Training in progress, step 16000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88c828e9a5ac22cf6dc1cce8a9e4eba4907f38121d874041ad815e9f2a3c568b
+oid sha256:c3e3cd7750a71ba24a73246f69fdf7daec1177ea5853eea232a257d18883c36c
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6c863eb9dc692a7af5553639cc48b58879fa14bd82e27273107d9691b68e075
+oid sha256:1da40d74928c909c113322ad282f56feadf39a270ef5d886cdca23750487bd7a
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:024dc893ba560d2de7dd4d2f0b7ab5729ba9520ec363dd17bb65cf05af476b2b
+oid sha256:3d89c80e2c9bcd130c179737ff89fd355d5633e2baca37c40e9a81d122a9d5d9
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adfa8fca6cc5ca715985458253bcf718541f3a76aa3473952114e672d00e7b5
+oid sha256:281dc54ed0520d353628c056d22e94e782117e47679a149519cb09d64d5041fb
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:580e7db3eccdb01c1237319104eea4cc8a57ea956da0fe94439b4fbfeb184146
+oid sha256:e08be80793261ac03b00ebc0b1eac4cdf6646c0ac612f93a04f7f6b012b5292c
 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": 8.787346221441124,
+  "epoch": 9.373169302870533,
   "eval_steps": 1000,
-  "global_step": 15000,
+  "global_step": 16000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1193,6 +1193,85 @@
       "eval_steps_per_second": 0.426,
       "eval_wer": 0.19834954317712938,
       "step": 15000
+    },
+    {
+      "epoch": 8.845928529584066,
+      "grad_norm": 6.900521278381348,
+      "learning_rate": 1.1949305974652989e-05,
+      "loss": 0.8797,
+      "step": 15100
+    },
+    {
+      "epoch": 8.904510837727006,
+      "grad_norm": 13.14035701751709,
+      "learning_rate": 1.1345805672902837e-05,
+      "loss": 0.8691,
+      "step": 15200
+    },
+    {
+      "epoch": 8.963093145869948,
+      "grad_norm": 6.80872106552124,
+      "learning_rate": 1.0742305371152686e-05,
+      "loss": 0.859,
+      "step": 15300
+    },
+    {
+      "epoch": 9.021675454012888,
+      "grad_norm": 5.7985520362854,
+      "learning_rate": 1.0138805069402535e-05,
+      "loss": 0.8905,
+      "step": 15400
+    },
+    {
+      "epoch": 9.08025776215583,
+      "grad_norm": 7.384444236755371,
+      "learning_rate": 9.535304767652383e-06,
+      "loss": 0.7981,
+      "step": 15500
+    },
+    {
+      "epoch": 9.13884007029877,
+      "grad_norm": 6.441751956939697,
+      "learning_rate": 8.931804465902233e-06,
+      "loss": 0.9026,
+      "step": 15600
+    },
+    {
+      "epoch": 9.197422378441711,
+      "grad_norm": 5.471485614776611,
+      "learning_rate": 8.328304164152082e-06,
+      "loss": 0.8357,
+      "step": 15700
+    },
+    {
+      "epoch": 9.256004686584651,
+      "grad_norm": 6.093921661376953,
+      "learning_rate": 7.724803862401932e-06,
+      "loss": 0.8427,
+      "step": 15800
+    },
+    {
+      "epoch": 9.314586994727593,
+      "grad_norm": 5.414072036743164,
+      "learning_rate": 7.121303560651781e-06,
+      "loss": 0.8235,
+      "step": 15900
+    },
+    {
+      "epoch": 9.373169302870533,
+      "grad_norm": 5.2771897315979,
+      "learning_rate": 6.5178032589016296e-06,
+      "loss": 0.8363,
+      "step": 16000
+    },
+    {
+      "epoch": 9.373169302870533,
+      "eval_loss": 0.08421996235847473,
+      "eval_runtime": 150.6901,
+      "eval_samples_per_second": 3.318,
+      "eval_steps_per_second": 0.418,
+      "eval_wer": 0.19820218096080164,
+      "step": 16000
     }
   ],
   "logging_steps": 100,
@@ -1212,7 +1291,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.951102081695744e+19,
+  "total_flos": 2.081167965683712e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null