Training in progress, step 8000, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cdd883a5460a3d6fef3ba86dc48a5c7818f0b59f546569efce6e0c6c05644fb
+oid sha256:da65298fcbe65ec90ace7a34200b691786bbbf741cb0bcefde53bae793c0c150
 size 4993448880

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c3361154434454a2c82e489b524924f18144e43f09f9bc443707201e953d6cb
+oid sha256:05b4684e020b85bbfca68cd478e00f24ed336b20da011cf724b3610bbdaf0ebb
 size 1180663192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8225f7d2b350449309cf6cb95eacece99044be12a3a7aa483bdf0783e22ec40f
+oid sha256:bab032ab8a6d161826bec34f3047be0921deb634160832f7b92503b7128c5ea4
 size 3095446256

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da289394bd41e2cdd34e1fa9b7ba6ae9221802035398fe0e37a4ddc28b5db9f6
+oid sha256:a2de0b7a38bec3fb98aa32f323336a214d83264d9703f7d612b7245ed18581e0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:380aebeeba070e703dcd469862cff7b4aace5b115dadb0d7385847d018530611
+oid sha256:0c52f6b6405132e6ee658c09ea95ff4a1e46ef9dee4259ea08581b6ffffd433f
 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": 41.91616766467066,
+  "epoch": 47.90419161676647,
   "eval_steps": 1000,
-  "global_step": 7000,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1750,6 +1750,255 @@
       "eval_steps_per_second": 0.089,
       "eval_wer": 42.35190583576261,
       "step": 7000
+    },
+    {
+      "epoch": 42.07,
+      "learning_rate": 6.654871794871795e-07,
+      "loss": 0.0011,
+      "step": 7025
+    },
+    {
+      "epoch": 42.22,
+      "learning_rate": 6.642051282051282e-07,
+      "loss": 0.0009,
+      "step": 7050
+    },
+    {
+      "epoch": 42.37,
+      "learning_rate": 6.629230769230769e-07,
+      "loss": 0.001,
+      "step": 7075
+    },
+    {
+      "epoch": 42.51,
+      "learning_rate": 6.616410256410256e-07,
+      "loss": 0.0011,
+      "step": 7100
+    },
+    {
+      "epoch": 42.66,
+      "learning_rate": 6.603589743589744e-07,
+      "loss": 0.0014,
+      "step": 7125
+    },
+    {
+      "epoch": 42.81,
+      "learning_rate": 6.590769230769231e-07,
+      "loss": 0.001,
+      "step": 7150
+    },
+    {
+      "epoch": 42.96,
+      "learning_rate": 6.577948717948718e-07,
+      "loss": 0.0012,
+      "step": 7175
+    },
+    {
+      "epoch": 43.11,
+      "learning_rate": 6.565128205128205e-07,
+      "loss": 0.0011,
+      "step": 7200
+    },
+    {
+      "epoch": 43.26,
+      "learning_rate": 6.552307692307693e-07,
+      "loss": 0.001,
+      "step": 7225
+    },
+    {
+      "epoch": 43.41,
+      "learning_rate": 6.539487179487179e-07,
+      "loss": 0.0015,
+      "step": 7250
+    },
+    {
+      "epoch": 43.56,
+      "learning_rate": 6.526666666666666e-07,
+      "loss": 0.0016,
+      "step": 7275
+    },
+    {
+      "epoch": 43.71,
+      "learning_rate": 6.513846153846153e-07,
+      "loss": 0.0017,
+      "step": 7300
+    },
+    {
+      "epoch": 43.86,
+      "learning_rate": 6.501025641025641e-07,
+      "loss": 0.0014,
+      "step": 7325
+    },
+    {
+      "epoch": 44.01,
+      "learning_rate": 6.488205128205128e-07,
+      "loss": 0.0012,
+      "step": 7350
+    },
+    {
+      "epoch": 44.16,
+      "learning_rate": 6.475384615384615e-07,
+      "loss": 0.0014,
+      "step": 7375
+    },
+    {
+      "epoch": 44.31,
+      "learning_rate": 6.462564102564102e-07,
+      "loss": 0.001,
+      "step": 7400
+    },
+    {
+      "epoch": 44.46,
+      "learning_rate": 6.44974358974359e-07,
