Upload folder using huggingface_hub

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec41a0782b6318bc15c8f675366b016d127cbfdca60b12d2bf1a24c898b06082
+oid sha256:c8812c64fe873ccccaa06bce81ca573f218d52e1edaec68ecada6595fd710905
 size 297614301

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58e212f3353754d87ac53835f03575cdce01b0392151759678950572d16504cf
+size 151097459

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63af957ee3b34e42669c1057cdc6588be7f6f80ecf40ef0ce11d46a18f4edccc
+oid sha256:c697a902817aee34d66b970112c7ee2c24a5d924304347ce2a6944a1bab07de6
 size 623

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.3898635477582846,
+  "best_metric": 0.3861003861003861,
   "best_model_checkpoint": "D:\\development\\whisper-finetune\\output_tiny\\checkpoint-1000",
   "epoch": 1000.0,
   "eval_steps": 1000,
@@ -11,64 +11,64 @@
     {
       "epoch": 33.33,
       "learning_rate": 9.88e-06,
-      "loss": 0.8251,
+      "loss": 0.8261,
       "step": 500
     },
     {
       "epoch": 66.67,
       "learning_rate": 9.659310344827587e-06,
-      "loss": 0.0035,
+      "loss": 0.0028,
       "step": 1000
     },
     {
       "epoch": 66.67,
-      "eval_loss": 0.0014676946448162198,
-      "eval_runtime": 20.2982,
-      "eval_samples_per_second": 5.666,
-      "eval_steps_per_second": 0.739,
-      "eval_wer": 0.3898635477582846,
+      "eval_loss": 0.002442890079692006,
+      "eval_runtime": 21.9145,
+      "eval_samples_per_second": 5.339,
+      "eval_steps_per_second": 0.684,
+      "eval_wer": 0.3861003861003861,
       "step": 1000
     },
     {
       "epoch": 100.0,
       "learning_rate": 9.314482758620691e-06,
-      "loss": 0.0014,
+      "loss": 0.0016,
       "step": 1500
     },
     {
       "epoch": 133.33,
       "learning_rate": 8.969655172413794e-06,
-      "loss": 0.0013,
+      "loss": 0.0014,
       "step": 2000
     },
     {
       "epoch": 133.33,
-      "eval_loss": 0.0020876836497336626,
-      "eval_runtime": 19.7859,
-      "eval_samples_per_second": 5.812,
-      "eval_steps_per_second": 0.758,
-      "eval_wer": 0.3898635477582846,
+      "eval_loss": 0.0016565920086577535,
+      "eval_runtime": 21.8481,
+      "eval_samples_per_second": 5.355,
+      "eval_steps_per_second": 0.687,
+      "eval_wer": 0.3861003861003861,
       "step": 2000
     },
     {
       "epoch": 166.67,
       "learning_rate": 8.624827586206898e-06,
-      "loss": 0.0013,
+      "loss": 0.0014,
       "step": 2500
     },
     {
       "epoch": 200.0,
       "learning_rate": 8.28e-06,
-      "loss": 0.0013,
+      "loss": 0.0012,
       "step": 3000
     },
     {
       "epoch": 200.0,
-      "eval_loss": 0.0014716371661052108,
-      "eval_runtime": 21.0452,
-      "eval_samples_per_second": 5.464,
-      "eval_steps_per_second": 0.713,
-      "eval_wer": 0.3898635477582846,
+      "eval_loss": 0.0012075488921254873,
+      "eval_runtime": 21.8068,
+      "eval_samples_per_second": 5.365,
+      "eval_steps_per_second": 0.688,
+      "eval_wer": 0.3861003861003861,
       "step": 3000
     },
     {
@@ -80,247 +80,247 @@
     {
       "epoch": 266.67,
       "learning_rate": 7.590344827586208e-06,
-      "loss": 0.0012,
+      "loss": 0.0011,
       "step": 4000
     },
