End of training

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 6.0,
-    "eval_loss": 0.27584555745124817,
-    "eval_runtime": 371.4251,
+    "epoch": 12.0,
+    "eval_loss": 0.25491979718208313,
+    "eval_runtime": 392.0567,
     "eval_samples": 4297,
-    "eval_samples_per_second": 11.569,
-    "eval_steps_per_second": 0.363,
-    "eval_wer": 0.17918264285046293,
-    "train_loss": 0.5975231319014925,
-    "train_runtime": 88923.2167,
+    "eval_samples_per_second": 10.96,
+    "eval_steps_per_second": 0.344,
+    "eval_wer": 0.15725760362438562,
+    "train_loss": 0.5676147035501541,
+    "train_runtime": 172546.67,
     "train_samples": 240334,
-    "train_samples_per_second": 16.216,
-    "train_steps_per_second": 0.127
+    "train_samples_per_second": 16.714,
+    "train_steps_per_second": 0.131
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 6.0,
-    "eval_loss": 0.27584555745124817,
-    "eval_runtime": 371.4251,
+    "epoch": 12.0,
+    "eval_loss": 0.25491979718208313,
+    "eval_runtime": 392.0567,
     "eval_samples": 4297,
-    "eval_samples_per_second": 11.569,
-    "eval_steps_per_second": 0.363,
-    "eval_wer": 0.17918264285046293
+    "eval_samples_per_second": 10.96,
+    "eval_steps_per_second": 0.344,
+    "eval_wer": 0.15725760362438562
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d5c1c57dbfb9637ee8f5c4ec4299da59900783a2c20dad42e953788fdce6594
+oid sha256:38f9952471847b9dbd693d34fa642974ebb6a016e7677a8ccfb3e3458f45e32a
 size 1262112241

runs/Jan30_13-38-42_job-336a688f-553a-4e6e-83b3-ad5d10274b51/events.out.tfevents.1643552601.job-336a688f-553a-4e6e-83b3-ad5d10274b51.2135399.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25f16d965553c6ef65d102e7ebf415f33a5c538682941f2ce987d0771dd2dc67
-size 15788
+oid sha256:58d2ffd14afa2fe9002da018be9ba7570c3afef91435956aa2d565252f94017e
+size 16148

runs/Jan30_13-38-42_job-336a688f-553a-4e6e-83b3-ad5d10274b51/events.out.tfevents.1643725543.job-336a688f-553a-4e6e-83b3-ad5d10274b51.2135399.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:454a150fa046a76b31aba582143cc6b1784dda9e4a4190c2b53f77438650e98f
+size 364

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 6.0,
-    "train_loss": 0.5975231319014925,
-    "train_runtime": 88923.2167,
+    "epoch": 12.0,
+    "train_loss": 0.5676147035501541,
+    "train_runtime": 172546.67,
     "train_samples": 240334,
-    "train_samples_per_second": 16.216,
-    "train_steps_per_second": 0.127
+    "train_samples_per_second": 16.714,
+    "train_steps_per_second": 0.131
 }

