End of training

all_results.json

@@ -1,18 +1,18 @@
 {
-    "epoch": 0.01,
-    "eval_gen_len": 54.246,
-    "eval_loss": 2.0983006954193115,
-    "eval_rouge1": 27.0694,
-    "eval_rouge2": 8.4785,
-    "eval_rougeL": 18.847,
-    "eval_rougeLsum": 23.5128,
-    "eval_runtime": 246.6118,
+    "epoch": 10.0,
+    "eval_gen_len": 52.79333333333334,
+    "eval_loss": 2.089439868927002,
+    "eval_rouge1": 27.2746,
+    "eval_rouge2": 8.6492,
+    "eval_rougeL": 19.2012,
+    "eval_rougeLsum": 23.6795,
+    "eval_runtime": 240.2925,
     "eval_samples": 1500,
-    "eval_samples_per_second": 6.082,
-    "eval_steps_per_second": 0.762,
-    "train_loss": 2.251833915710449,
-    "train_runtime": 10.4954,
+    "eval_samples_per_second": 6.242,
+    "eval_steps_per_second": 0.782,
+    "train_loss": 1.9915602294921875,
+    "train_runtime": 6202.8399,
     "train_samples": 7000,
-    "train_samples_per_second": 7.622,
-    "train_steps_per_second": 0.953
+    "train_samples_per_second": 11.285,
+    "train_steps_per_second": 1.411
 }

eval_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 0.01,
-    "eval_gen_len": 54.246,
-    "eval_loss": 2.0983006954193115,
-    "eval_rouge1": 27.0694,
-    "eval_rouge2": 8.4785,
-    "eval_rougeL": 18.847,
-    "eval_rougeLsum": 23.5128,
-    "eval_runtime": 246.6118,
+    "epoch": 10.0,
+    "eval_gen_len": 52.79333333333334,
+    "eval_loss": 2.089439868927002,
+    "eval_rouge1": 27.2746,
+    "eval_rouge2": 8.6492,
+    "eval_rougeL": 19.2012,
+    "eval_rougeLsum": 23.6795,
+    "eval_runtime": 240.2925,
     "eval_samples": 1500,
-    "eval_samples_per_second": 6.082,
-    "eval_steps_per_second": 0.762
+    "eval_samples_per_second": 6.242,
+    "eval_steps_per_second": 0.782
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 0.01,
-    "train_loss": 2.251833915710449,
-    "train_runtime": 10.4954,
+    "epoch": 10.0,
+    "train_loss": 1.9915602294921875,
+    "train_runtime": 6202.8399,
     "train_samples": 7000,
-    "train_samples_per_second": 7.622,
-    "train_steps_per_second": 0.953
+    "train_samples_per_second": 11.285,
+    "train_steps_per_second": 1.411
 }

trainer_state.json

@@ -1,25 +1,127 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011428571428571429,
-  "global_step": 10,
+  "epoch": 10.0,
+  "global_step": 8750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.01,
-      "step": 10,
-      "total_flos": 48716631244800.0,
-      "train_loss": 2.251833915710449,
-      "train_runtime": 10.4954,
-      "train_samples_per_second": 7.622,
-      "train_steps_per_second": 0.953
+      "epoch": 0.57,
+      "learning_rate": 4.714285714285714e-05,
+      "loss": 2.2723,
+      "step": 500
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 4.428571428571428e-05,
+      "loss": 2.2403,
+      "step": 1000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 4.1428571428571437e-05,
+      "loss": 2.1762,
+      "step": 1500
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 3.857142857142858e-05,
+      "loss": 2.1189,
+      "step": 2000
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 2.0971,
+      "step": 2500
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 3.285714285714286e-05,
+      "loss": 2.031,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3e-05,
+      "loss": 2.04,
+      "step": 3500
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 2.714285714285714e-05,
+      "loss": 1.9684,
+      "step": 4000
+    },
+    {
+      "epoch": 5.14,
+      "learning_rate": 2.4285714285714288e-05,
+      "loss": 1.9595,
+      "step": 4500
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 1.9248,
+      "step": 5000
+    },
+    {
+      "epoch": 6.29,
+      "learning_rate": 1.8571428571428572e-05,
+      "loss": 1.9309,
+      "step": 5500
+    },
+    {
+      "epoch": 6.86,
+      "learning_rate": 1.5714285714285715e-05,
+      "loss": 1.892,
+      "step": 6000
+    },
+    {
+      "epoch": 7.43,
+      "learning_rate": 1.2857142857142857e-05,
+      "loss": 1.8745,
+      "step": 6500
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 1e-05,
+      "loss": 1.8727,
+      "step": 7000
+    },
+    {
+      "epoch": 8.57,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 1.854,
+      "step": 7500
+    },
+    {
+      "epoch": 9.14,
+      "learning_rate": 4.285714285714286e-06,
+      "loss": 1.8427,
+      "step": 8000
+    },
+    {
+      "epoch": 9.71,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 1.8392,
+      "step": 8500
+    },
+    {
+      "epoch": 10.0,
+      "step": 8750,
+      "total_flos": 4.260908808142848e+16,
+      "train_loss": 1.9915602294921875,
+      "train_runtime": 6202.8399,
+      "train_samples_per_second": 11.285,
+      "train_steps_per_second": 1.411
     }
   ],
-  "max_steps": 10,
-  "num_train_epochs": 1,
-  "total_flos": 48716631244800.0,
+  "max_steps": 8750,
+  "num_train_epochs": 10,
+  "total_flos": 4.260908808142848e+16,
   "trial_name": null,
   "trial_params": null
 }