Training in progress, step 1830, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c690532dde75d7f037320b5f3913514c7a0bff79f52688dcc983d5fb97dd97f
+oid sha256:a3b3ca44ca71849aa9736bf2caa6c4a33b670570063ad036bc8fbcd3ed610f45
 size 966995080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecbdfd3f209ee1395730dd360cba7a898e53096ef2ca33f731a207501938165c
+oid sha256:264c7200f301cadaabfb6edb2eb02ced5f68f63db4926b53e608150943e45424
 size 1925064044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5e82f96b77a35761cfa17e364b44b3b766596ff201963b0dda148aa2e1b89fb
+oid sha256:735fd23f13374ea6c149d7a80aeb18d5231b8a21165e2180edd2ac1a60e8d824
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f3e57b087a882ce0fe38f97583d72cfa40b57e6b36b780759bd14633217f9fd
+oid sha256:ae192710b7980b12a4f538a2ff8c8fb9bdd8115f7bf58fc2370cc0fc415fe3b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 6.666951123247926,
   "best_model_checkpoint": "./whisper-small-accented-zh/checkpoint-1000",
-  "epoch": 1.639344262295082,
+  "epoch": 3.0,
   "eval_steps": 1000,
-  "global_step": 1000,
+  "global_step": 1830,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -296,6 +296,237 @@
       "eval_steps_per_second": 0.173,
       "eval_wer": 6.666951123247926,
       "step": 1000
+    },
+    {
+      "epoch": 1.680327868852459,
+      "grad_norm": 2.7260067462921143,
+      "learning_rate": 6.067669172932331e-06,
+      "loss": 0.0887,
+      "step": 1025
+    },
+    {
+      "epoch": 1.721311475409836,
+      "grad_norm": 3.793546438217163,
+      "learning_rate": 5.879699248120301e-06,
+      "loss": 0.0805,
+      "step": 1050
+    },
+    {
+      "epoch": 1.762295081967213,
+      "grad_norm": 3.374661684036255,
+      "learning_rate": 5.6917293233082715e-06,
+      "loss": 0.0815,
+      "step": 1075
+    },
+    {
+      "epoch": 1.8032786885245902,
+      "grad_norm": 3.6348347663879395,
+      "learning_rate": 5.503759398496241e-06,
+      "loss": 0.0777,
+      "step": 1100
+    },
+    {
+      "epoch": 1.8442622950819674,
+      "grad_norm": 3.1936988830566406,
+      "learning_rate": 5.315789473684211e-06,
+      "loss": 0.0748,
+      "step": 1125
+    },
+    {
+      "epoch": 1.8852459016393444,
+      "grad_norm": 3.0702261924743652,
+      "learning_rate": 5.12781954887218e-06,
+      "loss": 0.0869,
+      "step": 1150
+    },
+    {
+      "epoch": 1.9262295081967213,
+      "grad_norm": 2.608741283416748,
+      "learning_rate": 4.9398496240601505e-06,
+      "loss": 0.0807,
+      "step": 1175
+    },
+    {
+      "epoch": 1.9672131147540983,
+      "grad_norm": 3.992398500442505,
+      "learning_rate": 4.751879699248121e-06,
+      "loss": 0.0743,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0081967213114753,
+      "grad_norm": 2.5503103733062744,
+      "learning_rate": 4.56390977443609e-06,
+      "loss": 0.0613,
+      "step": 1225
+    },
+    {
+      "epoch": 2.0491803278688523,
+      "grad_norm": 2.326587438583374,
+      "learning_rate": 4.375939849624061e-06,
+      "loss": 0.0247,
+      "step": 1250
+    },
+    {
+      "epoch": 2.0901639344262297,
+      "grad_norm": 1.7671444416046143,
+      "learning_rate": 4.18796992481203e-06,
+      "loss": 0.0306,
+      "step": 1275
+    },
+    {
+      "epoch": 2.1311475409836067,
+      "grad_norm": 2.0086865425109863,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0252,
+      "step": 1300
+    },
+    {
+      "epoch": 2.1721311475409837,
+      "grad_norm": 0.9309338331222534,
+      "learning_rate": 3.81203007518797e-06,
+      "loss": 0.0236,
+      "step": 1325
+    },
+    {
+      "epoch": 2.2131147540983607,
+      "grad_norm": 0.9044923782348633,
