Training in progress, step 29000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e9c5b5c507c25afe3cf4d5aec82c7836af315794f646ccd78331b1ef69b9976
+oid sha256:ec88174490cfeceb1eeed4a5fd12e3ce8c444f5222aa1c0363ca14c82aca47ab
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37dd8023aeda17192fa3cd957ae713351d08b56ea14a8b05ae51168a5029d04
+oid sha256:2a72f5c17a9f73a7ce9c5f0a27e6dbf2b25e9148a69728ce4404d21158eea6b0
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2940908599d69a8410ea56cae7b048228912580fd3318d429840a0c58b1c925b
+oid sha256:a9b02826eed8232c5d6f49534a02071ef467235ea90c4dc0efe574539d40a7df
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbd563d83932cc7d0da7780f68883324db1a55e2e28771f70432de2590ff8acb
+oid sha256:8138f4edda6774d231042061422daa95c14292f7d8422fb63a164ad1a3d05072
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62d34f5456d530d45292bdc7a7b57a95952306ee03d49e82ed6ce0cb924518d
+oid sha256:632f25ed3184110f036602f4425c7c10f68cae7f3c7d7478f62304f907d5484f
 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": 16.403046280023432,
+  "epoch": 16.988869361452842,
   "eval_steps": 1000,
-  "global_step": 28000,
+  "global_step": 29000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2220,6 +2220,85 @@
       "eval_steps_per_second": 0.425,
       "eval_wer": 0.18110816386678455,
       "step": 28000
+    },
+    {
+      "epoch": 16.461628588166374,
+      "grad_norm": 9.010910034179688,
+      "learning_rate": 2.5554595995034276e-05,
+      "loss": 0.7898,
+      "step": 28100
+    },
+    {
+      "epoch": 16.520210896309315,
+      "grad_norm": 11.093189239501953,
+      "learning_rate": 2.5284719598423923e-05,
+      "loss": 0.7682,
+      "step": 28200
+    },
+    {
+      "epoch": 16.578793204452257,
+      "grad_norm": 7.964006423950195,
+      "learning_rate": 2.501484320181357e-05,
+      "loss": 0.7481,
+      "step": 28300
+    },
+    {
+      "epoch": 16.637375512595195,
+      "grad_norm": 10.423765182495117,
+      "learning_rate": 2.474496680520322e-05,
+      "loss": 0.7515,
+      "step": 28400
+    },
+    {
+      "epoch": 16.695957820738137,
+      "grad_norm": 6.754664897918701,
+      "learning_rate": 2.4475090408592866e-05,
+      "loss": 0.8024,
+      "step": 28500
+    },
+    {
+      "epoch": 16.75454012888108,
+      "grad_norm": 10.269820213317871,
+      "learning_rate": 2.4205214011982513e-05,
+      "loss": 0.7533,
+      "step": 28600
+    },
+    {
+      "epoch": 16.81312243702402,
+      "grad_norm": 14.783397674560547,
+      "learning_rate": 2.3935337615372163e-05,
+      "loss": 0.7937,
+      "step": 28700
+    },
+    {
+      "epoch": 16.87170474516696,
+      "grad_norm": 8.369039535522461,
+      "learning_rate": 2.366546121876181e-05,
+      "loss": 0.8246,
+      "step": 28800
+    },
+    {
+      "epoch": 16.9302870533099,
+      "grad_norm": 8.320894241333008,
+      "learning_rate": 2.3395584822151456e-05,
+      "loss": 0.7703,
+      "step": 28900
+    },
+    {
+      "epoch": 16.988869361452842,
+      "grad_norm": 10.491236686706543,
+      "learning_rate": 2.3125708425541102e-05,
+      "loss": 0.8261,
+      "step": 29000
+    },
+    {
+      "epoch": 16.988869361452842,
+      "eval_loss": 0.0840698629617691,
+      "eval_runtime": 145.4812,
+      "eval_samples_per_second": 3.437,
+      "eval_steps_per_second": 0.433,
+      "eval_wer": 0.18493958149130563,
+      "step": 29000
     }
   ],
   "logging_steps": 100,
@@ -2239,7 +2318,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.642039874879488e+19,
+  "total_flos": 3.772122019135488e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null