End of training

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 3.0,
-    "eval_loss": 0.3033297657966614,
-    "eval_runtime": 395.7148,
+    "epoch": 6.0,
+    "eval_loss": 0.27584555745124817,
+    "eval_runtime": 371.4251,
     "eval_samples": 4297,
-    "eval_samples_per_second": 10.859,
-    "eval_steps_per_second": 0.341,
-    "eval_wer": 0.19506011201512932,
-    "train_loss": 0.46717894900821066,
-    "train_runtime": 42700.8803,
+    "eval_samples_per_second": 11.569,
+    "eval_steps_per_second": 0.363,
+    "eval_wer": 0.17918264285046293,
+    "train_loss": 0.5975231319014925,
+    "train_runtime": 88923.2167,
     "train_samples": 240334,
-    "train_samples_per_second": 16.885,
-    "train_steps_per_second": 0.132
+    "train_samples_per_second": 16.216,
+    "train_steps_per_second": 0.127
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 3.0,
-    "eval_loss": 0.3033297657966614,
-    "eval_runtime": 395.7148,
+    "epoch": 6.0,
+    "eval_loss": 0.27584555745124817,
+    "eval_runtime": 371.4251,
     "eval_samples": 4297,
-    "eval_samples_per_second": 10.859,
-    "eval_steps_per_second": 0.341,
-    "eval_wer": 0.19506011201512932
+    "eval_samples_per_second": 11.569,
+    "eval_steps_per_second": 0.363,
+    "eval_wer": 0.17918264285046293
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a05be9118ae044d3c6958be4c34d587836260410070d92f1137dca25860b760
+oid sha256:f89ec5de9dd87da4f2a4c2382f07f15a131a2b2c9de36a7ae27f30c07f7e2540
 size 1262112241

runs/Jan29_11-55-18_job-336a688f-553a-4e6e-83b3-ad5d10274b51/events.out.tfevents.1643460077.job-336a688f-553a-4e6e-83b3-ad5d10274b51.1539029.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60869ad2db0b6adf88d1fcfa5c0248d385effdf7ebc963a710fb67b170b81db3
-size 5695
+oid sha256:1247dfe6bd0d58cb74bf4ef78970d1f112256fcf3df6fe455135e580b51f0fe3
+size 10324

runs/Jan29_11-55-18_job-336a688f-553a-4e6e-83b3-ad5d10274b51/events.out.tfevents.1643549374.job-336a688f-553a-4e6e-83b3-ad5d10274b51.1539029.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ea16ea09e4540e71e147fec1294192500786f27cab5e5cc71cbb8e3a338092a
+size 358

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 0.46717894900821066,
-    "train_runtime": 42700.8803,
+    "epoch": 6.0,
+    "train_loss": 0.5975231319014925,
+    "train_runtime": 88923.2167,
     "train_samples": 240334,
-    "train_samples_per_second": 16.885,
-    "train_steps_per_second": 0.132
+    "train_samples_per_second": 16.216,
+    "train_steps_per_second": 0.127
 }

