update model with lower lr and longer epoch

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0e36aaf1858a24d803db0a490c64e5dd62fbdad7832df57072c1b306cab70de
+oid sha256:9cb1f03e6996f45067b37846665462c9469495843102ce187588b897e28a7f4e
 size 2490659335

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6100534b99cfe1d84ca744d05d3f994e2906bad2ef513efedd3eec3e36661154
+oid sha256:8cf9e30486947e5ed90fbee04baf77edce0daadf0effb971a783e7eee53f6215
 size 1262224919

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b50cc95e12bd09b0797fb537b7270584feb80c90ed9167113cb636c72c3194d
+oid sha256:4eadfc8ad40d25eb205d452eb44ca33a8d304d9199be7da405ad3378ff843c81
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.297029702970297,
-  "global_step": 800,
+  "epoch": 23.83828382838284,
+  "global_step": 3600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -10,35 +10,133 @@
     {
       "epoch": 2.65,
       "learning_rate": 0.00023999999999999998,
-      "loss": 6.8625,
+      "loss": 6.5741,
       "step": 400
     },
     {
       "epoch": 2.65,
-      "eval_loss": 3.4594738483428955,
-      "eval_runtime": 211.356,
-      "eval_samples_per_second": 10.352,
+      "eval_loss": 3.4423439502716064,
+      "eval_runtime": 231.306,
+      "eval_samples_per_second": 9.459,
       "eval_wer": 1.0,
       "step": 400
     },
     {
       "epoch": 5.3,
-      "learning_rate": 7.832512315270935e-05,
-      "loss": 1.5787,
+      "learning_rate": 0.0002711907810499359,
+      "loss": 1.6231,
       "step": 800
     },
     {
       "epoch": 5.3,
-      "eval_loss": 0.6689605116844177,
-      "eval_runtime": 220.0088,
-      "eval_samples_per_second": 9.945,
-      "eval_wer": 0.6838202674440712,
+      "eval_loss": 0.6918022036552429,
+      "eval_runtime": 234.8428,
+      "eval_samples_per_second": 9.317,
+      "eval_wer": 0.7177260916407884,
       "step": 800
+    },
+    {
+      "epoch": 7.94,
+      "learning_rate": 0.00023277848911651725,
+      "loss": 0.5103,
+      "step": 1200
+    },
+    {
+      "epoch": 7.94,
+      "eval_loss": 0.5981740951538086,
+      "eval_runtime": 233.6413,
+      "eval_samples_per_second": 9.365,
+      "eval_wer": 0.6444007858546169,
+      "step": 1200
+    },
+    {
+      "epoch": 10.59,
+      "learning_rate": 0.0001943661971830986,
+      "loss": 0.316,
+      "step": 1600
+    },
+    {
+      "epoch": 10.59,
+      "eval_loss": 0.6127611398696899,
+      "eval_runtime": 239.3303,
+      "eval_samples_per_second": 9.142,
+      "eval_wer": 0.6053615564991445,
+      "step": 1600
+    },
+    {
+      "epoch": 13.24,
+      "learning_rate": 0.0001559539052496799,
+      "loss": 0.227,
+      "step": 2000
+    },
+    {
+      "epoch": 13.24,
+      "eval_loss": 0.6392495036125183,
+      "eval_runtime": 236.7294,
+      "eval_samples_per_second": 9.243,
+      "eval_wer": 0.5767158882058432,
+      "step": 2000
+    },
+    {
+      "epoch": 15.89,
+      "learning_rate": 0.00011754161331626119,
+      "loss": 0.1783,
+      "step": 2400
+    },
+    {
+      "epoch": 15.89,
+      "eval_loss": 0.6448690891265869,
+      "eval_runtime": 240.8912,
+      "eval_samples_per_second": 9.083,
+      "eval_wer": 0.5625831801761836,
+      "step": 2400
+    },
+    {
+      "epoch": 18.54,
+      "learning_rate": 7.91293213828425e-05,
+      "loss": 0.1346,
+      "step": 2800
+    },
+    {
+      "epoch": 18.54,
+      "eval_loss": 0.6509573459625244,
+      "eval_runtime": 238.9168,
+      "eval_samples_per_second": 9.158,
+      "eval_wer": 0.5524431206033336,
+      "step": 2800
+    },
+    {
+      "epoch": 21.19,
+      "learning_rate": 4.071702944942381e-05,
+      "loss": 0.1149,
+      "step": 3200
+    },
+    {
+      "epoch": 21.19,
+      "eval_loss": 0.7118895053863525,
+      "eval_runtime": 239.1827,
+      "eval_samples_per_second": 9.148,
+      "eval_wer": 0.5582736548577223,
+      "step": 3200
+    },
+    {
+      "epoch": 23.84,
+      "learning_rate": 2.3047375160051214e-06,
+      "loss": 0.1024,
+      "step": 3600
+    },
+    {
+      "epoch": 23.84,
+      "eval_loss": 0.6984374523162842,
+      "eval_runtime": 239.7197,
+      "eval_samples_per_second": 9.127,
+      "eval_wer": 0.5488307243805057,
+      "step": 3600
     }
   ],
-  "max_steps": 906,
-  "num_train_epochs": 6,
-  "total_flos": 3.298739982613021e+18,
+  "max_steps": 3624,
+  "num_train_epochs": 24,
+  "total_flos": 1.4828294022260212e+19,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:856f3181b05eb1e8d3fc464f45704f4c8f04c07811d54bd5f1d8ef94d984ec90
+oid sha256:172c59484ed932416417e6a198f03373837732beb2793acc906d873aa5e63514
 size 2351

