Training in progress, step 24000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0bab03553a8f77e3f2e75a219bf665b1e186562895618ce139e5848329d72c0
+oid sha256:03838466207713eada91f2fe35ebdce379d78e8d934980b6a41a370b4b241fc4
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7360ae04b8536c8e7734abe26a3cb990db4674fc1a73c36fccd184dbe7d1cf2
+oid sha256:39381cb8b076341e0af800d6001aac00e14f538bf29b54baa76c4fc71f6897cf
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88042024e6d5504b01726176e8796950dc6789ee4ca9b044a81439e6b5885a63
+oid sha256:0a545a607a6cfc5a7cda494aeb18574f85c33430e90245257ba8c7ea46b1621b
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75504dd6b832b35e51d6c4316ef57c81197d178d6353c029e3628a6d2fc3a886
+oid sha256:40d683cb85559512f55ce631fbe47e10637f39943ba3b0a1a0e4edcbc56eadf7
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa8d73ca82fcf012384d060c02e2014b86a7e07a27ad6eb60874128d1cc9f9d5
+oid sha256:b664452bdc5abce0bae066b21b5f9a31052c253dc280d18e5bee7ce919977cb2
 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": 13.989330171902786,
+  "epoch": 14.226437462951985,
   "eval_steps": 400,
-  "global_step": 23600,
+  "global_step": 24000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2191,6 +2191,43 @@
       "eval_steps_per_second": 0.421,
       "eval_wer": 0.20100206307102858,
       "step": 23600
+    },
+    {
+      "epoch": 14.048606994665086,
+      "grad_norm": 9.336543083190918,
+      "learning_rate": 6.5269098971981455e-06,
+      "loss": 0.9795,
+      "step": 23700
+    },
+    {
+      "epoch": 14.107883817427386,
+      "grad_norm": 7.267581462860107,
+      "learning_rate": 6.1237653698851035e-06,
+      "loss": 0.9808,
+      "step": 23800
+    },
+    {
+      "epoch": 14.167160640189685,
+      "grad_norm": 11.863088607788086,
+      "learning_rate": 5.720620842572062e-06,
+      "loss": 0.8712,
+      "step": 23900
+    },
+    {
+      "epoch": 14.226437462951985,
+      "grad_norm": 9.668085098266602,
+      "learning_rate": 5.317476315259021e-06,
+      "loss": 0.9332,
+      "step": 24000
+    },
+    {
+      "epoch": 14.226437462951985,
+      "eval_loss": 0.08777602016925812,
+      "eval_runtime": 147.5257,
+      "eval_samples_per_second": 3.389,
+      "eval_steps_per_second": 0.427,
+      "eval_wer": 0.19923371647509577,
+      "step": 24000
     }
   ],
   "logging_steps": 100,
@@ -2210,7 +2247,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.069568683343872e+19,
+  "total_flos": 3.121573085577216e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null