cp 17600

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:644e8bd2b69b37fca5754768f276d194935d131c7de9be692538bd6b5e6fb479
+oid sha256:5dc817f3687769e04e797f4a2d65e705085e218a0e605bfbc439368268116963
 size 2490339591

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de31c8911196c0ecac7af2e29267430caa4c7f19fac913f7fd19f959c8790000
+oid sha256:a9fe9ece7c8d596406cb8184e772cd600ac8713a89bd8b7cfcd2b5fcf1aef922
 size 1262065048

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aed5cf7ebeae316ea13263624242bfab7943ae4e78766c20314f6d796611af6e
+oid sha256:2b8d971c35266efc366e4ed2b2f0e0bd8cccd0cc38cab1592331781a3b1c85ea
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.055951169888097,
-  "global_step": 14800,
+  "epoch": 17.904374364191252,
+  "global_step": 17600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -524,11 +524,109 @@
       "eval_samples_per_second": 7.977,
       "eval_wer": 0.3517199017199017,
       "step": 14800
+    },
+    {
+      "epoch": 15.46,
+      "learning_rate": 0.00014787857882028285,
+      "loss": 0.0717,
+      "step": 15200
+    },
+    {
+      "epoch": 15.46,
+      "eval_loss": 0.49670103192329407,
+      "eval_runtime": 236.0843,
+      "eval_samples_per_second": 7.925,
+      "eval_wer": 0.3600737100737101,
+      "step": 15200
+    },
+    {
+      "epoch": 15.87,
+      "learning_rate": 0.00014373922042083476,
+      "loss": 0.0708,
+      "step": 15600
+    },
+    {
+      "epoch": 15.87,
+      "eval_loss": 0.46058785915374756,
+      "eval_runtime": 242.6156,
+      "eval_samples_per_second": 7.712,
+      "eval_wer": 0.35982800982800983,
+      "step": 15600
+    },
+    {
+      "epoch": 16.28,
+      "learning_rate": 0.00013959986202138666,
+      "loss": 0.0673,
+      "step": 16000
+    },
+    {
+      "epoch": 16.28,
+      "eval_loss": 0.45084264874458313,
+      "eval_runtime": 234.0195,
+      "eval_samples_per_second": 7.995,
+      "eval_wer": 0.3546683046683047,
+      "step": 16000
+    },
+    {
+      "epoch": 16.68,
+      "learning_rate": 0.0001354605036219386,
+      "loss": 0.0664,
+      "step": 16400
+    },
+    {
+      "epoch": 16.68,
+      "eval_loss": 0.4838450849056244,
+      "eval_runtime": 237.8079,
+      "eval_samples_per_second": 7.868,
+      "eval_wer": 0.35614250614250614,
+      "step": 16400
+    },
+    {
+      "epoch": 17.09,
+      "learning_rate": 0.0001313211452224905,
+      "loss": 0.0639,
+      "step": 16800
+    },
+    {
+      "epoch": 17.09,
+      "eval_loss": 0.4703587591648102,
+      "eval_runtime": 235.9394,
+      "eval_samples_per_second": 7.93,
+      "eval_wer": 0.35657248157248156,
+      "step": 16800
+    },
+    {
+      "epoch": 17.5,
+      "learning_rate": 0.0001271817868230424,
+      "loss": 0.0597,
+      "step": 17200
+    },
+    {
+      "epoch": 17.5,
+      "eval_loss": 0.47286155819892883,
+      "eval_runtime": 237.4364,
+      "eval_samples_per_second": 7.88,
+      "eval_wer": 0.35657248157248156,
+      "step": 17200
+    },
+    {
+      "epoch": 17.9,
+      "learning_rate": 0.00012304242842359434,
+      "loss": 0.068,
+      "step": 17600
+    },
+    {
+      "epoch": 17.9,
+      "eval_loss": 0.42778506875038147,
+      "eval_runtime": 235.8032,
+      "eval_samples_per_second": 7.935,
+      "eval_wer": 0.3484029484029484,
+      "step": 17600
     }
   ],
   "max_steps": 29490,
   "num_train_epochs": 30,
-  "total_flos": 8.21317833556874e+19,
+  "total_flos": 9.766671614435893e+19,
   "trial_name": null,
   "trial_params": null
 }