Training in progress, step 32000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:869a0e57d1d1ee9a2fb1d0c01f9524bb4c80a900cd8117beeba130d80f1bf321
+oid sha256:411df52b26563077a81a7b08db369d27d102503f690c603f3564427326c2c3fb
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb63c0ce7275a1c9ee86300c27e661af044d42bb26561a6ccd9d69c137ff500d
+oid sha256:315eea51d967b636aee06c9fab61b28d456ea20155b0f905d9a2894b1cd4bb1c
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dc6f8b922ca5c3d24f7537f685a761eded3c26ca293345adbe507125769101a
+oid sha256:d2615f31c2bde960c4cad72e76e8275160a20b219557b38cecad80fda50c2154
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3931a748c5d903224857a1ab9abba558951fac8f6dc32f736599e211fe96e5ce
+oid sha256:e91277e0d15d4cadb5461d7609fda108b605cd367d55a41118269783b39513b9
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:def63641a6ca9901171b06d19cec2f06e49d8d9307e1c178a24fd97f04041d2a
+oid sha256:06016ca44c3c2f7f6ce102c4b35b77805b28e5c34909f86718e837c850c7f578
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 28000,
   "best_metric": 0.18110816386678455,
   "best_model_checkpoint": "./distil-whisper/checkpoint-28000",
-  "epoch": 18.16051552431166,
+  "epoch": 18.746338605741066,
   "eval_steps": 1000,
-  "global_step": 31000,
+  "global_step": 32000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2457,6 +2457,85 @@
       "eval_steps_per_second": 0.427,
       "eval_wer": 0.1905393457117595,
       "step": 31000
+    },
+    {
+      "epoch": 18.219097832454597,
+      "grad_norm": 6.72420597076416,
+      "learning_rate": 1.74583040967237e-05,
+      "loss": 0.7028,
+      "step": 31100
+    },
+    {
+      "epoch": 18.27768014059754,
+      "grad_norm": 5.8699140548706055,
+      "learning_rate": 1.7188427700113348e-05,
+      "loss": 0.7548,
+      "step": 31200
+    },
+    {
+      "epoch": 18.33626244874048,
+      "grad_norm": 6.714815139770508,
+      "learning_rate": 1.6921250067469098e-05,
+      "loss": 0.7619,
+      "step": 31300
+    },
+    {
+      "epoch": 18.394844756883423,
+      "grad_norm": 9.205123901367188,
+      "learning_rate": 1.6651373670858748e-05,
+      "loss": 0.7146,
+      "step": 31400
+    },
+    {
+      "epoch": 18.45342706502636,
+      "grad_norm": 7.359625339508057,
+      "learning_rate": 1.6381497274248395e-05,
+      "loss": 0.7425,
+      "step": 31500
+    },
+    {
+      "epoch": 18.512009373169303,
+      "grad_norm": 12.034134864807129,
+      "learning_rate": 1.6114319641604145e-05,
+      "loss": 0.7325,
+      "step": 31600
+    },
+    {
+      "epoch": 18.570591681312244,
+      "grad_norm": 12.600486755371094,
+      "learning_rate": 1.584444324499379e-05,
+      "loss": 0.7628,
+      "step": 31700
+    },
+    {
+      "epoch": 18.629173989455186,
+      "grad_norm": 5.2866530418396,
+      "learning_rate": 1.557456684838344e-05,
+      "loss": 0.7636,
+      "step": 31800
+    },
+    {
+      "epoch": 18.687756297598124,
+      "grad_norm": 5.383816719055176,
+      "learning_rate": 1.5304690451773088e-05,
+      "loss": 0.727,
+      "step": 31900
+    },
+    {
+      "epoch": 18.746338605741066,
+      "grad_norm": 8.094857215881348,
+      "learning_rate": 1.5034814055162735e-05,
+      "loss": 0.7976,
+      "step": 32000
+    },
+    {
+      "epoch": 18.746338605741066,
+      "eval_loss": 0.08411071449518204,
+      "eval_runtime": 145.6438,
+      "eval_samples_per_second": 3.433,
+      "eval_steps_per_second": 0.433,
+      "eval_wer": 0.18376068376068377,
+      "step": 32000
     }
   ],
   "logging_steps": 100,
@@ -2476,7 +2555,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.032253787111424e+19,
+  "total_flos": 4.162335931367424e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null