End of training

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+.run_speech_recognition_seq2seq_streaming.py.swp filter=lfs diff=lfs merge=lfs -text

.run_speech_recognition_seq2seq_streaming.py.swp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5afad038ca66e4a3fe2adc83255d2b1830295ec385663ae7117e72f55f25982a
+size 20480

all_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 18.52,
-    "eval_loss": 1.1797882318496704,
-    "eval_runtime": 450.6771,
-    "eval_samples_per_second": 1.136,
+    "epoch": 22.22,
+    "eval_loss": 1.2309296131134033,
+    "eval_runtime": 450.2608,
+    "eval_samples_per_second": 1.137,
     "eval_steps_per_second": 0.142,
-    "eval_wer": 57.87681598062954,
-    "train_loss": 0.0056979965269565586,
-    "train_runtime": 579.6036,
-    "train_samples_per_second": 13.803,
-    "train_steps_per_second": 0.863
+    "eval_wer": 56.651029055690074,
+    "train_loss": 0.001749273296445608,
+    "train_runtime": 576.5843,
+    "train_samples_per_second": 16.65,
+    "train_steps_per_second": 1.041
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 18.52,
-    "eval_loss": 1.1797882318496704,
-    "eval_runtime": 450.6771,
-    "eval_samples_per_second": 1.136,
+    "epoch": 22.22,
+    "eval_loss": 1.2309296131134033,
+    "eval_runtime": 450.2608,
+    "eval_samples_per_second": 1.137,
     "eval_steps_per_second": 0.142,
-    "eval_wer": 57.87681598062954
+    "eval_wer": 56.651029055690074
 }

runs/Dec16_18-03-10_129-146-104-29/events.out.tfevents.1671214896.129-146-104-29.137983.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ba67a7b84b79d789629e06628df81253985de536e93a6637efe8768b88cf00d
+size 358

train_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 18.52,
-    "train_loss": 0.0056979965269565586,
-    "train_runtime": 579.6036,
-    "train_samples_per_second": 13.803,
-    "train_steps_per_second": 0.863
+    "epoch": 22.22,
+    "train_loss": 0.001749273296445608,
+    "train_runtime": 576.5843,
+    "train_samples_per_second": 16.65,
+    "train_steps_per_second": 1.041
 }

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 57.87681598062954,
-  "best_model_checkpoint": "./checkpoint-500",
-  "epoch": 18.51851851851852,
-  "global_step": 500,
+  "best_metric": 56.651029055690074,
+  "best_model_checkpoint": "./checkpoint-600",
+  "epoch": 22.22222222222222,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -245,18 +245,87 @@
       "step": 500
     },
     {
-      "epoch": 18.52,
-      "step": 500,
-      "total_flos": 2.30348866535424e+18,
-      "train_loss": 0.0056979965269565586,
-      "train_runtime": 579.6036,
-      "train_samples_per_second": 13.803,
-      "train_steps_per_second": 0.863
+      "epoch": 18.89,
+      "learning_rate": 9.4e-06,
+      "loss": 0.019,
+      "step": 510
+    },
+    {
+      "epoch": 19.26,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 0.021,
+      "step": 520
+    },
+    {
+      "epoch": 19.63,
+      "learning_rate": 7.4e-06,
+      "loss": 0.0139,
+      "step": 530
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.013,
+      "step": 540
+    },
+    {
+      "epoch": 20.37,
+      "learning_rate": 5.400000000000001e-06,
+      "loss": 0.007,
+      "step": 550
+    },
+    {
+      "epoch": 20.74,
+      "learning_rate": 4.4e-06,
+      "loss": 0.0082,
+      "step": 560
+    },
+    {
+      "epoch": 21.11,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.009,
+      "step": 570
+    },
+    {
+      "epoch": 21.48,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.0045,
+      "step": 580
+    },
+    {
+      "epoch": 21.85,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 0.0049,
+      "step": 590
+    },
+    {
+      "epoch": 22.22,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 0.0045,
+      "step": 600
+    },
+    {
+      "epoch": 22.22,
+      "eval_loss": 1.2309296131134033,
+      "eval_runtime": 449.2432,
+      "eval_samples_per_second": 1.14,
+      "eval_steps_per_second": 0.142,
+      "eval_wer": 56.651029055690074,
+      "step": 600
+    },
+    {
+      "epoch": 22.22,
+      "step": 600,
+      "total_flos": 2.76407096426496e+18,
+      "train_loss": 0.001749273296445608,
+      "train_runtime": 576.5843,
+      "train_samples_per_second": 16.65,
+      "train_steps_per_second": 1.041
     }
   ],
-  "max_steps": 500,
-  "num_train_epochs": 19,
-  "total_flos": 2.30348866535424e+18,
+  "max_steps": 600,
+  "num_train_epochs": 23,
+  "total_flos": 2.76407096426496e+18,
   "trial_name": null,
   "trial_params": null
 }