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.9996005858074826,
-  "global_step": 5631,
+  "epoch": 5.999600585807483,
+  "global_step": 11262,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -173,18 +173,183 @@
       "step": 5500
     },
     {
-      "epoch": 3.0,
-      "step": 5631,
-      "total_flos": 1.4549289807228204e+20,
-      "train_loss": 0.46717894900821066,
-      "train_runtime": 42700.8803,
-      "train_samples_per_second": 16.885,
-      "train_steps_per_second": 0.132
+      "epoch": 3.2,
+      "learning_rate": 4.263388037141005e-05,
+      "loss": 1.213,
+      "step": 6000
+    },
+    {
+      "epoch": 3.2,
+      "eval_loss": 0.3051116168498993,
+      "eval_runtime": 371.5477,
+      "eval_samples_per_second": 11.565,
+      "eval_steps_per_second": 0.363,
+      "eval_wer": 0.19797998690732255,
+      "step": 6000
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 3.8585078816670256e-05,
+      "loss": 1.2074,
+      "step": 6500
+    },
+    {
+      "epoch": 3.46,
+      "eval_loss": 0.3011966645717621,
+      "eval_runtime": 372.0587,
+      "eval_samples_per_second": 11.549,
+      "eval_steps_per_second": 0.363,
+      "eval_wer": 0.18792148549934018,
+      "step": 6500
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 3.4536277261930465e-05,
+      "loss": 1.1918,
+      "step": 7000
+    },
+    {
+      "epoch": 3.73,
+      "eval_loss": 0.29471954703330994,
+      "eval_runtime": 372.8767,
+      "eval_samples_per_second": 11.524,
+      "eval_steps_per_second": 0.362,
+      "eval_wer": 0.18287145276764655,
+      "step": 7000
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3.0487475707190668e-05,
+      "loss": 1.1893,
+      "step": 7500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.28953900933265686,
+      "eval_runtime": 372.4558,
+      "eval_samples_per_second": 11.537,
+      "eval_steps_per_second": 0.362,
+      "eval_wer": 0.1807205129004437,
+      "step": 7500
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 2.643867415245087e-05,
+      "loss": 1.1751,
+      "step": 8000
+    },
+    {
+      "epoch": 4.26,
+      "eval_loss": 0.2877567410469055,
+      "eval_runtime": 371.9244,
+      "eval_samples_per_second": 11.553,
+      "eval_steps_per_second": 0.363,
+      "eval_wer": 0.17759281773122604,
+      "step": 8000
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 2.2389872597711073e-05,
+      "loss": 1.1628,
+      "step": 8500
+    },
+    {
+      "epoch": 4.53,
+      "eval_loss": 0.28352275490760803,
+      "eval_runtime": 373.4388,
+      "eval_samples_per_second": 11.507,
+      "eval_steps_per_second": 0.362,
+      "eval_wer": 0.1730727267059447,
+      "step": 8500
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 1.834107104297128e-05,
+      "loss": 1.1577,
+      "step": 9000
+    },
+    {
+      "epoch": 4.79,
+      "eval_loss": 0.28156954050064087,
+      "eval_runtime": 371.5997,
+      "eval_samples_per_second": 11.564,
+      "eval_steps_per_second": 0.363,
+      "eval_wer": 0.17605494768124527,
+      "step": 9000
+    },
+    {
+      "epoch": 5.06,
+      "learning_rate": 1.4300367091340963e-05,
+      "loss": 1.1448,
+      "step": 9500
+    },
+    {
+      "epoch": 5.06,
+      "eval_loss": 0.2757455110549927,
+      "eval_runtime": 373.7148,
+      "eval_samples_per_second": 11.498,
+      "eval_steps_per_second": 0.361,
+      "eval_wer": 0.17397674491100096,
+      "step": 9500
+    },
+    {
+      "epoch": 5.33,
+      "learning_rate": 1.0251565536601165e-05,
+      "loss": 1.1407,
+      "step": 10000
+    },
+    {
+      "epoch": 5.33,
+      "eval_loss": 0.2768358588218689,
+      "eval_runtime": 373.2273,
+      "eval_samples_per_second": 11.513,
+      "eval_steps_per_second": 0.362,
+      "eval_wer": 0.17976453962613131,
+      "step": 10000
+    },
+    {
+      "epoch": 5.59,
+      "learning_rate": 6.202763981861369e-06,
+      "loss": 1.1401,
+      "step": 10500
+    },
+    {
+      "epoch": 5.59,
+      "eval_loss": 0.2780420780181885,
+      "eval_runtime": 375.3753,
+      "eval_samples_per_second": 11.447,
+      "eval_steps_per_second": 0.36,
+      "eval_wer": 0.18160374907779753,
+      "step": 10500
+    },
+    {
+      "epoch": 5.86,
+      "learning_rate": 2.153962427121572e-06,
+      "loss": 1.1333,
+      "step": 11000
+    },
+    {
+      "epoch": 5.86,
+      "eval_loss": 0.2748132646083832,
+      "eval_runtime": 371.6352,
+      "eval_samples_per_second": 11.562,
+      "eval_steps_per_second": 0.363,
+      "eval_wer": 0.17495350021301578,
+      "step": 11000
+    },
+    {
+      "epoch": 6.0,
+      "step": 11262,
+      "total_flos": 3.063803468240281e+20,
+      "train_loss": 0.5975231319014925,
+      "train_runtime": 88923.2167,
+      "train_samples_per_second": 16.216,
+      "train_steps_per_second": 0.127
     }
   ],
-  "max_steps": 5631,
-  "num_train_epochs": 3,
-  "total_flos": 1.4549289807228204e+20,
+  "max_steps": 11262,
+  "num_train_epochs": 6,
+  "total_flos": 3.063803468240281e+20,
   "trial_name": null,
   "trial_params": null
 }