Training in progress, step 9000, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da65298fcbe65ec90ace7a34200b691786bbbf741cb0bcefde53bae793c0c150
+oid sha256:13b0b8605d056f8ee7ce244a61451dfe6635de98c1b69d84b5289c60f0ab8eaa
 size 4993448880

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05b4684e020b85bbfca68cd478e00f24ed336b20da011cf724b3610bbdaf0ebb
+oid sha256:9e6087bf4500e0ab3b2cab5f97f24befceaa6ebbfdae315b4bd2490c05a5d511
 size 1180663192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bab032ab8a6d161826bec34f3047be0921deb634160832f7b92503b7128c5ea4
+oid sha256:13e72aba5acacb0929adffd5014b3aaa0ab0fa8f3ab6b8a64e401afdf7596199
 size 3095446256

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2de0b7a38bec3fb98aa32f323336a214d83264d9703f7d612b7245ed18581e0
+oid sha256:33ddc40084ed0bf1ba89d8a115875f6b967da1b3460fbfda40f8da959e6708a6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c52f6b6405132e6ee658c09ea95ff4a1e46ef9dee4259ea08581b6ffffd433f
+oid sha256:d1b89bc8aed79bb7d8a2beccf0e2fe565be37ff238354d0b75a836cc8219e4fe
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 41.91738628238271,
   "best_model_checkpoint": "warmestman/whisper-large-v3-mn-cv-fleurs/checkpoint-6000",
-  "epoch": 47.90419161676647,
+  "epoch": 53.89221556886228,
   "eval_steps": 1000,
-  "global_step": 8000,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1999,6 +1999,255 @@
       "eval_steps_per_second": 0.089,
       "eval_wer": 42.22540014300644,
       "step": 8000
+    },
+    {
+      "epoch": 48.05,
+      "learning_rate": 6.142051282051281e-07,
+      "loss": 0.0005,
+      "step": 8025
+    },
+    {
+      "epoch": 48.2,
+      "learning_rate": 6.129230769230769e-07,
+      "loss": 0.0004,
+      "step": 8050
+    },
+    {
+      "epoch": 48.35,
+      "learning_rate": 6.116410256410256e-07,
+      "loss": 0.0004,
+      "step": 8075
+    },
+    {
+      "epoch": 48.5,
+      "learning_rate": 6.103589743589743e-07,
+      "loss": 0.0004,
+      "step": 8100
+    },
+    {
+      "epoch": 48.65,
+      "learning_rate": 6.09076923076923e-07,
+      "loss": 0.0004,
+      "step": 8125
+    },
+    {
+      "epoch": 48.8,
+      "learning_rate": 6.077948717948718e-07,
+      "loss": 0.0004,
+      "step": 8150
+    },
+    {
+      "epoch": 48.95,
+      "learning_rate": 6.065128205128205e-07,
+      "loss": 0.0005,
+      "step": 8175
+    },
+    {
+      "epoch": 49.1,
+      "learning_rate": 6.052307692307692e-07,
+      "loss": 0.0004,
+      "step": 8200
+    },
+    {
+      "epoch": 49.25,
+      "learning_rate": 6.039487179487179e-07,
+      "loss": 0.0004,
+      "step": 8225
+    },
+    {
+      "epoch": 49.4,
+      "learning_rate": 6.026666666666667e-07,
+      "loss": 0.0004,
+      "step": 8250
+    },
+    {
+      "epoch": 49.55,
+      "learning_rate": 6.013846153846154e-07,
+      "loss": 0.0004,
+      "step": 8275
+    },
+    {
+      "epoch": 49.7,
+      "learning_rate": 6.001025641025641e-07,
+      "loss": 0.0004,
+      "step": 8300
+    },
+    {
+      "epoch": 49.85,
+      "learning_rate": 5.988205128205128e-07,
+      "loss": 0.0004,
+      "step": 8325
+    },
+    {
+      "epoch": 50.0,
+      "learning_rate": 5.975384615384616e-07,
+      "loss": 0.0004,
+      "step": 8350
+    },
+    {
+      "epoch": 50.15,
+      "learning_rate": 5.962564102564103e-07,
+      "loss": 0.0003,
+      "step": 8375
+    },
+    {
+      "epoch": 50.3,
+      "learning_rate": 5.94974358974359e-07,
+      "loss": 0.0004,
+      "step": 8400
+    },
+    {
