End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 3.648160934448242,
+    "eval_runtime": 152.0262,
+    "eval_samples": 856,
+    "eval_samples_per_second": 5.631,
+    "eval_steps_per_second": 0.704,
+    "eval_wer": 1.0,
+    "train_loss": 3.8949092686733353,
+    "train_runtime": 4254.8706,
+    "train_samples": 3420,
+    "train_samples_per_second": 4.019,
+    "train_steps_per_second": 0.126
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 3.648160934448242,
+    "eval_runtime": 152.0262,
+    "eval_samples": 856,
+    "eval_samples_per_second": 5.631,
+    "eval_steps_per_second": 0.704,
+    "eval_wer": 1.0
+}

runs/Jun18_10-17-33_e381e886a6f2/events.out.tfevents.1687088736.e381e886a6f2.13957.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e36ac3987817d3d08425965f21e6551cd408cec72ff3dda066154516f32c318c
+size 406

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 3.8949092686733353,
+    "train_runtime": 4254.8706,
+    "train_samples": 3420,
+    "train_samples_per_second": 4.019,
+    "train_steps_per_second": 0.126
+}

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 535,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.6305501461029053,
+      "eval_runtime": 149.517,
+      "eval_samples_per_second": 5.725,
+      "eval_steps_per_second": 0.716,
+      "eval_wer": 1.0,
+      "step": 107
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.6398332118988037,
+      "eval_runtime": 149.6843,
+      "eval_samples_per_second": 5.719,
+      "eval_steps_per_second": 0.715,
+      "eval_wer": 1.0,
+      "step": 214
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.6339974403381348,
+      "eval_runtime": 149.3998,
+      "eval_samples_per_second": 5.73,
+      "eval_steps_per_second": 0.716,
+      "eval_wer": 1.0,
+      "step": 321
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.6450517177581787,
+      "eval_runtime": 148.6995,
+      "eval_samples_per_second": 5.757,
+      "eval_steps_per_second": 0.72,
+      "eval_wer": 1.0,
+      "step": 428
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 8.96551724137931e-05,
+      "loss": 3.9157,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 3.648160934448242,
+      "eval_runtime": 149.436,
+      "eval_samples_per_second": 5.728,
+      "eval_steps_per_second": 0.716,
+      "eval_wer": 1.0,
+      "step": 535
+    },
+    {
+      "epoch": 5.0,
+      "step": 535,
+      "total_flos": 4.1064521881054213e+18,
+      "train_loss": 3.8949092686733353,
+      "train_runtime": 4254.8706,
+      "train_samples_per_second": 4.019,
+      "train_steps_per_second": 0.126
+    }
+  ],
+  "max_steps": 535,
+  "num_train_epochs": 5,
+  "total_flos": 4.1064521881054213e+18,
+  "trial_name": null,
+  "trial_params": null
+}