Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ca4effc12eba3aac6be54b6ebefbe335a68a355bfa1a4dd5f6a757e3d20e67a
+oid sha256:eebc1d9056f2e07f39b6f26b5b895ae666ebf27cb0c5e4d039d62197b8c21393
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fa103db88bb063249cf00198f06c391c0cbe109211197c08de8bcb1f223a081
+oid sha256:b23867f188536ea66fd72fb25f8b38af033d89e784868a9198bd8636f41aafd6
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fe4aa3c6d64b2359fdca2b677edc0f16c40c47a59d8fb0f684e2e556f14ffab
+oid sha256:532c517329b19c3c26a40128633dac433b21c2a9fdccf15f1ce841afac82a731
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2679b4f3b91289b00dcc38839d58e85292314e6e8c351585202758bc552e8648
+oid sha256:30018a217305d9e46abd87e309f4ff8defdc4db75aeb3c0990ab48e9f73bc2fd
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab9e93c2a1c338d0c2d563b755e9dc5f46b92db971a762ae1d3d9695b77e067d
+oid sha256:f8028b38e81306dbd3e5cdafcebbf51f8d644a14f781af304098d7365c655d64
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 4000,
   "best_metric": 0.18950781019746538,
   "best_model_checkpoint": "./distil-whisper/checkpoint-4000",
-  "epoch": 5.6905749851807945,
+  "epoch": 5.927682276229994,
   "eval_steps": 400,
-  "global_step": 9600,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -896,6 +896,43 @@
       "eval_steps_per_second": 0.431,
       "eval_wer": 0.1940760389036251,
       "step": 9600
+    },
+    {
+      "epoch": 5.749851807943094,
+      "grad_norm": 11.175410270690918,
+      "learning_rate": 2.927823945829486e-05,
+      "loss": 1.2928,
+      "step": 9700
+    },
+    {
+      "epoch": 5.809128630705394,
+      "grad_norm": 20.176969528198242,
+      "learning_rate": 2.850877192982456e-05,
+      "loss": 1.3725,
+      "step": 9800
+    },
+    {
+      "epoch": 5.868405453467695,
+      "grad_norm": 13.064400672912598,
+      "learning_rate": 2.7739304401354265e-05,
+      "loss": 1.4045,
+      "step": 9900
+    },
+    {
+      "epoch": 5.927682276229994,
+      "grad_norm": 17.69568634033203,
+      "learning_rate": 2.6969836872883965e-05,
+      "loss": 1.3055,
+      "step": 10000
+    },
+    {
+      "epoch": 5.927682276229994,
+      "eval_loss": 0.09068606048822403,
+      "eval_runtime": 145.6338,
+      "eval_samples_per_second": 3.433,
+      "eval_steps_per_second": 0.433,
+      "eval_wer": 0.19201296787503683,
+      "step": 10000
     }
   ],
   "logging_steps": 100,
@@ -915,7 +952,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.24864630751232e+19,
+  "total_flos": 1.30067916521472e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null