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 +1,15 @@
+{
+    "epoch": 10.0,
+    "eval_exact_match": 80.7909604519774,
+    "eval_f1": 80.7909604519774,
+    "eval_runtime": 30.3137,
+    "eval_samples": 3941,
+    "eval_samples_per_second": 130.007,
+    "eval_steps_per_second": 2.045,
+    "total_flos": 7.2313877426688e+16,
+    "train_loss": 0.21441613025533135,
+    "train_runtime": 5976.0993,
+    "train_samples": 27675,
+    "train_samples_per_second": 46.309,
+    "train_steps_per_second": 0.725
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac1ff23d18eb2b84a72a34c16eea821c3773a29a53a580ff4f411218412abfde
+size 14382489

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_exact_match": 80.7909604519774,
+    "eval_f1": 80.7909604519774,
+    "eval_runtime": 30.3137,
+    "eval_samples": 3941,
+    "eval_samples_per_second": 130.007,
+    "eval_steps_per_second": 2.045
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 7.2313877426688e+16,
+    "train_loss": 0.21441613025533135,
+    "train_runtime": 5976.0993,
+    "train_samples": 27675,
+    "train_samples_per_second": 46.309,
+    "train_steps_per_second": 0.725
+}

trainer_state.json

@@ -0,0 +1,98 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 4330,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.1547344110854503,
+      "grad_norm": 12.477436065673828,
+      "learning_rate": 2.653579676674365e-05,
+      "loss": 0.9832,
+      "step": 500
+    },
+    {
+      "epoch": 2.3094688221709005,
+      "grad_norm": 6.3677873611450195,
+      "learning_rate": 2.30715935334873e-05,
+      "loss": 0.3759,
+      "step": 1000
+    },
+    {
+      "epoch": 3.464203233256351,
+      "grad_norm": 13.403519630432129,
+      "learning_rate": 1.9607390300230947e-05,
+      "loss": 0.2116,
+      "step": 1500
+    },
+    {
+      "epoch": 4.618937644341801,
+      "grad_norm": 10.46613883972168,
+      "learning_rate": 1.6143187066974596e-05,
+      "loss": 0.1183,
+      "step": 2000
+    },
+    {
+      "epoch": 5.773672055427252,
+      "grad_norm": 1.2159202098846436,
+      "learning_rate": 1.2678983833718245e-05,
+      "loss": 0.0695,
+      "step": 2500
+    },
+    {
+      "epoch": 6.928406466512702,
+      "grad_norm": 5.752726078033447,
+      "learning_rate": 9.214780600461894e-06,
+      "loss": 0.0452,
+      "step": 3000
+    },
+    {
+      "epoch": 8.083140877598153,
+      "grad_norm": 3.9594123363494873,
+      "learning_rate": 5.750577367205543e-06,
+      "loss": 0.0272,
+      "step": 3500
+    },
+    {
+      "epoch": 9.237875288683602,
+      "grad_norm": 0.1741260439157486,
+      "learning_rate": 2.2863741339491914e-06,
+      "loss": 0.0175,
+      "step": 4000
+    },
+    {
+      "epoch": 10.0,
+      "step": 4330,
+      "total_flos": 7.2313877426688e+16,
+      "train_loss": 0.21441613025533135,
+      "train_runtime": 5976.0993,
+      "train_samples_per_second": 46.309,
+      "train_steps_per_second": 0.725
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4330,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.2313877426688e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}