Training in progress, step 3000, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80b1f8d231b5ff1859039320fa0188cee6c8c45459e38193a22bc1676daee37c
+oid sha256:374ed8949342602163ff342ab341b7f2396c86df086fc325532b8011637eade8
 size 4993448880

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9006daf5d78d90bf22b0c813d9e776720f90a688af4a7bd80cbc7dc7c09b019
+oid sha256:afa46570533cc904339e6f587cf429f834efd131ac812971f1bbe438d6109678
 size 1180663192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba2a236d039fcf4f5348b184a304acbdf17c1575f2f90a02947dc19886042b45
+oid sha256:401fa0df85ea07bc908110453d152ebafc1f512885a204e1dfe675e1f118de6f
 size 3095446256

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad76ae298f288aa3230881b9dfb28684fc083c10f565ddf65a09a40de5f4dc0c
+oid sha256:80e397e2074aa93e5dab4d712d0187ee9f61d0160362667daac2e2f5af3c9baa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:318a20b90d087d5ab98fe55e815e26cf3c50d3ca88ad22e2ca83eebaaef1c1d2
+oid sha256:88b9dc452a973f46fe6cf13a85f3a4e2b3a33ff360bd385917df50f48d4a73a2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 38.2982234200539,
   "best_model_checkpoint": "warmestman/whisper-large-v3-mn-cv-fleurs/checkpoint-2000",
-  "epoch": 11.976047904191617,
+  "epoch": 17.964071856287426,
   "eval_steps": 1000,
-  "global_step": 2000,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -505,6 +505,255 @@
       "eval_steps_per_second": 0.092,
       "eval_wer": 38.2982234200539,
       "step": 2000
+    },
+    {
+      "epoch": 12.13,
+      "learning_rate": 8.394736842105263e-05,
+      "loss": 0.0152,
+      "step": 2025
+    },
+    {
+      "epoch": 12.28,
+      "learning_rate": 8.36842105263158e-05,
+      "loss": 0.0127,
+      "step": 2050
+    },
+    {
+      "epoch": 12.43,
+      "learning_rate": 8.342105263157896e-05,
+      "loss": 0.0162,
+      "step": 2075
+    },
+    {
+      "epoch": 12.57,
+      "learning_rate": 8.315789473684212e-05,
+      "loss": 0.016,
+      "step": 2100
+    },
+    {
+      "epoch": 12.72,
+      "learning_rate": 8.289473684210527e-05,
+      "loss": 0.0146,
+      "step": 2125
+    },
+    {
+      "epoch": 12.87,
+      "learning_rate": 8.263157894736843e-05,
+      "loss": 0.0202,
+      "step": 2150
+    },
+    {
+      "epoch": 13.02,
+      "learning_rate": 8.236842105263158e-05,
+      "loss": 0.0208,
+      "step": 2175
+    },
+    {
+      "epoch": 13.17,
+      "learning_rate": 8.210526315789474e-05,
+      "loss": 0.0218,
+      "step": 2200
+    },
+    {
+      "epoch": 13.32,
+      "learning_rate": 8.18421052631579e-05,
+      "loss": 0.0191,
+      "step": 2225
+    },
+    {
+      "epoch": 13.47,
+      "learning_rate": 8.157894736842105e-05,
+      "loss": 0.0182,
+      "step": 2250
+    },
+    {
+      "epoch": 13.62,
+      "learning_rate": 8.131578947368421e-05,
+      "loss": 0.02,
+      "step": 2275
+    },
+    {
+      "epoch": 13.77,
+      "learning_rate": 8.105263157894737e-05,
+      "loss": 0.0227,
+      "step": 2300
+    },
+    {
+      "epoch": 13.92,
+      "learning_rate": 8.078947368421052e-05,
+      "loss": 0.0215,
+      "step": 2325
+    },
+    {
+      "epoch": 14.07,
+      "learning_rate": 8.052631578947368e-05,
+      "loss": 0.0207,
+      "step": 2350
+    },
+    {
+      "epoch": 14.22,
+      "learning_rate": 8.026315789473685e-05,
+      "loss": 0.0174,
+      "step": 2375
+    },
+    {
+      "epoch": 14.37,
+      "learning_rate": 8e-05,
+      "loss": 0.0163,
+      "step": 2400
+    },
+    {
