End of training

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.8382352941176471,
+    "eval_combined_score": 0.863562091503268,
+    "eval_f1": 0.8888888888888888,
+    "eval_loss": 0.3671809136867523,
+    "eval_runtime": 2.3053,
+    "eval_samples": 408,
+    "eval_samples_per_second": 176.984,
+    "eval_steps_per_second": 22.123,
+    "train_loss": 216498.08695652173,
+    "train_runtime": 176.1875,
+    "train_samples": 3668,
+    "train_samples_per_second": 83.275,
+    "train_steps_per_second": 2.611
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.8382352941176471,
+    "eval_combined_score": 0.863562091503268,
+    "eval_f1": 0.8888888888888888,
+    "eval_loss": 0.3671809136867523,
+    "eval_runtime": 2.3053,
+    "eval_samples": 408,
+    "eval_samples_per_second": 176.984,
+    "eval_steps_per_second": 22.123
+}

runs/Jun14_08-08-36_labgpu/events.out.tfevents.1655194578.labgpu.3403.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17d12262c5d228180e7ae03ac036f4db35612a76e8330fca0f7dc4b2d77e9937
+size 467

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 216498.08695652173,
+    "train_runtime": 176.1875,
+    "train_samples": 3668,
+    "train_samples_per_second": 83.275,
+    "train_steps_per_second": 2.611
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 460,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 4.0,
+      "step": 460,
+      "total_flos": 230014854881280.0,
+      "train_loss": 216498.08695652173,
+      "train_runtime": 176.1875,
+      "train_samples_per_second": 83.275,
+      "train_steps_per_second": 2.611
+    }
+  ],
+  "max_steps": 460,
+  "num_train_epochs": 4,
+  "total_flos": 230014854881280.0,
+  "trial_name": null,
+  "trial_params": null
+}