End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 0.6525373458862305,
+    "eval_matthews_correlation": 0.5981333967857257,
+    "eval_runtime": 3.1799,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 327.995,
+    "eval_steps_per_second": 41.196,
+    "train_loss": 0.28124569565502566,
+    "train_runtime": 650.0563,
+    "train_samples": 8551,
+    "train_samples_per_second": 65.771,
+    "train_steps_per_second": 2.061
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 0.6525373458862305,
+    "eval_matthews_correlation": 0.5981333967857257,
+    "eval_runtime": 3.1799,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 327.995,
+    "eval_steps_per_second": 41.196
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.28124569565502566,
+    "train_runtime": 650.0563,
+    "train_samples": 8551,
+    "train_samples_per_second": 65.771,
+    "train_steps_per_second": 2.061
+}

trainer_state.json

@@ -0,0 +1,37 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 1340,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.2537313432835823e-05,
+      "loss": 0.4347,
+      "step": 500
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 5.074626865671642e-06,
+      "loss": 0.2214,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "step": 1340,
+      "total_flos": 0.0,
+      "train_loss": 0.28124569565502566,
+      "train_runtime": 650.0563,
+      "train_samples_per_second": 65.771,
+      "train_steps_per_second": 2.061
+    }
+  ],
+  "max_steps": 1340,
+  "num_train_epochs": 5,
+  "total_flos": 0.0,
+  "trial_name": null,
+  "trial_params": null
+}