Training in progress, step 35000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:396a29a5a4787dbf082bfc1745fc5d4dbaf49c674cf87663f742af78ff889ac4
+oid sha256:3c40ac5768678ec5e02f1ef67d5a4309a7523549c081d4aa4dcec3a9e62775b9
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a681bae809c2c7355b83c2ba73ac835d0bd5c7c190fd2e0484e22164316f803
+oid sha256:04e97e0d3303ce9166cbde3be58ec202701027a873651cfd877e10f3438e1bef
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce2c6e00c180a2aec543a6c39f38b41238eae7e450c89c57b59b23abde749eed
+oid sha256:f9bbeae69b0c3ccad7b2da286244601c7cab8dcaae00fabe926ee3c6e16123c7
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d82f68a924bc6f264caa5b5167990f1fdb3b2c8f9254156d8c0f9ccc3c5489db
+oid sha256:f23d0e9ac8ef166c949e157928330a7cb0661782ade2d248d1a928b2ac29805e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:122a12c57bcb396697297c9c6111a0a8854f31fea532275de745584ad3eee2c3
+oid sha256:7d08ed08052d252f71cbe4b116766edbb8b5b9589f8f40bb95cb4854fc9cf848
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 28000,
   "best_metric": 0.18110816386678455,
   "best_model_checkpoint": "./distil-whisper/checkpoint-28000",
-  "epoch": 19.917984768599883,
+  "epoch": 20.50380785002929,
   "eval_steps": 1000,
-  "global_step": 34000,
+  "global_step": 35000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2694,6 +2694,85 @@
       "eval_steps_per_second": 0.425,
       "eval_wer": 0.18715001473622164,
       "step": 34000
+    },
+    {
+      "epoch": 19.976567076742825,
+      "grad_norm": 7.8604302406311035,
+      "learning_rate": 9.367409726345334e-06,
+      "loss": 0.7127,
+      "step": 34100
+    },
+    {
+      "epoch": 20.035149384885763,
+      "grad_norm": 6.885805130004883,
+      "learning_rate": 9.097533329734982e-06,
+      "loss": 0.6805,
+      "step": 34200
+    },
+    {
+      "epoch": 20.093731693028705,
+      "grad_norm": 5.695769786834717,
+      "learning_rate": 8.82765693312463e-06,
+      "loss": 0.7139,
+      "step": 34300
+    },
+    {
+      "epoch": 20.152314001171646,
+      "grad_norm": 6.634642124176025,
+      "learning_rate": 8.557780536514277e-06,
+      "loss": 0.6917,
+      "step": 34400
+    },
+    {
+      "epoch": 20.210896309314588,
+      "grad_norm": 5.601979732513428,
+      "learning_rate": 8.287904139903925e-06,
+      "loss": 0.6576,
+      "step": 34500
+    },
+    {
+      "epoch": 20.269478617457526,
+      "grad_norm": 4.387629508972168,
+      "learning_rate": 8.018027743293572e-06,
+      "loss": 0.7389,
+      "step": 34600
+    },
+    {
+      "epoch": 20.328060925600468,
+      "grad_norm": 5.184898853302002,
+      "learning_rate": 7.748151346683219e-06,
+      "loss": 0.6803,
+      "step": 34700
+    },
+    {
+      "epoch": 20.38664323374341,
+      "grad_norm": 9.722779273986816,
+      "learning_rate": 7.478274950072867e-06,
+      "loss": 0.7095,
+      "step": 34800
+    },
+    {
+      "epoch": 20.44522554188635,
+      "grad_norm": 6.964946269989014,
+      "learning_rate": 7.208398553462514e-06,
+      "loss": 0.7372,
+      "step": 34900
+    },
+    {
+      "epoch": 20.50380785002929,
+      "grad_norm": 9.976523399353027,
+      "learning_rate": 6.938522156852162e-06,
+      "loss": 0.6865,
+      "step": 35000
+    },
+    {
+      "epoch": 20.50380785002929,
+      "eval_loss": 0.08354520797729492,
+      "eval_runtime": 147.4678,
+      "eval_samples_per_second": 3.391,
+      "eval_steps_per_second": 0.427,
+      "eval_wer": 0.1843501326259947,
+      "step": 35000
     }
   ],
   "logging_steps": 100,
@@ -2713,7 +2792,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.422483959611392e+19,
+  "total_flos": 4.55254984359936e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null