Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bef927f8c396ddd8c50da8da318ff1c42907299e3a79bde434a85ac7f49a2550
+oid sha256:8b9b9dc38728326660a5803959668e45161b1b7d465252b3d56e1b257c7e95f8
 size 966995080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86c248475900a14c46742b6090ba55f11ec94c0c31bf29102e53fdbbda855f19
+oid sha256:ee777b8a52e51c9a2c54afacbb0a244e8835991713137e3ad121ba08ba6a8cc1
 size 1925064044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3540179bbcfe2a2e55d05fad49c806615d68122d33b057e8a5ff20ca08833829
+oid sha256:288431e5ace9e6b37eff2d42082421fa67fead32cec92b8c304d4a00352c2b93
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16c5423cafe411d3f46179be1a8a5339c36303199cd2d3e2b9b15fb8665e754c
+oid sha256:be67eb7baca5bcd6e24e6f8dd23860c38072729eb9b472efa943c743d281b6ca
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 21.531825600373047,
-  "best_model_checkpoint": "./whisper-small-clean_6-v5/checkpoint-1000",
-  "epoch": 1.8903591682419658,
+  "best_metric": 21.24038237351364,
+  "best_model_checkpoint": "./whisper-small-clean_6-v5/checkpoint-1500",
+  "epoch": 2.835538752362949,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,155 @@
       "eval_steps_per_second": 0.074,
       "eval_wer": 21.531825600373047,
       "step": 1000
+    },
+    {
+      "epoch": 1.9376181474480152,
+      "grad_norm": 2.2420036792755127,
+      "learning_rate": 3.2965517241379314e-06,
+      "loss": 0.07,
+      "step": 1025
+    },
+    {
+      "epoch": 1.9848771266540641,
+      "grad_norm": 2.1028268337249756,
+      "learning_rate": 3.124137931034483e-06,
+      "loss": 0.0696,
+      "step": 1050
+    },
+    {
+      "epoch": 2.0321361058601135,
+      "grad_norm": 0.9523705244064331,
+      "learning_rate": 2.9517241379310347e-06,
+      "loss": 0.0434,
+      "step": 1075
+    },
+    {
+      "epoch": 2.0793950850661624,
+      "grad_norm": 1.0530415773391724,
+      "learning_rate": 2.7793103448275864e-06,
+      "loss": 0.0361,
+      "step": 1100
+    },
+    {
+      "epoch": 2.126654064272212,
+      "grad_norm": 1.182856559753418,
+      "learning_rate": 2.606896551724138e-06,
+      "loss": 0.0338,
+      "step": 1125
+    },
+    {
+      "epoch": 2.1739130434782608,
+      "grad_norm": 1.229030966758728,
+      "learning_rate": 2.4344827586206897e-06,
+      "loss": 0.0366,
+      "step": 1150
+    },
+    {
+      "epoch": 2.22117202268431,
+      "grad_norm": 0.8785301446914673,
+      "learning_rate": 2.2620689655172414e-06,
+      "loss": 0.0335,
+      "step": 1175
+    },
+    {
+      "epoch": 2.268431001890359,
+      "grad_norm": 1.1652240753173828,
+      "learning_rate": 2.0896551724137935e-06,
+      "loss": 0.0322,
+      "step": 1200
+    },
+    {
+      "epoch": 2.3156899810964084,
+      "grad_norm": 1.4220497608184814,
+      "learning_rate": 1.917241379310345e-06,
+      "loss": 0.0336,
+      "step": 1225
+    },
+    {
+      "epoch": 2.3629489603024574,
+      "grad_norm": 1.073545217514038,
+      "learning_rate": 1.7448275862068966e-06,
+      "loss": 0.0357,
+      "step": 1250
+    },
+    {
+      "epoch": 2.4102079395085068,
+      "grad_norm": 1.13935124874115,
+      "learning_rate": 1.5724137931034483e-06,
+      "loss": 0.0353,
+      "step": 1275
+    },
+    {
+      "epoch": 2.4574669187145557,
+      "grad_norm": 1.7006205320358276,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 0.0333,
+      "step": 1300
+    },
+    {
+      "epoch": 2.504725897920605,
+      "grad_norm": 1.1877566576004028,
+      "learning_rate": 1.2275862068965518e-06,
+      "loss": 0.0345,
+      "step": 1325
+    },
+    {
+      "epoch": 2.551984877126654,
+      "grad_norm": 1.0281199216842651,
+      "learning_rate": 1.0551724137931035e-06,
+      "loss": 0.032,
+      "step": 1350
+    },
+    {
+      "epoch": 2.599243856332703,
+      "grad_norm": 1.086930274963379,
+      "learning_rate": 8.827586206896551e-07,
+      "loss": 0.0342,
+      "step": 1375
+    },
+    {
+      "epoch": 2.6465028355387523,
+      "grad_norm": 0.9773654341697693,
+      "learning_rate": 7.103448275862069e-07,
+      "loss": 0.0327,
+      "step": 1400
+    },
+    {
+      "epoch": 2.6937618147448017,
+      "grad_norm": 1.2316511869430542,
+      "learning_rate": 5.379310344827587e-07,
+      "loss": 0.035,
+      "step": 1425
+    },
+    {
+      "epoch": 2.7410207939508506,
+      "grad_norm": 1.2931500673294067,
+      "learning_rate": 3.6551724137931036e-07,
+      "loss": 0.0308,
+      "step": 1450
+    },
+    {
+      "epoch": 2.7882797731568996,
+      "grad_norm": 1.6682753562927246,
+      "learning_rate": 1.931034482758621e-07,
+      "loss": 0.0359,
+      "step": 1475
+    },
+    {
+      "epoch": 2.835538752362949,
+      "grad_norm": 1.6608833074569702,
+      "learning_rate": 2.0689655172413796e-08,
+      "loss": 0.0334,
+      "step": 1500
+    },
+    {
+      "epoch": 2.835538752362949,
+      "eval_loss": 0.27059563994407654,
+      "eval_runtime": 646.575,
+      "eval_samples_per_second": 2.359,
+      "eval_steps_per_second": 0.074,
+      "eval_wer": 21.24038237351364,
+      "step": 1500
     }
   ],
   "logging_steps": 25,
@@ -319,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.845243908186112e+19,
+  "total_flos": 2.767014535348224e+19,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null