End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst 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 +1,14 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 81.03122043519394,
+    "eval_f1": 88.29484994429006,
+    "eval_runtime": 104.2114,
+    "eval_samples": 10784,
+    "eval_samples_per_second": 103.482,
+    "eval_steps_per_second": 12.935,
+    "train_loss": 0.8053705267940447,
+    "train_runtime": 40595.6083,
+    "train_samples": 88524,
+    "train_samples_per_second": 4.361,
+    "train_steps_per_second": 0.363
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45dd68430acc4210e18f06352583392eff3a445f035fd712a6d1872a6055ad9a
+size 50515643

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 81.03122043519394,
+    "eval_f1": 88.29484994429006,
+    "eval_runtime": 104.2114,
+    "eval_samples": 10784,
+    "eval_samples_per_second": 103.482,
+    "eval_steps_per_second": 12.935
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.8053705267940447,
+    "train_runtime": 40595.6083,
+    "train_samples": 88524,
+    "train_samples_per_second": 4.361,
+    "train_steps_per_second": 0.363
+}

trainer_state.json

@@ -0,0 +1,199 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 14754,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.8983326555510372e-05,
+      "loss": 2.4651,
+      "step": 500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.796665311102074e-05,
+      "loss": 1.5288,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.694997966653111e-05,
+      "loss": 1.3954,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.593330622204148e-05,
+      "loss": 1.2758,
+      "step": 2000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.491663277755185e-05,
+      "loss": 1.25,
+      "step": 2500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.389995933306222e-05,
+      "loss": 1.202,
+      "step": 3000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.288328588857259e-05,
+      "loss": 1.1578,
+      "step": 3500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.1866612444082963e-05,
+      "loss": 1.1283,
+      "step": 4000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2.084993899959333e-05,
+      "loss": 1.1408,
+      "step": 4500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.9833265555103702e-05,
+      "loss": 1.0958,
+      "step": 5000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.8816592110614073e-05,
+      "loss": 1.0544,
+      "step": 5500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.779991866612444e-05,
+      "loss": 1.0803,
+      "step": 6000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6783245221634812e-05,
+      "loss": 1.0491,
+      "step": 6500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.576657177714518e-05,
+      "loss": 1.0356,
+      "step": 7000
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.4749898332655551e-05,
+      "loss": 0.9514,
+      "step": 7500
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.373322488816592e-05,
+      "loss": 0.756,
+      "step": 8000
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.271655144367629e-05,
+      "loss": 0.7192,
+      "step": 8500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.1699877999186661e-05,
+      "loss": 0.7438,
+      "step": 9000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.0683204554697033e-05,
+      "loss": 0.7476,
+      "step": 9500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 9.666531110207402e-06,
+      "loss": 0.6886,
+      "step": 10000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 8.649857665717772e-06,
+      "loss": 0.731,
+      "step": 10500
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 7.633184221228141e-06,
+      "loss": 0.7096,
+      "step": 11000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 6.616510776738511e-06,
+      "loss": 0.7151,
+      "step": 11500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 5.5998373322488825e-06,
+      "loss": 0.7143,
+      "step": 12000
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 4.583163887759252e-06,
+      "loss": 0.715,
+      "step": 12500
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 3.566490443269622e-06,
+      "loss": 0.6862,
+      "step": 13000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 2.549816998779992e-06,
+      "loss": 0.684,
+      "step": 13500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.533143554290362e-06,
+      "loss": 0.6941,
+      "step": 14000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5.164701098007319e-07,
+      "loss": 0.6954,
+      "step": 14500
+    },
+    {
+      "epoch": 2.0,
+      "step": 14754,
+      "total_flos": 3.4696551139946496e+16,
+      "train_loss": 0.8053705267940447,
+      "train_runtime": 40595.6083,
+      "train_samples_per_second": 4.361,
+      "train_steps_per_second": 0.363
+    }
+  ],
+  "max_steps": 14754,
+  "num_train_epochs": 2,
+  "total_flos": 3.4696551139946496e+16,
+  "trial_name": null,
+  "trial_params": null
+}