End of training

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8799019607843137,
+    "eval_combined_score": 0.8958068362480127,
+    "eval_f1": 0.9117117117117116,
+    "eval_loss": 0.3688029944896698,
+    "eval_runtime": 1.0872,
+    "eval_samples": 408,
+    "eval_samples_per_second": 375.273,
+    "eval_steps_per_second": 46.909,
+    "train_loss": 0.31258186008619226,
+    "train_runtime": 260.6094,
+    "train_samples": 3668,
+    "train_samples_per_second": 70.374,
+    "train_steps_per_second": 2.206
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8799019607843137,
+    "eval_combined_score": 0.8958068362480127,
+    "eval_f1": 0.9117117117117116,
+    "eval_loss": 0.3688029944896698,
+    "eval_runtime": 1.0872,
+    "eval_samples": 408,
+    "eval_samples_per_second": 375.273,
+    "eval_steps_per_second": 46.909
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.31258186008619226,
+    "train_runtime": 260.6094,
+    "train_samples": 3668,
+    "train_samples_per_second": 70.374,
+    "train_steps_per_second": 2.206
+}

trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 575,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 4.35,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 0.3375,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "step": 575,
+      "total_flos": 0.0,
+      "train_loss": 0.31258186008619226,
+      "train_runtime": 260.6094,
+      "train_samples_per_second": 70.374,
+      "train_steps_per_second": 2.206
+    }
+  ],
+  "max_steps": 575,
+  "num_train_epochs": 5,
+  "total_flos": 0.0,
+  "trial_name": null,
+  "trial_params": null
+}