End of training

all_results.json

@@ -0,0 +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,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 6.082,
+    "eval_steps_per_second": 0.762,
+    "train_loss": 2.251833915710449,
+    "train_runtime": 10.4954,
+    "train_samples": 7000,
+    "train_samples_per_second": 7.622,
+    "train_steps_per_second": 0.953
+}

eval_results.json

@@ -0,0 +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,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 6.082,
+    "eval_steps_per_second": 0.762
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.01,
+    "train_loss": 2.251833915710449,
+    "train_runtime": 10.4954,
+    "train_samples": 7000,
+    "train_samples_per_second": 7.622,
+    "train_steps_per_second": 0.953
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.011428571428571429,
+  "global_step": 10,
+  "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
+    }
+  ],
+  "max_steps": 10,
+  "num_train_epochs": 1,
+  "total_flos": 48716631244800.0,
+  "trial_name": null,
+  "trial_params": null
+}