QuickRead/fine-tune-Pegasus

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 1.0,
+    "eval_gen_len": 67.0552,
+    "eval_loss": 2.324213981628418,
+    "eval_rouge1": 17.993,
+    "eval_rouge2": 2.9392,
+    "eval_rougeL": 12.313,
+    "eval_rougeLsum": 13.3091,
+    "eval_runtime": 7752.5256,
+    "eval_samples": 11332,
+    "eval_samples_per_second": 1.462,
+    "eval_steps_per_second": 0.183,
+    "train_loss": 2.7845563131665427,
+    "train_runtime": 39.3075,
+    "train_samples": 500,
+    "train_samples_per_second": 12.72,
+    "train_steps_per_second": 1.603
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_gen_len": 67.0552,
+    "eval_loss": 2.324213981628418,
+    "eval_rouge1": 17.993,
+    "eval_rouge2": 2.9392,
+    "eval_rougeL": 12.313,
+    "eval_rougeLsum": 13.3091,
+    "eval_runtime": 7752.5256,
+    "eval_samples": 11332,
+    "eval_samples_per_second": 1.462,
+    "eval_steps_per_second": 0.183
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 2.7845563131665427,
+    "train_runtime": 39.3075,
+    "train_samples": 500,
+    "train_samples_per_second": 12.72,
+    "train_steps_per_second": 1.603
+}

trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 63,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.7149999999999995e-06,
+      "loss": 2.8257,
+      "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "step": 63,
+      "total_flos": 1193890577645568.0,
+      "train_loss": 2.7845563131665427,
+      "train_runtime": 39.3075,
+      "train_samples_per_second": 12.72,
+      "train_steps_per_second": 1.603
+    }
+  ],
+  "max_steps": 63,
+  "num_train_epochs": 1,
+  "total_flos": 1193890577645568.0,
+  "trial_name": null,
+  "trial_params": null
+}