End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 40.69682312011719,
+    "eval_runtime": 26.0441,
+    "eval_samples": 553,
+    "eval_samples_per_second": 21.233,
+    "eval_steps_per_second": 21.233,
+    "eval_wer": 1.0,
+    "train_loss": 109.71464342948718,
+    "train_runtime": 1380.1966,
+    "train_samples": 3119,
+    "train_samples_per_second": 2.26,
+    "train_steps_per_second": 0.141
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 40.69682312011719,
+    "eval_runtime": 26.0441,
+    "eval_samples": 553,
+    "eval_samples_per_second": 21.233,
+    "eval_steps_per_second": 21.233,
+    "eval_wer": 1.0
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 109.71464342948718,
+    "train_runtime": 1380.1966,
+    "train_samples": 3119,
+    "train_samples_per_second": 2.26,
+    "train_steps_per_second": 0.141
+}

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 195,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "eval_loss": 239.00135803222656,
+      "eval_runtime": 28.5979,
+      "eval_samples_per_second": 19.337,
+      "eval_steps_per_second": 19.337,
+      "eval_wer": 1.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 235.82070922851562,
+      "eval_runtime": 27.9371,
+      "eval_samples_per_second": 19.794,
+      "eval_steps_per_second": 19.794,
+      "eval_wer": 1.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 226.90093994140625,
+      "eval_runtime": 27.8094,
+      "eval_samples_per_second": 19.885,
+      "eval_steps_per_second": 19.885,
+      "eval_wer": 1.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 198.07687377929688,
+      "eval_runtime": 27.9651,
+      "eval_samples_per_second": 19.775,
+      "eval_steps_per_second": 19.775,
+      "eval_wer": 1.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 166.6727752685547,
+      "eval_runtime": 28.4525,
+      "eval_samples_per_second": 19.436,
+      "eval_steps_per_second": 19.436,
+      "eval_wer": 1.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 149.14447021484375,
+      "eval_runtime": 27.248,
+      "eval_samples_per_second": 20.295,
+      "eval_steps_per_second": 20.295,
+      "eval_wer": 1.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 138.44029235839844,
+      "eval_runtime": 26.1313,
+      "eval_samples_per_second": 21.162,
+      "eval_steps_per_second": 21.162,
+      "eval_wer": 1.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.41,
+      "eval_loss": 131.72488403320312,
+      "eval_runtime": 28.1944,
+      "eval_samples_per_second": 19.614,
+      "eval_steps_per_second": 19.614,
+      "eval_wer": 1.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.46,
+      "eval_loss": 125.558349609375,
+      "eval_runtime": 26.1125,
+      "eval_samples_per_second": 21.178,
+      "eval_steps_per_second": 21.178,
+      "eval_wer": 1.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 119.75148010253906,
+      "eval_runtime": 27.1597,
+      "eval_samples_per_second": 20.361,
+      "eval_steps_per_second": 20.361,
+      "eval_wer": 1.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.56,
+      "eval_loss": 113.72832489013672,
+      "eval_runtime": 26.3538,
+      "eval_samples_per_second": 20.984,
+      "eval_steps_per_second": 20.984,
+      "eval_wer": 1.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 107.24547576904297,
+      "eval_runtime": 26.997,
+      "eval_samples_per_second": 20.484,
+      "eval_steps_per_second": 20.484,
+      "eval_wer": 1.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 100.21720886230469,
+      "eval_runtime": 27.4511,
+      "eval_samples_per_second": 20.145,
+      "eval_steps_per_second": 20.145,
+      "eval_wer": 1.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 92.55851745605469,
+      "eval_runtime": 27.8487,
+      "eval_samples_per_second": 19.857,
+      "eval_steps_per_second": 19.857,
+      "eval_wer": 1.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.77,
+      "eval_loss": 84.25730895996094,
+      "eval_runtime": 26.3189,
+      "eval_samples_per_second": 21.012,
+      "eval_steps_per_second": 21.012,
+      "eval_wer": 1.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.82,
+      "eval_loss": 75.29525756835938,
+      "eval_runtime": 26.194,
+      "eval_samples_per_second": 21.112,
+      "eval_steps_per_second": 21.112,
+      "eval_wer": 1.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.87,
+      "eval_loss": 65.69525909423828,
+      "eval_runtime": 26.5696,
+      "eval_samples_per_second": 20.813,
+      "eval_steps_per_second": 20.813,
+      "eval_wer": 1.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.92,
+      "eval_loss": 55.75440216064453,
+      "eval_runtime": 27.1022,
+      "eval_samples_per_second": 20.404,
+      "eval_steps_per_second": 20.404,
+      "eval_wer": 1.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.97,
+      "eval_loss": 45.729740142822266,
+      "eval_runtime": 27.0279,
+      "eval_samples_per_second": 20.46,
+      "eval_steps_per_second": 20.46,
+      "eval_wer": 1.0,
+      "step": 190
+    },
+    {
+      "epoch": 1.0,
+      "step": 195,
+      "total_flos": 2.4781601494187277e+17,
+      "train_loss": 109.71464342948718,
+      "train_runtime": 1380.1966,
+      "train_samples_per_second": 2.26,
+      "train_steps_per_second": 0.141
+    }
+  ],
+  "max_steps": 195,
+  "num_train_epochs": 1,
+  "total_flos": 2.4781601494187277e+17,
+  "trial_name": null,
+  "trial_params": null
+}