End of training

all_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 5.0,
+    "eval_runtime": 4.3394,
+    "eval_samples_per_second": 57.612,
+    "eval_steps_per_second": 2.535,
+    "train_loss": 2.2425999959309895,
+    "train_runtime": 66.6893,
+    "train_samples_per_second": 18.744,
+    "train_steps_per_second": 0.9
+}

eval_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 5.0,
+    "eval_runtime": 4.3394,
+    "eval_samples_per_second": 57.612,
+    "eval_steps_per_second": 2.535
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 5.0,
+    "train_loss": 2.2425999959309895,
+    "train_runtime": 66.6893,
+    "train_samples_per_second": 18.744,
+    "train_steps_per_second": 0.9
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.0,
+      "step": 60,
+      "total_flos": 373901476800000.0,
+      "train_loss": 2.2425999959309895,
+      "train_runtime": 66.6893,
+      "train_samples_per_second": 18.744,
+      "train_steps_per_second": 0.9
+    }
+  ],
+  "max_steps": 60,
+  "num_train_epochs": 5,
+  "total_flos": 373901476800000.0,
+  "trial_name": null,
+  "trial_params": null
+}