vocab.json

@@ -1 +1 @@
-{"ฑ": 0, "ฆ": 1, "ช": 2, "ฏ": 3, "า": 4, "ข": 5, "ฤ": 6, "ซ": 8, "เ": 9, "ี": 10, "ค": 11, "ฐ": 12, "๊": 13, "ุ": 14, "’": 15, "ิ": 16, "ั": 17, "ษ": 18, "ม": 19, "ส": 20, "ฟ": 21, "ก": 22, "ท": 23, "ว": 24, "ถ": 25, "ล": 26, "ต": 27, "ะ": 28, "ป": 29, "ย": 30, "ฒ": 31, "ญ": 32, "ฬ": 33, "ณ": 34, "ึ": 35, "'": 36, "็": 37, "พ": 38, "้": 39, "อ": 40, "ๆ": 41, "ศ": 42, "ำ": 43, "๋": 44, "ด": 45, "ธ": 46, "ผ": 47, "บ": 48, "ํ": 49, "ฎ": 50, "ู": 51, "ง": 52, "์": 53, "ใ": 54, "ๅ": 55, "ร": 56, "ไ": 57, "ฝ": 58, "จ": 59, "่": 60, "ภ": 61, "น": 62, "ื": 63, "โ": 64, "แ": 65, "ฮ": 66, "ห": 67, "ฉ": 68, "|": 7, "[UNK]": 69, "[PAD]": 70}
+{"ู": 0, "ั": 1, "ะ": 2, "ฆ": 3, "ำ": 4, "ึ": 5, "๋": 6, "ส": 7, "์": 8, "ฮ": 9, "ค": 10, "่": 11, "ผ": 12, "ศ": 13, "จ": 14, "ล": 15, "ฒ": 16, "ป": 17, "ม": 18, "็": 19, "’": 20, "ง": 21, "ํ": 22, "ฝ": 23, "ื": 24, "โ": 25, "ห": 26, "้": 27, "ษ": 29, "ๆ": 30, "า": 31, "ฟ": 32, "แ": 33, "ด": 34, "ท": 35, "ใ": 36, "ณ": 37, "ฬ": 38, "ไ": 39, "ๅ": 40, "อ": 41, "ี": 42, "๊": 43, "บ": 44, "ย": 45, "ิ": 46, "ฉ": 47, "ภ": 48, "ฏ": 49, "ข": 50, "ก": 51, "'": 52, "เ": 53, "พ": 54, "ฐ": 55, "ญ": 56, "น": 57, "ธ": 58, "ถ": 59, "ซ": 60, "ร": 61, "ฤ": 62, "ช": 63, "ุ": 64, "ต": 65, "ฑ": 66, "ฎ": 67, "ว": 68, "|": 28, "[UNK]": 69, "[PAD]": 70}