End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.6462093862815884,
+    "eval_loss": 0.7911513447761536,
+    "eval_runtime": 3.0776,
+    "eval_samples": 277,
+    "eval_samples_per_second": 90.005,
+    "eval_steps_per_second": 11.372,
+    "train_loss": 0.48275831173627803,
+    "train_runtime": 237.1279,
+    "train_samples": 2490,
+    "train_samples_per_second": 52.503,
+    "train_steps_per_second": 1.645
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.6462093862815884,
+    "eval_loss": 0.7911513447761536,
+    "eval_runtime": 3.0776,
+    "eval_samples": 277,
+    "eval_samples_per_second": 90.005,
+    "eval_steps_per_second": 11.372
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.48275831173627803,
+    "train_runtime": 237.1279,
+    "train_samples": 2490,
+    "train_samples_per_second": 52.503,
+    "train_steps_per_second": 1.645
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 390,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.0,
+      "step": 390,
+      "total_flos": 818933159808000.0,
+      "train_loss": 0.48275831173627803,
+      "train_runtime": 237.1279,
+      "train_samples_per_second": 52.503,
+      "train_steps_per_second": 1.645
+    }
+  ],
+  "max_steps": 390,
+  "num_train_epochs": 5,
+  "total_flos": 818933159808000.0,
+  "trial_name": null,
+  "trial_params": null
+}