Training in progress, step 23600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae610937e70b8821d3a95f673534ececaf32e1a5c7a91cc91f420b8d0b3504a6
+oid sha256:4d9a3bf99664cae27c073055518be5e618859219ce0c4cc126973844088b23e7
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d9553129d74646d0142913b2ff5bc7d5b652b86694f6f9afdd91837a9e6adbe
+oid sha256:0d112c3743b72b3d287af6914aa1b449485771c9973ab53bd8f8fa446e77f384
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd2a16c621a6088b552c6371de52b5b43ee839d9d4e2a55fdb4031859156826b
+oid sha256:926d748c36044c22d8aef249e66668c13c49aaf45151cb27dffb465ad9d47cf2
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3519c66bef03d90fe5e133b9e08c9eb6330151ddd8811e14cc9972ce967e5af2
+oid sha256:2229a15bdf42c8dbae70a65f18e33cde5c16363745edce9ae10c3d4c94d5ed8e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f584f04892a93fc2b5b61b9739764ab14cba2a6af1d9d003974cfd05c836d94
+oid sha256:a6ab58750c0d8932deb4621f0a9a0b81209e9c8b7842a4cbe67e31f97248e146
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 18400,
   "best_metric": 0.19658119658119658,
   "best_model_checkpoint": "./distil-whisper/checkpoint-18400",
-  "epoch": 16.531623017993944,
+  "epoch": 16.81667557455906,
   "eval_steps": 400,
-  "global_step": 23200,
+  "global_step": 23600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2154,6 +2154,43 @@
       "eval_steps_per_second": 0.426,
       "eval_wer": 0.2002652519893899,
       "step": 23200
+    },
+    {
+      "epoch": 16.60288615713522,
+      "grad_norm": 12.050436019897461,
+      "learning_rate": 2.4281615348379086e-06,
+      "loss": 1.1627,
+      "step": 23300
+    },
+    {
+      "epoch": 16.6741492962765,
+      "grad_norm": 13.23355484008789,
+      "learning_rate": 1.999914350563145e-06,
+      "loss": 1.1094,
+      "step": 23400
+    },
+    {
+      "epoch": 16.74541243541778,
+      "grad_norm": 11.773246765136719,
+      "learning_rate": 1.5716671662883815e-06,
+      "loss": 1.1767,
+      "step": 23500
+    },
+    {
+      "epoch": 16.81667557455906,
+      "grad_norm": 11.992323875427246,
+      "learning_rate": 1.1434199820136182e-06,
+      "loss": 1.1193,
+      "step": 23600
+    },
+    {
+      "epoch": 16.81667557455906,
+      "eval_loss": 0.09421209245920181,
+      "eval_runtime": 146.8439,
+      "eval_samples_per_second": 3.405,
+      "eval_steps_per_second": 0.429,
+      "eval_wer": 0.19908635425876806,
+      "step": 23600
     }
   ],
   "logging_steps": 100,
@@ -2173,7 +2210,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.016267524734976e+19,
+  "total_flos": 3.068300382437376e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null