End of training

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 100.0,
+    "eval_exact_match": 1.0028382213812677,
+    "eval_f1": 8.613381279622576,
+    "eval_samples": 10793,
+    "train_loss": 1.1161543041467668,
+    "train_runtime": 70.3956,
+    "train_samples": 16,
+    "train_samples_per_second": 34.093,
+    "train_steps_per_second": 2.841
+}

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f5cb5bd75b58f7ca11b56ecb2d5bac1edcfb4977f9f344e01910007fbdc9530
-size 54135242
+oid sha256:8795b27d753b7c6f95445f99552464d5a5d88be7332118c8bef6dc2656983c69
+size 54059903

eval_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 100.0,
+    "eval_exact_match": 1.0028382213812677,
+    "eval_f1": 8.613381279622576,
+    "eval_samples": 10793
+}

runs/Oct04_17-40-58_g3010/events.out.tfevents.1664930958.g3010.9541.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4943208cbdea75bc5cfa365cfac3cc5797fcbd345d4c64e4381947c57e97a0a9
+size 191

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 100.0,
+    "train_loss": 1.1161543041467668,
+    "train_runtime": 70.3956,
+    "train_samples": 16,
+    "train_samples_per_second": 34.093,
+    "train_steps_per_second": 2.841
+}

trainer_state.json

@@ -0,0 +1,37 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 100.0,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 50.0,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 2.2247,
+      "step": 100
+    },
+    {
+      "epoch": 100.0,
+      "learning_rate": 0.0,
+      "loss": 0.0076,
+      "step": 200
+    },
+    {
+      "epoch": 100.0,
+      "step": 200,
+      "total_flos": 255121579477200.0,
+      "train_loss": 1.1161543041467668,
+      "train_runtime": 70.3956,
+      "train_samples_per_second": 34.093,
+      "train_steps_per_second": 2.841
+    }
+  ],
+  "max_steps": 200,
+  "num_train_epochs": 100,
+  "total_flos": 255121579477200.0,
+  "trial_name": null,
+  "trial_params": null
+}