Training in progress, step 32000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cafca5fce7ab45753baba0338f50645e6a1b9b7421c299ea82fec48d3bf3d36
+oid sha256:ee40e71245bf0f66c619c4566f44ff371a139d5158466fdc9d52c3e8ec2e3176
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b35c5d0465d9b3ece1745281e3d3c84209edd4483c5aea554c50fe7150a4481
+oid sha256:23d7f9f3b44eb0e3f4ac71847a56e56f764cdaa70a0e972cf685f8a504364deb
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d58b6a9a7b8cc6729fbb3b5459ccf762552d9a3d564aec2634f31bb934eb9e50
+oid sha256:889fba2dda612c6c0d4296e738b798d52e27bd546723613a9f1022c81f0a1b37
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbf4261ff9d86adf30ca05b86d56b875327e2250853d232d8b94713198d83e00
+oid sha256:01a2425ae56cb630c35a174629553276a10429b35fc53ac726db0dfb5fc49bea
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f300f5e6b28e35d46bb757938c0a422473b4c31b18fb2753c64908a1536391d7
+oid sha256:e27c322f011be2d3e98ac457c9a136957b37708f9a786651d2be8677d0d76424
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 18400,
   "best_metric": 0.19658119658119658,
   "best_model_checkpoint": "./distil-whisper/checkpoint-18400",
-  "epoch": 22.519508284339924,
+  "epoch": 22.80456084090504,
   "eval_steps": 400,
-  "global_step": 31600,
+  "global_step": 32000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2931,6 +2931,43 @@
       "eval_steps_per_second": 0.4,
       "eval_wer": 0.1987916298261126,
       "step": 31600
+    },
+    {
+      "epoch": 22.590771423481204,
+      "grad_norm": 16.371854782104492,
+      "learning_rate": 9.816341287057123e-06,
+      "loss": 1.0875,
+      "step": 31700
+    },
+    {
+      "epoch": 22.662034562622484,
+      "grad_norm": 12.373185157775879,
+      "learning_rate": 9.527114967462039e-06,
+      "loss": 1.0525,
+      "step": 31800
+    },
+    {
+      "epoch": 22.733297701763764,
+      "grad_norm": 16.901241302490234,
+      "learning_rate": 9.237888647866955e-06,
+      "loss": 0.9976,
+      "step": 31900
+    },
+    {
+      "epoch": 22.80456084090504,
+      "grad_norm": 11.734404563903809,
+      "learning_rate": 8.948662328271873e-06,
+      "loss": 1.0248,
+      "step": 32000
+    },
+    {
+      "epoch": 22.80456084090504,
+      "eval_loss": 0.09294673800468445,
+      "eval_runtime": 159.1061,
+      "eval_samples_per_second": 3.143,
+      "eval_steps_per_second": 0.396,
+      "eval_wer": 0.201886236368995,
+      "step": 32000
     }
   ],
   "logging_steps": 100,
@@ -2950,7 +2987,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.108368101769216e+19,
+  "total_flos": 4.160400959471616e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null