     {
       "epoch": 266.67,
-      "eval_loss": 0.0013525157701224089,
-      "eval_runtime": 20.7843,
-      "eval_samples_per_second": 5.533,
-      "eval_steps_per_second": 0.722,
-      "eval_wer": 0.3898635477582846,
+      "eval_loss": 0.0011881846003234386,
+      "eval_runtime": 22.3448,
+      "eval_samples_per_second": 5.236,
+      "eval_steps_per_second": 0.671,
+      "eval_wer": 0.3861003861003861,
       "step": 4000
     },
     {
       "epoch": 300.0,
-      "learning_rate": 7.24551724137931e-06,
-      "loss": 0.0011,
+      "learning_rate": 7.2468965517241385e-06,
+      "loss": 0.0013,
       "step": 4500
     },
     {
       "epoch": 333.33,
-      "learning_rate": 6.9006896551724145e-06,
-      "loss": 0.0012,
+      "learning_rate": 6.902068965517243e-06,
+      "loss": 0.0011,
       "step": 5000
     },
     {
       "epoch": 333.33,
-      "eval_loss": 0.0016531223664060235,
-      "eval_runtime": 21.1699,
-      "eval_samples_per_second": 5.432,
-      "eval_steps_per_second": 0.709,
-      "eval_wer": 0.3898635477582846,
+      "eval_loss": 0.0012107096845284104,
+      "eval_runtime": 21.9233,
+      "eval_samples_per_second": 5.337,
+      "eval_steps_per_second": 0.684,
+      "eval_wer": 0.3861003861003861,
       "step": 5000
     },
     {
       "epoch": 366.67,
-      "learning_rate": 6.555862068965517e-06,
+      "learning_rate": 6.557241379310345e-06,
       "loss": 0.0011,
       "step": 5500
     },
     {
       "epoch": 400.0,
-      "learning_rate": 6.211034482758621e-06,
-      "loss": 0.0012,
+      "learning_rate": 6.2124137931034485e-06,
+      "loss": 0.0011,
       "step": 6000
     },
     {
       "epoch": 400.0,
-      "eval_loss": 0.0016335018444806337,
-      "eval_runtime": 22.773,
-      "eval_samples_per_second": 5.05,
-      "eval_steps_per_second": 0.659,
-      "eval_wer": 0.3898635477582846,
+      "eval_loss": 0.0011809396091848612,
+      "eval_runtime": 21.8718,
+      "eval_samples_per_second": 5.349,
+      "eval_steps_per_second": 0.686,
+      "eval_wer": 0.3861003861003861,
       "step": 6000
     },
     {
       "epoch": 433.33,
-      "learning_rate": 5.8662068965517245e-06,
+      "learning_rate": 5.868275862068966e-06,
       "loss": 0.0011,
       "step": 6500
     },
     {
       "epoch": 466.67,
-      "learning_rate": 5.521379310344828e-06,
+      "learning_rate": 5.523448275862069e-06,
       "loss": 0.001,
       "step": 7000
     },
     {
       "epoch": 466.67,
-      "eval_loss": 0.0016853931592777371,
-      "eval_runtime": 21.6678,
-      "eval_samples_per_second": 5.307,
-      "eval_steps_per_second": 0.692,
-      "eval_wer": 0.3898635477582846,
+      "eval_loss": 0.0011794030433520675,
+      "eval_runtime": 21.8283,
+      "eval_samples_per_second": 5.36,
+      "eval_steps_per_second": 0.687,
+      "eval_wer": 0.3861003861003861,
       "step": 7000
     },
     {
       "epoch": 500.0,
-      "learning_rate": 5.176551724137931e-06,
-      "loss": 0.0011,
+      "learning_rate": 5.178620689655173e-06,
+      "loss": 0.001,
       "step": 7500
     },
     {
       "epoch": 533.33,
-      "learning_rate": 4.8317241379310345e-06,
-      "loss": 0.003,
+      "learning_rate": 4.833793103448276e-06,
