Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0d201c6fdc10947fdcbc30b3469c6b9077d585e2c5868215ae5e42116dc6474
+oid sha256:e3a296da5f4188d7fe604e5ce68cad00ee762ae67fec867847df7ca8be969d94
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:130507098d59862ec259645703f3fad405852b629bfaeee0268dc464f0e4f082
+oid sha256:5db4362036b0934a5c8708af6afcf5690a7c821d3e57902de82c1e3be8b6860a
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21322c6272f8d27c689906f590406c6587ddf5b7d44e771d42434753eeebb5d2
+oid sha256:66adb362f3962b993926e54f5d66da29ed9c0dd6b5b588230f18e1b72d0e0569
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e042f5ae15da2bc4849c16e6e602f27acac8d49038db98bbaa073c1c2141c422
+oid sha256:93eb2ca6af8f224511eca949745f6bb8af76938c5ba4b81612887470f2b8bec4
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d16e4263aed7ed8110daa9e5727beb6b5d763ac1620f2de37fbf4b96ef6a0aa
+oid sha256:9fd6eae26c7709efd6875f6d1711a51cd6b7291810956b22229aca7883513ec9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 9600,
-  "best_metric": 0.2045387562628942,
-  "best_model_checkpoint": "./distil-whisper/checkpoint-9600",
-  "epoch": 6.838054516301443,
+  "best_global_step": 10000,
+  "best_metric": 0.20218096080165046,
+  "best_model_checkpoint": "./distil-whisper/checkpoint-10000",
+  "epoch": 7.122572599323,
   "eval_steps": 400,
-  "global_step": 9600,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -896,6 +896,43 @@
       "eval_steps_per_second": 0.402,
       "eval_wer": 0.2045387562628942,
       "step": 9600
+    },
+    {
+      "epoch": 6.909317655442722,
+      "grad_norm": 59.62895202636719,
+      "learning_rate": 3.2113821138211384e-05,
+      "loss": 1.9717,
+      "step": 9700
+    },
+    {
+      "epoch": 6.980580794584001,
+      "grad_norm": 26.735105514526367,
+      "learning_rate": 3.137472283813747e-05,
+      "loss": 1.9839,
+      "step": 9800
+    },
+    {
+      "epoch": 7.051309460181721,
+      "grad_norm": 39.49419021606445,
+      "learning_rate": 3.063562453806356e-05,
+      "loss": 1.7422,
+      "step": 9900
+    },
+    {
+      "epoch": 7.122572599323,
+      "grad_norm": 36.06403732299805,
+      "learning_rate": 2.9896526237989653e-05,
+      "loss": 1.7238,
+      "step": 10000
+    },
+    {
+      "epoch": 7.122572599323,
+      "eval_loss": 0.09965246915817261,
+      "eval_runtime": 156.0402,
+      "eval_samples_per_second": 3.204,
+      "eval_steps_per_second": 0.404,
+      "eval_wer": 0.20218096080165046,
+      "step": 10000
     }
   ],
   "logging_steps": 100,
@@ -915,7 +952,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.248081263198208e+19,
+  "total_flos": 1.299996233957376e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null