Training in progress, step 24800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871e1a0f89abd57c35a7dbf130d5524fd292047262616b92ffd261d640fea12d
+oid sha256:c736fd594c380dd002a6342fa0604bc644313aed80303796815ff4b03e46442e
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d4051e416251f823f3179b18d1769dda91712dedabff1b2dc39dc8e904b7e65
+oid sha256:a3e2b9eff304abf490d045d1420af73881798301b076f854de745fb8bb32c5f5
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdf8ed808c01d757c6e38911720948b5f9db18cf7ee348b7781f51b3aebdcb61
+oid sha256:e2eaa69a43fe9ca74e4bd1e79b0bbd6af7b0c407425e6e1e3b18bd47b766849b
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6467edd96925a2153b86ff151f4249484a23bca6d403095f0ddb5893900e1b8a
+oid sha256:e15e488492623c161675a7bb297a1a2ecfcf210cea79271160fd0a257b5fa31e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d6539ca7d27098218a78f61589dfb4cc73931bd4c3c71ec49d7760c7d425bf5
+oid sha256:fd454cefdd5cc5bafc5dee97883508d8606ab9e8e2795ebeb6c8caeb65187032
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 4000,
   "best_metric": 0.18950781019746538,
   "best_model_checkpoint": "./distil-whisper/checkpoint-4000",
-  "epoch": 14.463544754001186,
+  "epoch": 14.700652045050385,
   "eval_steps": 400,
-  "global_step": 24400,
+  "global_step": 24800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2265,6 +2265,43 @@
       "eval_steps_per_second": 0.427,
       "eval_wer": 0.20247568523430592,
       "step": 24400
+    },
+    {
+      "epoch": 14.522821576763485,
+      "grad_norm": 8.844592094421387,
+      "learning_rate": 3.301753678693812e-06,
+      "loss": 0.941,
+      "step": 24500
+    },
+    {
+      "epoch": 14.582098399525785,
+      "grad_norm": 10.255487442016602,
+      "learning_rate": 2.89860915138077e-06,
+      "loss": 0.9698,
+      "step": 24600
+    },
+    {
+      "epoch": 14.641375222288085,
+      "grad_norm": 8.5720796585083,
+      "learning_rate": 2.4954646240677284e-06,
+      "loss": 0.9443,
+      "step": 24700
+    },
+    {
+      "epoch": 14.700652045050385,
+      "grad_norm": 7.877289295196533,
+      "learning_rate": 2.0923200967546868e-06,
+      "loss": 0.922,
+      "step": 24800
+    },
+    {
+      "epoch": 14.700652045050385,
+      "eval_loss": 0.0880463495850563,
+      "eval_runtime": 146.9212,
+      "eval_samples_per_second": 3.403,
+      "eval_steps_per_second": 0.429,
+      "eval_wer": 0.20085470085470086,
+      "step": 24800
     }
   ],
   "logging_steps": 100,
@@ -2284,7 +2321,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.173605943279616e+19,
+  "total_flos": 3.225638800982016e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null