End of training

all_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 143.0,
-    "eval_loss": 1.4602868556976318,
-    "eval_runtime": 1380.6124,
-    "eval_samples_per_second": 0.371,
+    "epoch": 171.43,
+    "eval_loss": 1.4806574583053589,
+    "eval_runtime": 1382.3743,
+    "eval_samples_per_second": 0.37,
     "eval_steps_per_second": 0.023,
-    "eval_wer": 50.56749394673123,
-    "train_loss": 3.4378880828425483e-07,
-    "train_runtime": 10.5939,
-    "train_samples_per_second": 6041.236,
-    "train_steps_per_second": 94.394
+    "eval_wer": 50.544794188861985,
+    "train_loss": 5.569725840662916e-05,
+    "train_runtime": 4535.4947,
+    "train_samples_per_second": 16.933,
+    "train_steps_per_second": 0.265
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 143.0,
-    "eval_loss": 1.4602868556976318,
-    "eval_runtime": 1380.6124,
-    "eval_samples_per_second": 0.371,
+    "epoch": 171.43,
+    "eval_loss": 1.4806574583053589,
+    "eval_runtime": 1382.3743,
+    "eval_samples_per_second": 0.37,
     "eval_steps_per_second": 0.023,
-    "eval_wer": 50.56749394673123
+    "eval_wer": 50.544794188861985
 }

runs/Dec10_09-37-22_132-145-129-157/events.out.tfevents.1670671102.132-145-129-157.108751.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3188d522185a9b6ba306435cde03da7574aabecf2970ad61c134bd905ff09937
+size 358

train_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 143.0,
-    "train_loss": 3.4378880828425483e-07,
-    "train_runtime": 10.5939,
-    "train_samples_per_second": 6041.236,
-    "train_steps_per_second": 94.394
+    "epoch": 171.43,
+    "train_loss": 5.569725840662916e-05,
+    "train_runtime": 4535.4947,
+    "train_samples_per_second": 16.933,
+    "train_steps_per_second": 0.265
 }

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 50.56749394673123,
-  "best_model_checkpoint": "./checkpoint-1000",
-  "epoch": 143.0,
-  "global_step": 1001,
+  "best_metric": 50.544794188861985,
+  "best_model_checkpoint": "./checkpoint-1200",
+  "epoch": 171.42857142857142,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -338,18 +338,84 @@
       "step": 1000
     },
     {
-      "epoch": 143.0,
-      "step": 1001,
-      "total_flos": 6.290294226518016e+19,
-      "train_loss": 3.4378880828425483e-07,
-      "train_runtime": 10.5939,
-      "train_samples_per_second": 6041.236,
-      "train_steps_per_second": 94.394
+      "epoch": 146.43,
+      "learning_rate": 1.4957983193277311e-06,
+      "loss": 0.0003,
+      "step": 1025
+    },
+    {
+      "epoch": 150.0,
+      "learning_rate": 1.2857142857142856e-06,
+      "loss": 0.0003,
+      "step": 1050
+    },
+    {
+      "epoch": 153.57,
+      "learning_rate": 1.0756302521008405e-06,
+      "loss": 0.0003,
+      "step": 1075
+    },
+    {
+      "epoch": 157.14,
+      "learning_rate": 8.65546218487395e-07,
+      "loss": 0.0003,
+      "step": 1100
+    },
+    {
+      "epoch": 157.14,
+      "eval_loss": 1.4750263690948486,
+      "eval_runtime": 1385.2093,
+      "eval_samples_per_second": 0.37,
+      "eval_steps_per_second": 0.023,
+      "eval_wer": 50.559927360774815,
+      "step": 1100
+    },
+    {
+      "epoch": 160.71,
+      "learning_rate": 6.554621848739497e-07,
+      "loss": 0.0003,
+      "step": 1125
+    },
+    {
+      "epoch": 164.29,
+      "learning_rate": 4.4537815126050424e-07,
+      "loss": 0.0003,
+      "step": 1150
+    },
+    {
+      "epoch": 167.86,
+      "learning_rate": 2.3529411764705883e-07,
+      "loss": 0.0003,
+      "step": 1175
+    },
+    {
+      "epoch": 171.43,
+      "learning_rate": 2.521008403361345e-08,
+      "loss": 0.0003,
+      "step": 1200
+    },
+    {
+      "epoch": 171.43,
+      "eval_loss": 1.4806574583053589,
+      "eval_runtime": 1382.0563,
+      "eval_samples_per_second": 0.37,
+      "eval_steps_per_second": 0.023,
+      "eval_wer": 50.544794188861985,
+      "step": 1200
+    },
+    {
+      "epoch": 171.43,
+      "step": 1200,
+      "total_flos": 7.541555843137536e+19,
+      "train_loss": 5.569725840662916e-05,
+      "train_runtime": 4535.4947,
+      "train_samples_per_second": 16.933,
+      "train_steps_per_second": 0.265
     }
   ],
-  "max_steps": 1000,
-  "num_train_epochs": 143,
-  "total_flos": 6.290294226518016e+19,
+  "max_steps": 1200,
+  "num_train_epochs": 172,
+  "total_flos": 7.541555843137536e+19,
   "trial_name": null,
   "trial_params": null
 }