Training in progress, step 31000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aac9fb703442293b19e405bf4164788bf426a64df5cc82596cf5e220aaa680b7
+oid sha256:869a0e57d1d1ee9a2fb1d0c01f9524bb4c80a900cd8117beeba130d80f1bf321
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d2a33825f6a5fff2b41693fbcc0f91ce6163ef73cdbd1c03e6554d0b82c5f42
+oid sha256:eb63c0ce7275a1c9ee86300c27e661af044d42bb26561a6ccd9d69c137ff500d
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b5cc2e059bf5994720338ae5c6e6dec69e298afa0568c75f8adaffc4768726d
+oid sha256:9dc6f8b922ca5c3d24f7537f685a761eded3c26ca293345adbe507125769101a
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6d46aec3833efc2c92b1486514727c87c4f32a04aeafab142f4a8c156f76f8d
+oid sha256:3931a748c5d903224857a1ab9abba558951fac8f6dc32f736599e211fe96e5ce
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ba53b40b2a30a25e436425c9258142131e66d9a345f8a16e78444d8fcb29696
+oid sha256:def63641a6ca9901171b06d19cec2f06e49d8d9307e1c178a24fd97f04041d2a
 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": 17.57469244288225,
+  "epoch": 18.16051552431166,
   "eval_steps": 1000,
-  "global_step": 30000,
+  "global_step": 31000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2378,6 +2378,85 @@
       "eval_steps_per_second": 0.428,
       "eval_wer": 0.18670792808723843,
       "step": 30000
+    },
+    {
+      "epoch": 17.63327475102519,
+      "grad_norm": 6.075071334838867,
+      "learning_rate": 2.0157068062827225e-05,
+      "loss": 0.7471,
+      "step": 30100
+    },
+    {
+      "epoch": 17.691857059168132,
+      "grad_norm": 6.894543647766113,
+      "learning_rate": 1.9887191666216872e-05,
+      "loss": 0.7926,
+      "step": 30200
+    },
+    {
+      "epoch": 17.75043936731107,
+      "grad_norm": 11.549782752990723,
+      "learning_rate": 1.9617315269606522e-05,
+      "loss": 0.7308,
+      "step": 30300
+    },
+    {
+      "epoch": 17.809021675454012,
+      "grad_norm": 7.361614227294922,
+      "learning_rate": 1.934743887299617e-05,
+      "loss": 0.7545,
+      "step": 30400
+    },
+    {
+      "epoch": 17.867603983596954,
+      "grad_norm": 12.995938301086426,
+      "learning_rate": 1.9077562476385815e-05,
+      "loss": 0.7809,
+      "step": 30500
+    },
+    {
+      "epoch": 17.926186291739896,
+      "grad_norm": 4.978572368621826,
+      "learning_rate": 1.8807686079775465e-05,
+      "loss": 0.7587,
+      "step": 30600
+    },
+    {
+      "epoch": 17.984768599882834,
+      "grad_norm": 6.543401718139648,
+      "learning_rate": 1.853780968316511e-05,
+      "loss": 0.7432,
+      "step": 30700
+    },
+    {
+      "epoch": 18.043350908025776,
+      "grad_norm": 8.726702690124512,
+      "learning_rate": 1.8267933286554758e-05,
+      "loss": 0.7305,
+      "step": 30800
+    },
+    {
+      "epoch": 18.101933216168717,
+      "grad_norm": 6.32004976272583,
+      "learning_rate": 1.7998056889944405e-05,
+      "loss": 0.7454,
+      "step": 30900
+    },
+    {
+      "epoch": 18.16051552431166,
+      "grad_norm": 5.896217346191406,
+      "learning_rate": 1.7728180493334055e-05,
+      "loss": 0.7166,
+      "step": 31000
+    },
+    {
+      "epoch": 18.16051552431166,
+      "eval_loss": 0.0838567316532135,
+      "eval_runtime": 147.3922,
+      "eval_samples_per_second": 3.392,
+      "eval_steps_per_second": 0.427,
+      "eval_wer": 0.1905393457117595,
+      "step": 31000
     }
   ],
   "logging_steps": 100,
@@ -2397,7 +2476,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.902187903123456e+19,
+  "total_flos": 4.032253787111424e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null