Training in progress, step 32400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee40e71245bf0f66c619c4566f44ff371a139d5158466fdc9d52c3e8ec2e3176
+oid sha256:720ec26f34508162cd3ed48aa354f1a55bde3c940e3b941db4493d80be90061c
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23d7f9f3b44eb0e3f4ac71847a56e56f764cdaa70a0e972cf685f8a504364deb
+oid sha256:288024677ae015fd9f07724ebcc4a5c2dde656deb4c2988d4acbc6416d681ba4
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:889fba2dda612c6c0d4296e738b798d52e27bd546723613a9f1022c81f0a1b37
+oid sha256:732b979418123e1232daa0215db26fcf01224d94c16971ed415238028e85e575
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a2425ae56cb630c35a174629553276a10429b35fc53ac726db0dfb5fc49bea
+oid sha256:676a0c92f411f549dea3afe0b01db3d2c7fd7a67a5bdccc0755488565188383a
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e27c322f011be2d3e98ac457c9a136957b37708f9a786651d2be8677d0d76424
+oid sha256:50ca82bbea02fc725f68bafbc19bec35c56c4c96823814172201a68e0f179761
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 18400,
-  "best_metric": 0.19658119658119658,
-  "best_model_checkpoint": "./distil-whisper/checkpoint-18400",
-  "epoch": 22.80456084090504,
+  "best_global_step": 32400,
+  "best_metric": 0.19510757441791923,
+  "best_model_checkpoint": "./distil-whisper/checkpoint-32400",
+  "epoch": 23.0890789239266,
   "eval_steps": 400,
-  "global_step": 32000,
+  "global_step": 32400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2968,6 +2968,43 @@
       "eval_steps_per_second": 0.396,
       "eval_wer": 0.201886236368995,
       "step": 32000
+    },
+    {
+      "epoch": 22.87582398004632,
+      "grad_norm": 13.594120025634766,
+      "learning_rate": 8.65943600867679e-06,
+      "loss": 1.0777,
+      "step": 32100
+    },
+    {
+      "epoch": 22.9470871191876,
+      "grad_norm": 15.224822044372559,
+      "learning_rate": 8.370209689081707e-06,
+      "loss": 1.0544,
+      "step": 32200
+    },
+    {
+      "epoch": 23.01781578478532,
+      "grad_norm": 11.079718589782715,
+      "learning_rate": 8.080983369486623e-06,
+      "loss": 1.0563,
+      "step": 32300
+    },
+    {
+      "epoch": 23.0890789239266,
+      "grad_norm": 12.417219161987305,
+      "learning_rate": 7.791757049891541e-06,
+      "loss": 0.9784,
+      "step": 32400
+    },
+    {
+      "epoch": 23.0890789239266,
+      "eval_loss": 0.0926588624715805,
+      "eval_runtime": 159.1992,
+      "eval_samples_per_second": 3.141,
+      "eval_steps_per_second": 0.396,
+      "eval_wer": 0.19510757441791923,
+      "step": 32400
     }
   ],
   "logging_steps": 100,
@@ -2987,7 +3024,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.160400959471616e+19,
+  "total_flos": 4.212315930230784e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null