Training in progress, step 33000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:411df52b26563077a81a7b08db369d27d102503f690c603f3564427326c2c3fb
+oid sha256:0cfc2369854afc94fdfa5a772fefa0c2c28012dcdc0bc0ea80f23b73f346c34a
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:315eea51d967b636aee06c9fab61b28d456ea20155b0f905d9a2894b1cd4bb1c
+oid sha256:59a0c5737e43b8c351af0642dc5e297ba4cfc310d2333fb3515ae84242ec7206
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2615f31c2bde960c4cad72e76e8275160a20b219557b38cecad80fda50c2154
+oid sha256:576380a256a4340c462ffc82306c52abbab7f38e65a7b12e9ab2634163e0fae7
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e91277e0d15d4cadb5461d7609fda108b605cd367d55a41118269783b39513b9
+oid sha256:5680c8a2f1d27c25e08e493d045a3f651f13f689a05908b8e76432cb1f7ace3b
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06016ca44c3c2f7f6ce102c4b35b77805b28e5c34909f86718e837c850c7f578
+oid sha256:3bb6ef00c1c865d5fe6826f62f53b17ea0c3488cfae31fdb4898bd3e20b4343e
 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": 18.746338605741066,
+  "epoch": 19.332161687170476,
   "eval_steps": 1000,
-  "global_step": 32000,
+  "global_step": 33000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2536,6 +2536,85 @@
       "eval_steps_per_second": 0.433,
       "eval_wer": 0.18376068376068377,
       "step": 32000
+    },
+    {
+      "epoch": 18.804920913884008,
+      "grad_norm": 11.049666404724121,
+      "learning_rate": 1.4764937658552383e-05,
+      "loss": 0.7523,
+      "step": 32100
+    },
+    {
+      "epoch": 18.86350322202695,
+      "grad_norm": 5.7121782302856445,
+      "learning_rate": 1.4495061261942031e-05,
+      "loss": 0.7462,
+      "step": 32200
+    },
+    {
+      "epoch": 18.922085530169888,
+      "grad_norm": 6.261909008026123,
+      "learning_rate": 1.4225184865331678e-05,
+      "loss": 0.6894,
+      "step": 32300
+    },
+    {
+      "epoch": 18.98066783831283,
+      "grad_norm": 9.238897323608398,
+      "learning_rate": 1.3955308468721326e-05,
+      "loss": 0.7625,
+      "step": 32400
+    },
+    {
+      "epoch": 19.03925014645577,
+      "grad_norm": 5.913239002227783,
+      "learning_rate": 1.3685432072110973e-05,
+      "loss": 0.7324,
+      "step": 32500
+    },
+    {
+      "epoch": 19.097832454598713,
+      "grad_norm": 6.142359733581543,
+      "learning_rate": 1.3415555675500621e-05,
+      "loss": 0.7275,
+      "step": 32600
+    },
+    {
+      "epoch": 19.15641476274165,
+      "grad_norm": 8.006820678710938,
+      "learning_rate": 1.314567927889027e-05,
+      "loss": 0.7335,
+      "step": 32700
+    },
+    {
+      "epoch": 19.214997070884593,
+      "grad_norm": 10.434711456298828,
+      "learning_rate": 1.2875802882279916e-05,
+      "loss": 0.7093,
+      "step": 32800
+    },
+    {
+      "epoch": 19.273579379027534,
+      "grad_norm": 7.119588375091553,
+      "learning_rate": 1.2605926485669564e-05,
+      "loss": 0.7213,
+      "step": 32900
+    },
+    {
+      "epoch": 19.332161687170476,
+      "grad_norm": 6.306182861328125,
+      "learning_rate": 1.2336050089059211e-05,
+      "loss": 0.7008,
+      "step": 33000
+    },
+    {
+      "epoch": 19.332161687170476,
+      "eval_loss": 0.08348561823368073,
+      "eval_runtime": 148.0399,
+      "eval_samples_per_second": 3.377,
+      "eval_steps_per_second": 0.426,
+      "eval_wer": 0.18641320365458297,
+      "step": 33000
     }
   ],
   "logging_steps": 100,
@@ -2555,7 +2634,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.162335931367424e+19,
+  "total_flos": 4.292401815355392e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null