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.999600585807483,
-  "global_step": 11262,
+  "epoch": 11.999600585807482,
+  "global_step": 22524,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -338,18 +338,363 @@
       "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
+      "epoch": 6.13,
+      "learning_rate": 4.029916195673358e-05,
+      "loss": 1.1571,
+      "step": 11500
+    },
+    {
+      "epoch": 6.13,
+      "eval_loss": 0.2807982861995697,
+      "eval_runtime": 393.9701,
+      "eval_samples_per_second": 10.907,
+      "eval_steps_per_second": 0.343,
+      "eval_wer": 0.17083865872793208,
+      "step": 11500
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 3.8472032742155524e-05,
+      "loss": 1.1505,
+      "step": 12000
+    },
+    {
+      "epoch": 6.39,
+      "eval_loss": 0.27258625626564026,
+      "eval_runtime": 389.5937,
+      "eval_samples_per_second": 11.029,
+      "eval_steps_per_second": 0.347,
+      "eval_wer": 0.16920726955329032,
+      "step": 12000
+    },
+    {
+      "epoch": 6.66,
+      "learning_rate": 3.6648557786006625e-05,
+      "loss": 1.1519,
+      "step": 12500
+    },
+    {
+      "epoch": 6.66,
+      "eval_loss": 0.2748955190181732,
+      "eval_runtime": 387.583,
+      "eval_samples_per_second": 11.087,
+      "eval_steps_per_second": 0.348,
+      "eval_wer": 0.16539376746989204,
+      "step": 12500
+    },
+    {
+      "epoch": 6.93,
+      "learning_rate": 3.482142857142857e-05,
+      "loss": 1.136,
+      "step": 13000
+    },
+    {
+      "epoch": 6.93,
+      "eval_loss": 0.276467502117157,
+      "eval_runtime": 393.6733,
+      "eval_samples_per_second": 10.915,
+      "eval_steps_per_second": 0.343,
+      "eval_wer": 0.16425075594625768,
+      "step": 13000
+    },
+    {
+      "epoch": 7.19,
+      "learning_rate": 3.299429935685051e-05,
+      "loss": 1.1326,
+      "step": 13500
+    },
+    {
+      "epoch": 7.19,
+      "eval_loss": 0.27056241035461426,
+      "eval_runtime": 391.6082,
+      "eval_samples_per_second": 10.973,
+      "eval_steps_per_second": 0.345,
+      "eval_wer": 0.1668277273813606,
+      "step": 13500
+    },
+    {
+      "epoch": 7.46,
+      "learning_rate": 3.116717014227246e-05,
+      "loss": 1.1342,
+      "step": 14000
+    },
+    {
+      "epoch": 7.46,
+      "eval_loss": 0.26654428243637085,
+      "eval_runtime": 388.567,
+      "eval_samples_per_second": 11.059,
+      "eval_steps_per_second": 0.347,
+      "eval_wer": 0.1638247243783576,
+      "step": 14000
+    },
+    {
+      "epoch": 7.72,
+      "learning_rate": 2.9340040927694404e-05,
+      "loss": 1.1286,
+      "step": 14500
+    },
+    {
+      "epoch": 7.72,
+      "eval_loss": 0.2668865919113159,
+      "eval_runtime": 384.4478,
+      "eval_samples_per_second": 11.177,
+      "eval_steps_per_second": 0.351,
+      "eval_wer": 0.1635857310597795,
+      "step": 14500
+    },
+    {
+      "epoch": 7.99,
+      "learning_rate": 2.7516565971545504e-05,
+      "loss": 1.1243,
+      "step": 15000
+    },
+    {
+      "epoch": 7.99,
+      "eval_loss": 0.2619013488292694,
+      "eval_runtime": 392.1143,
+      "eval_samples_per_second": 10.959,
+      "eval_steps_per_second": 0.344,
+      "eval_wer": 0.16234920041148415,
+      "step": 15000
+    },
+    {
+      "epoch": 8.26,
+      "learning_rate": 2.5689436756967453e-05,
+      "loss": 1.1173,
+      "step": 15500
+    },
+    {
+      "epoch": 8.26,
+      "eval_loss": 0.2651631236076355,
+      "eval_runtime": 388.7223,
+      "eval_samples_per_second": 11.054,
+      "eval_steps_per_second": 0.347,
+      "eval_wer": 0.16037490777975208,
+      "step": 15500
+    },
+    {
+      "epoch": 8.52,
+      "learning_rate": 2.3862307542389395e-05,
+      "loss": 1.1129,
+      "step": 16000
+    },
+    {
+      "epoch": 8.52,
+      "eval_loss": 0.26095372438430786,
+      "eval_runtime": 387.1141,
+      "eval_samples_per_second": 11.1,
+      "eval_steps_per_second": 0.349,
+      "eval_wer": 0.1597514469486788,
+      "step": 16000
+    },
+    {
+      "epoch": 8.79,
+      "learning_rate": 2.203517832781134e-05,
+      "loss": 1.1091,
+      "step": 16500
+    },
+    {
+      "epoch": 8.79,
+      "eval_loss": 0.2608127295970917,
+      "eval_runtime": 386.5271,
+      "eval_samples_per_second": 11.117,
+      "eval_steps_per_second": 0.349,
+      "eval_wer": 0.15837983312031756,
+      "step": 16500
+    },
+    {
+      "epoch": 9.06,
+      "learning_rate": 2.0208049113233286e-05,
+      "loss": 1.1053,
+      "step": 17000
+    },
+    {
+      "epoch": 9.06,
+      "eval_loss": 0.2632738947868347,
+      "eval_runtime": 389.2784,
+      "eval_samples_per_second": 11.038,
+      "eval_steps_per_second": 0.347,
