End of training

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8553921568627451,
+    "eval_combined_score": 0.8767461647871584,
+    "eval_f1": 0.8981001727115717,
+    "eval_loss": 0.49130943417549133,
+    "eval_runtime": 4.5516,
+    "eval_samples": 408,
+    "eval_samples_per_second": 89.639,
+    "eval_steps_per_second": 11.205,
+    "train_loss": 0.2986407089233398,
+    "train_runtime": 429.5878,
+    "train_samples": 3668,
+    "train_samples_per_second": 42.692,
+    "train_steps_per_second": 1.338
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8553921568627451,
+    "eval_combined_score": 0.8767461647871584,
+    "eval_f1": 0.8981001727115717,
+    "eval_loss": 0.49130943417549133,
+    "eval_runtime": 4.5516,
+    "eval_samples": 408,
+    "eval_samples_per_second": 89.639,
+    "eval_steps_per_second": 11.205
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.2986407089233398,
+    "train_runtime": 429.5878,
+    "train_samples": 3668,
+    "train_samples_per_second": 42.692,
+    "train_steps_per_second": 1.338
+}

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": 0.3272,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "step": 575,
+      "total_flos": 1206364188825600.0,
+      "train_loss": 0.2986407089233398,
+      "train_runtime": 429.5878,
+      "train_samples_per_second": 42.692,
+      "train_steps_per_second": 1.338
+    }
+  ],
+  "max_steps": 575,
+  "num_train_epochs": 5,
+  "total_flos": 1206364188825600.0,
+  "trial_name": null,
+  "trial_params": null
+}