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: 1.9589
 

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 9.74,
-    "eval_loss": 1.9205037355422974,
-    "eval_runtime": 2.0094,
+    "eval_loss": 1.9589176177978516,
+    "eval_runtime": 2.869,
     "eval_samples": 338,
-    "eval_samples_per_second": 168.21,
-    "eval_steps_per_second": 21.4,
-    "train_loss": 2.1082653863089424,
-    "train_runtime": 679.206,
+    "eval_samples_per_second": 117.812,
+    "eval_steps_per_second": 14.988,
+    "train_loss": 2.299447972433908,
+    "train_runtime": 1088.9846,
     "train_samples": 3673,
-    "train_samples_per_second": 54.078,
-    "train_steps_per_second": 0.206
+    "train_samples_per_second": 33.729,
+    "train_steps_per_second": 0.129
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 9.74,
-    "eval_loss": 1.9205037355422974,
-    "eval_runtime": 2.0094,
+    "eval_loss": 1.9589176177978516,
+    "eval_runtime": 2.869,
     "eval_samples": 338,
-    "eval_samples_per_second": 168.21,
-    "eval_steps_per_second": 21.4
+    "eval_samples_per_second": 117.812,
+    "eval_steps_per_second": 14.988
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 9.74,
-    "train_loss": 2.1082653863089424,
-    "train_runtime": 679.206,
+    "train_loss": 2.299447972433908,
+    "train_runtime": 1088.9846,
     "train_samples": 3673,
-    "train_samples_per_second": 54.078,
-    "train_steps_per_second": 0.206
+    "train_samples_per_second": 33.729,
+    "train_steps_per_second": 0.129
 }

