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": 5.0,
+    "eval_exact_match": 5.583250249252243,
+    "eval_f1": 5.583250249252243,
+    "eval_runtime": 83.0612,
+    "eval_samples": 3934,
+    "eval_samples_per_second": 47.363,
+    "eval_steps_per_second": 2.962,
+    "total_flos": 3.611513123226624e+16,
+    "train_loss": 4.290382243968822,
+    "train_runtime": 7091.0117,
+    "train_samples": 27643,
+    "train_samples_per_second": 19.492,
+    "train_steps_per_second": 0.609
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b710c5b4491cfbb9f2430f519c66bafe687cd0ad592bee2a21266f3834e2688f
+size 15741090

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_exact_match": 5.583250249252243,
+    "eval_f1": 5.583250249252243,
+    "eval_runtime": 83.0612,
+    "eval_samples": 3934,
+    "eval_samples_per_second": 47.363,
+    "eval_steps_per_second": 2.962
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 3.611513123226624e+16,
+    "train_loss": 4.290382243968822,
+    "train_runtime": 7091.0117,
+    "train_samples": 27643,
+    "train_samples_per_second": 19.492,
+    "train_steps_per_second": 0.609
+}

trainer_state.json

@@ -0,0 +1,98 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 4320,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5787037037037037,
+      "grad_norm": 4.67863130569458,
+      "learning_rate": 2.652777777777778e-05,
+      "loss": 4.7855,
+      "step": 500
+    },
+    {
+      "epoch": 1.1574074074074074,
+      "grad_norm": 4.733221530914307,
+      "learning_rate": 2.3055555555555554e-05,
+      "loss": 4.4953,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7361111111111112,
+      "grad_norm": 5.022942543029785,
+      "learning_rate": 1.9583333333333333e-05,
+      "loss": 4.3197,
+      "step": 1500
+    },
+    {
+      "epoch": 2.314814814814815,
+      "grad_norm": 6.777132987976074,
+      "learning_rate": 1.6111111111111115e-05,
+      "loss": 4.281,
+      "step": 2000
+    },
+    {
+      "epoch": 2.8935185185185186,
+      "grad_norm": 5.286303520202637,
+      "learning_rate": 1.2638888888888888e-05,
+      "loss": 4.2286,
+      "step": 2500
+    },
+    {
+      "epoch": 3.4722222222222223,
+      "grad_norm": 15.372255325317383,
+      "learning_rate": 9.166666666666668e-06,
+      "loss": 4.1566,
+      "step": 3000
+    },
+    {
+      "epoch": 4.050925925925926,
+      "grad_norm": 12.722051620483398,
+      "learning_rate": 5.694444444444445e-06,
+      "loss": 4.1296,
+      "step": 3500
+    },
+    {
+      "epoch": 4.62962962962963,
+      "grad_norm": 7.344661712646484,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 4.0602,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "step": 4320,
+      "total_flos": 3.611513123226624e+16,
+      "train_loss": 4.290382243968822,
+      "train_runtime": 7091.0117,
+      "train_samples_per_second": 19.492,
+      "train_steps_per_second": 0.609
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4320,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 3.611513123226624e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}