+      "loss": 0.0011,
+      "step": 7425
+    },
+    {
+      "epoch": 44.61,
+      "learning_rate": 6.436923076923077e-07,
+      "loss": 0.0012,
+      "step": 7450
+    },
+    {
+      "epoch": 44.76,
+      "learning_rate": 6.424102564102564e-07,
+      "loss": 0.0011,
+      "step": 7475
+    },
+    {
+      "epoch": 44.91,
+      "learning_rate": 6.411282051282051e-07,
+      "loss": 0.0012,
+      "step": 7500
+    },
+    {
+      "epoch": 45.06,
+      "learning_rate": 6.398461538461539e-07,
+      "loss": 0.0011,
+      "step": 7525
+    },
+    {
+      "epoch": 45.21,
+      "learning_rate": 6.385641025641026e-07,
+      "loss": 0.0008,
+      "step": 7550
+    },
+    {
+      "epoch": 45.36,
+      "learning_rate": 6.372820512820513e-07,
+      "loss": 0.001,
+      "step": 7575
+    },
+    {
+      "epoch": 45.51,
+      "learning_rate": 6.36e-07,
+      "loss": 0.0011,
+      "step": 7600
+    },
+    {
+      "epoch": 45.66,
+      "learning_rate": 6.347179487179488e-07,
+      "loss": 0.0009,
+      "step": 7625
+    },
+    {
+      "epoch": 45.81,
+      "learning_rate": 6.334358974358974e-07,
+      "loss": 0.0011,
+      "step": 7650
+    },
+    {
+      "epoch": 45.96,
+      "learning_rate": 6.321538461538461e-07,
+      "loss": 0.0009,
+      "step": 7675
+    },
+    {
+      "epoch": 46.11,
+      "learning_rate": 6.308717948717948e-07,
+      "loss": 0.0007,
+      "step": 7700
+    },
+    {
+      "epoch": 46.26,
+      "learning_rate": 6.295897435897435e-07,
+      "loss": 0.0006,
+      "step": 7725
+    },
+    {
+      "epoch": 46.41,
+      "learning_rate": 6.283076923076923e-07,
+      "loss": 0.0006,
+      "step": 7750
+    },
+    {
+      "epoch": 46.56,
+      "learning_rate": 6.27025641025641e-07,
+      "loss": 0.0008,
+      "step": 7775
+    },
+    {
+      "epoch": 46.71,
+      "learning_rate": 6.257435897435897e-07,
+      "loss": 0.0007,
+      "step": 7800
+    },
+    {
+      "epoch": 46.86,
+      "learning_rate": 6.244615384615384e-07,
+      "loss": 0.0008,
+      "step": 7825
+    },
+    {
+      "epoch": 47.01,
+      "learning_rate": 6.231794871794872e-07,
+      "loss": 0.0007,
+      "step": 7850
+    },
+    {
+      "epoch": 47.16,
+      "learning_rate": 6.218974358974358e-07,
+      "loss": 0.0005,
+      "step": 7875
+    },
+    {
+      "epoch": 47.31,
+      "learning_rate": 6.206153846153845e-07,
+      "loss": 0.0005,
+      "step": 7900
+    },
+    {
+      "epoch": 47.46,
+      "learning_rate": 6.193333333333332e-07,
+      "loss": 0.0005,
+      "step": 7925
+    },
+    {
+      "epoch": 47.6,
+      "learning_rate": 6.18051282051282e-07,
+      "loss": 0.0004,
+      "step": 7950
+    },
+    {
+      "epoch": 47.75,
+      "learning_rate": 6.167692307692307e-07,
+      "loss": 0.0004,
+      "step": 7975
+    },
+    {
+      "epoch": 47.9,
+      "learning_rate": 6.154871794871794e-07,
+      "loss": 0.0005,
+      "step": 8000
+    },
+    {
+      "epoch": 47.9,
+      "eval_loss": 0.7143049240112305,
+      "eval_runtime": 593.312,
+      "eval_samples_per_second": 0.706,
+      "eval_steps_per_second": 0.089,
+      "eval_wer": 42.22540014300644,
+      "step": 8000
     }
   ],
   "logging_steps": 25,
@@ -1757,7 +2006,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 120,
   "save_steps": 1000,
-  "total_flos": 3.801019180430131e+20,
+  "total_flos": 4.3440073597845504e+20,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null