Training in progress, step 15000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04f91bc09632d0ca44900fee5a57b22786f0ffd1c54b0da4556e61fa28621f2f
+oid sha256:88c828e9a5ac22cf6dc1cce8a9e4eba4907f38121d874041ad815e9f2a3c568b
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ecc271fe9090035a3a652375c681b827d76b3bd635e7efcdc02a095e29e7c80
+oid sha256:d6c863eb9dc692a7af5553639cc48b58879fa14bd82e27273107d9691b68e075
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:613bc7490770dcf68fa9d54869bc0b3e8eab8d28558ef327003153a0f6445f20
+oid sha256:024dc893ba560d2de7dd4d2f0b7ab5729ba9520ec363dd17bb65cf05af476b2b
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ef7c8d45fc5d3a46e66964194a46b9205f7ed9df86dc3ce05b4cb8e8f4d5993
+oid sha256:5adfa8fca6cc5ca715985458253bcf718541f3a76aa3473952114e672d00e7b5
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fb722111df53fcc783bd102468cba8b679f6233ec8483bf8ae8f9c6d76a52fa
+oid sha256:580e7db3eccdb01c1237319104eea4cc8a57ea956da0fe94439b4fbfeb184146
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 14000,
   "best_metric": 0.18538166814028884,
   "best_model_checkpoint": "./distil-whisper/checkpoint-14000",
-  "epoch": 8.201523140011716,
+  "epoch": 8.787346221441124,
   "eval_steps": 1000,
-  "global_step": 14000,
+  "global_step": 15000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1114,6 +1114,85 @@
       "eval_steps_per_second": 0.428,
       "eval_wer": 0.18538166814028884,
       "step": 14000
+    },
+    {
+      "epoch": 8.260105448154658,
+      "grad_norm": 7.585418701171875,
+      "learning_rate": 1.7978273989136995e-05,
+      "loss": 0.8818,
+      "step": 14100
+    },
+    {
+      "epoch": 8.318687756297598,
+      "grad_norm": 9.436836242675781,
+      "learning_rate": 1.7374773687386845e-05,
+      "loss": 0.8864,
+      "step": 14200
+    },
+    {
+      "epoch": 8.37727006444054,
+      "grad_norm": 12.12936019897461,
+      "learning_rate": 1.6771273385636692e-05,
+      "loss": 0.8744,
+      "step": 14300
+    },
+    {
+      "epoch": 8.43585237258348,
+      "grad_norm": 11.584985733032227,
+      "learning_rate": 1.6167773083886542e-05,
+      "loss": 0.8542,
+      "step": 14400
+    },
+    {
+      "epoch": 8.494434680726421,
+      "grad_norm": 7.6883440017700195,
+      "learning_rate": 1.5564272782136393e-05,
+      "loss": 0.8714,
+      "step": 14500
+    },
+    {
+      "epoch": 8.553016988869361,
+      "grad_norm": 13.686609268188477,
+      "learning_rate": 1.496077248038624e-05,
+      "loss": 0.8726,
+      "step": 14600
+    },
+    {
+      "epoch": 8.611599297012303,
+      "grad_norm": 10.200602531433105,
+      "learning_rate": 1.436330718165359e-05,
+      "loss": 0.8839,
+      "step": 14700
+    },
+    {
+      "epoch": 8.670181605155243,
+      "grad_norm": 6.929018020629883,
+      "learning_rate": 1.3759806879903441e-05,
+      "loss": 0.8628,
+      "step": 14800
+    },
+    {
+      "epoch": 8.728763913298184,
+      "grad_norm": 9.72988224029541,
+      "learning_rate": 1.3156306578153291e-05,
+      "loss": 0.8672,
+      "step": 14900
+    },
+    {
+      "epoch": 8.787346221441124,
+      "grad_norm": 7.273561477661133,
+      "learning_rate": 1.255280627640314e-05,
+      "loss": 0.8293,
+      "step": 15000
+    },
+    {
+      "epoch": 8.787346221441124,
+      "eval_loss": 0.08473628014326096,
+      "eval_runtime": 147.7929,
+      "eval_samples_per_second": 3.383,
+      "eval_steps_per_second": 0.426,
+      "eval_wer": 0.19834954317712938,
+      "step": 15000
     }
   ],
   "logging_steps": 100,
@@ -1133,7 +1212,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.821019937439744e+19,
+  "total_flos": 1.951102081695744e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null