End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.6895306859205776,
+    "eval_loss": 0.6972283720970154,
+    "eval_runtime": 1.3468,
+    "eval_samples": 277,
+    "eval_samples_per_second": 205.68,
+    "eval_steps_per_second": 25.988,
+    "train_loss": 0.5218920259394197,
+    "train_runtime": 132.1109,
+    "train_samples": 2490,
+    "train_samples_per_second": 56.543,
+    "train_steps_per_second": 3.542
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.6895306859205776,
+    "eval_loss": 0.6972283720970154,
+    "eval_runtime": 1.3468,
+    "eval_samples": 277,
+    "eval_samples_per_second": 205.68,
+    "eval_steps_per_second": 25.988
+}

runs/Jun21_20-39-36_pikachu/events.out.tfevents.1655815670.pikachu.3238873.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24254d343e6e7a89386c884ddee888d187d75f8f6bca008223596b3a7b707a68
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.5218920259394197,
+    "train_runtime": 132.1109,
+    "train_samples": 2490,
+    "train_samples_per_second": 56.543,
+    "train_steps_per_second": 3.542
+}

trainer_state.json

@@ -0,0 +1,52 @@
+{
+  "best_metric": 0.6895306859205776,
+  "best_model_checkpoint": "./fine-tune/bert-base-uncased/rte/checkpoint-468",
+  "epoch": 3.0,
+  "global_step": 468,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.631768953068592,
+      "eval_loss": 0.6537421941757202,
+      "eval_runtime": 1.4835,
+      "eval_samples_per_second": 186.725,
+      "eval_steps_per_second": 23.593,
+      "step": 156
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6534296028880866,
+      "eval_loss": 0.6383388042449951,
+      "eval_runtime": 1.4171,
+      "eval_samples_per_second": 195.465,
+      "eval_steps_per_second": 24.698,
+      "step": 312
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6895306859205776,
+      "eval_loss": 0.6972283720970154,
+      "eval_runtime": 1.4627,
+      "eval_samples_per_second": 189.379,
+      "eval_steps_per_second": 23.929,
+      "step": 468
+    },
+    {
+      "epoch": 3.0,
+      "step": 468,
+      "total_flos": 491359895884800.0,
+      "train_loss": 0.5218920259394197,
+      "train_runtime": 132.1109,
+      "train_samples_per_second": 56.543,
+      "train_steps_per_second": 3.542
+    }
+  ],
+  "max_steps": 468,
+  "num_train_epochs": 3,
+  "total_flos": 491359895884800.0,
+  "trial_name": null,
+  "trial_params": null
+}