+      "epoch": 14.52,
+      "learning_rate": 7.973684210526316e-05,
+      "loss": 0.0161,
+      "step": 2425
+    },
+    {
+      "epoch": 14.67,
+      "learning_rate": 7.947368421052632e-05,
+      "loss": 0.014,
+      "step": 2450
+    },
+    {
+      "epoch": 14.82,
+      "learning_rate": 7.921052631578948e-05,
+      "loss": 0.0157,
+      "step": 2475
+    },
+    {
+      "epoch": 14.97,
+      "learning_rate": 7.894736842105263e-05,
+      "loss": 0.0171,
+      "step": 2500
+    },
+    {
+      "epoch": 15.12,
+      "learning_rate": 7.868421052631579e-05,
+      "loss": 0.0111,
+      "step": 2525
+    },
+    {
+      "epoch": 15.27,
+      "learning_rate": 7.842105263157895e-05,
+      "loss": 0.0119,
+      "step": 2550
+    },
+    {
+      "epoch": 15.42,
+      "learning_rate": 7.81578947368421e-05,
+      "loss": 0.0136,
+      "step": 2575
+    },
+    {
+      "epoch": 15.57,
+      "learning_rate": 7.789473684210526e-05,
+      "loss": 0.0148,
+      "step": 2600
+    },
+    {
+      "epoch": 15.72,
+      "learning_rate": 7.763157894736843e-05,
+      "loss": 0.0123,
+      "step": 2625
+    },
+    {
+      "epoch": 15.87,
+      "learning_rate": 7.736842105263159e-05,
+      "loss": 0.0108,
+      "step": 2650
+    },
+    {
+      "epoch": 16.02,
+      "learning_rate": 7.710526315789474e-05,
+      "loss": 0.013,
+      "step": 2675
+    },
+    {
+      "epoch": 16.17,
+      "learning_rate": 7.68421052631579e-05,
+      "loss": 0.0106,
+      "step": 2700
+    },
+    {
+      "epoch": 16.32,
+      "learning_rate": 7.657894736842105e-05,
+      "loss": 0.0123,
+      "step": 2725
+    },
+    {
+      "epoch": 16.47,
+      "learning_rate": 7.631578947368422e-05,
+      "loss": 0.0152,
+      "step": 2750
+    },
+    {
+      "epoch": 16.62,
+      "learning_rate": 7.605263157894738e-05,
+      "loss": 0.0126,
+      "step": 2775
+    },
+    {
+      "epoch": 16.77,
+      "learning_rate": 7.578947368421054e-05,
+      "loss": 0.0137,
+      "step": 2800
+    },
+    {
+      "epoch": 16.92,
+      "learning_rate": 7.55263157894737e-05,
+      "loss": 0.0163,
+      "step": 2825
+    },
+    {
+      "epoch": 17.07,
+      "learning_rate": 7.526315789473685e-05,
+      "loss": 0.0132,
+      "step": 2850
+    },
+    {
+      "epoch": 17.22,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.011,
+      "step": 2875
+    },
+    {
+      "epoch": 17.37,
+      "learning_rate": 7.473684210526316e-05,
+      "loss": 0.0094,
+      "step": 2900
+    },
+    {
+      "epoch": 17.51,
+      "learning_rate": 7.447368421052632e-05,
+      "loss": 0.0094,
+      "step": 2925
+    },
+    {
+      "epoch": 17.66,
+      "learning_rate": 7.421052631578948e-05,
+      "loss": 0.0107,
+      "step": 2950
+    },
+    {
+      "epoch": 17.81,
+      "learning_rate": 7.394736842105263e-05,
+      "loss": 0.011,
+      "step": 2975
+    },
+    {
+      "epoch": 17.96,
+      "learning_rate": 7.368421052631579e-05,
+      "loss": 0.012,
+      "step": 3000
+    },
+    {
+      "epoch": 17.96,
+      "eval_loss": 0.5328223705291748,
+      "eval_runtime": 578.3593,
+      "eval_samples_per_second": 0.724,
+      "eval_steps_per_second": 0.092,
+      "eval_wer": 38.54023431054397,
+      "step": 3000
     }
   ],
   "logging_steps": 25,
@@ -512,7 +761,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 60,
   "save_steps": 1000,
-  "total_flos": 1.0860782836580352e+20,
+  "total_flos": 1.6290664630124544e+20,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null