+      "loss": 0.001,
       "step": 8000
     },
     {
       "epoch": 533.33,
-      "eval_loss": 0.0015577995218336582,
-      "eval_runtime": 21.0956,
-      "eval_samples_per_second": 5.451,
-      "eval_steps_per_second": 0.711,
-      "eval_wer": 0.3898635477582846,
+      "eval_loss": 0.0011808406561613083,
+      "eval_runtime": 21.7413,
+      "eval_samples_per_second": 5.381,
+      "eval_steps_per_second": 0.69,
+      "eval_wer": 0.3861003861003861,
       "step": 8000
     },
     {
       "epoch": 566.67,
-      "learning_rate": 4.486896551724138e-06,
-      "loss": 0.0011,
+      "learning_rate": 4.489655172413793e-06,
+      "loss": 0.001,
       "step": 8500
     },
     {
       "epoch": 600.0,
-      "learning_rate": 4.142068965517242e-06,
+      "learning_rate": 4.144827586206897e-06,
       "loss": 0.001,
       "step": 9000
     },
     {
       "epoch": 600.0,
-      "eval_loss": 0.0015839524567127228,
-      "eval_runtime": 21.0168,
-      "eval_samples_per_second": 5.472,
-      "eval_steps_per_second": 0.714,
-      "eval_wer": 0.3898635477582846,
+      "eval_loss": 0.00120567309204489,
+      "eval_runtime": 21.8405,
+      "eval_samples_per_second": 5.357,
+      "eval_steps_per_second": 0.687,
+      "eval_wer": 0.3861003861003861,
       "step": 9000
     },
     {
       "epoch": 633.33,
-      "learning_rate": 3.7972413793103454e-06,
+      "learning_rate": 3.8000000000000005e-06,
       "loss": 0.001,
       "step": 9500
     },
     {
       "epoch": 666.67,
-      "learning_rate": 3.4524137931034487e-06,
+      "learning_rate": 3.455172413793104e-06,
       "loss": 0.001,
       "step": 10000
     },
     {
       "epoch": 666.67,
-      "eval_loss": 0.0015147783560678363,
-      "eval_runtime": 21.21,
-      "eval_samples_per_second": 5.422,
-      "eval_steps_per_second": 0.707,
-      "eval_wer": 0.3898635477582846,
+      "eval_loss": 0.0011991177452728152,
+      "eval_runtime": 21.7109,
+      "eval_samples_per_second": 5.389,
+      "eval_steps_per_second": 0.691,
+      "eval_wer": 0.3861003861003861,
       "step": 10000
     },
     {
       "epoch": 700.0,
-      "learning_rate": 3.1082758620689657e-06,
+      "learning_rate": 3.111034482758621e-06,
       "loss": 0.001,
       "step": 10500
     },
     {
       "epoch": 733.33,
-      "learning_rate": 2.763448275862069e-06,
+      "learning_rate": 2.766206896551724e-06,
       "loss": 0.001,
       "step": 11000
     },
     {
       "epoch": 733.33,
-      "eval_loss": 0.0014770556008443236,
-      "eval_runtime": 21.0935,
-      "eval_samples_per_second": 5.452,
-      "eval_steps_per_second": 0.711,
-      "eval_wer": 0.3898635477582846,
+      "eval_loss": 0.0011818531202152371,
+      "eval_runtime": 21.7427,
+      "eval_samples_per_second": 5.381,
+      "eval_steps_per_second": 0.69,
+      "eval_wer": 0.3861003861003861,
       "step": 11000
     },
     {
       "epoch": 766.67,
-      "learning_rate": 2.4186206896551724e-06,
-      "loss": 0.001,
+      "learning_rate": 2.4220689655172416e-06,
+      "loss": 0.0009,
       "step": 11500
     },
     {
       "epoch": 800.0,
-      "learning_rate": 2.073793103448276e-06,
+      "learning_rate": 2.077931034482759e-06,
       "loss": 0.001,
