Training in progress, step 30000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec88174490cfeceb1eeed4a5fd12e3ce8c444f5222aa1c0363ca14c82aca47ab
+oid sha256:aac9fb703442293b19e405bf4164788bf426a64df5cc82596cf5e220aaa680b7
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a72f5c17a9f73a7ce9c5f0a27e6dbf2b25e9148a69728ce4404d21158eea6b0
+oid sha256:7d2a33825f6a5fff2b41693fbcc0f91ce6163ef73cdbd1c03e6554d0b82c5f42
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9b02826eed8232c5d6f49534a02071ef467235ea90c4dc0efe574539d40a7df
+oid sha256:4b5cc2e059bf5994720338ae5c6e6dec69e298afa0568c75f8adaffc4768726d
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8138f4edda6774d231042061422daa95c14292f7d8422fb63a164ad1a3d05072
+oid sha256:c6d46aec3833efc2c92b1486514727c87c4f32a04aeafab142f4a8c156f76f8d
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:632f25ed3184110f036602f4425c7c10f68cae7f3c7d7478f62304f907d5484f
+oid sha256:3ba53b40b2a30a25e436425c9258142131e66d9a345f8a16e78444d8fcb29696
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 28000,
   "best_metric": 0.18110816386678455,
   "best_model_checkpoint": "./distil-whisper/checkpoint-28000",
-  "epoch": 16.988869361452842,
+  "epoch": 17.57469244288225,
   "eval_steps": 1000,
-  "global_step": 29000,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2299,6 +2299,85 @@
       "eval_steps_per_second": 0.433,
       "eval_wer": 0.18493958149130563,
       "step": 29000
+    },
+    {
+      "epoch": 17.047451669595784,
+      "grad_norm": 6.7529377937316895,
+      "learning_rate": 2.2855832028930752e-05,
+      "loss": 0.8091,
+      "step": 29100
+    },
+    {
+      "epoch": 17.106033977738722,
+      "grad_norm": 6.652218341827393,
+      "learning_rate": 2.25859556323204e-05,
+      "loss": 0.7695,
+      "step": 29200
+    },
+    {
+      "epoch": 17.164616285881664,
+      "grad_norm": 7.654794692993164,
+      "learning_rate": 2.2316079235710046e-05,
+      "loss": 0.7926,
+      "step": 29300
+    },
+    {
+      "epoch": 17.223198594024606,
+      "grad_norm": 8.277422904968262,
+      "learning_rate": 2.2046202839099696e-05,
+      "loss": 0.7702,
+      "step": 29400
+    },
+    {
+      "epoch": 17.281780902167544,
+      "grad_norm": 15.797304153442383,
+      "learning_rate": 2.1776326442489342e-05,
+      "loss": 0.7597,
+      "step": 29500
+    },
+    {
+      "epoch": 17.340363210310485,
+      "grad_norm": 6.769285202026367,
+      "learning_rate": 2.150645004587899e-05,
+      "loss": 0.7588,
+      "step": 29600
+    },
+    {
+      "epoch": 17.398945518453427,
+      "grad_norm": 8.328302383422852,
+      "learning_rate": 2.123657364926864e-05,
+      "loss": 0.7719,
+      "step": 29700
+    },
+    {
+      "epoch": 17.45752782659637,
+      "grad_norm": 5.7514190673828125,
+      "learning_rate": 2.0966697252658282e-05,
+      "loss": 0.7985,
+      "step": 29800
+    },
+    {
+      "epoch": 17.516110134739307,
+      "grad_norm": 5.553383827209473,
+      "learning_rate": 2.069682085604793e-05,
+      "loss": 0.7602,
+      "step": 29900
+    },
+    {
+      "epoch": 17.57469244288225,
+      "grad_norm": 7.833782196044922,
+      "learning_rate": 2.042694445943758e-05,
+      "loss": 0.7531,
+      "step": 30000
+    },
+    {
+      "epoch": 17.57469244288225,
+      "eval_loss": 0.08400005102157593,
+      "eval_runtime": 147.1645,
+      "eval_samples_per_second": 3.398,
+      "eval_steps_per_second": 0.428,
+      "eval_wer": 0.18670792808723843,
+      "step": 30000
     }
   ],
   "logging_steps": 100,
@@ -2318,7 +2397,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.772122019135488e+19,
+  "total_flos": 3.902187903123456e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null