+      "eval_wer": 0.1664016958134605,
+      "step": 17000
+    },
+    {
+      "epoch": 9.32,
+      "learning_rate": 1.8384574157084387e-05,
+      "loss": 1.1004,
+      "step": 17500
+    },
+    {
+      "epoch": 9.32,
+      "eval_loss": 0.2594461441040039,
+      "eval_runtime": 388.9349,
+      "eval_samples_per_second": 11.048,
+      "eval_steps_per_second": 0.347,
+      "eval_wer": 0.16618348452258486,
+      "step": 17500
+    },
+    {
+      "epoch": 9.59,
+      "learning_rate": 1.6557444942506332e-05,
+      "loss": 1.0995,
+      "step": 18000
+    },
+    {
+      "epoch": 9.59,
+      "eval_loss": 0.26234543323516846,
+      "eval_runtime": 383.4387,
+      "eval_samples_per_second": 11.206,
+      "eval_steps_per_second": 0.352,
+      "eval_wer": 0.15694587320884898,
+      "step": 18000
+    },
+    {
+      "epoch": 9.86,
+      "learning_rate": 1.4730315727928276e-05,
+      "loss": 1.0964,
+      "step": 18500
+    },
+    {
+      "epoch": 9.86,
+      "eval_loss": 0.26244357228279114,
+      "eval_runtime": 384.9493,
+      "eval_samples_per_second": 11.163,
+      "eval_steps_per_second": 0.351,
+      "eval_wer": 0.15968910086557145,
+      "step": 18500
+    },
+    {
+      "epoch": 10.12,
+      "learning_rate": 1.2903186513350224e-05,
+      "loss": 1.09,
+      "step": 19000
+    },
+    {
+      "epoch": 10.12,
+      "eval_loss": 0.2576591968536377,
+      "eval_runtime": 391.5397,
+      "eval_samples_per_second": 10.975,
+      "eval_steps_per_second": 0.345,
+      "eval_wer": 0.15782910938620281,
+      "step": 19000
+    },
+    {
+      "epoch": 10.39,
+      "learning_rate": 1.108336581563048e-05,
+      "loss": 1.089,
+      "step": 19500
+    },
+    {
+      "epoch": 10.39,
+      "eval_loss": 0.25744903087615967,
+      "eval_runtime": 384.7348,
+      "eval_samples_per_second": 11.169,
+      "eval_steps_per_second": 0.351,
+      "eval_wer": 0.1531219801115995,
+      "step": 19500
+    },
+    {
+      "epoch": 10.66,
+      "learning_rate": 9.256236601052426e-06,
+      "loss": 1.0864,
+      "step": 20000
+    },
+    {
+      "epoch": 10.66,
+      "eval_loss": 0.2556162476539612,
+      "eval_runtime": 391.8515,
+      "eval_samples_per_second": 10.966,
+      "eval_steps_per_second": 0.345,
+      "eval_wer": 0.15464945914772904,
+      "step": 20000
+    },
+    {
+      "epoch": 10.92,
+      "learning_rate": 7.429107386474371e-06,
+      "loss": 1.0806,
+      "step": 20500
+    },
+    {
+      "epoch": 10.92,
+      "eval_loss": 0.2548317313194275,
+      "eval_runtime": 384.3272,
+      "eval_samples_per_second": 11.181,
+      "eval_steps_per_second": 0.351,
+      "eval_wer": 0.1583174870372102,
+      "step": 20500
+    },
+    {
+      "epoch": 11.19,
+      "learning_rate": 5.6019781718963155e-06,
+      "loss": 1.0842,
+      "step": 21000
+    },
+    {
+      "epoch": 11.19,
+      "eval_loss": 0.25501224398612976,
+      "eval_runtime": 383.8764,
+      "eval_samples_per_second": 11.194,
+      "eval_steps_per_second": 0.352,
+      "eval_wer": 0.1542026455521265,
+      "step": 21000
+    },
+    {
+      "epoch": 11.45,
+      "learning_rate": 3.774848957318261e-06,
+      "loss": 1.0805,
+      "step": 21500
+    },
+    {
+      "epoch": 11.45,
+      "eval_loss": 0.25607678294181824,
+      "eval_runtime": 388.7678,
+      "eval_samples_per_second": 11.053,
+      "eval_steps_per_second": 0.347,
+      "eval_wer": 0.15236343610046033,
+      "step": 21500
+    },
+    {
+      "epoch": 11.72,
+      "learning_rate": 1.9477197427402063e-06,
+      "loss": 1.0722,
+      "step": 22000
+    },
+    {
+      "epoch": 11.72,
+      "eval_loss": 0.25402259826660156,
+      "eval_runtime": 385.5053,
+      "eval_samples_per_second": 11.146,
+      "eval_steps_per_second": 0.35,
+      "eval_wer": 0.1565614056963538,
+      "step": 22000
+    },
+    {
+      "epoch": 11.99,
+      "learning_rate": 1.2059052816215163e-07,
+      "loss": 1.0763,
+      "step": 22500
+    },
+    {
+      "epoch": 11.99,
+      "eval_loss": 0.2549177408218384,
+      "eval_runtime": 379.953,
+      "eval_samples_per_second": 11.309,
+      "eval_steps_per_second": 0.355,
+      "eval_wer": 0.15720564855512953,
+      "step": 22500
+    },
+    {
+      "epoch": 12.0,
+      "step": 22524,
+      "total_flos": 6.281601139352125e+20,
+      "train_loss": 0.5676147035501541,
+      "train_runtime": 172546.67,
+      "train_samples_per_second": 16.714,
+      "train_steps_per_second": 0.131
     }
   ],
-  "max_steps": 11262,
-  "num_train_epochs": 6,
-  "total_flos": 3.063803468240281e+20,
+  "max_steps": 22524,
+  "num_train_epochs": 12,
+  "total_flos": 6.281601139352125e+20,
   "trial_name": null,
   "trial_params": null
 }