Training in progress, step 34800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c7bac0ecd11e105ba77bc6b9c1e49b56f9b9523b4862c6989ad212585b9e24c
+oid sha256:0f7dae2ef7ee593f3538aaa6b82ffa9d1f1c25158bce0b16bfcef64990842cf2
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19981691c62f8f347e95b064d87dda28cd05190b739901bc88cf7a374983b649
+oid sha256:c1d9d69521be3186c12bbcf7f82ad7887950292b40e89c4f0568320d47d007ec
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce15f59f8cb64bc668dfb4e258be90d962b7c8172b3c45431bfac7361d50154f
+oid sha256:d192b17c946d4e8c6ffa043d27c88285e9730f8f25c4548f4ebad751766fe79d
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9dbb3e5d0fc7426e887c7892235a6eb2991774261a344c85f92b5b41d28ebaf
+oid sha256:ccad179fca47f744bd8841fa7b8ffca61f638eb75c8ea566979a113e3a81cc55
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee882eac40b50fbdc8d881b62f827901f35cd88d24357d996c81a66bb3343b11
+oid sha256:543cf6bdade6b2853c07fa084693cf34dbcacdca498d2d62eedabfdfde62e19b
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 32400,
   "best_metric": 0.19510757441791923,
   "best_model_checkpoint": "./distil-whisper/checkpoint-32400",
-  "epoch": 24.513807233208624,
+  "epoch": 24.79885978977374,
   "eval_steps": 400,
-  "global_step": 34400,
+  "global_step": 34800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3190,6 +3190,43 @@
       "eval_steps_per_second": 0.398,
       "eval_wer": 0.19599174771588565,
       "step": 34400
+    },
+    {
+      "epoch": 24.585070372349904,
+      "grad_norm": 15.199273109436035,
+      "learning_rate": 1.7208966015907449e-06,
+      "loss": 0.99,
+      "step": 34500
+    },
+    {
+      "epoch": 24.65633351149118,
+      "grad_norm": 8.751911163330078,
+      "learning_rate": 1.4316702819956617e-06,
+      "loss": 0.9746,
+      "step": 34600
+    },
+    {
+      "epoch": 24.72759665063246,
+      "grad_norm": 11.815445899963379,
+      "learning_rate": 1.1424439624005785e-06,
+      "loss": 1.0184,
+      "step": 34700
+    },
+    {
+      "epoch": 24.79885978977374,
+      "grad_norm": 12.593855857849121,
+      "learning_rate": 8.532176428054954e-07,
+      "loss": 1.0567,
+      "step": 34800
+    },
+    {
+      "epoch": 24.79885978977374,
+      "eval_loss": 0.09248282015323639,
+      "eval_runtime": 161.1515,
+      "eval_samples_per_second": 3.103,
+      "eval_steps_per_second": 0.391,
+      "eval_wer": 0.19864426760978485,
+      "step": 34800
     }
   ],
   "logging_steps": 100,
@@ -3209,7 +3246,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.472362331799552e+19,
+  "total_flos": 4.524395189501952e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null