Training in progress, step 10000, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13b0b8605d056f8ee7ce244a61451dfe6635de98c1b69d84b5289c60f0ab8eaa
+oid sha256:4d7f288875c8726d4f74614c4b4d578bf9f6c37fad3979dd0d09151a806084ec
 size 4993448880

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e6087bf4500e0ab3b2cab5f97f24befceaa6ebbfdae315b4bd2490c05a5d511
+oid sha256:52fbb2dcbc66d7c4ed8d2f213452b756beef85e83d9865c31ecac6cbf30b67a6
 size 1180663192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13e72aba5acacb0929adffd5014b3aaa0ab0fa8f3ab6b8a64e401afdf7596199
+oid sha256:931c79968a2b40db2a2f1274cfd99c95dae4c27c65afcce2ab924300046d3108
 size 3095446256

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33ddc40084ed0bf1ba89d8a115875f6b967da1b3460fbfda40f8da959e6708a6
+oid sha256:233fa719614ba3255a065a1e0c9c0afee77a964a4cb4878352b10cf17f61bece
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1b89bc8aed79bb7d8a2beccf0e2fe565be37ff238354d0b75a836cc8219e4fe
+oid sha256:11d4981b9ead74252fd412088033260fc7419a972daef228681b9d5d3c51ee44
 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": 53.89221556886228,
+  "epoch": 59.880239520958085,
   "eval_steps": 1000,
-  "global_step": 9000,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2248,6 +2248,255 @@
       "eval_steps_per_second": 0.089,
       "eval_wer": 42.20889940047302,
       "step": 9000
+    },
+    {
+      "epoch": 54.04,
+      "learning_rate": 5.629230769230769e-07,
+      "loss": 0.0003,
+      "step": 9025
+    },
+    {
+      "epoch": 54.19,
+      "learning_rate": 5.616410256410256e-07,
+      "loss": 0.0003,
+      "step": 9050
+    },
+    {
+      "epoch": 54.34,
+      "learning_rate": 5.603589743589743e-07,
+      "loss": 0.0003,
+      "step": 9075
+    },
+    {
+      "epoch": 54.49,
+      "learning_rate": 5.59076923076923e-07,
+      "loss": 0.0003,
+      "step": 9100
+    },
+    {
+      "epoch": 54.64,
+      "learning_rate": 5.577948717948717e-07,
+      "loss": 0.0003,
+      "step": 9125
+    },
+    {
+      "epoch": 54.79,
+      "learning_rate": 5.565128205128204e-07,
+      "loss": 0.0003,
+      "step": 9150
+    },
+    {
+      "epoch": 54.94,
+      "learning_rate": 5.552307692307692e-07,
+      "loss": 0.0003,
+      "step": 9175
+    },
+    {
+      "epoch": 55.09,
+      "learning_rate": 5.539487179487179e-07,
+      "loss": 0.0002,
+      "step": 9200
+    },
+    {
+      "epoch": 55.24,
+      "learning_rate": 5.526666666666666e-07,
+      "loss": 0.0002,
+      "step": 9225
+    },
+    {
+      "epoch": 55.39,
+      "learning_rate": 5.513846153846153e-07,
+      "loss": 0.0002,
+      "step": 9250
+    },
+    {
+      "epoch": 55.54,
+      "learning_rate": 5.501025641025641e-07,
+      "loss": 0.0002,
+      "step": 9275
+    },
+    {
+      "epoch": 55.69,
+      "learning_rate": 5.488205128205128e-07,
+      "loss": 0.0003,
+      "step": 9300
+    },
+    {
+      "epoch": 55.84,
+      "learning_rate": 5.475384615384615e-07,
+      "loss": 0.0002,
+      "step": 9325
+    },
+    {
+      "epoch": 55.99,
+      "learning_rate": 5.462564102564102e-07,
+      "loss": 0.0002,
+      "step": 9350
+    },
+    {
+      "epoch": 56.14,
+      "learning_rate": 5.44974358974359e-07,
+      "loss": 0.0002,
+      "step": 9375
+    },
+    {
+      "epoch": 56.29,
+      "learning_rate": 5.436923076923077e-07,
+      "loss": 0.0002,
+      "step": 9400
+    },
+    {
+      "epoch": 56.44,
+      "learning_rate": 5.424102564102564e-07,
