Training in progress, step 4500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0df53010fbda674d66d4e7bc9ec5ddc0a9d670bb01914b6ea6d1b3de14f8b08d
+oid sha256:fe6340c896a7c2c061df0dd733b5cf530a152b2532fd7a214b42dfcd66d3dcca
 size 151061672

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63c6a670910fe12d16745356d07433dfcc6ac6ea8edc3cb256b71fe86054182e
+oid sha256:81902ac01d8aa613a26aa6114cce08cf29471cd8ff9696ad67e2ddcd60f2d64b
 size 302227787

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a7dfa59f323bb7227795999d0c7cb18a2c95f21da91866b640cb672e937307b
+oid sha256:2fb9a2d94090c8b7124c6a39ee5f76482a7830faab97d12a16276fa23c8b2793
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d0fc538266fee5c306edf72b32800812ba484b4157c432f9c91b1ab8fe68284
+oid sha256:06c5c8055f75339b21a661c9cb8f3a65736faa1a59a4e03ad8836f33d9e6ab5f
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4624c8f27770eb1a16767e932c8100ec43af2360d1e792bedb1826eaf2f685b3
+oid sha256:426baa7f553935a148ab2ac05c277463a9fe7b24ac5c757cfb9a99895ed184c1
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 3000,
   "best_metric": 0.703578531742096,
   "best_model_checkpoint": "./openai/whisper-tiny-sid-waxal/checkpoint-3000",
-  "epoch": 3.341687552213868,
+  "epoch": 3.7593984962406015,
   "eval_steps": 500,
-  "global_step": 4000,
+  "global_step": 4500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1208,6 +1208,156 @@
       "eval_steps_per_second": 0.506,
       "eval_wer": 0.42202241587121264,
       "step": 4000
+    },
+    {
+      "epoch": 3.3625730994152048,
+      "grad_norm": 3.37201189994812,
+      "learning_rate": 9.004800903699521e-05,
+      "loss": 0.40936187744140623,
+      "step": 4025
+    },
+    {
+      "epoch": 3.3834586466165413,
+      "grad_norm": 2.939957618713379,
+      "learning_rate": 8.997740751200226e-05,
+      "loss": 0.4089693832397461,
+      "step": 4050
+    },
+    {
+      "epoch": 3.4043441938178782,
+      "grad_norm": 3.129723072052002,
+      "learning_rate": 8.990680598700933e-05,
+      "loss": 0.4094087219238281,
+      "step": 4075
+    },
+    {
+      "epoch": 3.4252297410192147,
+      "grad_norm": 3.143145799636841,
+      "learning_rate": 8.983620446201638e-05,
+      "loss": 0.41129344940185547,
+      "step": 4100
+    },
+    {
+      "epoch": 3.4461152882205512,
+      "grad_norm": 2.852447032928467,
+      "learning_rate": 8.976560293702345e-05,
+      "loss": 0.4309309768676758,
+      "step": 4125
+    },
+    {
+      "epoch": 3.467000835421888,
+      "grad_norm": 3.04453182220459,
+      "learning_rate": 8.96950014120305e-05,
+      "loss": 0.4245978546142578,
+      "step": 4150
+    },
+    {
+      "epoch": 3.4878863826232247,
+      "grad_norm": 3.4194531440734863,
+      "learning_rate": 8.962439988703757e-05,
+      "loss": 0.41548053741455077,
+      "step": 4175
+    },
+    {
+      "epoch": 3.5087719298245617,
+      "grad_norm": 2.7085516452789307,
+      "learning_rate": 8.955379836204463e-05,
+      "loss": 0.42301589965820313,
+      "step": 4200
+    },
+    {
+      "epoch": 3.529657477025898,
+      "grad_norm": 2.965217113494873,
+      "learning_rate": 8.948319683705169e-05,
+      "loss": 0.4241177749633789,
+      "step": 4225
+    },
+    {
+      "epoch": 3.5505430242272347,
+      "grad_norm": 3.2024154663085938,
+      "learning_rate": 8.941259531205874e-05,
+      "loss": 0.4297440338134766,
+      "step": 4250
+    },
+    {
+      "epoch": 3.571428571428571,
+      "grad_norm": 2.9695773124694824,
+      "learning_rate": 8.93419937870658e-05,
+      "loss": 0.3943584442138672,
+      "step": 4275
+    },
+    {
+      "epoch": 3.592314118629908,
+      "grad_norm": 3.200519561767578,
+      "learning_rate": 8.927139226207286e-05,
+      "loss": 0.4294881820678711,
+      "step": 4300
+    },
+    {
+      "epoch": 3.6131996658312446,
+      "grad_norm": 2.9448063373565674,
+      "learning_rate": 8.920079073707993e-05,
+      "loss": 0.4301759338378906,
+      "step": 4325
+    },
+    {
+      "epoch": 3.6340852130325816,
+      "grad_norm": 3.1099841594696045,
+      "learning_rate": 8.913018921208699e-05,
+      "loss": 0.42306079864501955,
+      "step": 4350
+    },
+    {
+      "epoch": 3.654970760233918,
+      "grad_norm": 3.556462049484253,
+      "learning_rate": 8.905958768709405e-05,
+      "loss": 0.42727806091308596,
+      "step": 4375
+    },
+    {
+      "epoch": 3.6758563074352546,
+      "grad_norm": 3.5050208568573,
+      "learning_rate": 8.898898616210111e-05,
+      "loss": 0.42058845520019533,
+      "step": 4400
+    },
+    {
+      "epoch": 3.6967418546365916,
+      "grad_norm": 3.299497365951538,
+      "learning_rate": 8.891838463710817e-05,
+      "loss": 0.4445077514648437,
+      "step": 4425
+    },
+    {
+      "epoch": 3.717627401837928,
+      "grad_norm": 3.4903392791748047,
+      "learning_rate": 8.884778311211522e-05,
+      "loss": 0.43223350524902343,
+      "step": 4450
+    },
+    {
+      "epoch": 3.738512949039265,
+      "grad_norm": 3.2760531902313232,
+      "learning_rate": 8.877718158712229e-05,
+      "loss": 0.41040069580078126,
+      "step": 4475
+    },
+    {
+      "epoch": 3.7593984962406015,
+      "grad_norm": 2.6590590476989746,
+      "learning_rate": 8.870658006212934e-05,
+      "loss": 0.4209041976928711,
+      "step": 4500
+    },
+    {
+      "epoch": 3.7593984962406015,
+      "eval_cer": 0.10421973321402364,
+      "eval_loss": 0.7152175903320312,
+      "eval_runtime": 95.3684,
+      "eval_samples_per_second": 32.348,
+      "eval_steps_per_second": 0.514,
+      "eval_wer": 0.41531705019326415,
+      "step": 4500
     }
   ],
   "logging_steps": 25,
@@ -1222,7 +1372,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -1231,12 +1381,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.15040487215104e+18,
+  "total_flos": 3.54430703407104e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null