End of training

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.06589564281871974,
+    "eval_loss": 2.6640625,
+    "eval_runtime": 17.5909,
+    "eval_samples": 78,
+    "eval_samples_per_second": 4.434,
+    "eval_steps_per_second": 0.568,
+    "perplexity": 14.354485905365031,
+    "train_loss": 1.82276857816256,
+    "train_runtime": 1007.1646,
+    "train_samples": 416,
+    "train_samples_per_second": 0.826,
+    "train_steps_per_second": 0.103
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.06589564281871974,
+    "eval_loss": 2.6640625,
+    "eval_runtime": 17.5909,
+    "eval_samples": 78,
+    "eval_samples_per_second": 4.434,
+    "eval_steps_per_second": 0.568,
+    "perplexity": 14.354485905365031
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 1.82276857816256,
+    "train_runtime": 1007.1646,
+    "train_samples": 416,
+    "train_samples_per_second": 0.826,
+    "train_steps_per_second": 0.103
+}

trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 104,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 0,
+      "loss": 2.6804,
+      "step": 1
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 5e-05,
+      "loss": 2.5958,
+      "step": 16
+    },
+    {
+      "epoch": 0.31,
+      "eval_accuracy": 0.06585978124439663,
+      "eval_loss": 2.537109375,
+      "eval_runtime": 16.98,
+      "eval_samples_per_second": 4.594,
+      "eval_steps_per_second": 0.589,
+      "step": 16
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 5e-05,
+      "loss": 2.3784,
+      "step": 32
+    },
+    {
+      "epoch": 0.62,
+      "eval_accuracy": 0.06695355926125157,
+      "eval_loss": 2.50390625,
+      "eval_runtime": 17.6527,
+      "eval_samples_per_second": 4.419,
+      "eval_steps_per_second": 0.566,
+      "step": 32
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5e-05,
+      "loss": 2.3578,
+      "step": 48
+    },
+    {
+      "epoch": 0.92,
+      "eval_accuracy": 0.06535771920387305,
+      "eval_loss": 2.607421875,
+      "eval_runtime": 17.1023,
+      "eval_samples_per_second": 4.561,
+      "eval_steps_per_second": 0.585,
+      "step": 48
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 5e-05,
+      "loss": 1.3819,
+      "step": 64
+    },
+    {
+      "epoch": 1.23,
+      "eval_accuracy": 0.06575219652142729,
+      "eval_loss": 2.66796875,
+      "eval_runtime": 16.8667,
+      "eval_samples_per_second": 4.625,
+      "eval_steps_per_second": 0.593,
+      "step": 64
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 5e-05,
+      "loss": 1.1529,
+      "step": 80
+    },
+    {
+      "epoch": 1.54,
+      "eval_accuracy": 0.06650528958221266,
+      "eval_loss": 2.673828125,
+      "eval_runtime": 17.3671,
+      "eval_samples_per_second": 4.491,
+      "eval_steps_per_second": 0.576,
+      "step": 80
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 5e-05,
+      "loss": 1.2938,
+      "step": 96
+    },
+    {
+      "epoch": 1.85,
+      "eval_accuracy": 0.06621839698762776,
+      "eval_loss": 2.6640625,
+      "eval_runtime": 17.6569,
+      "eval_samples_per_second": 4.418,
+      "eval_steps_per_second": 0.566,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "step": 104,
+      "total_flos": 7482848575488.0,
+      "train_loss": 1.82276857816256,
+      "train_runtime": 1007.1646,
+      "train_samples_per_second": 0.826,
+      "train_steps_per_second": 0.103
+    }
+  ],
+  "max_steps": 104,
+  "num_train_epochs": 2,
+  "total_flos": 7482848575488.0,
+  "trial_name": null,
+  "trial_params": null
+}