End of training

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 88.99716177861873,
+    "eval_f1": 94.60136233653391,
+    "eval_samples": 10790,
+    "train_loss": 0.7406173908623277,
+    "train_runtime": 8011.1743,
+    "train_samples": 88568,
+    "train_samples_per_second": 22.111,
+    "train_steps_per_second": 0.921
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab8927912026d2aab63d107a2e2f4f7aab4bd6b8ff2e31c46687c614dbae8d68
+size 49375913

eval_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 88.99716177861873,
+    "eval_f1": 94.60136233653391,
+    "eval_samples": 10790
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.7406173908623277,
+    "train_runtime": 8011.1743,
+    "train_samples": 88568,
+    "train_samples_per_second": 22.111,
+    "train_steps_per_second": 0.921
+}

trainer_state.json

@@ -0,0 +1,109 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 7382,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.7968030344080195e-05,
+      "loss": 1.3568,
+      "step": 500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.5936060688160393e-05,
+      "loss": 0.9714,
+      "step": 1000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.3904091032240584e-05,
+      "loss": 0.915,
+      "step": 1500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.187212137632078e-05,
+      "loss": 0.8459,
+      "step": 2000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.9840151720400976e-05,
+      "loss": 0.8315,
+      "step": 2500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7808182064481173e-05,
+      "loss": 0.7995,
+      "step": 3000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5776212408561364e-05,
+      "loss": 0.7776,
+      "step": 3500
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.374424275264156e-05,
+      "loss": 0.6493,
+      "step": 4000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.1712273096721756e-05,
+      "loss": 0.5626,
+      "step": 4500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 9.68030344080195e-06,
+      "loss": 0.5631,
+      "step": 5000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 7.648333784882147e-06,
+      "loss": 0.564,
+      "step": 5500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 5.616364128962341e-06,
+      "loss": 0.5734,
+      "step": 6000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 3.584394473042536e-06,
+      "loss": 0.5533,
+      "step": 6500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.552424817122731e-06,
+      "loss": 0.5477,
+      "step": 7000
+    },
+    {
+      "epoch": 2.0,
+      "step": 7382,
+      "total_flos": 1.2338058008251597e+17,
+      "train_loss": 0.7406173908623277,
+      "train_runtime": 8011.1743,
+      "train_samples_per_second": 22.111,
+      "train_steps_per_second": 0.921
+    }
+  ],
+  "max_steps": 7382,
+  "num_train_epochs": 2,
+  "total_flos": 1.2338058008251597e+17,
+  "trial_name": null,
+  "trial_params": null
+}