Upload 9 files

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da38f3bc2fe6927f77f1e949dacaaa5c88d1ff1e7b5b630565b9bad55cdc8037
+oid sha256:9a895d3647e473dba8b32f7496e84d2b35bf2e8a9da7924568994ea0e23c8d96
 size 2490594117

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0e93138c7536f15d081a2517332243e990720ea7e4c526912b3a5cff073cf49
+oid sha256:5a8f6e6b312fa1b113a4c77869f2bcb7cc23f4abbc0d1ca811079f79220ece74
 size 1262168365

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:061193452a858228d1c66af4f1074191f8ac9e88dfc0f2e16c6ccd6079a33e18
+oid sha256:e6c46fdc39595e4492274898b6b3506defdd41d1ceec77870a782f04c4492b4d
 size 14639

scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7076cb3d5134abd5db45f65ae43a71e92139309531dd802207a13ea550dea80b
+oid sha256:940e29fecbb01cce370af89051d4b7e269c9468bdcab1fb705f4b1715779ddb5
 size 557

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c024168d11f393cebc0d70778a05dbba26ed981c876446f516b34a4b4b7f2cc
+oid sha256:e0606add1ed65078f140d7e321f11e032f96a3f3c5f6aec240beb600a5f0782b
 size 627

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.867992766726944,
-  "global_step": 1500,
+  "epoch": 14.491862567811935,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -10,94 +10,103 @@
     {
       "epoch": 1.09,
       "learning_rate": 9.99963765490253e-06,
-      "loss": 0.0157,
+      "loss": 0.009,
       "step": 150
     },
     {
       "epoch": 2.17,
-      "learning_rate": 9.998550619610118e-06,
-      "loss": 0.0123,
+      "learning_rate": 9.998557866512066e-06,
+      "loss": 0.0075,
       "step": 300
     },
     {
       "epoch": 3.26,
-      "learning_rate": 9.997463584317706e-06,
-      "loss": 0.0152,
+      "learning_rate": 9.997470831219655e-06,
+      "loss": 0.0088,
       "step": 450
     },
-    {
-      "epoch": 3.62,
-      "eval_loss": 0.23832739889621735,
-      "eval_runtime": 297.425,
-      "eval_samples_per_second": 13.271,
-      "eval_steps_per_second": 1.661,
-      "eval_wer": 0.17043338199023506,
-      "step": 500
-    },
     {
       "epoch": 4.35,
-      "learning_rate": 9.996376549025293e-06,
-      "loss": 0.0167,
+      "learning_rate": 9.996383795927241e-06,
+      "loss": 0.0139,
       "step": 600
     },
     {
       "epoch": 5.43,
-      "learning_rate": 9.99528951373288e-06,
-      "loss": 0.0148,
+      "learning_rate": 9.995296760634829e-06,
+      "loss": 0.0151,
       "step": 750
     },
     {
       "epoch": 6.52,
-      "learning_rate": 9.994202478440467e-06,
-      "loss": 0.0153,
+      "learning_rate": 9.994209725342417e-06,
+      "loss": 0.0148,
       "step": 900
     },
     {
       "epoch": 7.25,
-      "eval_loss": 0.24725446105003357,
-      "eval_runtime": 201.8594,
-      "eval_samples_per_second": 19.553,
-      "eval_steps_per_second": 2.447,
-      "eval_wer": 0.16867166658277546,
+      "eval_loss": 0.25712448358535767,
+      "eval_runtime": 419.2266,
+      "eval_samples_per_second": 9.415,
+      "eval_steps_per_second": 1.178,
+      "eval_wer": 0.1661549302864046,
       "step": 1000
     },
     {
       "epoch": 7.61,
-      "learning_rate": 9.993115443148055e-06,
-      "loss": 0.0163,
+      "learning_rate": 9.993122690050005e-06,
+      "loss": 0.0151,
       "step": 1050
     },
     {
       "epoch": 8.69,
-      "learning_rate": 9.992028407855643e-06,
-      "loss": 0.0158,
+      "learning_rate": 9.99203565475759e-06,
+      "loss": 0.0144,
       "step": 1200
     },
     {
       "epoch": 9.78,
       "learning_rate": 9.99094861946518e-06,
-      "loss": 0.0146,
+      "loss": 0.0131,
       "step": 1350
     },
     {
       "epoch": 10.87,
       "learning_rate": 9.989861584172766e-06,
-      "loss": 0.0154,
+      "loss": 0.0143,
       "step": 1500
     },
     {
-      "epoch": 10.87,
-      "eval_loss": 0.24820923805236816,
-      "eval_runtime": 211.4153,
-      "eval_samples_per_second": 18.669,
-      "eval_steps_per_second": 2.337,
-      "eval_wer": 0.1679669804197916,
-      "step": 1500
+      "epoch": 11.95,
+      "learning_rate": 9.988774548880354e-06,
+      "loss": 0.0141,
+      "step": 1650
+    },
+    {
+      "epoch": 13.04,
+      "learning_rate": 9.987687513587942e-06,
+      "loss": 0.0136,
+      "step": 1800
+    },
+    {
+      "epoch": 14.13,
+      "learning_rate": 9.98660772519748e-06,
+      "loss": 0.0137,
+      "step": 1950
+    },
+    {
+      "epoch": 14.49,
+      "eval_loss": 0.26535430550575256,
+      "eval_runtime": 234.4518,
+      "eval_samples_per_second": 16.835,
+      "eval_steps_per_second": 2.107,
+      "eval_wer": 0.16665827754567877,
+      "step": 2000
     }
   ],
   "max_steps": 1380000,
   "num_train_epochs": 10000,
-  "total_flos": 3.4217202294237536e+19,
+  "total_flos": 4.548899267190198e+19,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8a48147752c3a8083ebf5cdd854e3c3535a7d951355ce96dd9e8d52de7d94ab
+oid sha256:67fe320fc812e3797fe9b29ebf41e5b8a98264c8f1cd5c379b532ee8b5a418ed
 size 3323