+      "epoch": 50.45,
+      "learning_rate": 5.936923076923077e-07,
+      "loss": 0.0003,
+      "step": 8425
+    },
+    {
+      "epoch": 50.6,
+      "learning_rate": 5.924102564102565e-07,
+      "loss": 0.0003,
+      "step": 8450
+    },
+    {
+      "epoch": 50.75,
+      "learning_rate": 5.911282051282051e-07,
+      "loss": 0.0003,
+      "step": 8475
+    },
+    {
+      "epoch": 50.9,
+      "learning_rate": 5.898461538461538e-07,
+      "loss": 0.0003,
+      "step": 8500
+    },
+    {
+      "epoch": 51.05,
+      "learning_rate": 5.885641025641025e-07,
+      "loss": 0.0003,
+      "step": 8525
+    },
+    {
+      "epoch": 51.2,
+      "learning_rate": 5.872820512820513e-07,
+      "loss": 0.0003,
+      "step": 8550
+    },
+    {
+      "epoch": 51.35,
+      "learning_rate": 5.86e-07,
+      "loss": 0.0003,
+      "step": 8575
+    },
+    {
+      "epoch": 51.5,
+      "learning_rate": 5.847179487179487e-07,
+      "loss": 0.0003,
+      "step": 8600
+    },
+    {
+      "epoch": 51.65,
+      "learning_rate": 5.834358974358974e-07,
+      "loss": 0.0003,
+      "step": 8625
+    },
+    {
+      "epoch": 51.8,
+      "learning_rate": 5.821538461538462e-07,
+      "loss": 0.0003,
+      "step": 8650
+    },
+    {
+      "epoch": 51.95,
+      "learning_rate": 5.808717948717949e-07,
+      "loss": 0.0003,
+      "step": 8675
+    },
+    {
+      "epoch": 52.1,
+      "learning_rate": 5.795897435897436e-07,
+      "loss": 0.0003,
+      "step": 8700
+    },
+    {
+      "epoch": 52.25,
+      "learning_rate": 5.783076923076922e-07,
+      "loss": 0.0003,
+      "step": 8725
+    },
+    {
+      "epoch": 52.4,
+      "learning_rate": 5.77025641025641e-07,
+      "loss": 0.0003,
+      "step": 8750
+    },
+    {
+      "epoch": 52.54,
+      "learning_rate": 5.757435897435897e-07,
+      "loss": 0.0003,
+      "step": 8775
+    },
+    {
+      "epoch": 52.69,
+      "learning_rate": 5.744615384615384e-07,
+      "loss": 0.0003,
+      "step": 8800
+    },
+    {
+      "epoch": 52.84,
+      "learning_rate": 5.731794871794871e-07,
+      "loss": 0.0003,
+      "step": 8825
+    },
+    {
+      "epoch": 52.99,
+      "learning_rate": 5.718974358974358e-07,
+      "loss": 0.0003,
+      "step": 8850
+    },
+    {
+      "epoch": 53.14,
+      "learning_rate": 5.706153846153846e-07,
+      "loss": 0.0003,
+      "step": 8875
+    },
+    {
+      "epoch": 53.29,
+      "learning_rate": 5.693333333333333e-07,
+      "loss": 0.0003,
+      "step": 8900
+    },
+    {
+      "epoch": 53.44,
+      "learning_rate": 5.68051282051282e-07,
+      "loss": 0.0003,
+      "step": 8925
+    },
+    {
+      "epoch": 53.59,
+      "learning_rate": 5.667692307692307e-07,
+      "loss": 0.0003,
+      "step": 8950
+    },
+    {
+      "epoch": 53.74,
+      "learning_rate": 5.654871794871795e-07,
+      "loss": 0.0003,
+      "step": 8975
+    },
+    {
+      "epoch": 53.89,
+      "learning_rate": 5.642051282051282e-07,
+      "loss": 0.0003,
+      "step": 9000
+    },
+    {
+      "epoch": 53.89,
+      "eval_loss": 0.7420342564582825,
+      "eval_runtime": 596.5217,
+      "eval_samples_per_second": 0.702,
+      "eval_steps_per_second": 0.089,
+      "eval_wer": 42.20889940047302,
+      "step": 9000
     }
   ],
   "logging_steps": 25,
@@ -2006,7 +2255,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 120,
   "save_steps": 1000,
-  "total_flos": 4.3440073597845504e+20,
+  "total_flos": 4.8869955391389696e+20,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null