trainer_state.json

@@ -10,175 +10,175 @@
     {
       "epoch": 0.7,
       "learning_rate": 9.285714285714286e-05,
-      "loss": 3.3723,
+      "loss": 3.519,
       "step": 10
     },
     {
       "epoch": 0.97,
-      "eval_loss": 2.261305332183838,
-      "eval_runtime": 1.7879,
-      "eval_samples_per_second": 189.047,
-      "eval_steps_per_second": 24.05,
+      "eval_loss": 2.3055925369262695,
+      "eval_runtime": 3.071,
+      "eval_samples_per_second": 110.064,
+      "eval_steps_per_second": 14.002,
       "step": 14
     },
     {
       "epoch": 1.39,
-      "learning_rate": 8.642857142857143e-05,
-      "loss": 2.4888,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 2.6644,
       "step": 20
     },
     {
       "epoch": 1.95,
-      "eval_loss": 2.087858200073242,
-      "eval_runtime": 1.8469,
-      "eval_samples_per_second": 183.011,
-      "eval_steps_per_second": 23.283,
+      "eval_loss": 2.1348636150360107,
+      "eval_runtime": 2.9701,
+      "eval_samples_per_second": 113.801,
+      "eval_steps_per_second": 14.478,
       "step": 28
     },
     {
       "epoch": 2.09,
-      "learning_rate": 7.928571428571429e-05,
-      "loss": 2.3065,
+      "learning_rate": 7.857142857142858e-05,
+      "loss": 2.465,
       "step": 30
     },
     {
       "epoch": 2.78,
-      "learning_rate": 7.214285714285714e-05,
-      "loss": 2.1694,
+      "learning_rate": 7.142857142857143e-05,
+      "loss": 2.3418,
       "step": 40
     },
     {
       "epoch": 2.99,
-      "eval_loss": 2.0183253288269043,
-      "eval_runtime": 1.7709,
-      "eval_samples_per_second": 190.86,
-      "eval_steps_per_second": 24.281,
+      "eval_loss": 2.0616259574890137,
+      "eval_runtime": 2.731,
+      "eval_samples_per_second": 123.764,
+      "eval_steps_per_second": 15.745,
       "step": 43
     },
     {
       "epoch": 3.48,
-      "learning_rate": 6.500000000000001e-05,
-      "loss": 2.0846,
+      "learning_rate": 6.428571428571429e-05,
+      "loss": 2.258,
       "step": 50
     },
     {
       "epoch": 3.97,
-      "eval_loss": 1.983121395111084,
-      "eval_runtime": 1.724,
-      "eval_samples_per_second": 196.056,
-      "eval_steps_per_second": 24.942,
+      "eval_loss": 2.035996913909912,
+      "eval_runtime": 2.9612,
+      "eval_samples_per_second": 114.144,
+      "eval_steps_per_second": 14.521,
       "step": 57
     },
     {
       "epoch": 4.17,
-      "learning_rate": 5.785714285714287e-05,
-      "loss": 2.026,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 2.2166,
       "step": 60
     },
     {
       "epoch": 4.87,
-      "learning_rate": 5.0714285714285716e-05,
-      "loss": 1.9812,
+      "learning_rate": 5e-05,
+      "loss": 2.169,
       "step": 70
     },
     {
       "epoch": 4.94,
-      "eval_loss": 1.9576869010925293,
-      "eval_runtime": 2.058,
-      "eval_samples_per_second": 164.239,
-      "eval_steps_per_second": 20.894,
+      "eval_loss": 1.9996529817581177,
+      "eval_runtime": 2.9471,
+      "eval_samples_per_second": 114.69,
+      "eval_steps_per_second": 14.591,
       "step": 71
     },
     {
       "epoch": 5.57,
-      "learning_rate": 4.3571428571428576e-05,
-      "loss": 1.9352,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 2.1336,
       "step": 80
     },
     {
       "epoch": 5.98,
-      "eval_loss": 1.9370218515396118,
-      "eval_runtime": 1.7855,
-      "eval_samples_per_second": 189.305,
-      "eval_steps_per_second": 24.083,
+      "eval_loss": 1.986232042312622,
+      "eval_runtime": 2.9637,
+      "eval_samples_per_second": 114.046,
+      "eval_steps_per_second": 14.509,
       "step": 86
     },
     {
       "epoch": 6.26,
-      "learning_rate": 3.642857142857143e-05,
-      "loss": 1.9164,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 2.1131,
       "step": 90
     },
     {
       "epoch": 6.96,
-      "learning_rate": 2.9285714285714288e-05,
-      "loss": 1.8822,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 2.0952,
       "step": 100
     },
     {
       "epoch": 6.96,
-      "eval_loss": 1.9341849088668823,
-      "eval_runtime": 1.8263,
-      "eval_samples_per_second": 185.074,
-      "eval_steps_per_second": 23.545,
+      "eval_loss": 1.9753971099853516,
+      "eval_runtime": 2.8395,
+      "eval_samples_per_second": 119.034,
+      "eval_steps_per_second": 15.143,
       "step": 100
     },
     {
       "epoch": 7.65,
-      "learning_rate": 2.214285714285714e-05,
-      "loss": 1.853,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 2.0666,
       "step": 110
     },
     {
       "epoch": 8.0,
-      "eval_loss": 1.9238194227218628,
-      "eval_runtime": 1.8358,
-      "eval_samples_per_second": 184.114,
-      "eval_steps_per_second": 23.423,
+      "eval_loss": 1.9659732580184937,
+      "eval_runtime": 2.7307,
+      "eval_samples_per_second": 123.779,
+      "eval_steps_per_second": 15.747,
       "step": 115
     },
     {
       "epoch": 8.35,
-      "learning_rate": 1.5e-05,
-      "loss": 1.8446,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 2.0563,
       "step": 120
     },
     {
       "epoch": 8.97,
-      "eval_loss": 1.9229856729507446,
-      "eval_runtime": 1.8246,
-      "eval_samples_per_second": 185.25,
-      "eval_steps_per_second": 23.567,
+      "eval_loss": 1.9610240459442139,
+      "eval_runtime": 2.8488,
+      "eval_samples_per_second": 118.648,
+      "eval_steps_per_second": 15.094,
       "step": 129
     },
     {
       "epoch": 9.04,
-      "learning_rate": 7.857142857142858e-06,
-      "loss": 1.8343,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 2.051,
       "step": 130
     },
     {
       "epoch": 9.74,
-      "learning_rate": 7.142857142857143e-07,
-      "loss": 1.8211,
+      "learning_rate": 0.0,
+      "loss": 2.0426,
       "step": 140
     },
     {
       "epoch": 9.74,
-      "eval_loss": 1.9205037355422974,
-      "eval_runtime": 1.9363,
-      "eval_samples_per_second": 174.556,
-      "eval_steps_per_second": 22.207,
+      "eval_loss": 1.9589176177978516,
+      "eval_runtime": 2.9503,
+      "eval_samples_per_second": 114.564,
+      "eval_steps_per_second": 14.575,
       "step": 140
     },
     {
       "epoch": 9.74,
       "step": 140,
       "total_flos": 2.181454126645248e+16,
-      "train_loss": 2.1082653863089424,
-      "train_runtime": 679.206,
-      "train_samples_per_second": 54.078,
-      "train_steps_per_second": 0.206
+      "train_loss": 2.299447972433908,
+      "train_runtime": 1088.9846,
+      "train_samples_per_second": 33.729,
+      "train_steps_per_second": 0.129
     }
   ],
   "max_steps": 140,