Training in progress, step 23200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8e1cfa450bc1631dc0d4ca9532b037d8f4141a775ec4d7dfad4da82a77360c8
+oid sha256:ae610937e70b8821d3a95f673534ececaf32e1a5c7a91cc91f420b8d0b3504a6
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c135d56ddce4b6d456311ae6182ea00830eec6b256914c9ec2cb8fa20821b91e
+oid sha256:9d9553129d74646d0142913b2ff5bc7d5b652b86694f6f9afdd91837a9e6adbe
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:655ba72e36f10c7f956ab70669a006ce6e55496a0911355ef1935b6aac9323dd
+oid sha256:cd2a16c621a6088b552c6371de52b5b43ee839d9d4e2a55fdb4031859156826b
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8edbab88b9194dbd28edaf319bbf668dd66029a5ff793f58e92f27367be912ed
+oid sha256:3519c66bef03d90fe5e133b9e08c9eb6330151ddd8811e14cc9972ce967e5af2
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40ee3f6d664b35df3858a440a589f64ea9771c6046a8a298433a87d5ee7d5d40
+oid sha256:0f584f04892a93fc2b5b61b9739764ab14cba2a6af1d9d003974cfd05c836d94
 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": 16.246570461428824,
+  "epoch": 16.531623017993944,
   "eval_steps": 400,
-  "global_step": 22800,
+  "global_step": 23200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2117,6 +2117,43 @@
       "eval_steps_per_second": 0.425,
       "eval_wer": 0.2049808429118774,
       "step": 22800
+    },
+    {
+      "epoch": 16.317833600570104,
+      "grad_norm": 15.153692245483398,
+      "learning_rate": 4.141150271936962e-06,
+      "loss": 1.184,
+      "step": 22900
+    },
+    {
+      "epoch": 16.389096739711384,
+      "grad_norm": 17.136568069458008,
+      "learning_rate": 3.7129030876621984e-06,
+      "loss": 1.18,
+      "step": 23000
+    },
+    {
+      "epoch": 16.460359878852664,
+      "grad_norm": 17.46211051940918,
+      "learning_rate": 3.2846559033874353e-06,
+      "loss": 1.173,
+      "step": 23100
+    },
+    {
+      "epoch": 16.531623017993944,
+      "grad_norm": 13.692911148071289,
+      "learning_rate": 2.8564087191126717e-06,
+      "loss": 1.2505,
+      "step": 23200
+    },
+    {
+      "epoch": 16.531623017993944,
+      "eval_loss": 0.0941072553396225,
+      "eval_runtime": 147.9642,
+      "eval_samples_per_second": 3.379,
+      "eval_steps_per_second": 0.426,
+      "eval_wer": 0.2002652519893899,
+      "step": 23200
     }
   ],
   "logging_steps": 100,
@@ -2136,7 +2173,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.964234667032576e+19,
+  "total_flos": 3.016267524734976e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null