End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.5633802816901409,
+    "eval_loss": 0.6958662867546082,
+    "eval_runtime": 4.2207,
+    "eval_samples": 71,
+    "eval_samples_per_second": 16.822,
+    "eval_steps_per_second": 2.132,
+    "train_loss": 0.7037681579589844,
+    "train_runtime": 461.9652,
+    "train_samples": 635,
+    "train_samples_per_second": 4.124,
+    "train_steps_per_second": 0.13
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.5633802816901409,
+    "eval_loss": 0.6958662867546082,
+    "eval_runtime": 4.2207,
+    "eval_samples": 71,
+    "eval_samples_per_second": 16.822,
+    "eval_steps_per_second": 2.132
+}

runs/Jun21_16-25-20_mewtwo/events.out.tfevents.1655829627.mewtwo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:044bce2e31c98b1749f7cecbd4613f8eec7c1620fdf91a8f2504432a21997d6d
+size 40

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.7037681579589844,
+    "train_runtime": 461.9652,
+    "train_samples": 635,
+    "train_samples_per_second": 4.124,
+    "train_steps_per_second": 0.13
+}

trainer_state.json

@@ -0,0 +1,52 @@
+{
+  "best_metric": 0.5633802816901409,
+  "best_model_checkpoint": "./fine-tune/bert-base-uncased/wnli/checkpoint-40",
+  "epoch": 3.0,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5492957746478874,
+      "eval_loss": 0.6933255195617676,
+      "eval_runtime": 4.3206,
+      "eval_samples_per_second": 16.433,
+      "eval_steps_per_second": 2.083,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6958662867546082,
+      "eval_runtime": 4.2571,
+      "eval_samples_per_second": 16.678,
+      "eval_steps_per_second": 2.114,
+      "step": 40
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5352112676056338,
+      "eval_loss": 0.6977640390396118,
+      "eval_runtime": 4.138,
+      "eval_samples_per_second": 17.158,
+      "eval_steps_per_second": 2.175,
+      "step": 60
+    },
+    {
+      "epoch": 3.0,
+      "step": 60,
+      "total_flos": 125306640115200.0,
+      "train_loss": 0.7037681579589844,
+      "train_runtime": 461.9652,
+      "train_samples_per_second": 4.124,
+      "train_steps_per_second": 0.13
+    }
+  ],
+  "max_steps": 60,
+  "num_train_epochs": 3,
+  "total_flos": 125306640115200.0,
+  "trial_name": null,
+  "trial_params": null
+}