+      "loss": 0.0002,
+      "step": 9425
+    },
+    {
+      "epoch": 56.59,
+      "learning_rate": 5.411282051282051e-07,
+      "loss": 0.0002,
+      "step": 9450
+    },
+    {
+      "epoch": 56.74,
+      "learning_rate": 5.398461538461539e-07,
+      "loss": 0.0002,
+      "step": 9475
+    },
+    {
+      "epoch": 56.89,
+      "learning_rate": 5.385641025641026e-07,
+      "loss": 0.0002,
+      "step": 9500
+    },
+    {
+      "epoch": 57.04,
+      "learning_rate": 5.372820512820513e-07,
+      "loss": 0.0002,
+      "step": 9525
+    },
+    {
+      "epoch": 57.19,
+      "learning_rate": 5.36e-07,
+      "loss": 0.0002,
+      "step": 9550
+    },
+    {
+      "epoch": 57.34,
+      "learning_rate": 5.347179487179488e-07,
+      "loss": 0.0002,
+      "step": 9575
+    },
+    {
+      "epoch": 57.49,
+      "learning_rate": 5.334358974358975e-07,
+      "loss": 0.0002,
+      "step": 9600
+    },
+    {
+      "epoch": 57.63,
+      "learning_rate": 5.321538461538462e-07,
+      "loss": 0.0002,
+      "step": 9625
+    },
+    {
+      "epoch": 57.78,
+      "learning_rate": 5.308717948717949e-07,
+      "loss": 0.0002,
+      "step": 9650
+    },
+    {
+      "epoch": 57.93,
+      "learning_rate": 5.295897435897437e-07,
+      "loss": 0.0002,
+      "step": 9675
+    },
+    {
+      "epoch": 58.08,
+      "learning_rate": 5.283076923076923e-07,
+      "loss": 0.0002,
+      "step": 9700
+    },
+    {
+      "epoch": 58.23,
+      "learning_rate": 5.27025641025641e-07,
+      "loss": 0.0002,
+      "step": 9725
+    },
+    {
+      "epoch": 58.38,
+      "learning_rate": 5.257435897435897e-07,
+      "loss": 0.0002,
+      "step": 9750
+    },
+    {
+      "epoch": 58.53,
+      "learning_rate": 5.244615384615385e-07,
+      "loss": 0.0002,
+      "step": 9775
+    },
+    {
+      "epoch": 58.68,
+      "learning_rate": 5.231794871794871e-07,
+      "loss": 0.0002,
+      "step": 9800
+    },
+    {
+      "epoch": 58.83,
+      "learning_rate": 5.218974358974358e-07,
+      "loss": 0.0002,
+      "step": 9825
+    },
+    {
+      "epoch": 58.98,
+      "learning_rate": 5.206153846153845e-07,
+      "loss": 0.0002,
+      "step": 9850
+    },
+    {
+      "epoch": 59.13,
+      "learning_rate": 5.193333333333332e-07,
+      "loss": 0.0002,
+      "step": 9875
+    },
+    {
+      "epoch": 59.28,
+      "learning_rate": 5.18051282051282e-07,
+      "loss": 0.0002,
+      "step": 9900
+    },
+    {
+      "epoch": 59.43,
+      "learning_rate": 5.167692307692307e-07,
+      "loss": 0.0002,
+      "step": 9925
+    },
+    {
+      "epoch": 59.58,
+      "learning_rate": 5.154871794871794e-07,
+      "loss": 0.0002,
+      "step": 9950
+    },
+    {
+      "epoch": 59.73,
+      "learning_rate": 5.142051282051281e-07,
+      "loss": 0.0002,
+      "step": 9975
+    },
+    {
+      "epoch": 59.88,
+      "learning_rate": 5.129230769230769e-07,
+      "loss": 0.0002,
+      "step": 10000
+    },
+    {
+      "epoch": 59.88,
+      "eval_loss": 0.7664361596107483,
+      "eval_runtime": 596.9914,
+      "eval_samples_per_second": 0.702,
+      "eval_steps_per_second": 0.089,
+      "eval_wer": 42.69842142896431,
+      "step": 10000
     }
   ],
   "logging_steps": 25,
@@ -2255,7 +2504,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 120,
   "save_steps": 1000,
-  "total_flos": 4.8869955391389696e+20,
+  "total_flos": 5.429983718493389e+20,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null