End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.7654190063476562,
+    "eval_runtime": 69.7723,
+    "eval_samples": 1716,
+    "eval_samples_per_second": 24.594,
+    "eval_steps_per_second": 0.774,
+    "eval_wer": 0.5185841828658266,
+    "train_loss": 3.4940547976286513,
+    "train_runtime": 2130.2547,
+    "train_samples": 3670,
+    "train_samples_per_second": 17.228,
+    "train_steps_per_second": 0.54
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.7654190063476562,
+    "eval_runtime": 69.7723,
+    "eval_samples": 1716,
+    "eval_samples_per_second": 24.594,
+    "eval_steps_per_second": 0.774,
+    "eval_wer": 0.5185841828658266
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3221b9c28943b03d04aa88289fd364b0f078d534902800b84f78f85e820dcec
+oid sha256:23d23e377b908f06fea252ccbf8dbcbd6cc1f0217db94f725fb5f5a23cb45d41
 size 1262104049

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 3.4940547976286513,
+    "train_runtime": 2130.2547,
+    "train_samples": 3670,
+    "train_samples_per_second": 17.228,
+    "train_steps_per_second": 0.54
+}

trainer_state.json

@@ -0,0 +1,109 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 1150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.68e-05,
+      "loss": 11.4306,
+      "step": 100
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 3.4299999999999993e-05,
+      "loss": 4.3407,
+      "step": 200
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 5.179999999999999e-05,
+      "loss": 3.2465,
+      "step": 300
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 6.929999999999999e-05,
+      "loss": 3.0269,
+      "step": 400
+    },
+    {
+      "epoch": 3.48,
+      "eval_loss": 2.9771385192871094,
+      "eval_runtime": 71.2409,
+      "eval_samples_per_second": 24.087,
+      "eval_steps_per_second": 0.758,
+      "eval_wer": 1.0,
+      "step": 400
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 6.104e-05,
+      "loss": 2.9973,
+      "step": 500
+    },
+    {
+      "epoch": 5.22,
+      "learning_rate": 5.1706666666666664e-05,
+      "loss": 2.9206,
+      "step": 600
+    },
+    {
+      "epoch": 6.09,
+      "learning_rate": 4.237333333333332e-05,
+      "loss": 2.8692,
+      "step": 700
+    },
+    {
+      "epoch": 6.96,
+      "learning_rate": 3.3039999999999995e-05,
+      "loss": 2.7902,
+      "step": 800
+    },
+    {
+      "epoch": 6.96,
+      "eval_loss": 2.4356915950775146,
+      "eval_runtime": 71.3351,
+      "eval_samples_per_second": 24.055,
+      "eval_steps_per_second": 0.757,
+      "eval_wer": 0.9988602545431521,
+      "step": 800
+    },
+    {
+      "epoch": 7.83,
+      "learning_rate": 2.3706666666666664e-05,
+      "loss": 2.3184,
+      "step": 900
+    },
+    {
+      "epoch": 8.7,
+      "learning_rate": 1.4373333333333332e-05,
+      "loss": 1.8236,
+      "step": 1000
+    },
+    {
+      "epoch": 9.57,
+      "learning_rate": 5.039999999999999e-06,
+      "loss": 1.6258,
+      "step": 1100
+    },
+    {
+      "epoch": 10.0,
+      "step": 1150,
+      "total_flos": 5.422401103281132e+18,
+      "train_loss": 3.4940547976286513,
+      "train_runtime": 2130.2547,
+      "train_samples_per_second": 17.228,
+      "train_steps_per_second": 0.54
+    }
+  ],
+  "max_steps": 1150,
+  "num_train_epochs": 10,
+  "total_flos": 5.422401103281132e+18,
+  "trial_name": null,
+  "trial_params": null
+}