+      "learning_rate": 3.6240601503759406e-06,
+      "loss": 0.027,
+      "step": 1350
+    },
+    {
+      "epoch": 2.2540983606557377,
+      "grad_norm": 1.874260425567627,
+      "learning_rate": 3.43609022556391e-06,
+      "loss": 0.0298,
+      "step": 1375
+    },
+    {
+      "epoch": 2.2950819672131146,
+      "grad_norm": 0.8456152081489563,
+      "learning_rate": 3.24812030075188e-06,
+      "loss": 0.0207,
+      "step": 1400
+    },
+    {
+      "epoch": 2.3360655737704916,
+      "grad_norm": 1.6556758880615234,
+      "learning_rate": 3.06015037593985e-06,
+      "loss": 0.0349,
+      "step": 1425
+    },
+    {
+      "epoch": 2.3770491803278686,
+      "grad_norm": 1.3671510219573975,
+      "learning_rate": 2.8721804511278195e-06,
+      "loss": 0.0284,
+      "step": 1450
+    },
+    {
+      "epoch": 2.418032786885246,
+      "grad_norm": 1.1702046394348145,
+      "learning_rate": 2.68421052631579e-06,
+      "loss": 0.024,
+      "step": 1475
+    },
+    {
+      "epoch": 2.459016393442623,
+      "grad_norm": 2.4468085765838623,
+      "learning_rate": 2.4962406015037594e-06,
+      "loss": 0.0258,
+      "step": 1500
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.201532244682312,
+      "learning_rate": 2.3082706766917294e-06,
+      "loss": 0.0254,
+      "step": 1525
+    },
+    {
+      "epoch": 2.540983606557377,
+      "grad_norm": 0.9549139738082886,
+      "learning_rate": 2.1203007518796993e-06,
+      "loss": 0.0256,
+      "step": 1550
+    },
+    {
+      "epoch": 2.581967213114754,
+      "grad_norm": 2.483381509780884,
+      "learning_rate": 1.9323308270676693e-06,
+      "loss": 0.0299,
+      "step": 1575
+    },
+    {
+      "epoch": 2.6229508196721314,
+      "grad_norm": 1.537619709968567,
+      "learning_rate": 1.7443609022556392e-06,
+      "loss": 0.0291,
+      "step": 1600
+    },
+    {
+      "epoch": 2.663934426229508,
+      "grad_norm": 1.5355826616287231,
+      "learning_rate": 1.5563909774436092e-06,
+      "loss": 0.0269,
+      "step": 1625
+    },
+    {
+      "epoch": 2.7049180327868854,
+      "grad_norm": 1.311331033706665,
+      "learning_rate": 1.3684210526315791e-06,
+      "loss": 0.0273,
+      "step": 1650
+    },
+    {
+      "epoch": 2.7459016393442623,
+      "grad_norm": 0.8623602390289307,
+      "learning_rate": 1.1804511278195489e-06,
+      "loss": 0.0219,
+      "step": 1675
+    },
+    {
+      "epoch": 2.7868852459016393,
+      "grad_norm": 1.6167572736740112,
+      "learning_rate": 9.924812030075188e-07,
+      "loss": 0.0303,
+      "step": 1700
+    },
+    {
+      "epoch": 2.8278688524590163,
+      "grad_norm": 2.8278274536132812,
+      "learning_rate": 8.045112781954888e-07,
+      "loss": 0.0245,
+      "step": 1725
+    },
+    {
+      "epoch": 2.8688524590163933,
+      "grad_norm": 2.3211958408355713,
+      "learning_rate": 6.165413533834587e-07,
+      "loss": 0.0241,
+      "step": 1750
+    },
+    {
+      "epoch": 2.9098360655737707,
+      "grad_norm": 1.8018407821655273,
+      "learning_rate": 4.285714285714286e-07,
+      "loss": 0.022,
+      "step": 1775
+    },
+    {
+      "epoch": 2.9508196721311473,
+      "grad_norm": 1.6640270948410034,
+      "learning_rate": 2.406015037593985e-07,
+      "loss": 0.025,
+      "step": 1800
+    },
+    {
+      "epoch": 2.9918032786885247,
+      "grad_norm": 0.6498773694038391,
+      "learning_rate": 5.263157894736842e-08,
+      "loss": 0.0234,
+      "step": 1825
     }
   ],
   "logging_steps": 25,
@@ -310,12 +541,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.61419196571648e+18,
+  "total_flos": 8.44025720315904e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null