End of training

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.36584496431695074,
+    "eval_loss": 3.5665595531463623,
+    "eval_runtime": 3.3682,
+    "eval_samples": 266,
+    "eval_samples_per_second": 78.974,
+    "eval_steps_per_second": 2.672,
+    "perplexity": 35.3946101587927,
+    "train_loss": 3.7494896997379352,
+    "train_runtime": 102.1454,
+    "train_samples": 5035,
+    "train_samples_per_second": 49.292,
+    "train_steps_per_second": 1.547
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.36584496431695074,
+    "eval_loss": 3.5665595531463623,
+    "eval_runtime": 3.3682,
+    "eval_samples": 266,
+    "eval_samples_per_second": 78.974,
+    "eval_steps_per_second": 2.672,
+    "perplexity": 35.3946101587927
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 3.7494896997379352,
+    "train_runtime": 102.1454,
+    "train_samples": 5035,
+    "train_samples_per_second": 49.292,
+    "train_steps_per_second": 1.547
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 158,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "step": 158,
+      "total_flos": 2631733425995776.0,
+      "train_loss": 3.7494896997379352,
+      "train_runtime": 102.1454,
+      "train_samples_per_second": 49.292,
+      "train_steps_per_second": 1.547
+    }
+  ],
+  "max_steps": 158,
+  "num_train_epochs": 1,
+  "total_flos": 2631733425995776.0,
+  "trial_name": null,
+  "trial_params": null
+}