End of training

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.05,
+    "eval_loss": 0.974454939365387,
+    "eval_runtime": 20.3472,
+    "eval_samples": 64,
+    "eval_samples_per_second": 3.145,
+    "eval_steps_per_second": 0.098,
+    "eval_wer": 75.27472527472527,
+    "train_loss": 0.041942973931630455,
+    "train_runtime": 33.8193,
+    "train_samples_per_second": 18.924,
+    "train_steps_per_second": 0.591
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.05,
+    "eval_loss": 0.974454939365387,
+    "eval_runtime": 20.3472,
+    "eval_samples": 64,
+    "eval_samples_per_second": 3.145,
+    "eval_steps_per_second": 0.098,
+    "eval_wer": 75.27472527472527
+}

runs/Dec12_19-20-12_13ea4557542f/events.out.tfevents.1670872941.13ea4557542f.7255.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14d37370fa62b290fb860bc578e906fe2a5176b5967438a4cf0f699cee3d39aa
+size 352

train.log

@@ -2,3 +2,9 @@
 {'eval_loss': 1.3674653768539429, 'eval_wer': 95.42124542124543, 'eval_runtime': 44.1027, 'eval_samples_per_second': 1.451, 'eval_steps_per_second': 0.045, 'epoch': 0.5}
 {'loss': 1.256, 'learning_rate': 2e-05, 'epoch': 1.0}
 {'train_runtime': 33.8193, 'train_samples_per_second': 18.924, 'train_steps_per_second': 0.591, 'train_loss': 0.041942973931630455, 'epoch': 1.05}
+***** train metrics *****
+  epoch                    =       1.05
+  train_loss               =     0.0419
+  train_runtime            = 0:00:33.81
+  train_samples_per_second =     18.924
+  train_steps_per_second   =      0.591

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.05,
+    "train_loss": 0.041942973931630455,
+    "train_runtime": 33.8193,
+    "train_samples_per_second": 18.924,
+    "train_steps_per_second": 0.591
+}

trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": 75.27472527472527,
+  "best_model_checkpoint": "./checkpoint-20",
+  "epoch": 1.05,
+  "global_step": 21,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 8.666666666666667e-05,
+      "loss": 2.4473,
+      "step": 10
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 1.3674653768539429,
+      "eval_runtime": 44.1027,
+      "eval_samples_per_second": 1.451,
+      "eval_steps_per_second": 0.045,
+      "eval_wer": 95.42124542124543,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2e-05,
+      "loss": 1.256,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.974454939365387,
+      "eval_runtime": 19.7011,
+      "eval_samples_per_second": 3.249,
+      "eval_steps_per_second": 0.102,
+      "eval_wer": 75.27472527472527,
+      "step": 20
+    },
+    {
+      "epoch": 1.05,
+      "step": 21,
+      "total_flos": 1.654389080064e+16,
+      "train_loss": 0.041942973931630455,
+      "train_runtime": 33.8193,
+      "train_samples_per_second": 18.924,
+      "train_steps_per_second": 0.591
+    }
+  ],
+  "max_steps": 20,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 1.654389080064e+16,
+  "trial_name": null,
+  "trial_params": null
+}