End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 3.198709011077881,
+    "eval_runtime": 301.945,
+    "eval_samples": 1684,
+    "eval_samples_per_second": 5.577,
+    "eval_steps_per_second": 0.699,
+    "eval_wer": 1.0,
+    "train_loss": 7.086420855944669,
+    "train_runtime": 3137.6984,
+    "train_samples": 5053,
+    "train_samples_per_second": 3.221,
+    "train_steps_per_second": 0.201
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 3.198709011077881,
+    "eval_runtime": 301.945,
+    "eval_samples": 1684,
+    "eval_samples_per_second": 5.577,
+    "eval_steps_per_second": 0.699,
+    "eval_wer": 1.0
+}

runs/Nov22_20-37-30_face223ae11a/events.out.tfevents.1669158139.face223ae11a.699.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a19ff62aeeea6cf107853a60680bfc5b41cfb1702ef9d7cd994e228881cafd08
+size 358

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 7.086420855944669,
+    "train_runtime": 3137.6984,
+    "train_samples": 5053,
+    "train_samples_per_second": 3.221,
+    "train_steps_per_second": 0.201
+}

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 3.198709011077881,
+  "best_model_checkpoint": "./xls-r-300m-nyanja-fullset/checkpoint-500",
+  "epoch": 2.0,
+  "global_step": 632,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.98e-06,
+      "loss": 16.4299,
+      "step": 100
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.96e-06,
+      "loss": 11.8017,
+      "step": 200
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 5.96e-06,
+      "loss": 5.1722,
+      "step": 300
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 7.96e-06,
+      "loss": 3.9289,
+      "step": 400
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.960000000000001e-06,
+      "loss": 3.3815,
+      "step": 500
+    },
+    {
+      "epoch": 1.58,
+      "eval_loss": 3.198709011077881,
+      "eval_runtime": 304.4784,
+      "eval_samples_per_second": 5.531,
+      "eval_steps_per_second": 0.693,
+      "eval_wer": 1.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.196e-05,
+      "loss": 3.1096,
+      "step": 600
+    },
+    {
+      "epoch": 2.0,
+      "step": 632,
+      "total_flos": 2.9733883621978947e+18,
+      "train_loss": 7.086420855944669,
+      "train_runtime": 3137.6984,
+      "train_samples_per_second": 3.221,
+      "train_steps_per_second": 0.201
+    }
+  ],
+  "max_steps": 632,
+  "num_train_epochs": 2,
+  "total_flos": 2.9733883621978947e+18,
+  "trial_name": null,
+  "trial_params": null
+}