
       "step": 80
     },
     {
       "epoch": 5.98,
-      "eval_loss": 1.986232042312622,
-      "eval_runtime": 2.9637,
-      "eval_samples_per_second": 114.046,
-      "eval_steps_per_second": 14.509,
+      "eval_loss": 2.0358786582946777,
+      "eval_runtime": 2.6297,
+      "eval_samples_per_second": 128.531,
+      "eval_steps_per_second": 16.352,
       "step": 86
     },
     {
       "epoch": 6.26,
       "learning_rate": 3.571428571428572e-05,
-      "loss": 2.1131,
+      "loss": 2.0399,
       "step": 90
     },
     {
       "epoch": 6.96,
       "learning_rate": 2.857142857142857e-05,
-      "loss": 2.0952,
+      "loss": 2.0117,
       "step": 100
     },
     {
       "epoch": 6.96,
-      "eval_loss": 1.9753971099853516,
-      "eval_runtime": 2.8395,
-      "eval_samples_per_second": 119.034,
-      "eval_steps_per_second": 15.143,
+      "eval_loss": 2.032505750656128,
+      "eval_runtime": 3.3953,
+      "eval_samples_per_second": 99.549,
+      "eval_steps_per_second": 12.665,
       "step": 100
     },
     {
       "epoch": 7.65,
       "learning_rate": 2.1428571428571428e-05,
-      "loss": 2.0666,
+      "loss": 1.9849,
       "step": 110
     },
     {
       "epoch": 8.0,
-      "eval_loss": 1.9659732580184937,
-      "eval_runtime": 2.7307,
-      "eval_samples_per_second": 123.779,
-      "eval_steps_per_second": 15.747,
+      "eval_loss": 2.025442600250244,
+      "eval_runtime": 3.0905,
+      "eval_samples_per_second": 109.368,
+      "eval_steps_per_second": 13.914,
       "step": 115
     },
     {
       "epoch": 8.35,
       "learning_rate": 1.4285714285714285e-05,
-      "loss": 2.0563,
+      "loss": 1.9803,
       "step": 120
     },
     {
       "epoch": 8.97,
-      "eval_loss": 1.9610240459442139,
-      "eval_runtime": 2.8488,
-      "eval_samples_per_second": 118.648,
-      "eval_steps_per_second": 15.094,
+      "eval_loss": 2.0218234062194824,
+      "eval_runtime": 3.3517,
+      "eval_samples_per_second": 100.846,
+      "eval_steps_per_second": 12.829,
       "step": 129
     },
     {
       "epoch": 9.04,
       "learning_rate": 7.142857142857143e-06,
-      "loss": 2.051,
+      "loss": 1.9694,
       "step": 130
     },
     {
       "epoch": 9.74,
       "learning_rate": 0.0,
-      "loss": 2.0426,
+      "loss": 1.9584,
       "step": 140
     },
     {
       "epoch": 9.74,
-      "eval_loss": 1.9589176177978516,
-      "eval_runtime": 2.9503,
-      "eval_samples_per_second": 114.564,
-      "eval_steps_per_second": 14.575,
+      "eval_loss": 2.020766019821167,
+      "eval_runtime": 2.8283,
+      "eval_samples_per_second": 119.505,
+      "eval_steps_per_second": 15.203,
       "step": 140
     },
     {
       "epoch": 9.74,
       "step": 140,
       "total_flos": 2.181454126645248e+16,
-      "train_loss": 2.299447972433908,
-      "train_runtime": 1088.9846,
-      "train_samples_per_second": 33.729,
+      "train_loss": 2.210656370435442,
+      "train_runtime": 1086.7433,
+      "train_samples_per_second": 33.798,
       "train_steps_per_second": 0.129
     }
   ],