       "step": 12000
     },
     {
       "epoch": 800.0,
-      "eval_loss": 0.0015582370106130838,
-      "eval_runtime": 21.0889,
-      "eval_samples_per_second": 5.453,
-      "eval_steps_per_second": 0.711,
-      "eval_wer": 0.3898635477582846,
+      "eval_loss": 0.0011808592826128006,
+      "eval_runtime": 21.9404,
+      "eval_samples_per_second": 5.333,
+      "eval_steps_per_second": 0.684,
+      "eval_wer": 0.3861003861003861,
       "step": 12000
     },
     {
       "epoch": 833.33,
-      "learning_rate": 1.7289655172413794e-06,
+      "learning_rate": 1.733103448275862e-06,
       "loss": 0.0009,
       "step": 12500
     },
     {
       "epoch": 866.67,
-      "learning_rate": 1.3848275862068967e-06,
+      "learning_rate": 1.3882758620689656e-06,
       "loss": 0.0009,
       "step": 13000
     },
     {
       "epoch": 866.67,
-      "eval_loss": 0.0016244335565716028,
-      "eval_runtime": 21.0544,
-      "eval_samples_per_second": 5.462,
-      "eval_steps_per_second": 0.712,
-      "eval_wer": 0.3898635477582846,
+      "eval_loss": 0.0012090284144505858,
+      "eval_runtime": 21.6103,
+      "eval_samples_per_second": 5.414,
+      "eval_steps_per_second": 0.694,
+      "eval_wer": 0.3861003861003861,
       "step": 13000
     },
     {
       "epoch": 900.0,
-      "learning_rate": 1.04e-06,
+      "learning_rate": 1.043448275862069e-06,
       "loss": 0.0009,
       "step": 13500
     },
     {
       "epoch": 933.33,
-      "learning_rate": 6.951724137931034e-07,
+      "learning_rate": 6.993103448275862e-07,
       "loss": 0.0009,
       "step": 14000
     },
     {
       "epoch": 933.33,
-      "eval_loss": 0.001572693814523518,
-      "eval_runtime": 21.1472,
-      "eval_samples_per_second": 5.438,
-      "eval_steps_per_second": 0.709,
-      "eval_wer": 0.3898635477582846,
+      "eval_loss": 0.0012141974875703454,
+      "eval_runtime": 21.6816,
+      "eval_samples_per_second": 5.396,
+      "eval_steps_per_second": 0.692,
+      "eval_wer": 0.3861003861003861,
       "step": 14000
     },
     {
       "epoch": 966.67,
-      "learning_rate": 3.50344827586207e-07,
-      "loss": 0.001,
+      "learning_rate": 3.558620689655173e-07,
+      "loss": 0.0009,
       "step": 14500
     },
     {
       "epoch": 1000.0,
-      "learning_rate": 6.206896551724139e-09,
+      "learning_rate": 1.1034482758620692e-08,
       "loss": 0.0009,
       "step": 15000
     },
     {
       "epoch": 1000.0,
-      "eval_loss": 0.0015988650266081095,
-      "eval_runtime": 21.2054,
-      "eval_samples_per_second": 5.423,
-      "eval_steps_per_second": 0.707,
-      "eval_wer": 0.3898635477582846,
+      "eval_loss": 0.0012086295755580068,
+      "eval_runtime": 22.0752,
+      "eval_samples_per_second": 5.3,
+      "eval_steps_per_second": 0.679,
+      "eval_wer": 0.3861003861003861,
       "step": 15000
     }
   ],
@@ -329,7 +329,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1000,
   "save_steps": 1000,
-  "total_flos": 2.8311717888e+18,
+  "total_flos": 2.88040955904e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:846d03b932f04329ac38183c3b8644cc26aaec372708364b91ec993b90cf9f75
+oid sha256:6616deffac2284b0d54a1924417ac3aa669129ba55bdbb7a1b5ecda4b25bf76d
 size 4463