Training in progress, step 200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e899319e2a6deced8832230fdfd05f5866c1c499db7790d3cc8a3fd23431bebd
+oid sha256:fca209fbf14bb03b14596a4a7a7e641686e5c741ee80a8d63177163d98de4032
 size 290403936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f52777292bc4955b21021034bd356919653befec6b7cbe5b883450548ad7558
+oid sha256:88bd5955ffa0d6a8ab77c320b1bac1d2b8c25c3ecdfa9fac75f30e17a28c7795
 size 574811514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9b1d6fb48751f5d2b47d7f0ba3ae8e90c30c9802e10d676d0257941f38d0753
+oid sha256:3b6321d2d69b9a8969ff838f442e78895a976e15f45834ce2fec948fc2a5b7ab
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46cb3a7cf266128ea12b82e6f01a8b22cd7a573c098bba1dca18d6b9fda3121d
+oid sha256:401546997e9540c36b01d5a34535bd43dfe01519d1e848bfb7825d3197c47e9d
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5065b6b7372b99dc75b33ee3c07c8e8f0697cdb322a117e8f7109e80a71e97cf
+oid sha256:f612818c5fb8e8465abfb32d1a77c014d6d3622c9188f348caa044647cbde875
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 100,
   "best_metric": 26.867363647814585,
   "best_model_checkpoint": "whisper-base-synth-v1/checkpoint-100",
-  "epoch": 1.0638297872340425,
+  "epoch": 2.127659574468085,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -46,6 +46,44 @@
       "eval_wer": 26.867363647814585,
       "eval_wer_ortho": 29.74588938714499,
       "step": 100
+    },
+    {
+      "epoch": 1.3297872340425532,
+      "grad_norm": 4.06046724319458,
+      "learning_rate": 6.489361702127659e-06,
+      "loss": 4.6403,
+      "step": 125
+    },
+    {
+      "epoch": 1.5957446808510638,
+      "grad_norm": 4.466408729553223,
+      "learning_rate": 7.819148936170213e-06,
+      "loss": 4.4984,
+      "step": 150
+    },
+    {
+      "epoch": 1.8617021276595744,
+      "grad_norm": 4.118725776672363,
+      "learning_rate": 9.148936170212767e-06,
+      "loss": 4.3114,
+      "step": 175
+    },
+    {
+      "epoch": 2.127659574468085,
+      "grad_norm": 3.9775619506835938,
+      "learning_rate": 1.047872340425532e-05,
+      "loss": 4.0801,
+      "step": 200
+    },
+    {
+      "epoch": 2.127659574468085,
+      "eval_loss": 0.42653512954711914,
+      "eval_runtime": 777.2367,
+      "eval_samples_per_second": 3.604,
+      "eval_steps_per_second": 0.057,
+      "eval_wer": 82.38653062938238,
+      "eval_wer_ortho": 79.16874273376516,
+      "step": 200
     }
   ],
   "logging_steps": 25,
@@ -65,7 +103,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.1406621548544e+17,
+  "total_flos": 8.2813243097088e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null