End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 1.18,
+    "eval_loss": 0.05235398933291435,
+    "eval_runtime": 552.5432,
+    "eval_samples": 1957,
+    "eval_samples_per_second": 3.542,
+    "eval_steps_per_second": 0.887,
+    "eval_wer": 0.030392570704938792,
+    "train_loss": 0.2986385275920232,
+    "train_runtime": 6075.1114,
+    "train_samples": 8140,
+    "train_samples_per_second": 1.58,
+    "train_steps_per_second": 0.049
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.18,
+    "eval_loss": 0.05235398933291435,
+    "eval_runtime": 552.5432,
+    "eval_samples": 1957,
+    "eval_samples_per_second": 3.542,
+    "eval_steps_per_second": 0.887,
+    "eval_wer": 0.030392570704938792
+}

runs/May12_11-26-29_d5a36637e51e/events.out.tfevents.1683897940.d5a36637e51e.23778.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64804edc2b3229cb4157ae2b003a47be03457d022b78d5ddd99bef2733278967
+size 358

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.18,
+    "train_loss": 0.2986385275920232,
+    "train_runtime": 6075.1114,
+    "train_samples": 8140,
+    "train_samples_per_second": 1.58,
+    "train_steps_per_second": 0.049
+}

trainer_state.json

@@ -0,0 +1,151 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.1793611793611793,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.3000000000000004e-06,
+      "loss": 2.1385,
+      "step": 25
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.5702,
+      "step": 50
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 0.25573939085006714,
+      "eval_runtime": 560.3577,
+      "eval_samples_per_second": 3.492,
+      "eval_steps_per_second": 0.874,
+      "eval_wer": 0.10067539046010975,
+      "step": 50
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 0.182,
+      "step": 75
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.7e-06,
+      "loss": 0.1181,
+      "step": 100
+    },
+    {
+      "epoch": 0.39,
+      "eval_loss": 0.11441328376531601,
+      "eval_runtime": 575.9655,
+      "eval_samples_per_second": 3.398,
+      "eval_steps_per_second": 0.851,
+      "eval_wer": 0.07750105529759392,
+      "step": 100
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 8.900000000000001e-06,
+      "loss": 0.1092,
+      "step": 125
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.650000000000001e-06,
+      "loss": 0.1084,
+      "step": 150
+    },
+    {
+      "epoch": 0.59,
+      "eval_loss": 0.07465687394142151,
+      "eval_runtime": 564.2644,
+      "eval_samples_per_second": 3.468,
+      "eval_steps_per_second": 0.868,
+      "eval_wer": 0.04816378218657662,
+      "step": 150
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.0875,
+      "step": 175
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.150000000000001e-06,
+      "loss": 0.0737,
+      "step": 200
+    },
+    {
+      "epoch": 0.79,
+      "eval_loss": 0.06162061169743538,
+      "eval_runtime": 556.7887,
+      "eval_samples_per_second": 3.515,
+      "eval_steps_per_second": 0.88,
+      "eval_wer": 0.03685099197973828,
+      "step": 200
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.900000000000001e-06,
+      "loss": 0.0625,
+      "step": 225
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.6500000000000005e-06,
+      "loss": 0.064,
+      "step": 250
+    },
+    {
+      "epoch": 0.98,
+      "eval_loss": 0.05563344433903694,
+      "eval_runtime": 586.4235,
+      "eval_samples_per_second": 3.337,
+      "eval_steps_per_second": 0.836,
+      "eval_wer": 0.04402701561840439,
+      "step": 250
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 0.0384,
+      "step": 275
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 0.0313,
+      "step": 300
+    },
+    {
+      "epoch": 1.18,
+      "eval_loss": 0.05235398933291435,
+      "eval_runtime": 555.7607,
+      "eval_samples_per_second": 3.521,
+      "eval_steps_per_second": 0.882,
+      "eval_wer": 0.030392570704938792,
+      "step": 300
+    },
+    {
+      "epoch": 1.18,
+      "step": 300,
+      "total_flos": 9.797807213861929e+18,
+      "train_loss": 0.2986385275920232,
+      "train_runtime": 6075.1114,
+      "train_samples_per_second": 1.58,
+      "train_steps_per_second": 0.049
+    }
+  ],
+  "max_steps": 300,
+  "num_train_epochs": 2,
+  "total_flos": 9.797807213861929e+18,
+  "trial_name": null,
+  "trial_params": null
+}