Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6ca160ebd32f9b6125c3dd36a5d6573acb9672630324f2075c548064cdb9194
+oid sha256:bef927f8c396ddd8c50da8da318ff1c42907299e3a79bde434a85ac7f49a2550
 size 966995080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b988b144320cf446c72f27d1fd01487cd6b74514dbe1e1ba3833b371e19d67c
+oid sha256:86c248475900a14c46742b6090ba55f11ec94c0c31bf29102e53fdbbda855f19
 size 1925064044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9203abee247094b80f8593f8b0ff02ca19083755923e560ee1aad7ddcb2a175
+oid sha256:3540179bbcfe2a2e55d05fad49c806615d68122d33b057e8a5ff20ca08833829
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22779510dc9a41d36aa48252a2f1fad4b94049570f50176e14da0be07e35a06e
+oid sha256:16c5423cafe411d3f46179be1a8a5339c36303199cd2d3e2b9b15fb8665e754c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 23.047330380041966,
-  "best_model_checkpoint": "./whisper-small-clean_6-v5/checkpoint-500",
-  "epoch": 0.945179584120983,
+  "best_metric": 21.531825600373047,
+  "best_model_checkpoint": "./whisper-small-clean_6-v5/checkpoint-1000",
+  "epoch": 1.8903591682419658,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -156,6 +156,155 @@
       "eval_steps_per_second": 0.074,
       "eval_wer": 23.047330380041966,
       "step": 500
+    },
+    {
+      "epoch": 0.9924385633270322,
+      "grad_norm": 2.7852671146392822,
+      "learning_rate": 6.744827586206897e-06,
+      "loss": 0.1428,
+      "step": 525
+    },
+    {
+      "epoch": 1.0396975425330812,
+      "grad_norm": 1.9958089590072632,
+      "learning_rate": 6.572413793103449e-06,
+      "loss": 0.0829,
+      "step": 550
+    },
+    {
+      "epoch": 1.0869565217391304,
+      "grad_norm": 2.1867661476135254,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.0698,
+      "step": 575
+    },
+    {
+      "epoch": 1.1342155009451795,
+      "grad_norm": 1.7803280353546143,
+      "learning_rate": 6.227586206896552e-06,
+      "loss": 0.0717,
+      "step": 600
+    },
+    {
+      "epoch": 1.1814744801512287,
+      "grad_norm": 1.8491047620773315,
+      "learning_rate": 6.055172413793105e-06,
+      "loss": 0.0734,
+      "step": 625
+    },
+    {
+      "epoch": 1.2287334593572778,
+      "grad_norm": 2.021000862121582,
+      "learning_rate": 5.882758620689656e-06,
+      "loss": 0.0673,
+      "step": 650
+    },
+    {
+      "epoch": 1.275992438563327,
+      "grad_norm": 2.592538833618164,
+      "learning_rate": 5.710344827586207e-06,
+      "loss": 0.0713,
+      "step": 675
+    },
+    {
+      "epoch": 1.3232514177693762,
+      "grad_norm": 4.53612756729126,
+      "learning_rate": 5.5379310344827585e-06,
+      "loss": 0.0756,
+      "step": 700
+    },
+    {
+      "epoch": 1.3705103969754253,
+      "grad_norm": 2.295854091644287,
+      "learning_rate": 5.365517241379311e-06,
+      "loss": 0.069,
+      "step": 725
+    },
+    {
+      "epoch": 1.4177693761814745,
+      "grad_norm": 2.696308135986328,
+      "learning_rate": 5.193103448275863e-06,
+      "loss": 0.0724,
+      "step": 750
+    },
+    {
+      "epoch": 1.4650283553875236,
+      "grad_norm": 2.185211420059204,
+      "learning_rate": 5.020689655172414e-06,
+      "loss": 0.071,
+      "step": 775
+    },
+    {
+      "epoch": 1.5122873345935728,
+      "grad_norm": 2.22100830078125,
+      "learning_rate": 4.848275862068966e-06,
+      "loss": 0.0722,
+      "step": 800
+    },
+    {
+      "epoch": 1.559546313799622,
+      "grad_norm": 2.4104700088500977,
+      "learning_rate": 4.675862068965517e-06,
+      "loss": 0.0693,
+      "step": 825
+    },
+    {
+      "epoch": 1.606805293005671,
+      "grad_norm": 2.2482173442840576,
+      "learning_rate": 4.503448275862069e-06,
+      "loss": 0.0662,
+      "step": 850
+    },
+    {
+      "epoch": 1.6540642722117203,
+      "grad_norm": 1.6513797044754028,
+      "learning_rate": 4.3310344827586206e-06,
+      "loss": 0.075,
+      "step": 875
+    },
+    {
+      "epoch": 1.7013232514177694,
+      "grad_norm": 1.8004822731018066,
+      "learning_rate": 4.158620689655173e-06,
+      "loss": 0.0651,
+      "step": 900
+    },
+    {
+      "epoch": 1.7485822306238186,
+      "grad_norm": 2.4322433471679688,
+      "learning_rate": 3.986206896551724e-06,
+      "loss": 0.0729,
+      "step": 925
+    },
+    {
+      "epoch": 1.7958412098298677,
+      "grad_norm": 1.786984920501709,
+      "learning_rate": 3.813793103448276e-06,
+      "loss": 0.0698,
+      "step": 950
+    },
+    {
+      "epoch": 1.8431001890359169,
+      "grad_norm": 2.466444253921509,
+      "learning_rate": 3.641379310344828e-06,
+      "loss": 0.0737,
+      "step": 975
+    },
+    {
+      "epoch": 1.8903591682419658,
+      "grad_norm": 2.1226634979248047,
+      "learning_rate": 3.4689655172413793e-06,
+      "loss": 0.0631,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8903591682419658,
+      "eval_loss": 0.2692776620388031,
+      "eval_runtime": 652.5262,
+      "eval_samples_per_second": 2.337,
+      "eval_steps_per_second": 0.074,
+      "eval_wer": 21.531825600373047,
+      "step": 1000
     }
   ],
   "logging_steps": 25,
@@ -175,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.23473281024e+18,
+  "total_flos": 1.845243908186112e+19,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null