cp 20400

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dc817f3687769e04e797f4a2d65e705085e218a0e605bfbc439368268116963
+oid sha256:0945f1bf7c98f4ac934097e8ef8ab2919316ce53ea4cc4751119da54d414cda7
 size 2490339591

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9fe9ece7c8d596406cb8184e772cd600ac8713a89bd8b7cfcd2b5fcf1aef922
+oid sha256:a09990b9efc7ffabb4bdc496b4da095e3488af429a66a70ca846910f231ab2e3
 size 1262065048

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b8d971c35266efc366e4ed2b2f0e0bd8cccd0cc38cab1592331781a3b1c85ea
+oid sha256:37249dc8b4dcbc8b9631b65ac84943e7b2fc20fb2b2e37f4921afe4b0f120bdd
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.904374364191252,
-  "global_step": 17600,
+  "epoch": 20.752797558494404,
+  "global_step": 20400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -622,11 +622,109 @@
       "eval_samples_per_second": 7.935,
       "eval_wer": 0.3484029484029484,
       "step": 17600
+    },
+    {
+      "epoch": 18.31,
+      "learning_rate": 0.00011890307002414625,
+      "loss": 0.0582,
+      "step": 18000
+    },
+    {
+      "epoch": 18.31,
+      "eval_loss": 0.47386595606803894,
+      "eval_runtime": 238.3257,
+      "eval_samples_per_second": 7.851,
+      "eval_wer": 0.34864864864864864,
+      "step": 18000
+    },
+    {
+      "epoch": 18.72,
+      "learning_rate": 0.00011476371162469816,
+      "loss": 0.0593,
+      "step": 18400
+    },
+    {
+      "epoch": 18.72,
+      "eval_loss": 0.46009212732315063,
+      "eval_runtime": 238.7244,
+      "eval_samples_per_second": 7.837,
+      "eval_wer": 0.3468673218673219,
+      "step": 18400
+    },
+    {
+      "epoch": 19.13,
+      "learning_rate": 0.00011062435322525008,
+      "loss": 0.0554,
+      "step": 18800
+    },
+    {
+      "epoch": 19.13,
+      "eval_loss": 0.506970226764679,
+      "eval_runtime": 236.9238,
+      "eval_samples_per_second": 7.897,
+      "eval_wer": 0.34594594594594597,
+      "step": 18800
+    },
+    {
+      "epoch": 19.53,
+      "learning_rate": 0.00010648499482580198,
+      "loss": 0.0567,
+      "step": 19200
+    },
+    {
+      "epoch": 19.53,
+      "eval_loss": 0.47986453771591187,
+      "eval_runtime": 237.1448,
+      "eval_samples_per_second": 7.89,
+      "eval_wer": 0.3435503685503685,
+      "step": 19200
+    },
+    {
+      "epoch": 19.94,
+      "learning_rate": 0.00010234563642635392,
+      "loss": 0.0554,
+      "step": 19600
+    },
+    {
+      "epoch": 19.94,
+      "eval_loss": 0.47748732566833496,
+      "eval_runtime": 236.6967,
+      "eval_samples_per_second": 7.905,
+      "eval_wer": 0.34877149877149877,
+      "step": 19600
+    },
+    {
+      "epoch": 20.35,
+      "learning_rate": 9.820627802690582e-05,
+      "loss": 0.0532,
+      "step": 20000
+    },
+    {
+      "epoch": 20.35,
+      "eval_loss": 0.5038613677024841,
+      "eval_runtime": 237.1224,
+      "eval_samples_per_second": 7.89,
+      "eval_wer": 0.34342751842751845,
+      "step": 20000
+    },
+    {
+      "epoch": 20.75,
+      "learning_rate": 9.406691962745773e-05,
+      "loss": 0.0503,
+      "step": 20400
+    },
+    {
+      "epoch": 20.75,
+      "eval_loss": 0.48931312561035156,
+      "eval_runtime": 236.3616,
+      "eval_samples_per_second": 7.916,
+      "eval_wer": 0.3406633906633907,
+      "step": 20400
     }
   ],
   "max_steps": 29490,
   "num_train_epochs": 30,
-  "total_flos": 9.766671614435893e+19,
+  "total_flos": 1.1319628335303795e+20,
   "trial_name": null,
   "trial_params": null
 }