End of training

.gitattributes

@@ -29,3 +29,4 @@ 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": 1.0,
+    "eval_exact_match": 79.33774834437087,
+    "eval_f1": 87.12191251890178,
+    "eval_samples": 12097,
+    "train_loss": 1.2300268692036653,
+    "train_runtime": 4576.3813,
+    "train_samples": 97408,
+    "train_samples_per_second": 21.285,
+    "train_steps_per_second": 1.33
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0ff4aa82b05987f5fc97da148f6608891d99f0e6f3032d5196f81408c2b9329
+size 49409449

eval_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 1.0,
+    "eval_exact_match": 79.33774834437087,
+    "eval_f1": 87.12191251890178,
+    "eval_samples": 12097
+}

runs/Aug09_16-23-09_58e64a916bd5/events.out.tfevents.1660067587.58e64a916bd5.6121.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c4689ee32794ea1f2dee8fcbfe83584a5b95ffd701f56149de7ce3e637e96a
+size 191

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.2300268692036653,
+    "train_runtime": 4576.3813,
+    "train_samples": 97408,
+    "train_samples_per_second": 21.285,
+    "train_steps_per_second": 1.33
+}

trainer_state.json

@@ -0,0 +1,97 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 6088,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.7536136662286466e-05,
+      "loss": 2.3317,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.5072273324572932e-05,
+      "loss": 1.4294,
+      "step": 1000
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.2608409986859398e-05,
+      "loss": 1.3087,
+      "step": 1500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.014454664914586e-05,
+      "loss": 1.2303,
+      "step": 2000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.7680683311432326e-05,
+      "loss": 1.1531,
+      "step": 2500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.5216819973718791e-05,
+      "loss": 1.1192,
+      "step": 3000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.2752956636005257e-05,
+      "loss": 1.0921,
+      "step": 3500
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.0289093298291721e-05,
+      "loss": 1.078,
+      "step": 4000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.825229960578187e-06,
+      "loss": 1.043,
+      "step": 4500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 5.361366622864652e-06,
+      "loss": 0.9911,
+      "step": 5000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.8975032851511168e-06,
+      "loss": 1.006,
+      "step": 5500
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.336399474375821e-07,
+      "loss": 1.02,
+      "step": 6000
+    },
+    {
+      "epoch": 1.0,
+      "step": 6088,
+      "total_flos": 1.2726197240070144e+16,
+      "train_loss": 1.2300268692036653,
+      "train_runtime": 4576.3813,
+      "train_samples_per_second": 21.285,
+      "train_steps_per_second": 1.33
+    }
+  ],
+  "max_steps": 6088,
+  "num_train_epochs": 1,
+  "total_flos": 1.2726197240070144e+16,
+  "trial_name": null,
+  "trial_params": null
+}