Training in progress, step 27000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3d8f77727b5b4ef950b93d62c1b07493ebd7d4bea85543ea1654b59f3c483f3
+oid sha256:ab3400935acbe3cf5f906085ec93d6116aa5d1e99af0633a73d3e706f2cd16a6
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43f224cb291da070e142cb6ea868df08935add46875a306306495bd60678bf1d
+oid sha256:9bdd076291545d47b6464e519aaf46f4e9dfe2f8be4e7566d7c31c135a1c9323
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66432b4a08797e94140bc153b8542d6959b5455a4424229f739a5d8c8a8076a0
+oid sha256:59f831aeb48368d39337afe7a48ffe4212a4e417eb7aff215653e8d3fa1dcee0
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c33ea924ad35e1a1156b5f295ad34a99c2c9f60887c2357eaef9fdd16be7edee
+oid sha256:bc8355cb3493000d81a40060fd9086d3994b8013129a708704b751a5d7398bbe
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f76f154dd8dd104593482c38bad816b91e8cdf002cfd8b0ab080c2e1683fb35d
+oid sha256:eae2ff98708f58a5d722c91db9dc346e6b11df9cbdf8ea9de78b33a14ae6319e
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 25000,
   "best_metric": 0.18243442381373415,
   "best_model_checkpoint": "./distil-whisper/checkpoint-25000",
-  "epoch": 15.231400117164617,
+  "epoch": 15.817223198594025,
   "eval_steps": 1000,
-  "global_step": 26000,
+  "global_step": 27000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2062,6 +2062,85 @@
       "eval_steps_per_second": 0.43,
       "eval_wer": 0.1825817860300619,
       "step": 26000
+    },
+    {
+      "epoch": 15.289982425307556,
+      "grad_norm": 6.403947353363037,
+      "learning_rate": 4.572579442040878e-06,
+      "loss": 0.728,
+      "step": 26100
+    },
+    {
+      "epoch": 15.348564733450498,
+      "grad_norm": 6.236737251281738,
+      "learning_rate": 4.199612113978816e-06,
+      "loss": 0.7462,
+      "step": 26200
+    },
+    {
+      "epoch": 15.407147041593438,
+      "grad_norm": 5.554813385009766,
+      "learning_rate": 3.826644785916754e-06,
+      "loss": 0.7403,
+      "step": 26300
+    },
+    {
+      "epoch": 15.46572934973638,
+      "grad_norm": 4.909285068511963,
+      "learning_rate": 3.453677457854692e-06,
+      "loss": 0.7653,
+      "step": 26400
+    },
+    {
+      "epoch": 15.52431165787932,
+      "grad_norm": 5.502344608306885,
+      "learning_rate": 3.0807101297926304e-06,
+      "loss": 0.7319,
+      "step": 26500
+    },
+    {
+      "epoch": 15.582893966022262,
+      "grad_norm": 7.525850772857666,
+      "learning_rate": 2.7077428017305685e-06,
+      "loss": 0.7295,
+      "step": 26600
+    },
+    {
+      "epoch": 15.641476274165202,
+      "grad_norm": 7.245991230010986,
+      "learning_rate": 2.3347754736685067e-06,
+      "loss": 0.7382,
+      "step": 26700
+    },
+    {
+      "epoch": 15.700058582308143,
+      "grad_norm": 5.762548923492432,
+      "learning_rate": 1.961808145606445e-06,
+      "loss": 0.7253,
+      "step": 26800
+    },
+    {
+      "epoch": 15.758640890451083,
+      "grad_norm": 6.127166271209717,
+      "learning_rate": 1.5888408175443833e-06,
+      "loss": 0.7399,
+      "step": 26900
+    },
+    {
+      "epoch": 15.817223198594025,
+      "grad_norm": 6.195973873138428,
+      "learning_rate": 1.2158734894823213e-06,
+      "loss": 0.7379,
+      "step": 27000
+    },
+    {
+      "epoch": 15.817223198594025,
+      "eval_loss": 0.08341451734304428,
+      "eval_runtime": 146.5011,
+      "eval_samples_per_second": 3.413,
+      "eval_steps_per_second": 0.43,
+      "eval_wer": 0.18287651046271736,
+      "step": 27000
     }
   ],
   "logging_steps": 100,
@@ -2081,7 +2160,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.38189184663552e+19,
+  "total_flos": 3.51197399089152e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null