Training in progress, step 1600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d436a2faf2808b5ca3ca4f28513c6308d2f1a669a1126e427e0cafeab0f2c28
+oid sha256:62deb87529039cbc1a82ab0b2c2c097e1116c967e4ff5a61dbfa5f3121bc149d
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6158aa31bac85837af2e2a3b6dd823093907acd64000f5d832aef5a3c02e1b27
+oid sha256:350d7ce567924319983aca0e7f7be8b583f5d84a69d17ee26937019e17041e63
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba5c1c59a616aa7b0f9e4dba43c7f771e98199d6e889d414c4046cb6db67e0db
+oid sha256:6de54eb0387d3e1bf778e48ab81b040825a9de5fcb77ae848e4ced4e0ee2e87d
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cfa6a40d74b0a4f6ca147fe45b859220132f65b1f4967c356e1f5127a7ae1f1
+oid sha256:be693887ab268fef1b2a4ac85d14acb908b9ba7b6d150718a85d227f055394a8
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff4f207fb87ffe1badbf72415757a46ce85d22e55b3649589a00635535f33997
+oid sha256:01bb6c0bd39168ba3e617f645d356e6f5a0f2faf5a8d66225a0993c8e3755d43
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 1200,
-  "best_metric": 0.3020925434718538,
-  "best_model_checkpoint": "./distil-whisper/checkpoint-1200",
-  "epoch": 0.8551576696953501,
+  "best_global_step": 1600,
+  "best_metric": 0.26760978485116416,
+  "best_model_checkpoint": "./distil-whisper/checkpoint-1600",
+  "epoch": 1.1396757527169072,
   "eval_steps": 400,
-  "global_step": 1200,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,43 @@
       "eval_steps_per_second": 0.397,
       "eval_wer": 0.3020925434718538,
       "step": 1200
+    },
+    {
+      "epoch": 0.9264208088366293,
+      "grad_norm": 158.05364990234375,
+      "learning_rate": 7.883526557023457e-05,
+      "loss": 10.1998,
+      "step": 1300
+    },
+    {
+      "epoch": 0.9976839479779084,
+      "grad_norm": 159.1658935546875,
+      "learning_rate": 7.613912105688865e-05,
+      "loss": 10.1922,
+      "step": 1400
+    },
+    {
+      "epoch": 1.068412613575628,
+      "grad_norm": 78.29598236083984,
+      "learning_rate": 7.344297654354275e-05,
+      "loss": 7.8385,
+      "step": 1500
+    },
+    {
+      "epoch": 1.1396757527169072,
+      "grad_norm": 75.16740417480469,
+      "learning_rate": 7.074683203019682e-05,
+      "loss": 8.1383,
+      "step": 1600
+    },
+    {
+      "epoch": 1.1396757527169072,
+      "eval_loss": 0.1211259588599205,
+      "eval_runtime": 155.5495,
+      "eval_samples_per_second": 3.214,
+      "eval_steps_per_second": 0.405,
+      "eval_wer": 0.26760978485116416,
+      "step": 1600
     }
   ],
   "logging_steps": 100,
@@ -138,7 +175,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.560985731072e+18,
+  "total_flos": 2.08013543866368e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null