Training in progress, step 25200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c736fd594c380dd002a6342fa0604bc644313aed80303796815ff4b03e46442e
+oid sha256:781ba7beccdb6f2de672bde036b555a9c2452f37617312f1ada22f7dd95b7516
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3e2b9eff304abf490d045d1420af73881798301b076f854de745fb8bb32c5f5
+oid sha256:70b435d6180ac5725ee8b276e9d4bcd3f744ed2b2d69e97b908f1fc38b66b25f
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eaa69a43fe9ca74e4bd1e79b0bbd6af7b0c407425e6e1e3b18bd47b766849b
+oid sha256:72a46adf461123b3c04c2270eadae64d4ce1b5a208dd5fc2b1d415269f53fe47
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e15e488492623c161675a7bb297a1a2ecfcf210cea79271160fd0a257b5fa31e
+oid sha256:b21eaeb6df3448a126aa3c865471f11d93d5da05e32d2b0b19d5120cef1d8306
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd454cefdd5cc5bafc5dee97883508d8606ab9e8e2795ebeb6c8caeb65187032
+oid sha256:b54547c361b34cbfc85f7276b4e56c67fff255001445cd0390ae05eba8160d38
 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": 14.700652045050385,
+  "epoch": 14.937759336099585,
   "eval_steps": 400,
-  "global_step": 24800,
+  "global_step": 25200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2302,6 +2302,43 @@
       "eval_steps_per_second": 0.429,
       "eval_wer": 0.20085470085470086,
       "step": 24800
+    },
+    {
+      "epoch": 14.759928867812686,
+      "grad_norm": 8.114453315734863,
+      "learning_rate": 1.689175569441645e-06,
+      "loss": 0.8946,
+      "step": 24900
+    },
+    {
+      "epoch": 14.819205690574986,
+      "grad_norm": 8.182477951049805,
+      "learning_rate": 1.2860310421286033e-06,
+      "loss": 0.9534,
+      "step": 25000
+    },
+    {
+      "epoch": 14.878482513337286,
+      "grad_norm": 6.653454303741455,
+      "learning_rate": 8.828865148155615e-07,
+      "loss": 0.9688,
+      "step": 25100
+    },
+    {
+      "epoch": 14.937759336099585,
+      "grad_norm": 9.1705322265625,
+      "learning_rate": 4.837734327756501e-07,
+      "loss": 0.8976,
+      "step": 25200
+    },
+    {
+      "epoch": 14.937759336099585,
+      "eval_loss": 0.08782143890857697,
+      "eval_runtime": 149.7053,
+      "eval_samples_per_second": 3.34,
+      "eval_steps_per_second": 0.421,
+      "eval_wer": 0.20159151193633953,
+      "step": 25200
     }
   ],
   "logging_steps": 100,
@@ -2321,7 +2358,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.225638800982016e+19,
+  "total_flos": 3.277671658684416e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null